diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..82f927558a3dff0ea8c20858856e70779fd02c93
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+# For a library or package, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+# This is especially recommended for binary packages to ensure reproducibility, and is more
+# commonly ignored for libraries.
+# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+# in version control.
+# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+# and can be added to the global gitignore or merged into this file. For a more nuclear
+# option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000000000000000000000000000000000000..3963f35c44922d45047f1cd3c69f92cd9a75472f
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 McGill NLP
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..66077cd6aadffe97568401d60a09ab6cd2a7ddb6
--- /dev/null
+++ b/README.md
@@ -0,0 +1,139 @@
+# *AURORA: Learning Action and Reasoning-Centric Image Editing from Videos and Simulation*
+
+[](https://aurora-editing.github.io/)
+[](https://arxiv.org/abs/2407.03471)
+[](https://huggingface.co/datasets/McGill-NLP/AURORA)
+[](https://huggingface.co/datasets/McGill-NLP/aurora-bench)
+[](https://huggingface.co/spaces/McGill-NLP/AURORA)
+[](https://github.com/McGill-NLP/AURORA/blob/main/LICENSE)
+
+AURORA (Action Reasoning Object Attribute) enables training an instruction-guided image editing model that can perform action and reasoning-centric edits, in addition to "simpler" established object, attribute or global edits. Here we release 1) training data, 2) trained model, 3) benchmark, 4) reproducible training and evaluation.
+
+
+ 
+
+
+Please reach out to [benno.krojer@mila.quebec](mailto:benno.krojer@mila.quebec) or raise an issue if anything does not work!
+
+
+
+## Updates
+**5th December 2024**: uploaded cleaner (actually usable) human ratings on AURORA-Bench. This can be useful for evaluating metrics via human correlation across a wide range of tasks. It includes 2K human ratings on outputs from 5 models.
+
+## Data
+
+On the data side, we release three artifacts and a [Datasheet documentation](https://github.com/McGill-NLP/AURORA/blob/main/datasheet.md):
+1. The training dataset (AURORA)
+2. A benchmark for testing diverse editing skills (AURORA-Bench): object-centric, action-centric, reasoning-centric, and global edits
+3. Human ratings on AURORA-Bench, i.e. for other researchers working image editing metrics
+
+You can also check out our [Huggingface dataset](https://huggingface.co/datasets/McGill-NLP/AURORA).
+
+### Training Data (AURORA)
+
+The edit instructions are stored as `data/TASK/train.json` for each of the four tasks.
+
+For the image pairs, you can download them easily via zenodo:
+```
+wget https://zenodo.org/record/11552426/files/ag_images.zip
+wget https://zenodo.org/record/11552426/files/kubric_images.zip
+wget https://zenodo.org/record/11552426/files/magicbrush_images.zip
+```
+
+Now put them into their respective directory `data/NAME` and rename them images.zip.
+So in the end you should have `data/kubric/images` as a directory etc.
+
+For Something-Something-Edit, you need to go to the [original source](https://developer.qualcomm.com/software/ai-datasets/something-something) and download all the zip files and put *all* the videos in a folder named `data/something/videos/`.
+
+Then run
+```
+cd data/something
+python extract_frames.py
+python filter_keywords.py
+```
+
+For each sub-dataset of AURORA, an entry would look like this:
+
+
+```json
+[
+ {
+ "instruction": "Leave the door while standing closer",
+ "input": "data/ag/images/1K0SU.mp4_4_left.png",
+ "output": "data/ag/images/1K0SU.mp4_4_right.png"
+ },
+ {"..."}
+]
+```
+
+If you are interested in developing your own similar Kubric data, it takes some effort (i.e. Docker+Blender setup), but we provide some starting code under `eq-kubric`.
+
+### Benchmark: AURORA-Bench
+
+For measuring how well models do on various editing skills (action, reasoning, object/attribute, global), we introduce AURORA-Bench hosted here on this repository under `test.json` with the respective images under `data/TASK/images/`.
+
+### Human Ratings
+
+We also release human ratings of image editing outputs on AURORA-Bench examples, which forms the basis of our main evaluation in the paper.
+The output images and assocaciated human ratings can be downloaded from Google Drive and is straightforward to use e.g. for computing correlations with a new metric: [json](https://drive.google.com/file/d/1uWpVOit_eUvI6GnY_Bvaj_vPd3H8cTbT/view?usp=sharing), [images files](https://drive.google.com/file/d/1wUwlxN1ArqTlCQQgnsj7DoXNoPRX71Ao/view?usp=sharing)
+
+## Running stuff
+
+Similar to [MagicBrush](https://github.com/OSU-NLP-Group/MagicBrush) we adopt the [pix2pix codebase](https://github.com/timothybrooks/instruct-pix2pix) for running and training models.
+
+### Inference
+
+Please create a python environment and install the requirements.txt file (it is unfortunately important to use 3.9 due to taming-transformers):
+```
+python3.9 -m venv env
+pip3 install -r requirements.txt
+```
+
+You can download our trained checkpoint from Google Drive: [Link](https://drive.google.com/file/d/1omV0xGyX6rVx1gp2EFgdcK8qSw1gUcnx/view?usp=sharing), place it in the main directory and run our AURORA-trained model on an example image:
+```
+python3 edit_cli.py
+```
+
+### Training
+To reproduce our training, first download an initial checkpoint that is the reproduced MagicBrush model: [Google Drive Link](https://drive.google.com/file/d/1qwkRwsa9jJu1uyYkaWOGL1CpXWlBI1jN/view?usp=sharing)
+
+Due to weird versioning of libraries/python, you have to go to `env/src/taming-transformers/taming/data/utils.py` and comment out line 11: `from torch._six import string_classes`.
+
+Now you can run the the train script (hyperparameters can be changed under `configs/finetune_magicbrush_ag_something_kubric_15-15-1-1_init-magic.yaml`):
+
+```
+python3 main.py --gpus 0,
+```
+
+Specify more gpus with i.e. `--gpus 0,1,2,3`.
+
+
+## Reproduce Evaluation
+
+We primarily rely on human evaluation of model outputs on AURORA-Bench.
+However our second proposed evaluation metric is automatic and here is how you reproduce it.
+
+First, run `python3 disc_edit.py --task TASK` (i.e. `--task whatsup`). This will generate outputs in a folder called itm_evaluation, that will then be evaluated via `python3 eval_disc_edit.py`
+
+## Citation
+
+```bibtex
+@inproceedings{krojer2024aurora,
+ author={Benno Krojer and Dheeraj Vattikonda and Luis Lara and Varun Jampani and Eva Portelance and Christopher Pal and Siva Reddy},
+ title={{Learning Action and Reasoning-Centric Image Editing from Videos and Simulations}},
+ booktitle={NeurIPS},
+ year={2024},
+ note={Spotlight Paper},
+ url={https://arxiv.org/abs/2407.03471}
+}
+```
+
+## Acknowledgements & License
+
+We use the [MIT License](https://github.com/McGill-NLP/AURORA/blob/main/LICENSE).
+
+We want to thank several repositories that made our life much easier on this project:
+
+1. The [MagicBrush](https://github.com/OSU-NLP-Group/MagicBrush) and [InstructPix2Pix](https://github.com/timothybrooks/instruct-pix2pix) code base and datasets, especially the correspondance with MagicBrush authors helped us a lot.
+2. The dataset/engines we use to build AURORA: [Something Something v2](https://developer.qualcomm.com/software/ai-datasets/something-something), [Action-Genome](https://github.com/JingweiJ/ActionGenome) and [Kubric](https://github.com/google-research/kubric)
+3. Source code from [EQBEN](https://github.com/Wangt-CN/EqBen) for generating images with the Kubric engine
diff --git a/app.py b/app.py
new file mode 100644
index 0000000000000000000000000000000000000000..756b9c0f17409df833f72f14914d9ba1d157f65b
--- /dev/null
+++ b/app.py
@@ -0,0 +1,90 @@
+from __future__ import annotations
+import math
+import gradio as gr
+import torch
+from PIL import Image, ImageOps
+from diffusers import StableDiffusionInstructPix2PixPipeline
+
+def main():
+ pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("McGill-NLP/AURORA", safety_checker=None).to("cuda")
+ example_image = Image.open("example.jpg").convert("RGB")
+
+ def generate(
+ input_image: Image.Image,
+ instruction: str,
+ steps: int,
+ seed: int,
+ text_cfg_scale: float,
+ image_cfg_scale: float,
+ ):
+ width, height = input_image.size
+ factor = 512 / max(width, height)
+ factor = math.ceil(min(width, height) * factor / 64) * 64 / min(width, height)
+ width = int((width * factor) // 64) * 64
+ height = int((height * factor) // 64) * 64
+ input_image = ImageOps.fit(input_image, (width, height), method=Image.Resampling.LANCZOS)
+
+ if instruction == "":
+ return [input_image, seed]
+
+ generator = torch.manual_seed(seed)
+ edited_image = pipe(
+ instruction, image=input_image,
+ guidance_scale=text_cfg_scale, image_guidance_scale=image_cfg_scale,
+ num_inference_steps=steps, generator=generator,
+ ).images[0]
+ return [seed, text_cfg_scale, image_cfg_scale, edited_image]
+
+ def reset():
+ return ["", 50, 42, 7.5, 1.5, None, None]
+
+ with gr.Blocks() as demo:
+ gr.HTML("""
+ AURORA: Learning Action and Reasoning-Centric Image Editing from Videos and Simulations
+
+
+ AURORA (Action Reasoning Object Attribute) enables training an instruction-guided image editing model that can perform action and reasoning-centric edits, in addition to "simpler" established object, attribute or global edits.
+
""")
+
+ with gr.Row():
+ with gr.Column(scale=3):
+ instruction = gr.Textbox(value="move the lemon to the right of the table", lines=1, label="Edit instruction", interactive=True)
+ with gr.Column(scale=1, min_width=100):
+ generate_button = gr.Button("Generate", variant="primary")
+ with gr.Column(scale=1, min_width=100):
+ reset_button = gr.Button("Reset", variant="stop")
+
+ with gr.Row():
+ input_image = gr.Image(value=example_image, label="Input image", type="pil", interactive=True)
+ edited_image = gr.Image(label=f"Edited image", type="pil", interactive=False)
+
+ with gr.Row():
+ steps = gr.Number(value=50, precision=0, label="Steps", interactive=True)
+ seed = gr.Number(value=42, precision=0, label="Seed", interactive=True)
+ text_cfg_scale = gr.Number(value=7.5, label=f"Text CFG", interactive=True)
+ image_cfg_scale = gr.Number(value=1.5, label=f"Image CFG", interactive=True)
+
+ generate_button.click(
+ fn=generate,
+ inputs=[
+ input_image,
+ instruction,
+ steps,
+ seed,
+ text_cfg_scale,
+ image_cfg_scale,
+ ],
+ outputs=[seed, text_cfg_scale, image_cfg_scale, edited_image],
+ )
+ reset_button.click(
+ fn=reset,
+ inputs=[],
+ outputs=[instruction, steps, seed, text_cfg_scale, image_cfg_scale, edited_image, input_image],
+ )
+
+ demo.queue()
+ demo.launch()
+ # demo.launch(share=True)
+
+if __name__ == "__main__":
+ main()
\ No newline at end of file
diff --git a/data-formatter.py b/data-formatter.py
new file mode 100644
index 0000000000000000000000000000000000000000..3a211c1b63819298afa62531e989a38a193f47bb
--- /dev/null
+++ b/data-formatter.py
@@ -0,0 +1,69 @@
+import json
+import argparse
+import os
+
+if __name__ == "__main__":
+ parser = argparse.ArgumentParser()
+ parser.add_argument("--dataset", type=str, required=True)
+ parser.add_argument("--training-format", type=str, required=True)
+ args = parser.parse_args()
+
+ # Load the input JSON file
+ with open("data/{s}/train.json".format(s=args.dataset), "r") as f:
+ data = json.load(f)
+
+ jsonl_data = []
+
+ # Convert the input JSON to JSONL format
+ for key, value in enumerate(data):
+
+ if args.dataset == "something":
+ input_path = value["input"]
+ output_path = value["output"]
+ file_check = os.path.exists(input_path) and os.path.exists(output_path)
+ else:
+ file_check = True
+
+ if file_check:
+
+ if args.training_format == "sft-editing":
+ entry = {
+ "id": f"{int(key):012d}",
+ "images": ["AURORA/"+value["input"], "AURORA/"+value["output"]],
+ "conversations": [
+ {
+ "from": "human",
+ "value": f"\nEditing the given image according to the following prompt: {value['instruction']}"
+ },
+ {
+ "from": "gpt",
+ "value": ""
+ }
+ ]
+ }
+ elif args.training_format == "sft-action-verbolise":
+ entry = {
+ "id": f"{int(key):012d}",
+ "images": ["AURORA/"+value["input"], "AURORA/"+value["output"]],
+ "conversations": [
+ {
+ "from": "human",
+ "value": f"You are given two sequential observations in the form of images.\n\nPast observations:\n\nNext observation after taking the action:\n\n\nYour task is to infer and describe the most likely action that occurred between the past and next observations. The action should be described concisely in natural language, capturing key changes that explain the state transition."
+ },
+ {
+ "from": "gpt",
+ "value": "The most likely action that occurred between the observations is: "+value['instruction']
+ }
+ ]
+ }
+ else:
+ raise NotImplementedError
+ jsonl_data.append(entry)
+
+ else:
+ continue
+
+ # Save to a JSONL file
+ with open("data/{s}/{f}-train.jsonl".format(s=args.dataset, f=args.training_format), "w") as f:
+ for line in jsonl_data:
+ f.write(json.dumps(line) + "\n")
diff --git a/datasheet.md b/datasheet.md
new file mode 100644
index 0000000000000000000000000000000000000000..af6d6532f657b4f1a308242e4924a2b50a99a753
--- /dev/null
+++ b/datasheet.md
@@ -0,0 +1,311 @@
+# Datasheet for dataset "AURORA"
+
+Questions from the [Datasheets for Datasets](https://arxiv.org/abs/1803.09010) paper, v7.
+
+Jump to section:
+
+- [Motivation](#motivation)
+- [Composition](#composition)
+- [Collection process](#collection-process)
+- [Preprocessing/cleaning/labeling](#preprocessingcleaninglabeling)
+- [Uses](#uses)
+- [Distribution](#distribution)
+- [Maintenance](#maintenance)
+
+## Motivation
+
+_The questions in this section are primarily intended to encourage dataset creators
+to clearly articulate their reasons for creating the dataset and to promote transparency
+about funding interests._
+
+### For what purpose was the dataset created?
+
+We collected AURORA since there is no current high-quality dataset for instruction-guided image editing where the instruction is an action such as "move carrots into the sink". As a result, the current image editing are quite limited and not as "general" as one would hope. This is an important subtask of image editing and can enable many downstream applications. There have been few training datasets for these sort of edit instructions and the ones that exist have very noisy data, i.e. where the target image shows far more changes than described in the text, or the change described is not even properly shown.
+
+### Who created the dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)?
+It was developed primarily at "Mila - Quebec Artificial Intelligence Institute", specifically in Siva Reddy's lab by his PhD student Benno Krojer. Other collaborators on the paper were involved in the ideation, many of them also at Mila and one of them at Stability AI.
+
+### Who funded the creation of the dataset?
+The dataset was funded by the PI, Siva Reddy.
+
+### Any other comments?
+None.
+
+## Composition
+
+_Most of these questions are intended to provide dataset consumers with the
+information they need to make informed decisions about using the dataset for
+specific tasks. The answers to some of these questions reveal information
+about compliance with the EU’s General Data Protection Regulation (GDPR) or
+comparable regulations in other jurisdictions._
+
+### What do the instances that comprise the dataset represent (e.g., documents, photos, people, countries)?
+
+Each datapoint is a triplet of (source image, prompt, target image), i.e. (an image of a dog, "make the dog smile", an image of a dog smiling).
+Our data consists of four sub-datasets:
+1. MagicBrush: **Source images** are diverse web-scrapped images ([MS-COCO](https://cocodataset.org/#home) which comes from websites like Flickr). **Prompt** and **target images** were previously crowd-sourced with humans using the DALL-E 2 editing interface.
+2. Action-Genome-Edit and Something-Something-Edit:** source** and **target images** are video frames depicting activities mostly at home; the **prompt** is human written (crowd-sourced by us or in the case of Something Something at the time of video recording in the original dataset).
+3. Kubric-Edit: **Source** and **target images** were generated in a simulation engine (Kubric), and depict non-human objects. The **prompt** is templated.
+
+### How many instances are there in total (of each type, if appropriate)?
+9K (MagicBrush) + 11K (Action-Genome-Edit) + 119K (Something-Something-Edit) + 150K (Kubric-Edit) = 149K + 150K = 399K
+
+### Does the dataset contain all possible instances or is it a sample (not necessarily random) of instances from a larger set?
+
+It is not really a sample, but we did have to filter out video frames that were too noisy or showed too much change such as camera movement.
+
+### What data does each instance consist of?
+
+Two raw images (source & target), and a string (the prompt).
+
+### Is there a label or target associated with each instance?
+
+The **target image** is the structure that the model has to predict during training and test time.
+
+### Is any information missing from individual instances?
+
+No.
+
+### Are relationships between individual instances made explicit (e.g., users’ movie ratings, social network links)?
+
+In MagicBrush there are sequential edits, that are indicated by the json key "img_id".
+In Action-Genome edit, some datapoints can come from the same video clip, which can be checked in the filename.
+
+### Are there recommended data splits (e.g., training, development/validation, testing)?
+
+We release training data separately from the AURORA-Bench data. The test data is much smaller and the test split of each of our training sub-datasets contributes to it.
+
+### Are there any errors, sources of noise, or redundancies in the dataset?
+
+The main source of noise comes with the video-frame-based data where sometimes there can be more changes than described in language. Or the change described in the prompt is not shown clearly.
+
+### Is the dataset self-contained, or does it link to or otherwise rely on external resources (e.g., websites, tweets, other datasets)?
+
+Self-contained, except that we ask people to download the videos from the original Something Something website, instead of providing the actual image files.
+
+### Does the dataset contain data that might be considered confidential (e.g., data that is protected by legal privilege or by doctor-patient confidentiality, data that includes the content of individuals’ non-public communications)?
+
+No, it was crowd-souced with paid workers who agreed to work on this task.
+
+### Does the dataset contain data that, if viewed directly, might be offensive, insulting, threatening, or might otherwise cause anxiety?
+
+No.
+
+### Does the dataset relate to people?
+
+Especially the Action-Genome-Edit data depicts people in their homes.
+
+### Does the dataset identify any subpopulations (e.g., by age, gender)?
+
+We do not know the exact recruitment for Action-Genome and Something Something videos (we build on top of these), but there are usually requirements such as speaking English.
+In our case, we only worked with 7 workers that had shown to produce high-quality data. We do not know their age or other personal details as this information is not direclty shown in Amazon Mechanical Turk.
+
+### Is it possible to identify individuals (i.e., one or more natural persons), either directly or indirectly (i.e., in combination with other data) from the dataset?
+
+If someone really tried, they might be able to identify some of the people in Action-Genome-Edit since they are shown fully and in their home. This would have to rely on advanced facial recognition and matching with other databases.
+
+### Does the dataset contain data that might be considered sensitive in any way (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history)?
+
+No.
+
+### Any other comments?
+None.
+
+## Collection process
+
+_\[T\]he answers to questions here may provide information that allow others to
+reconstruct the dataset without access to it._
+
+### How was the data associated with each instance acquired?
+
+_Was the data directly observable (e.g., raw text, movie ratings), reported by subjects (e.g.,
+survey responses), or indirectly inferred/derived from other data (e.g., part-of-speech tags,
+model-based guesses for age or language)? If data was reported by subjects or indirectly
+inferred/derived from other data, was the data validated/verified? If so, please describe how._
+
+For the sub-datasets MagicBrush, Action-Genome-Edit and Something-Something-Edit the prompts were written by humans and in the case of MagicBrush, the edited images were also produced in collaboration with an AI editing tool (DALL-E 2).
+Only Kubric-Edit is fully synthetic.
+
+The data was verified for "truly minimal" image pairs (as described in the paper), i.e. that all the changes from source to target are also described in the prompt. Only for Something-Something-Edit, this was not done on an instance-level but based on categories/labels and thus there will be some non-minimal pairs.
+
+### What mechanisms or procedures were used to collect the data (e.g., hardware apparatus or sensor, manual human curation, software program, software API)?
+
+_How were these mechanisms or procedures validated?_
+
+For the data we collected ourselves with humans (Action-Genome-Edit), we used Amazon Mechanical Turk (see Appendix of the paper for screenshots of our interface).
+We recruited the best workers from previous test runs and had lengthy e-mail exchanges to verify everything makes sense for them and we get good quality.
+For Kubric-Edit we used a simulation engine called Kubric.
+
+### If the dataset is a sample from a larger set, what was the sampling strategy (e.g., deterministic, probabilistic with specific sampling probabilities)?
+
+### Who was involved in the data collection process (e.g., students, crowdworkers, contractors) and how were they compensated (e.g., how much were crowdworkers paid)?
+
+We worked with 7 workers from Amazon Mechanical Turk and paid them 0.22$ USD per example, resulting in an estimated 10-20$ per hour.
+
+### Over what timeframe was the data collected?
+
+_Does this timeframe match the creation timeframe of the data associated with the instances (e.g.
+recent crawl of old news articles)? If not, please describe the timeframe in which the data
+associated with the instances was created._
+
+Around a week at the end of April 2024 for the main collection of Action-Genome. For the others, we constructed it from March to May with refinements.
+
+### Were any ethical review processes conducted (e.g., by an institutional review board)?
+
+No.
+
+### Does the dataset relate to people?
+
+Only in the sense that the prompts were written by people and that 1-2 dataset we build on top of depicts people.
+
+### Did you collect the data from the individuals in question directly, or obtain it via third parties or other sources (e.g., websites)?
+
+We collected it directly from AMT.
+
+### Were the individuals in question notified about the data collection?
+
+_If so, please describe (or show with screenshots or other information) how notice was provided,
+and provide a link or other access point to, or otherwise reproduce, the exact language of the
+notification itself._
+
+Workers on AMT see the posting with details like price and task description. In our case, we simply emailed workers from previous collections, and also told them it is for a research publication (i.e. linking to similar papers to give them an idea of what they are working on).
+
+### Did the individuals in question consent to the collection and use of their data?
+
+They implicitly agreed to various uses through the terms of service by MTurk: https://www.mturk.com/participation-agreement
+
+### If consent was obtained, were the consenting individuals provided with a mechanism to revoke their consent in the future or for certain uses?
+
+I am not sure about that part of MTurk's legal agreement but would guess no. I could not find an exact passage describing this, perhaps the the section "Use of Information; Publicity and Confidentiality"
+
+### Has an analysis of the potential impact of the dataset and its use on data subjects (e.g., a data protection impact analysis) been conducted?
+
+No.
+
+### Any other comments?
+
+None.
+
+## Preprocessing/cleaning/labeling
+
+_The questions in this section are intended to provide dataset consumers with the information
+they need to determine whether the “raw” data has been processed in ways that are compatible
+with their chosen tasks. For example, text that has been converted into a “bag-of-words” is
+not suitable for tasks involving word order._
+
+### Was any preprocessing/cleaning/labeling of the data done (e.g., discretization or bucketing, tokenization, part-of-speech tagging, SIFT feature extraction, removal of instances, processing of missing values)?
+
+We mainly filtered out image pairs with too many changes: We told workers to discard images with too many (or in rare cases too few changes). We automatically pre-filtered by "CLIP-score" (the cosine similarity between the visual embeddings of source and target image) for Action-Genome-Edit and Something-Something-Edit.
+
+### Was the “raw” data saved in addition to the preprocessed/cleaned/labeled data (e.g., to support unanticipated future uses)?
+
+It was not directly saved but can be accessed again by downloading the original sources we build upon such as Action-Genome videos (or frames from [EQBEN](https://github.com/Wangt-CN/EqBen), or the Something Something dataset.
+
+### Is the software used to preprocess/clean/label the instances available?
+
+We provide scripts on how to go from raw videos/frames to the cleaner ones on our repository.
+
+### Any other comments?
+
+None.
+
+## Uses
+
+_These questions are intended to encourage dataset creators to reflect on the tasks
+for which the dataset should and should not be used. By explicitly highlighting these tasks,
+dataset creators can help dataset consumers to make informed decisions, thereby avoiding
+potential risks or harms._
+
+### Has the dataset been used for any tasks already?
+
+We used it to train an image editing model. We expect similar applications, also to video generation models.
+MagicBrush has been used by several people.
+
+### Is there a repository that links to any or all papers or systems that use the dataset?
+
+Our code repository, or [MagicBrush](https://github.com/OSU-NLP-Group/MagicBrush).
+
+### What (other) tasks could the dataset be used for?
+
+Training models for video generation, change descriptions (i.e. Vision-and-Language LLMs) or discrimination of two similar images.
+A possible negative application further down the road is surveillance systems that need to detect minor changes.
+
+### Is there anything about the composition of the dataset or the way it was collected and preprocessed/cleaned/labeled that might impact future uses?
+
+Not that I can think of.
+
+### Are there tasks for which the dataset should not be used?
+
+Unsure.
+
+### Any other comments?
+
+None.
+
+## Distribution
+
+### Will the dataset be distributed to third parties outside of the entity (e.g., company, institution, organization) on behalf of which the dataset was created?
+
+We will fully open-source it and provide access via Zenodo/json files as well as Huggingface Datasets.
+
+### How will the dataset will be distributed (e.g., tarball on website, API, GitHub)?
+
+Both Zenodo and Huggingface datasets.
+
+### When will the dataset be distributed?
+
+The weeks after submission to NeurIPS Dataset & Benchmark track, so in June 2024.
+
+### Will the dataset be distributed under a copyright or other intellectual property (IP) license, and/or under applicable terms of use (ToU)?
+
+We stick with the standard open-source license: MIT License
+
+### Have any third parties imposed IP-based or other restrictions on the data associated with the instances?
+
+Something Something is the only dataset with a restricted license (it seems, I don't speak legalese: [License Terms](https://developer.qualcomm.com/software/ai-datasets/something-something)).
+So we are planning to link to their website and provide scripts to get to our final data.
+
+### Do any export controls or other regulatory restrictions apply to the dataset or to individual instances?
+
+[Official access and licensing](https://developer.qualcomm.com/software/ai-datasets/something-something) of Something Something dataset.
+
+### Any other comments?
+
+None.
+
+## Maintenance
+
+_These questions are intended to encourage dataset creators to plan for dataset maintenance
+and communicate this plan with dataset consumers._
+
+### Who is supporting/hosting/maintaining the dataset?
+
+The main author is responsible for ensuring long-term accessibility, which relies on Zenodo and Huggingface.
+
+### How can the owner/curator/manager of the dataset be contacted (e.g., email address)?
+
+benno.krojer@mila.quebec (or after I finish my PhD benno.krojer@gmail.com)
+
+### Is there an erratum?
+
+Not yet!
+
+### Will the dataset be updated (e.g., to correct labeling errors, add new instances, delete instances)?
+
+Not sure yet. If we find that people are interested in the data or trained model, we will continue our efforts.
+
+### If the dataset relates to people, are there applicable limits on the retention of the data associated with the instances (e.g., were individuals in question told that their data would be retained for a fixed period of time and then deleted)?
+
+No.
+
+### Will older versions of the dataset continue to be supported/hosted/maintained?
+
+If there ever was an update, yes.
+
+### If others want to extend/augment/build on/contribute to the dataset, is there a mechanism for them to do so?
+
+Since we use a non-restricting license (MIT license), anyone can build on top or include in their training data mixture.
+
+### Any other comments?
+
+No. We hope the data is useful to people!
diff --git a/disc_edit.py b/disc_edit.py
new file mode 100644
index 0000000000000000000000000000000000000000..05569b4c333ae9f5bd27ddcc6ce2418f8031e9d2
--- /dev/null
+++ b/disc_edit.py
@@ -0,0 +1,251 @@
+from __future__ import annotations
+
+import math
+import random
+import sys
+from argparse import ArgumentParser
+
+import einops
+import k_diffusion as K
+import numpy as np
+import torch
+import torch.nn as nn
+from einops import rearrange
+from omegaconf import OmegaConf
+from PIL import Image, ImageOps
+from torch import autocast
+from PIL import Image, ImageDraw, ImageFont
+import textwrap
+import json
+import os
+from dataset_loading import get_dataset
+from edit_dataset import EditITMDataset
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+import clip
+from collections import defaultdict
+
+sys.path.append("./stable_diffusion")
+from stable_diffusion.ldm.util import instantiate_from_config
+
+# Assuming CFGDenoiser and other dependencies are correctly set up,
+# no changes needed there for image aspect ratio handling.
+
+
+def calculate_clip_similarity(generated_images, original_image, clip_model, preprocess, device):
+ original_image_processed = preprocess(original_image).unsqueeze(0).to(device)
+
+ with torch.no_grad():
+ original_features = clip_model.encode_image(original_image_processed)
+
+ similarities = []
+ for img in generated_images:
+ img_processed = preprocess(img).unsqueeze(0).to(device)
+ with torch.no_grad():
+ generated_features = clip_model.encode_image(img_processed)
+ similarity = torch.nn.functional.cosine_similarity(generated_features, original_features, dim=-1)
+ similarities.append(similarity.item())
+
+ #concat both img and original_image for visualization
+ # original_image_np = np.array(original_image)
+ # img_np = np.array(img)
+ # both = np.concatenate((original_image_np, img_np), axis=1)
+ # both = Image.fromarray(both)
+ # if not os.path.exists('eval_output/edit_itm/flickr_edit_clip_sim/'):
+ # os.makedirs('eval_output/edit_itm/flickr_edit_clip_sim/')
+ # random_id = random.randint(0, 100000)
+ # both.save(f'eval_output/edit_itm/flickr_edit_clip_sim/{similarity.item()}_{random_id}.png')
+
+ # average_similarity = sum(similarities) / len(similarities)
+ # dist = 1 - average_similarity
+ dists = [1 - sim for sim in similarities]
+ return dists
+
+
+class CFGDenoiser(nn.Module):
+ def __init__(self, model):
+ super().__init__()
+ self.inner_model = model
+
+ def forward(self, z, sigma, cond, uncond, text_cfg_scale, image_cfg_scale, conditional_only=False):
+ # cfg_z = einops.repeat(z, "1 ... -> n ...", n=3)
+ cfg_z = z.repeat(3, 1, 1, 1)
+ # cfg_sigma = einops.repeat(sigma, "1 ... -> n ...", n=3)
+ cfg_sigma = sigma.repeat(3)
+ cfg_cond = {
+ "c_crossattn": [torch.cat([cond["c_crossattn"][0], uncond["c_crossattn"][0], uncond["c_crossattn"][0]])],
+ "c_concat": [torch.cat([cond["c_concat"][0], cond["c_concat"][0], uncond["c_concat"][0]])],
+ }
+ out_cond, out_img_cond, out_uncond = self.inner_model(cfg_z, cfg_sigma, cond=cfg_cond).chunk(3)
+ if conditional_only:
+ return out_cond
+ else:
+ return out_uncond + text_cfg_scale * (out_cond - out_img_cond) + image_cfg_scale * (out_img_cond - out_uncond)
+
+def load_model_from_config(config, ckpt, vae_ckpt=None, verbose=False):
+ print(f"Loading model from {ckpt}")
+ pl_sd = torch.load(ckpt, map_location="cpu")
+ if "global_step" in pl_sd:
+ print(f"Global Step: {pl_sd['global_step']}")
+ sd = pl_sd["state_dict"]
+ if vae_ckpt is not None:
+ print(f"Loading VAE from {vae_ckpt}")
+ vae_sd = torch.load(vae_ckpt, map_location="cpu")["state_dict"]
+ sd = {
+ k: vae_sd[k[len("first_stage_model.") :]] if k.startswith("first_stage_model.") else v
+ for k, v in sd.items()
+ }
+ model = instantiate_from_config(config.model)
+ m, u = model.load_state_dict(sd, strict=False)
+ if len(m) > 0 and verbose:
+ print("missing keys:")
+ print(m)
+ if len(u) > 0 and verbose:
+ print("unexpected keys:")
+ print(u)
+ return model
+
+def calculate_accuracy(losses):
+ correct_count = 0
+ for loss in losses:
+ if loss[0] < min(loss[1:]):
+ correct_count += 1
+ return correct_count, len(losses) # Return counts for aggregation
+
+
+def main():
+ parser = ArgumentParser()
+ parser.add_argument("--config", default="configs/generate.yaml", type=str)
+ parser.add_argument("--ckpt", default="aurora-mixratio-15-15-1-1-42k-steps.ckpt", type=str)
+ parser.add_argument("--vae-ckpt", default=None, type=str)
+ parser.add_argument("--task", default='flickr_edit', type=str)
+ parser.add_argument("--batchsize", default=1, type=int)
+ parser.add_argument("--samples", default=4, type=int)
+ parser.add_argument("--size", default=512, type=int)
+ parser.add_argument("--steps", default=20, type=int)
+ parser.add_argument("--cfg-text", default=7.5, type=float)
+ parser.add_argument("--cfg-image", default=1.5, type=float)
+ parser.add_argument('--targets', type=str, nargs='*', help="which target groups for mmbias",default='')
+ parser.add_argument("--device", default=0, type=int, help="GPU device index")
+ parser.add_argument("--log_imgs", action="store_true")
+ parser.add_argument("--conditional_only", action="store_true")
+ parser.add_argument("--metric", default="latent", type=str)
+ parser.add_argument("--split", default='test', type=str)
+ parser.add_argument("--skip", default=1, type=int)
+ args = parser.parse_args()
+ device = torch.device(f"cuda:{args.device}" if torch.cuda.is_available() else "cpu")
+
+ config = OmegaConf.load(args.config)
+ model = load_model_from_config(config, args.ckpt, args.vae_ckpt)
+ model.eval()
+ model.to(dtype=torch.float)
+ model = model.to(device)
+ model_wrap = K.external.CompVisDenoiser(model)
+ model_wrap_cfg = CFGDenoiser(model_wrap)
+ null_token = model.get_learned_conditioning([""])
+
+ clip_model, preprocess = clip.load("ViT-B/32", device=device)
+
+ dataset = EditITMDataset(split=args.split, task=args.task, min_resize_res=args.size, max_resize_res=args.size, crop_res=args.size)
+ dataloader= DataLoader(dataset,batch_size=args.batchsize,num_workers=1,worker_init_fn=None,shuffle=False, persistent_workers=True)
+
+ if os.path.exists(f'itm_evaluation/{args.split}/{args.task}/{args.ckpt.replace("/", "_")}_results.json'):
+ with open(f'itm_evaluation/{args.split}/{args.task}/{args.ckpt.replace("/", "_")}_results.json', 'r') as f:
+ results = json.load(f)
+ results = defaultdict(dict, results)
+ else:
+ results = defaultdict(dict)
+
+ for i, batch in tqdm(enumerate(dataloader), total=len(dataloader)):
+ if len(batch['input'][0].shape) < 3:
+ continue
+ for j, prompt in enumerate(batch['texts']):
+ # check if we already have results for this image
+ img_id = batch['path'][0] + f'_{i}'
+ # if img_id in results and ('pos' in results[img_id] and 'neg' in results[img_id]):
+ # continue
+
+ with torch.no_grad(), autocast("cuda"), model.ema_scope():
+ prompt = prompt[0]
+ cond = {}
+ cond["c_crossattn"] = [model.get_learned_conditioning([prompt])]
+ input_image = batch['input'][0].to(device)
+ cond["c_concat"] = [model.encode_first_stage(input_image.unsqueeze(0)).mode()]
+ scaled_input = model.scale_factor * input_image
+
+ uncond = {}
+ uncond["c_crossattn"] = [null_token]
+ uncond["c_concat"] = [torch.zeros_like(cond["c_concat"][0])]
+
+ sigmas = model_wrap.get_sigmas(args.steps)
+ # move everything to the device
+ cond = {k: [v.to(device) for v in vs] for k, vs in cond.items()}
+ uncond = {k: [v.to(device) for v in vs] for k, vs in uncond.items()}
+
+ cond["c_concat"][0] = cond["c_concat"][0].repeat(args.samples, 1, 1, 1)
+ cond["c_crossattn"][0] = cond["c_crossattn"][0].repeat(args.samples, 1, 1)
+ uncond["c_concat"][0] = uncond["c_concat"][0].repeat(args.samples, 1, 1, 1)
+ uncond["c_crossattn"][0] = uncond["c_crossattn"][0].repeat(args.samples, 1, 1)
+
+ extra_args = {
+ "cond": cond,
+ "uncond": uncond,
+ "text_cfg_scale": args.cfg_text,
+ "image_cfg_scale": args.cfg_image,
+ "conditional_only": args.conditional_only,
+ }
+ # torch.manual_seed(i)
+ torch.manual_seed(42)
+ z = torch.randn_like(cond["c_concat"][0]) * sigmas[0]
+ z = K.sampling.sample_euler_ancestral(model_wrap_cfg, z, sigmas, extra_args=extra_args, disable=True)
+ x = model.decode_first_stage(z)
+ x = torch.clamp((x + 1.0) / 2.0, min=0.0, max=1.0)
+
+ ######## LOG IMAGES ########
+ input_image_pil = ((input_image + 1) * 0.5).clamp(0, 1)
+ input_image_pil = input_image_pil.permute(1, 2, 0) # Change from CxHxW to HxWxC for PIL
+ input_image_pil = (input_image_pil * 255).type(torch.uint8).cpu().numpy()
+
+ for k in range(2):
+ x_ = 255.0 * rearrange(x[k], "c h w -> h w c")
+ edited_image = x_.type(torch.uint8).cpu().numpy()
+ both = np.concatenate((input_image_pil, edited_image), axis=1)
+ both = Image.fromarray(both)
+ out_base = f'itm_evaluation/{args.split}/{args.task}/{args.ckpt.replace("/", "_")}'
+ if not os.path.exists(out_base):
+ os.makedirs(out_base)
+ prompt_str = prompt.replace(' ', '_')[0:100]
+ both.save(f'{out_base}/{i}_{"correct" if j == 0 else "incorrect"}_sample{k}_{prompt}.png')
+
+ ######## CLIP ########
+
+ edited_images = []
+ for k in range(args.samples):
+ x_ = 255.0 * rearrange(x[k], "c h w -> h w c")
+ edited_image = Image.fromarray(x_.type(torch.uint8).cpu().numpy())
+ edited_images.append(edited_image)
+ input_image_pil = ((input_image + 1) * 0.5).clamp(0, 1)
+ input_image_pil = input_image_pil.permute(1, 2, 0) # Change from CxHxW to HxWxC for PIL
+ input_image_pil = (input_image_pil * 255).type(torch.uint8).cpu().numpy()
+ input_image_pil = Image.fromarray(input_image_pil)
+ dists_clip = calculate_clip_similarity(edited_images, input_image_pil, clip_model, preprocess, device)
+
+ ######## LATENT ########
+ z = z.flatten(1)
+ original_latent = cond["c_concat"][0].flatten(1)
+ dists_latent = torch.norm(z - original_latent, dim=1, p=2).cpu().numpy().tolist()
+ cos_sim = torch.nn.functional.cosine_similarity(z, original_latent, dim=1).cpu().numpy().tolist()
+ cos_dists_latent = [1 - sim for sim in cos_sim]
+ ######## SAVE RESULTS ########
+ img_id = batch['path'][0] + f'_{i}'
+ results[img_id]['pos' if j == 0 else 'neg'] = {
+ "prompt" : prompt,
+ "clip": dists_clip,
+ "latent_l2": dists_latent,
+ "latent_cosine": cos_dists_latent
+ }
+ with open(f'itm_evaluation/{args.split}/{args.task}/{args.ckpt.replace("/", "_")}_results.json', 'w') as f:
+ json.dump(results, f, indent=2)
+
+if __name__ == "__main__":
+ main()
diff --git a/edit_cli.py b/edit_cli.py
new file mode 100644
index 0000000000000000000000000000000000000000..2d160eaf6f49c586d7d64a69591e60d2a6096d06
--- /dev/null
+++ b/edit_cli.py
@@ -0,0 +1,124 @@
+from __future__ import annotations
+
+import math
+import random
+import sys
+from argparse import ArgumentParser
+
+import einops
+import k_diffusion as K
+import numpy as np
+import torch
+import torch.nn as nn
+from einops import rearrange
+from omegaconf import OmegaConf
+from PIL import Image, ImageOps
+from torch import autocast
+
+sys.path.append("./stable_diffusion")
+
+from stable_diffusion.ldm.util import instantiate_from_config
+
+
+class CFGDenoiser(nn.Module):
+ def __init__(self, model):
+ super().__init__()
+ self.inner_model = model
+
+ def forward(self, z, sigma, cond, uncond, text_cfg_scale, image_cfg_scale):
+ cfg_z = einops.repeat(z, "1 ... -> n ...", n=3)
+ cfg_sigma = einops.repeat(sigma, "1 ... -> n ...", n=3)
+ cfg_cond = {
+ "c_crossattn": [torch.cat([cond["c_crossattn"][0], uncond["c_crossattn"][0], uncond["c_crossattn"][0]])],
+ "c_concat": [torch.cat([cond["c_concat"][0], cond["c_concat"][0], uncond["c_concat"][0]])],
+ }
+ out_cond, out_img_cond, out_uncond = self.inner_model(cfg_z, cfg_sigma, cond=cfg_cond).chunk(3)
+ return out_uncond + text_cfg_scale * (out_cond - out_img_cond) + image_cfg_scale * (out_img_cond - out_uncond)
+
+
+def load_model_from_config(config, ckpt, vae_ckpt=None, verbose=False):
+ print(f"Loading model from {ckpt}")
+ pl_sd = torch.load(ckpt, map_location="cpu")
+ if "global_step" in pl_sd:
+ print(f"Global Step: {pl_sd['global_step']}")
+ sd = pl_sd["state_dict"]
+ if vae_ckpt is not None:
+ print(f"Loading VAE from {vae_ckpt}")
+ vae_sd = torch.load(vae_ckpt, map_location="cpu")["state_dict"]
+ sd = {
+ k: vae_sd[k[len("first_stage_model.") :]] if k.startswith("first_stage_model.") else v
+ for k, v in sd.items()
+ }
+ model = instantiate_from_config(config.model)
+ m, u = model.load_state_dict(sd, strict=False)
+ if len(m) > 0 and verbose:
+ print("missing keys:")
+ print(m)
+ if len(u) > 0 and verbose:
+ print("unexpected keys:")
+ print(u)
+ return model
+
+
+def main():
+ parser = ArgumentParser()
+ parser.add_argument("--resolution", default=512, type=int)
+ parser.add_argument("--steps", default=50, type=int)
+ parser.add_argument("--config", default="configs/generate.yaml", type=str)
+ parser.add_argument("--ckpt", default="aurora-mixratio-15-15-1-1-42k-steps.ckpt", type=str)
+ parser.add_argument("--vae-ckpt", default=None, type=str)
+ parser.add_argument("--input", default='example.jpg', type=str)
+ parser.add_argument("--output", default='example_output.jpg', type=str)
+ parser.add_argument("--edit", default='move the lemon to the right of the table', type=str)
+ parser.add_argument("--cfg-text", default=7.5, type=float)
+ parser.add_argument("--cfg-image", default=1.5, type=float)
+ parser.add_argument("--seed", default=42, type=int)
+ args = parser.parse_args()
+
+ config = OmegaConf.load(args.config)
+ model = load_model_from_config(config, args.ckpt, args.vae_ckpt)
+ model.eval().to('cuda:7')
+ model_wrap = K.external.CompVisDenoiser(model)
+ model_wrap_cfg = CFGDenoiser(model_wrap)
+ null_token = model.get_learned_conditioning([""])
+
+ seed = random.randint(0, 100000) if args.seed is None else args.seed
+ input_image = Image.open(args.input).convert("RGB")
+ width, height = input_image.size
+ factor = args.resolution / max(width, height)
+ factor = math.ceil(min(width, height) * factor / 64) * 64 / min(width, height)
+ width = int((width * factor) // 64) * 64
+ height = int((height * factor) // 64) * 64
+ input_image = ImageOps.fit(input_image, (width, height), method=Image.Resampling.LANCZOS)
+
+ with torch.no_grad(), autocast("cuda"), model.ema_scope():
+ cond = {}
+ cond["c_crossattn"] = [model.get_learned_conditioning([args.edit])]
+ input_image = 2 * torch.tensor(np.array(input_image)).float() / 255 - 1
+ input_image = rearrange(input_image, "h w c -> 1 c h w").to(model.device)
+ cond["c_concat"] = [model.encode_first_stage(input_image).mode()]
+
+ uncond = {}
+ uncond["c_crossattn"] = [null_token]
+ uncond["c_concat"] = [torch.zeros_like(cond["c_concat"][0])]
+
+ sigmas = model_wrap.get_sigmas(args.steps)
+
+ extra_args = {
+ "cond": cond,
+ "uncond": uncond,
+ "text_cfg_scale": args.cfg_text,
+ "image_cfg_scale": args.cfg_image,
+ }
+ torch.manual_seed(seed)
+ z = torch.randn_like(cond["c_concat"][0]) * sigmas[0]
+ z = K.sampling.sample_euler_ancestral(model_wrap_cfg, z, sigmas, extra_args=extra_args)
+ x = model.decode_first_stage(z)
+ x = torch.clamp((x + 1.0) / 2.0, min=0.0, max=1.0)
+ x = 255.0 * rearrange(x, "1 c h w -> h w c")
+ edited_image = Image.fromarray(x.type(torch.uint8).cpu().numpy())
+ edited_image.save(args.output)
+
+
+if __name__ == "__main__":
+ main()
diff --git a/edit_dataset.py b/edit_dataset.py
new file mode 100644
index 0000000000000000000000000000000000000000..8a3ab5b3c43eafa59cb6f0903c7c153829d75610
--- /dev/null
+++ b/edit_dataset.py
@@ -0,0 +1,603 @@
+from __future__ import annotations
+
+import json
+import math
+from pathlib import Path
+from typing import Any
+
+import numpy as np
+import torch
+import torchvision
+from einops import rearrange
+from PIL import Image
+from torch.utils.data import Dataset
+import os
+from datasets import load_dataset, DownloadConfig
+from tqdm import tqdm
+
+from PIL import ImageFile
+ImageFile.LOAD_TRUNCATED_IMAGES = True
+
+class FinetuneDataset(Dataset):
+ def __init__(
+ self,
+ path: str = '',
+ split: str = "train",
+ splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+ min_resize_res: int = 256,
+ max_resize_res: int = 256,
+ crop_res: int = 256,
+ flip_prob: float = 0.5,
+ msr_vtt_cc_full: bool = False,
+ mix: list[str] = ['magicbrush', 'something', 'hq'],
+ mix_factors: list[float] = [40, 1, 1],
+ copy_prob: float = 0.0,
+ kubric_100k: bool = False,
+ ):
+ self.split = split
+ assert split in ("train", "val", "test")
+ assert sum(splits) == 1
+ self.path = path
+ self.min_resize_res = min_resize_res
+ self.max_resize_res = max_resize_res
+ self.crop_res = crop_res
+ self.flip_prob = flip_prob
+ self.mix_factors = mix_factors
+ self.msr_vtt_cc_full = msr_vtt_cc_full
+ self.copy_prob = copy_prob
+
+ self.data = []
+ for dataset in mix:
+ if dataset != 'hq':
+ for _ in range(mix_factors[mix.index(dataset)]):
+ if kubric_100k and dataset == 'kubric':
+ self.data.extend(json.load(open(f'data/{dataset}/train_100k.json', 'r')))
+ print("LODADED KUBRIC 100K")
+ else:
+ self.data.extend(json.load(open(f'data/{dataset}/train.json', 'r')))
+ # if dataset == 'msr-vtt-cc':
+ # self.data.extend(json.load(open(f'data/{dataset}/train_gpt.json', 'r')))
+
+ if split == 'val':
+ self.data = self.data[:2]
+
+ def __len__(self) -> int:
+ return len(self.data)
+
+ def __getitem__(self, i: int) -> dict[str, Any]:
+ # if i < len(self.data):
+ ex = self.data[i]
+ img_path0 = ex['input']
+ img_path1 = ex['output']
+ prompt = ex['instruction']
+ dataset = img_path0.split('/')[1]
+ if dataset == 'kubric':
+ subtask = img_path0.split('/')[2]
+ else:
+ subtask = '___'
+
+ if type(prompt) == list:
+ prompt = prompt[0]
+ spatial = 'left' in prompt.lower() or 'right' in prompt.lower()
+ image_1 = Image.open(img_path1).convert('RGB') if i < len(self.data) else img_path1
+
+ if subtask not in ['closer', 'counting', 'further_location', 'rotate']:
+ if self.copy_prob > 0 and torch.rand(1) < self.copy_prob:
+ image_0 = Image.open(img_path1).convert('RGB') if i < len(self.data) else img_path1
+ else:
+ image_0 = Image.open(img_path0).convert('RGB') if i < len(self.data) else img_path0
+ else:
+ image_0 = Image.open(img_path0).convert('RGB') if i < len(self.data) else img_path0
+
+ reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+ image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+ image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+ image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+ image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+ crop = torchvision.transforms.RandomCrop(self.crop_res)
+ flip_prob = 0.0 if spatial else self.flip_prob
+ flip = torchvision.transforms.RandomHorizontalFlip(float(flip_prob))
+ image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+ return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class MagicEditDataset(Dataset):
+ def __init__(
+ self,
+ path: str = '../../change_descriptions/something-something',
+ split: str = "train",
+ splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+ min_resize_res: int = 256,
+ max_resize_res: int = 256,
+ crop_res: int = 256,
+ flip_prob: float = 0.0,
+ debug: bool = False,
+ ):
+ self.min_resize_res = min_resize_res
+ self.max_resize_res = max_resize_res
+ self.crop_res = crop_res
+ self.flip_prob = flip_prob
+
+ print("Dataset params")
+ print(self.min_resize_res, self.max_resize_res, self.crop_res, self.flip_prob)
+
+ #clean json (if first and last are not both present, remove)
+ split = "train" if split == "train" else "dev"
+ self.dataset = load_dataset("osunlp/MagicBrush")[split]
+
+ # if split == 'dev':
+ # eval_data = json.load(open('eval_data/video_edit.json', 'r'))
+ # dummy_image = Image.new('RGB', (1, 1), (0, 0, 0))
+ # eval_data = {
+ # 'source_img': [Image.open(x['img0']) for x in eval_data],
+ # 'target_img': [Image.open(x['img1']) for x in eval_data],
+ # 'instruction': [x['edit'] if type(x['edit']) == str else x['edit'][0] for x in eval_data],
+ # 'img_id': ['' for _ in eval_data],
+ # 'turn_index': np.array([1 for _ in eval_data], dtype=np.int32),
+ # 'mask_img': [dummy_image for _ in eval_data] # Replace each entry with the dummy image
+ # }
+ # eval_dataset = HuggingFaceDataset.from_dict(eval_data)
+ # self.dataset = concatenate_datasets([self.dataset, eval_dataset])
+
+ if debug:
+ self.dataset = self.dataset.shuffle(seed=42).select(range(50))
+
+ def __len__(self) -> int:
+ return len(self.dataset)
+
+ def __getitem__(self, i: int) -> dict[str, Any]:
+
+ prompt = self.dataset[i]['instruction']
+ if type(prompt) == list:
+ prompt = prompt[0]
+ image_0 = self.dataset[i]['source_img']
+ image_1 = self.dataset[i]['target_img']
+ if image_0.mode == 'RGBA':
+ image_0 = image_0.convert('RGB')
+ if image_1.mode == 'RGBA':
+ image_1 = image_1.convert('RGB')
+ reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+ image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+ image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+ image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+ image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+ crop = torchvision.transforms.RandomCrop(self.crop_res)
+ flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+ image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+ return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class FrameEditDataset(Dataset):
+ def __init__(
+ self,
+ path: str = '../../change_descriptions/something-something',
+ split: str = "train",
+ splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+ task: str = 'flickr30k_text',
+ min_resize_res: int = 256,
+ max_resize_res: int = 256,
+ crop_res: int = 256,
+ flip_prob: float = 0.0,
+ debug: bool = False,
+ ):
+ self.split = split
+ self.task = task
+ if split == "train":
+ path = os.path.join(path, 'train.json')
+ self.json = json.load(open(path, 'r'))
+ np.random.shuffle(self.json)
+ self.min_resize_res = min_resize_res
+ self.max_resize_res = max_resize_res
+ self.crop_res = crop_res
+ self.flip_prob = flip_prob
+
+ #clean json (if first and last are not both present, remove)
+ if split == 'train':
+ new_json = []
+ for i in range(len(self.json)):
+ video_id = self.json[i]['id']
+ img_path0 = f'../../change_descriptions/something-something/frames/{video_id}/first.jpg'
+ img_path1 = f'../../change_descriptions/something-something/frames/{video_id}/last.jpg'
+ if os.path.exists(img_path0) and os.path.exists(img_path1):
+ new_json.append(self.json[i])
+ self.json = new_json
+ if debug:
+ self.json = self.json[:50]
+
+ def __len__(self) -> int:
+ return len(self.json)
+
+ def __getitem__(self, i: int) -> dict[str, Any]:
+ if self.split == 'train':
+ video_id = self.json[i]['id']
+ img_path0 = f'../../change_descriptions/something-something/frames/{video_id}/first.jpg'
+ img_path1 = f'../../change_descriptions/something-something/frames/{video_id}/last.jpg'
+ prompt = self.json[i]['label']
+
+ image_0 = Image.open(img_path0).convert('RGB')
+ image_1 = Image.open(img_path1).convert('RGB')
+
+ reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+ # image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+ # image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+ image_0 = image_0.resize((self.crop_res, self.crop_res))
+ image_1 = image_1.resize((self.crop_res, self.crop_res))
+
+ image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+ image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+ crop = torchvision.transforms.RandomCrop(self.crop_res)
+ flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+ image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+ # if i ever wanna reverse time
+ # if torch.rand(1) > 0.5:
+ # image_0, image_1 = image_1, image_0
+ # prompt = caption0
+ if self.split == 'train':
+ return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+ else:
+ return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=texts))
+
+class EditITMDataset(Dataset):
+ def __init__(
+ self,
+ path: str = '../../change_descriptions/something-something',
+ split: str = "test",
+ splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+ task: str = 'flickr30k_text',
+ min_resize_res: int = 256,
+ max_resize_res: int = 256,
+ crop_res: int = 256,
+ flip_prob: float = 0.0,
+ debug: bool = False,
+ ):
+ self.split = split
+ self.task = task
+ # if task == 'flickr_edit':
+ # path = 'data/flickr_edit/valid.json' if split == 'val' else 'data/flickr_edit/test.json'
+ # self.json = json.load(open(path, 'r'))
+ # #clean json, if "pos" key is empty string, remove
+ # self.json = [x for x in self.json if x['pos'] != '']
+ if task == 'whatsup':
+ path = 'data/whatsup/itm_test.json' if split == 'test' else 'data/whatsup/itm_valid.json'
+ self.json = json.load(open(path, 'r'))
+ elif task == 'svo':
+ path = 'data/svo/itm_test.json' if split == 'test' else 'data/svo/itm_valid.json'
+ self.json = json.load(open(path, 'r'))
+ else:
+ path = f'data/{task}/valid.json'
+ self.json = json.load(open(path, 'r'))
+ self.json = [x for x in self.json if x.get('pos', '') != '']
+ self.min_resize_res = min_resize_res
+ self.max_resize_res = max_resize_res
+ self.crop_res = crop_res
+ self.flip_prob = flip_prob
+
+ if debug:
+ self.json = self.json[:50]
+
+ def __len__(self) -> int:
+ return len(self.json)
+
+ def __getitem__(self, i: int) -> dict[str, Any]:
+ ex = self.json[i]
+ pos = ex.get('pos', '')
+ if pos == '':
+ pos = ex['prompt']
+ neg = ex.get('neg', '')
+ if neg == '':
+ neg = ex['prompt']
+ img_path0 = ex['input']
+ texts = [pos, neg]
+ # if self.task == 'whatsup' or self.task == 'svo':
+ # img_path0 = f"data/{self.task}/images/{ex['image']}" if self.task == 'flickr_edit' else ex['image']
+ # texts = [ex['pos'], ex['neg']]
+ # else:
+ # img_path0 = ex['input']
+ # texts = ex['pos'], ex['prompt']
+ # subtasks = ex['type'] if self.task == 'flickr_edit' else ''
+ try:
+ image_0 = Image.open(img_path0).convert('RGB')
+ reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+ image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+ image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+ except:
+ image_0 = 0
+
+ return dict(input=image_0, texts=texts, path=img_path0)
+
+class OldFrameEditDataset(Dataset):
+ def __init__(
+ self,
+ path: str = '../../change_descriptions/something-something',
+ split: str = "train",
+ splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+ task: str = 'flickr30k_text',
+ min_resize_res: int = 256,
+ max_resize_res: int = 256,
+ crop_res: int = 256,
+ flip_prob: float = 0.0,
+ debug: bool = False,
+ ):
+ if split == "train":
+ path = os.path.join(path, 'train.json')
+ elif split == "val":
+ path = os.path.join(path, 'validation.json')
+ self.json = json.load(open(path, 'r'))
+ np.random.shuffle(self.json)
+ self.min_resize_res = min_resize_res
+ self.max_resize_res = max_resize_res
+ self.crop_res = crop_res
+ self.flip_prob = flip_prob
+
+ #clean json (if first and last are not both present, remove)
+ new_json = []
+ for i in range(len(self.json)):
+ video_id = self.json[i]['id']
+ img_path0 = f'../../change_descriptions/something-something/frames/{video_id}/first.jpg'
+ img_path1 = f'../../change_descriptions/something-something/frames/{video_id}/last.jpg'
+ if os.path.exists(img_path0) and os.path.exists(img_path1):
+ new_json.append(self.json[i])
+ self.json = new_json
+ if debug:
+ self.json = self.json[:50]
+
+ def __len__(self) -> int:
+ return len(self.json)
+
+ def __getitem__(self, i: int) -> dict[str, Any]:
+ video_id = self.json[i]['id']
+ img_path0 = f'../../change_descriptions/something-something/frames/{video_id}/first.jpg'
+ img_path1 = f'../../change_descriptions/something-something/frames/{video_id}/last.jpg'
+ prompt = self.json[i]['label']
+ image_0 = Image.open(img_path0)
+ image_1 = Image.open(img_path1)
+
+ reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+ image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+ image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+ image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+ image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+ crop = torchvision.transforms.RandomCrop(self.crop_res)
+ flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+ image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+ # if i ever wanna reverse time
+ # if torch.rand(1) > 0.5:
+ # image_0, image_1 = image_1, image_0
+ # prompt = caption0
+
+ return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class EditDataset(Dataset):
+ def __init__(
+ self,
+ path: str = 'data/clip-filtered-dataset',
+ split: str = "train",
+ splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+ min_resize_res: int = 256,
+ max_resize_res: int = 256,
+ crop_res: int = 256,
+ flip_prob: float = 0.0,
+ ):
+ self.split = split
+ assert split in ("train", "val", "test")
+ assert sum(splits) == 1
+ self.path = path
+ self.min_resize_res = min_resize_res
+ self.max_resize_res = max_resize_res
+ self.crop_res = crop_res
+ self.flip_prob = flip_prob
+
+ self.genhowto = open('data/genhowto/genhowto_train_clip0.7_filtered.txt', 'r').readlines()
+ # self.genhowto = open('data/genhowto/genhowto_train.txt', 'r').readlines()
+ self.genhowto = [x.strip() for x in self.genhowto]
+
+ new_genhowto = []
+ for i in range(len(self.genhowto)):
+ img_path, prompt, prompt2 = self.genhowto[i].split(':')
+ new_genhowto.append((img_path, prompt, 'action'))
+ new_genhowto.append((img_path, prompt2, 'state'))
+ self.genhowto = new_genhowto
+
+ with open(Path(self.path, "seeds.json")) as f:
+ self.seeds = json.load(f)
+
+ split_0, split_1 = {
+ "train": (0.0, splits[0]),
+ "val": (splits[0], splits[0] + splits[1]),
+ "test": (splits[0] + splits[1], 1.0),
+ }[split]
+
+ idx_0 = math.floor(split_0 * len(self.seeds))
+ idx_1 = math.floor(split_1 * len(self.seeds))
+ self.seeds = self.seeds[idx_0:idx_1]
+ # shuffle seeds and genhowto
+ # np.random.seed(42)
+ # np.random.shuffle(self.seeds)
+ # np.random.shuffle(self.genhowto)
+
+ def __len__(self) -> int:
+ return len(self.seeds) + len(self.genhowto)
+
+ def __getitem__(self, i: int) -> dict[str, Any]:
+ if i < len(self.seeds):
+ name, seeds = self.seeds[i]
+ propt_dir = Path(self.path, name)
+ seed = seeds[torch.randint(0, len(seeds), ()).item()]
+ with open(propt_dir.joinpath("prompt.json")) as fp:
+ prompt = json.load(fp)["edit"]
+ image_0 = Image.open(propt_dir.joinpath(f"{seed}_0.jpg"))
+ image_1 = Image.open(propt_dir.joinpath(f"{seed}_1.jpg"))
+ else:
+ ex = self.genhowto[i - len(self.seeds)]
+ # img_path, prompt, prompt2 = ex.split(':')
+ # img_path = img_path.replace('changeit_detected_without_test', 'changeit_detected')
+ # img_path = 'data/genhowto/' + img_path
+ # full_img = Image.open(img_path).convert('RGB')
+ # image_0 = full_img.crop((0, 0, full_img.width // 3, full_img.height))
+ # image_1 = full_img.crop((full_img.width * 2 // 3, 0, full_img.width, full_img.height))
+ # image_2 = full_img.crop((full_img.width // 3, 0, full_img.width * 2 // 3, full_img.height))
+ # if torch.rand(1) > 0.5:
+ # image_1 = image_2
+ # prompt = prompt2
+ img_path, prompt, type = ex
+ img_path = img_path.replace('changeit_detected_without_test', 'changeit_detected')
+ img_path = 'data/genhowto/' + img_path
+ full_img = Image.open(img_path).convert('RGB')
+ image_0 = full_img.crop((0, 0, full_img.width // 3, full_img.height))
+ if type == 'action':
+ image_1 = full_img.crop((full_img.width // 3, 0, full_img.width * 2 // 3, full_img.height))
+ else:
+ image_1 = full_img.crop((full_img.width * 2 // 3, 0, full_img.width, full_img.height))
+
+
+ reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+ image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+ image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+ image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+ image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+ crop = torchvision.transforms.RandomCrop(self.crop_res)
+ flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+ image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+ return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class GenHowToDataset(Dataset):
+ def __init__(
+ self,
+ path: str = 'data/clip-filtered-dataset',
+ split: str = "train",
+ splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+ min_resize_res: int = 256,
+ max_resize_res: int = 256,
+ crop_res: int = 256,
+ flip_prob: float = 0.0,
+ ):
+ self.split = split
+ assert split in ("train", "val", "test")
+ assert sum(splits) == 1
+ self.path = path
+ self.min_resize_res = min_resize_res
+ self.max_resize_res = max_resize_res
+ self.crop_res = crop_res
+ self.flip_prob = flip_prob
+
+ self.genhowto = open('data/genhowto/genhowto_train.txt', 'r').readlines()
+ self.genhowto = [x.strip() for x in self.genhowto]
+
+ new_genhowto = []
+ for i in range(len(self.genhowto)):
+ img_path, prompt, prompt2 = self.genhowto[i].split(':')
+ new_genhowto.append((img_path, prompt, 'action'))
+ new_genhowto.append((img_path, prompt2, 'state'))
+ self.genhowto = new_genhowto
+ np.random.shuffle(self.genhowto)
+
+ # with open(Path(self.path, "seeds.json")) as f:
+ # self.seeds = json.load(f)
+
+ # split_0, split_1 = {
+ # "train": (0.0, splits[0]),
+ # "val": (splits[0], splits[0] + splits[1]),
+ # "test": (splits[0] + splits[1], 1.0),
+ # }[split]
+
+ # idx_0 = math.floor(split_0 * len(self.seeds))
+ # idx_1 = math.floor(split_1 * len(self.seeds))
+ # self.seeds = self.seeds[idx_0:idx_1]
+ # shuffle seeds and genhowto
+ # np.random.seed(42)
+ # np.random.shuffle(self.seeds)
+ # np.random.shuffle(self.genhowto)
+
+ def __len__(self) -> int:
+ return len(self.genhowto)
+
+ def __getitem__(self, i: int) -> dict[str, Any]:
+ ex = self.genhowto[i]
+ img_path, prompt, type = ex
+ img_path = img_path.replace('changeit_detected_without_test', 'changeit_detected')
+ img_path = 'data/genhowto/' + img_path
+ full_img = Image.open(img_path).convert('RGB')
+ image_0 = full_img.crop((0, 0, full_img.width // 3, full_img.height))
+ if type == 'action':
+ image_1 = full_img.crop((full_img.width // 3, 0, full_img.width * 2 // 3, full_img.height))
+ else:
+ image_1 = full_img.crop((full_img.width * 2 // 3, 0, full_img.width, full_img.height))
+
+
+ reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+ image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+ image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+ image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+ image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+ crop = torchvision.transforms.RandomCrop(self.crop_res)
+ flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+ image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+ return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class EditDatasetEval(Dataset):
+ def __init__(
+ self,
+ path: str,
+ split: str = "train",
+ splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+ res: int = 256,
+ ):
+ assert split in ("train", "val", "test")
+ assert sum(splits) == 1
+ self.path = path
+ self.res = res
+
+ with open(Path(self.path, "seeds.json")) as f:
+ self.seeds = json.load(f)
+
+ split_0, split_1 = {
+ "train": (0.0, splits[0]),
+ "val": (splits[0], splits[0] + splits[1]),
+ "test": (splits[0] + splits[1], 1.0),
+ }[split]
+
+ idx_0 = math.floor(split_0 * len(self.seeds))
+ idx_1 = math.floor(split_1 * len(self.seeds))
+ self.seeds = self.seeds[idx_0:idx_1]
+
+ def __len__(self) -> int:
+ return len(self.seeds)
+
+ def __getitem__(self, i: int) -> dict[str, Any]:
+ name, seeds = self.seeds[i]
+ propt_dir = Path(self.path, name)
+ seed = seeds[torch.randint(0, len(seeds), ()).item()]
+ with open(propt_dir.joinpath("prompt.json")) as fp:
+ prompt = json.load(fp)
+ edit = prompt["edit"]
+ input_prompt = prompt["input"]
+ output_prompt = prompt["output"]
+
+ image_0 = Image.open(propt_dir.joinpath(f"{seed}_0.jpg"))
+
+ reize_res = torch.randint(self.res, self.res + 1, ()).item()
+ image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+ image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+
+ return dict(image_0=image_0, input_prompt=input_prompt, edit=edit, output_prompt=output_prompt)
diff --git a/eq-kubric/3d_data/GSO.json b/eq-kubric/3d_data/GSO.json
new file mode 100644
index 0000000000000000000000000000000000000000..7d0de888d44be9be43e91a458b151b8cd7a1fa1e
--- /dev/null
+++ b/eq-kubric/3d_data/GSO.json
@@ -0,0 +1,30997 @@
+{
+ "assets": {
+ "11pro_SL_TRX_FG": {
+ "asset_type": "FileBasedObject",
+ "id": "11pro_SL_TRX_FG",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05124879581331957,
+ -0.13426463496800112,
+ -0.04408406541243304
+ ],
+ [
+ 0.046978204186680424,
+ 0.15667136503199888,
+ 0.07383293458756696
+ ]
+ ],
+ "mass": 0.0008831573715407045,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "11pro SL TRX FG\nFW-FIRM GROUND",
+ "nr_faces": 20706,
+ "nr_vertices": 11846,
+ "surface_area": 0.10847038351137667,
+ "volume": 0.0008831573715407045
+ }
+ },
+ "2_of_Jenga_Classic_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "2_of_Jenga_Classic_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0391314773401108,
+ -0.043134804875419326,
+ -0.14505538512030894
+ ],
+ [
+ 0.0397555226598892,
+ 0.04130319512458067,
+ 0.14704261487969109
+ ]
+ ],
+ "mass": 0.001469148294964422,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "2 of Jenga Classic Game",
+ "nr_faces": 8922,
+ "nr_vertices": 4932,
+ "surface_area": 0.10522810363357435,
+ "volume": 0.001469148294964422
+ }
+ },
+ "30_CONSTRUCTION_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "30_CONSTRUCTION_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16376866010118918,
+ -0.10854108544428925,
+ -0.07906509455821394
+ ],
+ [
+ 0.10565033989881081,
+ 0.11615691455571076,
+ 0.12795190544178608
+ ]
+ ],
+ "mass": 0.0008545506536792521,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "30 CONSTRUCTION SET\nThe pieces can be easily assembled and reassembled to create any imaginable form. Screwdriver included.",
+ "nr_faces": 23766,
+ "nr_vertices": 14354,
+ "surface_area": 0.1539406059217826,
+ "volume": 0.0008545506536792521
+ }
+ },
+ "3D_Dollhouse_Happy_Brother": {
+ "asset_type": "FileBasedObject",
+ "id": "3D_Dollhouse_Happy_Brother",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.026723852722585442,
+ -0.01745439572330229,
+ -0.047557430906925276
+ ],
+ [
+ 0.03264914727741456,
+ 0.013312604276697709,
+ 0.047942569093074726
+ ]
+ ],
+ "mass": 4.4849064412948164e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "3D Dollhouse Happy Brother",
+ "nr_faces": 14142,
+ "nr_vertices": 7505,
+ "surface_area": 0.011254228026575316,
+ "volume": 4.4849064412948164e-05
+ }
+ },
+ "3D_Dollhouse_Lamp": {
+ "asset_type": "FileBasedObject",
+ "id": "3D_Dollhouse_Lamp",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.024088324656030974,
+ -0.022682253608113854,
+ -0.09719308016472121
+ ],
+ [
+ 0.023891675343969025,
+ 0.023931746391886145,
+ 0.06962791983527877
+ ]
+ ],
+ "mass": 8.886284554864667e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "3D Dollhouse Lamp",
+ "nr_faces": 10490,
+ "nr_vertices": 5497,
+ "surface_area": 0.016527649035403155,
+ "volume": 8.886284554864667e-05
+ }
+ },
+ "3D_Dollhouse_Refrigerator": {
+ "asset_type": "FileBasedObject",
+ "id": "3D_Dollhouse_Refrigerator",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.039865447079539956,
+ -0.0406425931968834,
+ -0.10549159907347196
+ ],
+ [
+ 0.039841552920460044,
+ 0.032817406803116594,
+ 0.10447740092652803
+ ]
+ ],
+ "mass": 0.0010273192164318907,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "3D Dollhouse Refrigerator",
+ "nr_faces": 3202,
+ "nr_vertices": 1808,
+ "surface_area": 0.07104691980953148,
+ "volume": 0.0010273192164318907
+ }
+ },
+ "3D_Dollhouse_Sink": {
+ "asset_type": "FileBasedObject",
+ "id": "3D_Dollhouse_Sink",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04291704628210053,
+ -0.041634581010720664,
+ -0.051747663643321846
+ ],
+ [
+ 0.04252195371789947,
+ 0.031798418989279334,
+ 0.07933033635667816
+ ]
+ ],
+ "mass": 0.0005395708309459827,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "3D Dollhouse Sink",
+ "nr_faces": 7978,
+ "nr_vertices": 4356,
+ "surface_area": 0.05037467250053666,
+ "volume": 0.0005395708309459827
+ }
+ },
+ "3D_Dollhouse_Sofa": {
+ "asset_type": "FileBasedObject",
+ "id": "3D_Dollhouse_Sofa",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1050882917650944,
+ -0.052434382993111456,
+ -0.04719362216988259
+ ],
+ [
+ 0.1045447082349056,
+ 0.03437961700688854,
+ 0.055100377830117404
+ ]
+ ],
+ "mass": 0.000618820027269369,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "3D Dollhouse Sofa",
+ "nr_faces": 15052,
+ "nr_vertices": 7812,
+ "surface_area": 0.08308729649613138,
+ "volume": 0.000618820027269369
+ }
+ },
+ "3D_Dollhouse_Swing": {
+ "asset_type": "FileBasedObject",
+ "id": "3D_Dollhouse_Swing",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0524096448632462,
+ -0.057424242396357544,
+ -0.02675578665585615
+ ],
+ [
+ 0.0524093551367538,
+ 0.03783175760364245,
+ 0.06539021334414385
+ ]
+ ],
+ "mass": 0.00014358798637728482,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "3D Dollhouse Swing",
+ "nr_faces": 8876,
+ "nr_vertices": 4762,
+ "surface_area": 0.040352760307233906,
+ "volume": 0.00014358798637728482
+ }
+ },
+ "3D_Dollhouse_TablePurple": {
+ "asset_type": "FileBasedObject",
+ "id": "3D_Dollhouse_TablePurple",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.049647924032747585,
+ -0.044294253995552896,
+ -0.0379742027553476
+ ],
+ [
+ 0.04834007596725241,
+ 0.0457817460044471,
+ 0.019410797244652403
+ ]
+ ],
+ "mass": 9.068363876192367e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "3D Dollhouse Table-Purple",
+ "nr_faces": 6446,
+ "nr_vertices": 3629,
+ "surface_area": 0.02220204730081645,
+ "volume": 9.068363876192367e-05
+ }
+ },
+ "3M_Antislip_Surfacing_Light_Duty_White": {
+ "asset_type": "FileBasedObject",
+ "id": "3M_Antislip_Surfacing_Light_Duty_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07689825847789031,
+ -0.0766361089787033,
+ -0.014169478479359562
+ ],
+ [
+ 0.0778027415221097,
+ 0.07689689102129671,
+ 0.014490521520640438
+ ]
+ ],
+ "mass": 0.0003658385228281465,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "3M Antislip Surfacing; Light Duty; White",
+ "nr_faces": 4750,
+ "nr_vertices": 2478,
+ "surface_area": 0.046182899897214746,
+ "volume": 0.0003658385228281465
+ }
+ },
+ "3M_Vinyl_Tape_Green_1_x_36_yd": {
+ "asset_type": "FileBasedObject",
+ "id": "3M_Vinyl_Tape_Green_1_x_36_yd",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05544092366579215,
+ -0.05524789693140713,
+ -0.01330682733935257
+ ],
+ [
+ 0.055345076334207856,
+ 0.05516710306859287,
+ 0.01337717266064743
+ ]
+ ],
+ "mass": 0.00012464324935809517,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "3M Vinyl Tape, Green, 1\" x 36 yd",
+ "nr_faces": 11422,
+ "nr_vertices": 5911,
+ "surface_area": 0.02441273309037041,
+ "volume": 0.00012464324935809517
+ }
+ },
+ "45oz_RAMEKIN_ASST_DEEP_COLORS": {
+ "asset_type": "FileBasedObject",
+ "id": "45oz_RAMEKIN_ASST_DEEP_COLORS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.044717757259328465,
+ -0.04479763734743804,
+ -0.017673998529506466
+ ],
+ [
+ 0.04498924274067153,
+ 0.04519036265256196,
+ 0.026284001470493534
+ ]
+ ],
+ "mass": 7.799111003135782e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "4.5oz RAMEKIN ASST DEEP COLORS",
+ "nr_faces": 15358,
+ "nr_vertices": 7849,
+ "surface_area": 0.029197804157282486,
+ "volume": 7.799111003135782e-05
+ }
+ },
+ "50_BLOCKS": {
+ "asset_type": "FileBasedObject",
+ "id": "50_BLOCKS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18780417302765293,
+ -0.08603886467177346,
+ -0.03462015987605083
+ ],
+ [
+ 0.16798982697234707,
+ 0.06001213532822654,
+ 0.07594484012394917
+ ]
+ ],
+ "mass": 0.0015668335003616433,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "50 BLOCKS\nContains 36 natural blocks and 14 color blocks. ?The set reinforces creativity, expands children?s thinking ability, and stimulates their imagination.",
+ "nr_faces": 10728,
+ "nr_vertices": 6651,
+ "surface_area": 0.15367017019026624,
+ "volume": 0.0015668335003616433
+ }
+ },
+ "5_HTP": {
+ "asset_type": "FileBasedObject",
+ "id": "5_HTP",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02656369853001526,
+ -0.026253767156267118,
+ -0.040457275020305765
+ ],
+ [
+ 0.02655230146998474,
+ 0.02624023284373288,
+ 0.04836572497969423
+ ]
+ ],
+ "mass": 0.00016492092893135833,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "5 HTP",
+ "nr_faces": 8362,
+ "nr_vertices": 4292,
+ "surface_area": 0.017379391669970067,
+ "volume": 0.00016492092893135833
+ }
+ },
+ "60_CONSTRUCTION_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "60_CONSTRUCTION_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07777840167968358,
+ -0.1583298898532799,
+ -0.0901442348928813
+ ],
+ [
+ 0.08050559832031641,
+ 0.18526411014672012,
+ 0.1351447651071187
+ ]
+ ],
+ "mass": 0.0014243554084323042,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "60 CONSTRUCTION SET\nThe pieces can be easily assembled and reassembled to create any imaginable form. ?",
+ "nr_faces": 26126,
+ "nr_vertices": 16831,
+ "surface_area": 0.21534886430782899,
+ "volume": 0.0014243554084323042
+ }
+ },
+ "ACE_Coffee_Mug_Kristen_16_oz_cup": {
+ "asset_type": "FileBasedObject",
+ "id": "ACE_Coffee_Mug_Kristen_16_oz_cup",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05091152848475182,
+ -0.04607881137069598,
+ -0.06255976048966282
+ ],
+ [
+ 0.07541047151524818,
+ 0.044545188629304025,
+ 0.07237623951033718
+ ]
+ ],
+ "mass": 0.0001941827713465546,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "ACE Coffee Mug, Kristen, 16 oz cup",
+ "nr_faces": 11224,
+ "nr_vertices": 5806,
+ "surface_area": 0.07352322979904526,
+ "volume": 0.0001941827713465546
+ }
+ },
+ "ALPHABET_AZ_GRADIENT": {
+ "asset_type": "FileBasedObject",
+ "id": "ALPHABET_AZ_GRADIENT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15771439253324876,
+ -0.14281259491253945,
+ -0.005799297309105448
+ ],
+ [
+ 0.17461360746675125,
+ 0.13498240508746057,
+ 0.006741702690894553
+ ]
+ ],
+ "mass": 0.0005824211500757473,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "ALPHABET A-Z (GRADIENT)\nDevelop your fundamental skills with this alphabet set. The two-sided wooden tiles feature 26 intended capital letters and pictures of objects that correspond to the letter. Trace the letters with your finger and expand your vocabulary!",
+ "nr_faces": 14692,
+ "nr_vertices": 7779,
+ "surface_area": 0.17559044318100983,
+ "volume": 0.0005824211500757473
+ }
+ },
+ "ALPHABET_AZ_GRADIENT_WQb1ufEycSj": {
+ "asset_type": "FileBasedObject",
+ "id": "ALPHABET_AZ_GRADIENT_WQb1ufEycSj",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13491910482271757,
+ -0.16848602463961682,
+ -0.004680820654068869
+ ],
+ [
+ 0.14130089517728242,
+ 0.1634579753603832,
+ 0.0058301793459311305
+ ]
+ ],
+ "mass": 0.0005215021772800731,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "ALPHABET A-Z (GRADIENT)\nDevelop your fundamental skills with this alphabet set. The two-sided wooden tiles feature 26 intended capital letters and pictures of objects that correspond to the letter. Trace the letters with your finger and expand your vocabulary!",
+ "nr_faces": 13878,
+ "nr_vertices": 7257,
+ "surface_area": 0.17210088186789893,
+ "volume": 0.0005215021772800731
+ }
+ },
+ "AMBERLIGHT_UP_W": {
+ "asset_type": "FileBasedObject",
+ "id": "AMBERLIGHT_UP_W",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056002250504023916,
+ -0.1470083654053324,
+ -0.06110370996672471
+ ],
+ [
+ 0.04738874949597608,
+ 0.0983036345946676,
+ 0.11853829003327529
+ ]
+ ],
+ "mass": 0.0016114084652369739,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "AMBERLIGHT UP W",
+ "nr_faces": 23444,
+ "nr_vertices": 12917,
+ "surface_area": 0.10709713529353114,
+ "volume": 0.0016114084652369739
+ }
+ },
+ "ASICS_GEL1140V_WhiteBlackSilver": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GEL1140V_WhiteBlackSilver",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05906025148145178,
+ -0.14475419761792885,
+ -0.039453504207676016
+ ],
+ [
+ 0.04713574851854822,
+ 0.13601380238207114,
+ 0.08362149579232397
+ ]
+ ],
+ "mass": 0.0011914299197243185,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-1140V\u2122 - White/Black/Silver\nHigh on speed and cushioning, this update to our ever-popular 1000V series comes with a breathable mesh upper, the enhanced comfort of a Ventilated Sole Unit, rearfoot GEL\u00ae Cushioning System, a removable sockliner, a the super lightweight comfort of a Solyte\u00ae Midsole Material.",
+ "nr_faces": 37508,
+ "nr_vertices": 20136,
+ "surface_area": 0.1190785585207651,
+ "volume": 0.0011914299197243185
+ }
+ },
+ "ASICS_GEL1140V_WhiteRoyalSilver": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GEL1140V_WhiteRoyalSilver",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05885494617415207,
+ -0.15629089564908227,
+ -0.03964261156493644
+ ],
+ [
+ 0.04680905382584793,
+ 0.12442410435091775,
+ 0.08407938843506357
+ ]
+ ],
+ "mass": 0.0010159192030460618,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-1140V\u2122 - White/Royal/Silver\nHigh on speed and cushioning, this update to our ever-popular 1000V series comes with a breathable mesh upper, the enhanced comfort of a Ventilated Sole Unit, rearfoot GEL\u00ae Cushioning System, a removable sockliner, a the super lightweight comfort of a Solyte\u00ae Midsole Material.",
+ "nr_faces": 38246,
+ "nr_vertices": 21018,
+ "surface_area": 0.14421596159695793,
+ "volume": 0.0010159192030460618
+ }
+ },
+ "ASICS_GELAce_Pro_Pearl_WhitePink": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELAce_Pro_Pearl_WhitePink",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.057395375016985384,
+ -0.1609760222812207,
+ -0.0482151934905794
+ ],
+ [
+ 0.04794562498301462,
+ 0.1291869777187793,
+ 0.0853958065094206
+ ]
+ ],
+ "mass": 0.001038388073537098,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Ace\u2122 Pro - Pearl White/Pink\nASICS most advanced golf shoe, and the choice of pros the world over. Soft waterproof upper and GEL\u00ae Cushioning System mean comfort, while the supportive Trusstic System\u00ae will give you the stability for a balanced swing.",
+ "nr_faces": 45698,
+ "nr_vertices": 26158,
+ "surface_area": 0.1646454979772767,
+ "volume": 0.001038388073537098
+ }
+ },
+ "ASICS_GELBlur33_20_GS_BlackWhiteSafety_Orange": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELBlur33_20_GS_BlackWhiteSafety_Orange",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.052477074846003405,
+ -0.12721565168566876,
+ -0.03587227822134617
+ ],
+ [
+ 0.047038925153996596,
+ 0.12706234831433125,
+ 0.062324721778653835
+ ]
+ ],
+ "mass": 0.00089370687757805,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Blur33\u2122 2.0 GS - Black/White/Safety Orange\nFast and form fitting, the GEL-Blur33\u2122 2.0 GS delivers great comfort and flexibility in a lightweight package.",
+ "nr_faces": 39092,
+ "nr_vertices": 21285,
+ "surface_area": 0.09494383022699383,
+ "volume": 0.00089370687757805
+ }
+ },
+ "ASICS_GELBlur33_20_GS_Flash_YellowHot_PunchSilver": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELBlur33_20_GS_Flash_YellowHot_PunchSilver",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.053197069154732414,
+ -0.12657442736158006,
+ -0.03712090283085707
+ ],
+ [
+ 0.04593893084526758,
+ 0.12709557263841992,
+ 0.07742109716914293
+ ]
+ ],
+ "mass": 0.0008891659839215323,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Blur33\u2122 2.0 GS - Flash Yellow/Hot Punch/Silver\nFast and form fitting, the GEL-Blur33\u2122 2.0 GS delivers great comfort and flexibility in a lightweight package.",
+ "nr_faces": 30660,
+ "nr_vertices": 16551,
+ "surface_area": 0.0998927230514932,
+ "volume": 0.0008891659839215323
+ }
+ },
+ "ASICS_GELChallenger_9_Royal_BlueWhiteBlack": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELChallenger_9_Royal_BlueWhiteBlack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06211305670470753,
+ -0.15368701962702366,
+ -0.04197464825630685
+ ],
+ [
+ 0.05088494329529247,
+ 0.14477398037297634,
+ 0.07299035174369314
+ ]
+ ],
+ "mass": 0.0015239076704750137,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Challenger\u00ae 9 - Royal Blue/White/Black\nThe GEL-Challenger\u00ae 9 provides exceptional comfort with Rearfoot & Forefoot GEL\u00ae Cushioning Systems and outstanding stability and support with a hidden midfoot Trusstic System\u00ae. Excellent upper fit is addressed with P.H.F.\u2122 in the collar, while synthetic leather and mesh upper materials provide enhanced breathability and flexibility. A perfect choice for that everyday tennis enthusiast.",
+ "nr_faces": 33438,
+ "nr_vertices": 18155,
+ "surface_area": 0.1335674646755035,
+ "volume": 0.0015239076704750137
+ }
+ },
+ "ASICS_GELDirt_Dog_4_SunFlameBlack": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELDirt_Dog_4_SunFlameBlack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05659622024926075,
+ -0.14093574755776192,
+ -0.03860675229011897
+ ],
+ [
+ 0.04715077975073925,
+ 0.14334125244223805,
+ 0.07104524770988102
+ ]
+ ],
+ "mass": 0.0009873391790812334,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Dirt Dog\u00ae 4 - Sun/Flame/Black\nCross-country racers who like the comfort and platform of a track spike along with superior comfort and durability, will love the all-new amazing upper we've built into this popular performance favorite.",
+ "nr_faces": 44502,
+ "nr_vertices": 23859,
+ "surface_area": 0.10166446180114781,
+ "volume": 0.0009873391790812334
+ }
+ },
+ "ASICS_GELLinksmaster_WhiteCoffeeSand": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELLinksmaster_WhiteCoffeeSand",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06302602442868224,
+ -0.15770439777451506,
+ -0.05050779920411798
+ ],
+ [
+ 0.053281975571317766,
+ 0.14146460222548496,
+ 0.09083520079588202
+ ]
+ ],
+ "mass": 0.0014090550917967505,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Linksmaster\u00ae - White/Coffee/Sand\nThe traditional golfer's saddle design meets comfort and support in this shoe. Waterproof, for the dew-covered grass of early morning rounds, with a stable, supportive sole for comfort and fit. A great bargain.",
+ "nr_faces": 34586,
+ "nr_vertices": 20162,
+ "surface_area": 0.13601361789311284,
+ "volume": 0.0014090550917967505
+ }
+ },
+ "ASICS_GELLinksmaster_WhiteRasberryGunmetal": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELLinksmaster_WhiteRasberryGunmetal",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05759070906409638,
+ -0.1437085125741298,
+ -0.046403675589639926
+ ],
+ [
+ 0.04773229093590362,
+ 0.1291414874258702,
+ 0.07377132441036008
+ ]
+ ],
+ "mass": 0.0011082095927461898,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Linksmaster\u00ae - White/Rasberry/Gunmetal\nThe traditional golfer's saddle design meets comfort and support in this shoe. Waterproof, for the dew-covered grass of early morning rounds, with a stable, supportive sole for comfort and fit. A great bargain.",
+ "nr_faces": 31266,
+ "nr_vertices": 18033,
+ "surface_area": 0.10801904877738071,
+ "volume": 0.0011082095927461898
+ }
+ },
+ "ASICS_GELLinksmaster_WhiteSilverCarolina_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELLinksmaster_WhiteSilverCarolina_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05834851669068435,
+ -0.15381500166601875,
+ -0.04532822132375507
+ ],
+ [
+ 0.04848748330931565,
+ 0.11905299833398125,
+ 0.08733077867624492
+ ]
+ ],
+ "mass": 0.000873732413741357,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Linksmaster\u00ae - White/Silver/Carolina Blue\nThe traditional golfer's saddle design meets comfort and support in this shoe. Waterproof, for the dew-covered grass of early morning rounds, with a stable, supportive sole for comfort and fit. A great bargain.",
+ "nr_faces": 34160,
+ "nr_vertices": 19650,
+ "surface_area": 0.13863028001682257,
+ "volume": 0.000873732413741357
+ }
+ },
+ "ASICS_GELResolution_5_Flash_YellowBlackSilver": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELResolution_5_Flash_YellowBlackSilver",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06298948966165127,
+ -0.16719334570495115,
+ -0.03962277412052808
+ ],
+ [
+ 0.04986151033834873,
+ 0.13210665429504884,
+ 0.07472622587947192
+ ]
+ ],
+ "mass": 0.0012423159315045084,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Resolution\u00ae 5 - Flash Yellow/Black/Silver\nThe pinnacle of the ASICS stability tennis line, the GEL-Resolution\u00ae 5 doesn't disappoint. The newest edition to this series features an improved Flexion Fit\u2122 upper design providing one-of-kind upper comfort, in addition to a re-designed PGuard\u2122 improving upper flexibility. New to this model, a hidden Trusstic System\u00ae has been developed to allow full ground outsole contact all while providing the superb medial stability and torsional rigidity that this series is known for. The best just got better.",
+ "nr_faces": 36694,
+ "nr_vertices": 19614,
+ "surface_area": 0.1634307973916196,
+ "volume": 0.0012423159315045084
+ }
+ },
+ "ASICS_GELTour_Lyte_WhiteOrchidSilver": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_GELTour_Lyte_WhiteOrchidSilver",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05391635548113637,
+ -0.13655459463642902,
+ -0.042983707220308115
+ ],
+ [
+ 0.04637664451886363,
+ 0.129751405363571,
+ 0.07888929277969188
+ ]
+ ],
+ "mass": 0.0009783309706954814,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS GEL-Tour Lyte\u00ae - White/Orchid/Silver\nA favorite with the weekend golfers and those seeking a softer, more flexible shoe. Combines the comfort and fit of a great running shoe with the stability and support of a great golf shoe.",
+ "nr_faces": 26000,
+ "nr_vertices": 15434,
+ "surface_area": 0.10570288532853124,
+ "volume": 0.0009783309706954814
+ }
+ },
+ "ASICS_HyperRocketgirl_SP_5_WhiteMalibu_BlueBlack": {
+ "asset_type": "FileBasedObject",
+ "id": "ASICS_HyperRocketgirl_SP_5_WhiteMalibu_BlueBlack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04558995379493912,
+ -0.11736782440391182,
+ -0.03486080159463384
+ ],
+ [
+ 0.043949046205060883,
+ 0.13177817559608818,
+ 0.055432198405366166
+ ]
+ ],
+ "mass": 0.0006129476667228603,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ASICS Hyper-Rocketgirl\u2122 SP 5 - White/Malibu Blue/Black\nSleek and speedy in design, the 5th rendition of the sprint favorite features a combination of mesh and hotmelt TPU overlays in the rearfoot while maintaining it's supportive synthetic leather forefoot. The thin rubber outsole is combined with a lightweight nylon spike plate and five-pin spike design for optimal traction. If you've got a date with velocity, we have the perfect shoes.",
+ "nr_faces": 21152,
+ "nr_vertices": 11735,
+ "surface_area": 0.07776367090150918,
+ "volume": 0.0006129476667228603
+ }
+ },
+ "ASSORTED_VEGETABLE_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "ASSORTED_VEGETABLE_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1266298056585386,
+ -0.07258000172955723,
+ -0.024908079000718505
+ ],
+ [
+ 0.1035621943414614,
+ 0.06285099827044277,
+ 0.0502809209992815
+ ]
+ ],
+ "mass": 0.00045942716851214975,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "ASSORTED VEGETABLE SET\nThe set includes a cutting board, knife, and 5 sliceable veggies - tomato, mushroom, shallot, bell pepper, and cucumber. Tactile details offer realistic play.",
+ "nr_faces": 20336,
+ "nr_vertices": 12285,
+ "surface_area": 0.10394156572046372,
+ "volume": 0.00045942716851214975
+ }
+ },
+ "Adrenaline_GTS_13_Color_DrkDenimWhtBachlorBttnSlvr_Size_50_yfK40TNjq0V": {
+ "asset_type": "FileBasedObject",
+ "id": "Adrenaline_GTS_13_Color_DrkDenimWhtBachlorBttnSlvr_Size_50_yfK40TNjq0V",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06286790170860973,
+ -0.1572228809234142,
+ -0.0390465449953629
+ ],
+ [
+ 0.04892409829139027,
+ 0.1308331190765858,
+ 0.08528745500463711
+ ]
+ ],
+ "mass": 0.001057904861433184,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Adrenaline GTS 13, Color: DrkDenim/Wht/BachlorBttn/Slvr, Size: 5.0\nLucky 13 is our best Adrenaline GTS yet. We paid special attention to the underfoot flex by adding Omega Flex Grooves and continuing Omni Grooves in the forefoot, allowing the outsole to bend and shape naturally. Continuing with the tradition of a tailored fit, stretch eyelets lock into the medial side to capture the foot better and technologies like Flextra and anatomical Brooks DNA deliver customized stability and cushion. We're not the only Adrenaline junkies out there - Runner's World named the GTS 13 Editor's Choice in the Fall Shoe Guide in their December 2012 issue. They call the GTS 13 a \"classic stability shoe\", and quoted one wear tester as saying, \"it's soft enough that you can feel the road surface below, but there's enough padding that you don't feel as though you're running on concrete blocks.\" No luck here, just purely good design. > See the Men's Adrenaline GTS 13Category: Support Weight: 11.3 oz Platform: Universal Construction: Combination Midsole • Anatomical Brooks DNA - Working with BioMoGo, Brooks DNA responds to your every step, dispersing impact and providing ideal comfort and protection as the pace and surface change. • Full-length BioMoGo - Our midsoles are now more environmentally friendly by adding a non-toxic, natural additive to the MoGo compound that encourages anaerobic microbes to munch away once it hits an enclosed, active landfill. • Progressive Diagonal Rollbar (PDRB) - Our tri-density PDRB midsoles are biomechanically engineered to allow for progressive pronation control and to create smoother transitions from the midstance phase into the propulsion phase. • Omega Flex Grooves - This innovation enhances the flexibility of the midsole and provides an effortless forefoot ride while still offering great cushioning and midsole integrity. The unique shape of the groove allows it to flex dynamically without compromising cushioning. When at rest, it supports the shoe; when it's flexing, the groove opens up to...",
+ "nr_faces": 45866,
+ "nr_vertices": 25326,
+ "surface_area": 0.15882286562286344,
+ "volume": 0.001057904861433184
+ }
+ },
+ "Adrenaline_GTS_13_Color_WhtObsdianBlckOlmpcSlvr_Size_70": {
+ "asset_type": "FileBasedObject",
+ "id": "Adrenaline_GTS_13_Color_WhtObsdianBlckOlmpcSlvr_Size_70",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06568464989840186,
+ -0.166349329114277,
+ -0.0407394404062761
+ ],
+ [
+ 0.05251935010159814,
+ 0.140433670885723,
+ 0.0899395595937239
+ ]
+ ],
+ "mass": 0.0012223616020216026,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Adrenaline GTS 13, Color: Wht/Obsdian/Blck/Olmpc/Slvr, Size: 7.0\nLucky 13 is our best Adrenaline GTS yet. We paid special attention to the underfoot flex by adding Omega Flex Grooves and continuing Omni Grooves in the forefoot, allowing the outsole to bend and shape naturally. Continuing with the tradition of a tailored fit, stretch eyelets lock into the medial side to capture the foot better and technologies like Flextra and anatomical Brooks DNA deliver customized stability and cushion. We're not the only Adrenaline junkies out there - Runner's World named the GTS 13 Editor's Choice in the Fall Shoe Guide in their December 2012 issue. They call the GTS 13 a \"classic stability shoe\", and quoted one wear tester as saying, \"it's soft enough that you can feel the road surface below, but there's enough padding that you don't feel as though you're running on concrete blocks.\" No luck here, just purely good design. > See the Women's Adrenaline GTS 13Category: Support Weight: 11.3 oz Platform: Universal Construction: Combination Midsole • Anatomical Brooks DNA - Working with BioMoGo, Brooks DNA responds to your every step, dispersing impact and providing ideal comfort and protection as the pace and surface change. • Full-length BioMoGo - Our midsoles are now more environmentally friendly by adding a non-toxic, natural additive to the MoGo compound that encourages anaerobic microbes to munch away once it hits an enclosed, active landfill. • Progressive Diagonal Rollbar (PDRB) - Our tri-density PDRB midsoles are biomechanically engineered to allow for progressive pronation control and to create smoother transitions from the midstance phase into the propulsion phase. • Omega Flex Grooves - This innovation enhances the flexibility of the midsole and provides an effortless forefoot ride while still offering great cushioning and midsole integrity. The unique shape of the groove allows it to flex dynamically without compromising cushioning. When at rest, it supports the shoe; when it's flexing, the groove opens up to...",
+ "nr_faces": 48412,
+ "nr_vertices": 27687,
+ "surface_area": 0.17758617415774655,
+ "volume": 0.0012223616020216026
+ }
+ },
+ "Air_Hogs_Wind_Flyers_Set_Airplane_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Air_Hogs_Wind_Flyers_Set_Airplane_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13524384530405448,
+ -0.11168838229722974,
+ -0.027947983331190397
+ ],
+ [
+ 0.1331021546959455,
+ 0.16034361770277025,
+ 0.0223070166688096
+ ]
+ ],
+ "mass": 0.00017618873924928015,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Air Hogs Wind Flyers Set, Airplane, Red",
+ "nr_faces": 5762,
+ "nr_vertices": 3320,
+ "surface_area": 0.06360892848651806,
+ "volume": 0.00017618873924928015
+ }
+ },
+ "AllergenFree_JarroDophilus": {
+ "asset_type": "FileBasedObject",
+ "id": "AllergenFree_JarroDophilus",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02695335824507885,
+ -0.02670571766100563,
+ -0.04379079066796004
+ ],
+ [
+ 0.026935641754921153,
+ 0.02688128233899437,
+ 0.05220620933203997
+ ]
+ ],
+ "mass": 0.00018661403418632466,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Allergen-Free Jarro-Dophilus?",
+ "nr_faces": 8126,
+ "nr_vertices": 4163,
+ "surface_area": 0.018809745795664464,
+ "volume": 0.00018661403418632466
+ }
+ },
+ "Android_Figure_Chrome": {
+ "asset_type": "FileBasedObject",
+ "id": "Android_Figure_Chrome",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03480750697978227,
+ -0.02295768242173303,
+ -0.039971669813058934
+ ],
+ [
+ 0.03426849302021773,
+ 0.02303731757826697,
+ 0.04147933018694107
+ ]
+ ],
+ "mass": 0.0001017046049527675,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Android Figure, Chrome",
+ "nr_faces": 11836,
+ "nr_vertices": 6458,
+ "surface_area": 0.013507389926613312,
+ "volume": 0.0001017046049527675
+ }
+ },
+ "Android_Figure_Orange": {
+ "asset_type": "FileBasedObject",
+ "id": "Android_Figure_Orange",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03297670982993869,
+ -0.022997183275781888,
+ -0.03995028459696738
+ ],
+ [
+ 0.03303329017006131,
+ 0.022907816724218114,
+ 0.040736715403032614
+ ]
+ ],
+ "mass": 9.930552179513283e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Android Figure, Orange",
+ "nr_faces": 9698,
+ "nr_vertices": 5206,
+ "surface_area": 0.01372990120278495,
+ "volume": 9.930552179513283e-05
+ }
+ },
+ "Android_Figure_Panda": {
+ "asset_type": "FileBasedObject",
+ "id": "Android_Figure_Panda",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.029883394790535343,
+ -0.023036667409844964,
+ -0.03995078161708675
+ ],
+ [
+ 0.03087760520946466,
+ 0.023245332590155036,
+ 0.03578821838291326
+ ]
+ ],
+ "mass": 9.995828148993216e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Android Figure, Panda",
+ "nr_faces": 10618,
+ "nr_vertices": 5654,
+ "surface_area": 0.013912816746940207,
+ "volume": 9.995828148993216e-05
+ }
+ },
+ "Android_Lego": {
+ "asset_type": "FileBasedObject",
+ "id": "Android_Lego",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.048219832445059986,
+ -0.011972773737285544,
+ -0.05265769934448073
+ ],
+ [
+ 0.048584167554940015,
+ 0.009865226262714456,
+ 0.053691300655519275
+ ]
+ ],
+ "mass": 9.5538356494815e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "Android Lego",
+ "nr_faces": 14214,
+ "nr_vertices": 8226,
+ "surface_area": 0.019632894537553954,
+ "volume": 9.5538356494815e-05
+ }
+ },
+ "Animal_Crossing_New_Leaf_Nintendo_3DS_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Animal_Crossing_New_Leaf_Nintendo_3DS_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06684817924411086,
+ -0.06230467695668094,
+ -0.007270146064271115
+ ],
+ [
+ 0.07033182075588915,
+ 0.06257132304331907,
+ 0.007860853935728884
+ ]
+ ],
+ "mass": 0.00022459374033425146,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Animal Crossing: New Leaf [Nintendo 3DS Game]",
+ "nr_faces": 2444,
+ "nr_vertices": 1331,
+ "surface_area": 0.040088517829656056,
+ "volume": 0.00022459374033425146
+ }
+ },
+ "Animal_Planet_Foam_2Headed_Dragon": {
+ "asset_type": "FileBasedObject",
+ "id": "Animal_Planet_Foam_2Headed_Dragon",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05877973180016057,
+ -0.16764980677715124,
+ -0.08447802944420586
+ ],
+ [
+ 0.05949826819983943,
+ 0.2342531932228487,
+ 0.11533397055579414
+ ]
+ ],
+ "mass": 0.0011308986276811848,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Animal Planet Foam 2-Headed Dragon",
+ "nr_faces": 21978,
+ "nr_vertices": 12891,
+ "surface_area": 0.13414367097314955,
+ "volume": 0.0011308986276811848
+ }
+ },
+ "Apples_to_Apples_Kids_Edition": {
+ "asset_type": "FileBasedObject",
+ "id": "Apples_to_Apples_Kids_Edition",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06852588850786068,
+ -0.13467895163545252,
+ -0.03208644607795677
+ ],
+ [
+ 0.06830911149213932,
+ 0.13469204836454748,
+ 0.03204755392204323
+ ]
+ ],
+ "mass": 0.0022487508090413863,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Apples to Apples - Kids Edition",
+ "nr_faces": 1690,
+ "nr_vertices": 909,
+ "surface_area": 0.12002275850544344,
+ "volume": 0.0022487508090413863
+ }
+ },
+ "Arm_Hammer_Diaper_Pail_Refills_12_Pack_MFWkmoweejt": {
+ "asset_type": "FileBasedObject",
+ "id": "Arm_Hammer_Diaper_Pail_Refills_12_Pack_MFWkmoweejt",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04289860203835368,
+ -0.047490838065229087,
+ -0.08382121285021123
+ ],
+ [
+ 0.04286739796164632,
+ 0.047691161934770916,
+ 0.08539778714978877
+ ]
+ ],
+ "mass": 0.0013029645574030903,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Arm Hammer Diaper Pail Refills 12 Pack",
+ "nr_faces": 2820,
+ "nr_vertices": 1556,
+ "surface_area": 0.07202672113695796,
+ "volume": 0.0013029645574030903
+ }
+ },
+ "Aroma_Stainless_Steel_Milk_Frother_2_Cup": {
+ "asset_type": "FileBasedObject",
+ "id": "Aroma_Stainless_Steel_Milk_Frother_2_Cup",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0541628049527155,
+ -0.0461190233310127,
+ -0.07372493902748814
+ ],
+ [
+ 0.08814519504728449,
+ 0.1115579766689873,
+ 0.07458906097251186
+ ]
+ ],
+ "mass": 0.000925281226075692,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Aroma Stainless Steel Milk Frother - 2 Cup",
+ "nr_faces": 21582,
+ "nr_vertices": 11785,
+ "surface_area": 0.07530206467146557,
+ "volume": 0.000925281226075692
+ }
+ },
+ "Asus_80211ac_DualBand_Gigabit_Wireless_Router_RTAC68R": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_80211ac_DualBand_Gigabit_Wireless_Router_RTAC68R",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1591942956992603,
+ -0.049869166575298565,
+ -0.1191127157245486
+ ],
+ [
+ 0.1595567043007397,
+ 0.049153833424701435,
+ 0.11973728427545141
+ ]
+ ],
+ "mass": 0.0069709179441325795,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus - 802.11ac Dual-Band Gigabit Wireless Router RT-AC68R",
+ "nr_faces": 17458,
+ "nr_vertices": 9838,
+ "surface_area": 0.24450060416771463,
+ "volume": 0.0069709179441325795
+ }
+ },
+ "Asus_M5A78LMUSB3_Motherboard_Micro_ATX_Socket_AM3": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_M5A78LMUSB3_Motherboard_Micro_ATX_Socket_AM3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13739815598239022,
+ -0.03317988073460884,
+ -0.1330149272084578
+ ],
+ [
+ 0.1392878440176098,
+ 0.032557119265391156,
+ 0.13419307279154222
+ ]
+ ],
+ "mass": 0.004065767877641911,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus M5A78L-M/USB3 Motherboard Micro ATX Socket AM3+",
+ "nr_faces": 16504,
+ "nr_vertices": 8484,
+ "surface_area": 0.19801443312562167,
+ "volume": 0.004065767877641911
+ }
+ },
+ "Asus_M5A99FX_PRO_R20_Motherboard_ATX_Socket_AM3": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_M5A99FX_PRO_R20_Motherboard_ATX_Socket_AM3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1683565755348275,
+ -0.037537094433755296,
+ -0.13405287750537564
+ ],
+ [
+ 0.16627442446517252,
+ 0.036535905566244704,
+ 0.13402612249462434
+ ]
+ ],
+ "mass": 0.006054395776499807,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus M5A99FX PRO R2.0 Motherboard ATX Socket AM3+",
+ "nr_faces": 9370,
+ "nr_vertices": 4942,
+ "surface_area": 0.2543697723749209,
+ "volume": 0.006054395776499807
+ }
+ },
+ "Asus_Sabertooth_990FX_20_Motherboard_ATX_Socket_AM3": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_Sabertooth_990FX_20_Motherboard_ATX_Socket_AM3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17416057908492832,
+ -0.04259733681847225,
+ -0.13786394074002145
+ ],
+ [
+ 0.1760404209150717,
+ 0.04204366318152775,
+ 0.13949005925997857
+ ]
+ ],
+ "mass": 0.00761023011513752,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus Sabertooth 990FX 2.0 Motherboard ATX Socket AM3+",
+ "nr_faces": 1708,
+ "nr_vertices": 931,
+ "surface_area": 0.28206117122094304,
+ "volume": 0.00761023011513752
+ }
+ },
+ "Asus_Sabertooth_Z97_MARK_1_Motherboard_ATX_LGA1150_Socket": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_Sabertooth_Z97_MARK_1_Motherboard_ATX_LGA1150_Socket",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17437665294034801,
+ -0.045111901142200754,
+ -0.1381992149152848
+ ],
+ [
+ 0.176180347059652,
+ 0.04431209885779924,
+ 0.13824078508471518
+ ]
+ ],
+ "mass": 0.007793325153867058,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus Sabertooth Z97 MARK 1 - Motherboard - ATX - LGA1150 Socket",
+ "nr_faces": 3184,
+ "nr_vertices": 1767,
+ "surface_area": 0.2827303955038444,
+ "volume": 0.007793325153867058
+ }
+ },
+ "Asus_X99Deluxe_Motherboard_ATX_LGA2011v3_Socket": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_X99Deluxe_Motherboard_ATX_LGA2011v3_Socket",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17494086884345939,
+ -0.04376487031627295,
+ -0.13782578442398738
+ ],
+ [
+ 0.17533313115654062,
+ 0.04339512968372705,
+ 0.13839721557601262
+ ]
+ ],
+ "mass": 0.007715242182208634,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus X99-Deluxe Motherboard ATX LGA2011-v3 Socket",
+ "nr_faces": 2838,
+ "nr_vertices": 1566,
+ "surface_area": 0.28281752121538223,
+ "volume": 0.007715242182208634
+ }
+ },
+ "Asus_Z87PRO_Motherboard_ATX_LGA1150_Socket": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_Z87PRO_Motherboard_ATX_LGA1150_Socket",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1666611998528079,
+ -0.040210918914219206,
+ -0.1344712886781508
+ ],
+ [
+ 0.16750380014719213,
+ 0.041842081085780795,
+ 0.13487671132184917
+ ]
+ ],
+ "mass": 0.00637911942018083,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus Z87-PRO Motherboard ATX LGA1150 Socket",
+ "nr_faces": 3592,
+ "nr_vertices": 1970,
+ "surface_area": 0.25331547909746854,
+ "volume": 0.00637911942018083
+ }
+ },
+ "Asus_Z97AR_LGA_1150_Intel_ATX_Motherboard": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_Z97AR_LGA_1150_Intel_ATX_Motherboard",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1667129394796329,
+ -0.03635327013646326,
+ -0.13376362852186885
+ ],
+ [
+ 0.1674220605203671,
+ 0.036375729863536745,
+ 0.13391437147813118
+ ]
+ ],
+ "mass": 0.006062054954552315,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus Z97-AR LGA 1150 Intel ATX Motherboard",
+ "nr_faces": 5896,
+ "nr_vertices": 3118,
+ "surface_area": 0.2538821838720732,
+ "volume": 0.006062054954552315
+ }
+ },
+ "Asus_Z97IPLUS_Motherboard_Mini_ITX_LGA1150_Socket": {
+ "asset_type": "FileBasedObject",
+ "id": "Asus_Z97IPLUS_Motherboard_Mini_ITX_LGA1150_Socket",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11554807433453866,
+ -0.04972813123168207,
+ -0.09468868353459223
+ ],
+ [
+ 0.11598792566546133,
+ 0.049977868768317925,
+ 0.09492131646540777
+ ]
+ ],
+ "mass": 0.004121895423524619,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Asus Z97I-PLUS Motherboard Mini ITX LGA1150 Socket",
+ "nr_faces": 34176,
+ "nr_vertices": 17644,
+ "surface_area": 0.1630125845494333,
+ "volume": 0.004121895423524619
+ }
+ },
+ "Avengers_Gamma_Green_Smash_Fists": {
+ "asset_type": "FileBasedObject",
+ "id": "Avengers_Gamma_Green_Smash_Fists",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18183122610399144,
+ -0.0652159401327247,
+ -0.09979921748113081
+ ],
+ [
+ 0.17818377389600856,
+ 0.0585840598672753,
+ 0.08371978251886918
+ ]
+ ],
+ "mass": 0.003373868094016556,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Avengers Gamma Green Smash Fists",
+ "nr_faces": 18402,
+ "nr_vertices": 9498,
+ "surface_area": 0.2371366618489712,
+ "volume": 0.003373868094016556
+ }
+ },
+ "Avengers_Thor_PLlrpYniaeB": {
+ "asset_type": "FileBasedObject",
+ "id": "Avengers_Thor_PLlrpYniaeB",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14161885553646128,
+ -0.13404178337791695,
+ -0.04704558078349661
+ ],
+ [
+ 0.14135414446353872,
+ 0.14688821662208307,
+ 0.0855624192165034
+ ]
+ ],
+ "mass": 0.0006270483402649762,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Avengers Thor",
+ "nr_faces": 10822,
+ "nr_vertices": 6335,
+ "surface_area": 0.39875487477554156,
+ "volume": 0.0006270483402649762
+ }
+ },
+ "Azure_Snake_Tieks_Leather_Snake_Print_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Azure_Snake_Tieks_Leather_Snake_Print_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04697249466147659,
+ -0.12344823154831314,
+ -0.02809240427849991
+ ],
+ [
+ 0.04091850533852341,
+ 0.11950576845168687,
+ 0.053375595721500094
+ ]
+ ],
+ "mass": 0.0005066324753668051,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Azure Snake Tieks - Leather Snake Print Ballet Flats\nThese striking ballet flats combine Tiek Blue, cobalt, black and silver in a unique snake print. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 30976,
+ "nr_vertices": 16731,
+ "surface_area": 0.07733883072445924,
+ "volume": 0.0005066324753668051
+ }
+ },
+ "BABY_CAR": {
+ "asset_type": "FileBasedObject",
+ "id": "BABY_CAR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04219093394458363,
+ -0.048117486811076936,
+ -0.028651198622155608
+ ],
+ [
+ 0.042572066055416365,
+ 0.04873651318892307,
+ 0.04397680137784439
+ ]
+ ],
+ "mass": 0.00017652012775550032,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BABY CAR\nThis colorful toy car has a flexible body that reacts to your baby?s touch.",
+ "nr_faces": 17646,
+ "nr_vertices": 9649,
+ "surface_area": 0.037515836547785196,
+ "volume": 0.00017652012775550032
+ }
+ },
+ "BAGEL_WITH_CHEESE": {
+ "asset_type": "FileBasedObject",
+ "id": "BAGEL_WITH_CHEESE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06857701870909264,
+ -0.06485998956664343,
+ -0.013788820728205668
+ ],
+ [
+ 0.06506798129090736,
+ 0.06742501043335657,
+ 0.018721179271794335
+ ]
+ ],
+ "mass": 0.0002566278876686914,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BAGEL WITH CHEESE\nIncludes 1 bagel cut in half, 1 plate, 1 strawberry, ?1 slice of cheese, and 2 slices of cucumber, tomato, ?and onion.",
+ "nr_faces": 14524,
+ "nr_vertices": 7989,
+ "surface_area": 0.04629894055160326,
+ "volume": 0.0002566278876686914
+ }
+ },
+ "BAKING_UTENSILS": {
+ "asset_type": "FileBasedObject",
+ "id": "BAKING_UTENSILS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19619565206641437,
+ -0.159257383934293,
+ -0.0129155394605329
+ ],
+ [
+ 0.12982834793358566,
+ 0.09504061606570699,
+ 0.022673460539467095
+ ]
+ ],
+ "mass": 0.0002942919631679845,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BAKING UTENSILS\nIncludes a rolling pin, measuring spoons, whisk, pastry cutter, and a spatula.",
+ "nr_faces": 6782,
+ "nr_vertices": 3837,
+ "surface_area": 0.07245111175169677,
+ "volume": 0.0002942919631679845
+ }
+ },
+ "BALANCING_CACTUS": {
+ "asset_type": "FileBasedObject",
+ "id": "BALANCING_CACTUS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12888617175884862,
+ -0.07795884262304315,
+ -0.11330318668562371
+ ],
+ [
+ 0.13464982824115138,
+ 0.05679815737695685,
+ 0.1041518133143763
+ ]
+ ],
+ "mass": 0.0006026760717283341,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BALANCING CACTUS\nIt?s all about strategy! The player that can build and balance the cactus without making it fall is the winner. Ideal for 1 - 4 players.",
+ "nr_faces": 11788,
+ "nr_vertices": 6938,
+ "surface_area": 0.08751407501982941,
+ "volume": 0.0006026760717283341
+ }
+ },
+ "BATHROOM_CLASSIC": {
+ "asset_type": "FileBasedObject",
+ "id": "BATHROOM_CLASSIC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09111340172161045,
+ -0.10550845747331267,
+ -0.03554268049801226
+ ],
+ [
+ 0.08502459827838955,
+ 0.07970554252668734,
+ 0.11536931950198775
+ ]
+ ],
+ "mass": 0.0004990192903800595,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BATHROOM - CLASSIC\nChildren can enjoy decorating their dollhouse with the Classic set of furniture while developing their imagination and creating more interest time.",
+ "nr_faces": 6320,
+ "nr_vertices": 3560,
+ "surface_area": 0.09637414885002189,
+ "volume": 0.0004990192903800595
+ }
+ },
+ "BATHROOM_FURNITURE_SET_1": {
+ "asset_type": "FileBasedObject",
+ "id": "BATHROOM_FURNITURE_SET_1",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07046334732078006,
+ -0.13587753809141825,
+ -0.02727061508012074
+ ],
+ [
+ 0.09613265267921993,
+ 0.07437446190858173,
+ 0.12195538491987926
+ ]
+ ],
+ "mass": 0.0002486172590057005,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BATHROOM (FURNITURE SET 1)\nThis set includes stand up shower with removable shower head, a sink, a toilet, and a bathtub. Made of Eco-Friendly PlanWood and solid rubber wood.",
+ "nr_faces": 6798,
+ "nr_vertices": 3868,
+ "surface_area": 0.06726381996886646,
+ "volume": 0.0002486172590057005
+ }
+ },
+ "BEDROOM_CLASSIC": {
+ "asset_type": "FileBasedObject",
+ "id": "BEDROOM_CLASSIC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15558590351753468,
+ -0.21815207201116138,
+ -0.049850317616787106
+ ],
+ [
+ 0.11301109648246534,
+ 0.0968029279888386,
+ 0.1039296823832129
+ ]
+ ],
+ "mass": 0.001220548339031587,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BEDROOM - CLASSIC\nChildren can enjoy decorating their dollhouse with the Classic set of furniture while developing their imagination and creating more interest time.",
+ "nr_faces": 8436,
+ "nr_vertices": 5113,
+ "surface_area": 0.16297845419954946,
+ "volume": 0.001220548339031587
+ }
+ },
+ "BEDROOM_CLASSIC_Gi22DjScTVS": {
+ "asset_type": "FileBasedObject",
+ "id": "BEDROOM_CLASSIC_Gi22DjScTVS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.2209911301791313,
+ -0.0746373283487344,
+ -0.04946558374894942
+ ],
+ [
+ 0.12241086982086867,
+ 0.1033506716512656,
+ 0.10255241625105058
+ ]
+ ],
+ "mass": 0.0012209357248406402,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BEDROOM - CLASSIC\nChildren can enjoy decorating their dollhouse with the Classic set of furniture while developing their imagination and creating more interest time.",
+ "nr_faces": 8872,
+ "nr_vertices": 5367,
+ "surface_area": 0.16295451875611763,
+ "volume": 0.0012209357248406402
+ }
+ },
+ "BEDROOM_NEO": {
+ "asset_type": "FileBasedObject",
+ "id": "BEDROOM_NEO",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17019364740638956,
+ -0.1551504200023692,
+ -0.05351216412180401
+ ],
+ [
+ 0.09252035259361044,
+ 0.0928665799976308,
+ 0.11791583587819598
+ ]
+ ],
+ "mass": 0.00123506173633174,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BEDROOM - NEO\nThis selection of Neo Furniture sets specially designed in fun, bright colors.",
+ "nr_faces": 10840,
+ "nr_vertices": 6788,
+ "surface_area": 0.17047638159456102,
+ "volume": 0.00123506173633174
+ }
+ },
+ "BIA_Cordon_Bleu_White_Porcelain_Utensil_Holder_900028": {
+ "asset_type": "FileBasedObject",
+ "id": "BIA_Cordon_Bleu_White_Porcelain_Utensil_Holder_900028",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07446448856476562,
+ -0.07379531609756576,
+ -0.07353415248933359
+ ],
+ [
+ 0.07310551143523437,
+ 0.07495968390243424,
+ 0.1016608475106664
+ ]
+ ],
+ "mass": 0.00047170929340744277,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "B.I.A Cordon Bleu White Porcelain Utensil Holder 900028\nBIA Cordon Bleu Give your spatulas and serving spoons an elegant home with this 60 Oz. Made from porcelain, this piece is resistant to chipping, cracking and staining. The clean design and solid white glaze make this piece a classic addition to any table kitchen.",
+ "nr_faces": 14542,
+ "nr_vertices": 7446,
+ "surface_area": 0.1725599988655615,
+ "volume": 0.00047170929340744277
+ }
+ },
+ "BIA_Porcelain_Ramekin_With_Glazed_Rim_35_45_oz_cup": {
+ "asset_type": "FileBasedObject",
+ "id": "BIA_Porcelain_Ramekin_With_Glazed_Rim_35_45_oz_cup",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04451280089336566,
+ -0.04427495157332842,
+ -0.016904335037892987
+ ],
+ [
+ 0.04416619910663434,
+ 0.044378048426671576,
+ 0.026425664962107017
+ ]
+ ],
+ "mass": 7.450579237127483e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "BIA Porcelain Ramekin With Glazed Rim, 3.5\" - 4.5 oz cup",
+ "nr_faces": 16274,
+ "nr_vertices": 8304,
+ "surface_area": 0.028356163975513465,
+ "volume": 7.450579237127483e-05
+ }
+ },
+ "BIRD_RATTLE": {
+ "asset_type": "FileBasedObject",
+ "id": "BIRD_RATTLE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03518491681060212,
+ -0.0523076989477466,
+ -0.04205484964485487
+ ],
+ [
+ 0.027453083189397886,
+ 0.0588823010522534,
+ 0.048597150355145134
+ ]
+ ],
+ "mass": 8.283218510402833e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BIRD RATTLE\nThis cute Bird Rattle provides a source of stimulation. Encourage babies to explore sound, enhance fine motor skills while grasping and develop hand-eye coordination.",
+ "nr_faces": 17104,
+ "nr_vertices": 9275,
+ "surface_area": 0.024211709206021392,
+ "volume": 8.283218510402833e-05
+ }
+ },
+ "BRAILLE_ALPHABET_AZ": {
+ "asset_type": "FileBasedObject",
+ "id": "BRAILLE_ALPHABET_AZ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1688423571501734,
+ -0.16522701353870659,
+ -0.010054044044557637
+ ],
+ [
+ 0.16418464284982662,
+ 0.1604969864612934,
+ 0.014251955955442363
+ ]
+ ],
+ "mass": 0.0011671140700129645,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BRAILLE ALPHABET A-Z\nThis 26 piece Braille Alphabet set can be played 2 sided, one upper case, another one lower case. Each piece has a Braille symbol that represents each letter in the alphabet.",
+ "nr_faces": 16190,
+ "nr_vertices": 9236,
+ "surface_area": 0.19765665955788697,
+ "volume": 0.0011671140700129645
+ }
+ },
+ "BREAKFAST_MENU": {
+ "asset_type": "FileBasedObject",
+ "id": "BREAKFAST_MENU",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1268925365485101,
+ -0.09396647813648301,
+ -0.016654724714383548
+ ],
+ [
+ 0.1262374634514899,
+ 0.08766652186351699,
+ 0.059807275285616454
+ ]
+ ],
+ "mass": 0.0007105758892793917,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BREAKFAST MENU\nThe set includes 2 slices of bread, a bun, sausage, bacon, cheese, fried egg, boiled egg, salt and pepper that are served on a tray.",
+ "nr_faces": 11676,
+ "nr_vertices": 6674,
+ "surface_area": 0.1461727868792712,
+ "volume": 0.0007105758892793917
+ }
+ },
+ "BUILD_A_ROBOT": {
+ "asset_type": "FileBasedObject",
+ "id": "BUILD_A_ROBOT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.152721547598732,
+ -0.07176255764522713,
+ -0.04334991266199372
+ ],
+ [
+ 0.139809452401268,
+ 0.057112442354772856,
+ 0.0893890873380063
+ ]
+ ],
+ "mass": 0.0006037087033416211,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BUILD -A- ROBOT\nThis charming robot features four interchangeable heads, which teach emotions and offer different tactile & auditory experiences. Legs are movable for standing or sitting.",
+ "nr_faces": 11724,
+ "nr_vertices": 7014,
+ "surface_area": 0.08419006194029585,
+ "volume": 0.0006037087033416211
+ }
+ },
+ "BUILD_A_ZOO": {
+ "asset_type": "FileBasedObject",
+ "id": "BUILD_A_ZOO",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07073897136442943,
+ -0.010881860398024893,
+ -0.0987331376982262
+ ],
+ [
+ 0.07248602863557058,
+ 0.011455139601975108,
+ 0.11958086230177381
+ ]
+ ],
+ "mass": 0.0003062564590363653,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BUILD A ZOO\nHelp develop fine motor skills by building the zoo and matching the animal to its place using the forceps. It also reinforces color recognition and counting. The set consists of 16 wooden pieces and 5 animals.",
+ "nr_faces": 12958,
+ "nr_vertices": 7565,
+ "surface_area": 0.07245941628159272,
+ "volume": 0.0003062564590363653
+ }
+ },
+ "BUNNY_RACER": {
+ "asset_type": "FileBasedObject",
+ "id": "BUNNY_RACER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04602366675050188,
+ -0.04597680309040797,
+ -0.030467247600650227
+ ],
+ [
+ 0.04560433324949812,
+ 0.04203419690959203,
+ 0.08108075239934978
+ ]
+ ],
+ "mass": 0.00024315509958842014,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BUNNY RACER\nHave great fun with Rabbit cars. They have gently curve design which is easy for children to hold and push",
+ "nr_faces": 12146,
+ "nr_vertices": 6675,
+ "surface_area": 0.03422002092741528,
+ "volume": 0.00024315509958842014
+ }
+ },
+ "BUNNY_RATTLE": {
+ "asset_type": "FileBasedObject",
+ "id": "BUNNY_RATTLE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.040076752344210945,
+ -0.05585965392910121,
+ -0.03461011347689245
+ ],
+ [
+ 0.034573247655789056,
+ 0.02604934607089879,
+ 0.08005288652310756
+ ]
+ ],
+ "mass": 6.196271500190083e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "BUNNY RATTLE\nLittle Bunny Rattle makes a bell sound which stimulate baby's sound exploring and also enhances hand-eye coordination.",
+ "nr_faces": 11316,
+ "nr_vertices": 6209,
+ "surface_area": 0.018159122531681192,
+ "volume": 6.196271500190083e-05
+ }
+ },
+ "Baby_Elements_Stacking_Cups": {
+ "asset_type": "FileBasedObject",
+ "id": "Baby_Elements_Stacking_Cups",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.045889351221801,
+ -0.05710198157442796,
+ -0.1772242467155635
+ ],
+ [
+ 0.05693164877819899,
+ 0.04545801842557204,
+ 0.1691127532844365
+ ]
+ ],
+ "mass": 0.0014516549520806228,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Baby Elements Stacking Cups",
+ "nr_faces": 10528,
+ "nr_vertices": 5529,
+ "surface_area": 0.1256115212899751,
+ "volume": 0.0014516549520806228
+ }
+ },
+ "Balderdash_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Balderdash_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10223547322514656,
+ -0.030212785611216902,
+ -0.13399501266042452
+ ],
+ [
+ 0.10231752677485344,
+ 0.030297214388783095,
+ 0.13497098733957547
+ ]
+ ],
+ "mass": 0.0030397064425503125,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Balderdash Game",
+ "nr_faces": 1464,
+ "nr_vertices": 800,
+ "surface_area": 0.15550596586886448,
+ "volume": 0.0030397064425503125
+ }
+ },
+ "Beetle_Adventure_Racing_Nintendo_64": {
+ "asset_type": "FileBasedObject",
+ "id": "Beetle_Adventure_Racing_Nintendo_64",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05837564578617791,
+ -0.01196269685051553,
+ -0.03789244098074848
+ ],
+ [
+ 0.05812935421382209,
+ 0.01185230314948447,
+ 0.03965455901925152
+ ]
+ ],
+ "mass": 0.00015151346227316065,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Beetle Adventure Racing, Nintendo 64",
+ "nr_faces": 6770,
+ "nr_vertices": 3526,
+ "surface_area": 0.02322657764715793,
+ "volume": 0.00015151346227316065
+ }
+ },
+ "Beta_Glucan": {
+ "asset_type": "FileBasedObject",
+ "id": "Beta_Glucan",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.027129192713745226,
+ -0.02700841669928734,
+ -0.044334991561335475
+ ],
+ [
+ 0.026927807286254775,
+ 0.02681458330071266,
+ 0.053281008438664526
+ ]
+ ],
+ "mass": 0.0001913092676922485,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Beta Glucan",
+ "nr_faces": 8726,
+ "nr_vertices": 4482,
+ "surface_area": 0.0191677943330544,
+ "volume": 0.0001913092676922485
+ }
+ },
+ "Beyonc_Life_is_But_a_Dream_DVD": {
+ "asset_type": "FileBasedObject",
+ "id": "Beyonc_Life_is_But_a_Dream_DVD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0683668717874506,
+ -0.09459058903686832,
+ -0.00730924718291517
+ ],
+ [
+ 0.0718081282125494,
+ 0.09392641096313169,
+ 0.0077477528170848305
+ ]
+ ],
+ "mass": 0.0003283109498104488,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Beyonc? - Life is But a Dream [DVD]",
+ "nr_faces": 4630,
+ "nr_vertices": 2515,
+ "surface_area": 0.060739877167808036,
+ "volume": 0.0003283109498104488
+ }
+ },
+ "Bifidus_Balance_FOS": {
+ "asset_type": "FileBasedObject",
+ "id": "Bifidus_Balance_FOS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02700933182761905,
+ -0.026745054334392653,
+ -0.04401459361143099
+ ],
+ [
+ 0.02696666817238095,
+ 0.026459945665607346,
+ 0.05245240638856901
+ ]
+ ],
+ "mass": 0.0001869846235503495,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Bifidus Balance + FOS",
+ "nr_faces": 9344,
+ "nr_vertices": 4818,
+ "surface_area": 0.018693044279915087,
+ "volume": 0.0001869846235503495
+ }
+ },
+ "Big_Dot_Aqua_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Big_Dot_Aqua_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10471284712280163,
+ -0.04500089812391,
+ -0.04189098890088352
+ ],
+ [
+ 0.10341815287719837,
+ 0.04356410187609,
+ 0.05428801109911648
+ ]
+ ],
+ "mass": 0.0010159278412586903,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Big Dot Aqua Pencil Case",
+ "nr_faces": 12514,
+ "nr_vertices": 6755,
+ "surface_area": 0.06480429460065659,
+ "volume": 0.0010159278412586903
+ }
+ },
+ "Big_Dot_Pink_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Big_Dot_Pink_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10526438218708543,
+ -0.050192024092592366,
+ -0.04232264977104965
+ ],
+ [
+ 0.10848561781291456,
+ 0.04680797590740764,
+ 0.05780435022895035
+ ]
+ ],
+ "mass": 0.0010313214342090621,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Big Dot Pink Pencil Case",
+ "nr_faces": 11720,
+ "nr_vertices": 6277,
+ "surface_area": 0.06655927658545831,
+ "volume": 0.0010313214342090621
+ }
+ },
+ "Big_O_Sponges_Assorted_Cellulose_12_pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Big_O_Sponges_Assorted_Cellulose_12_pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.035133640150507246,
+ -0.06234395305517409,
+ -0.008827871108943987
+ ],
+ [
+ 0.03501735984949275,
+ 0.0634100469448259,
+ 0.009926128891056015
+ ]
+ ],
+ "mass": 0.00013353775485034567,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Big O Sponges, Assorted Cellulose - 12 pack",
+ "nr_faces": 31182,
+ "nr_vertices": 16421,
+ "surface_area": 0.024049222570975415,
+ "volume": 0.00013353775485034567
+ }
+ },
+ "BlackBlack_Nintendo_3DSXL": {
+ "asset_type": "FileBasedObject",
+ "id": "BlackBlack_Nintendo_3DSXL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07762507677428368,
+ -0.06790023591131598,
+ -0.021969418031302538
+ ],
+ [
+ 0.07791492322571632,
+ 0.06889276408868401,
+ 0.06855358196869746
+ ]
+ ],
+ "mass": 0.00027960923436424145,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Black/Black Nintendo 3DS?XL\nThe Nintendo 3DS XL system combines next-generation portable gaming with eye-popping 3D\nvisuals?without the need for special glasses. Take 3D photos, connect to friends, other players, or wireless hotspots with the wireless StreetPass? and SpotPass? communication modes. From games to photos and beyond, Nintendo 3DS XL is the ultimate 3D entertainment system. It comes bundled with a 4GB SD card, making it perfect for downloading content from the Nintendo eShop.\n\nThe Nintendo 3DS XL system plays all Nintendo DS games. Nintendo DS games will not appear in 3D.",
+ "nr_faces": 6932,
+ "nr_vertices": 3661,
+ "surface_area": 0.060771780471238684,
+ "volume": 0.00027960923436424145
+ }
+ },
+ "Black_Decker_CM2035B_12Cup_Thermal_Coffeemaker": {
+ "asset_type": "FileBasedObject",
+ "id": "Black_Decker_CM2035B_12Cup_Thermal_Coffeemaker",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11531218373323199,
+ -0.1279293871403682,
+ -0.16778921971146438
+ ],
+ [
+ 0.11162281626676801,
+ 0.1956996128596318,
+ 0.1691477802885356
+ ]
+ ],
+ "mass": 0.010727618330385703,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Black & Decker CM2035B 12-Cup Thermal Coffeemaker",
+ "nr_faces": 30034,
+ "nr_vertices": 15995,
+ "surface_area": 0.3435054115578244,
+ "volume": 0.010727618330385703
+ }
+ },
+ "Black_Decker_Stainless_Steel_Toaster_4_Slice": {
+ "asset_type": "FileBasedObject",
+ "id": "Black_Decker_Stainless_Steel_Toaster_4_Slice",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13960519931626472,
+ -0.15178071615155522,
+ -0.09053235359344093
+ ],
+ [
+ 0.14820580068373526,
+ 0.16651828384844478,
+ 0.09833664640655906
+ ]
+ ],
+ "mass": 0.010220124180526164,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Black & Decker Stainless Steel Toaster, 4 Slice",
+ "nr_faces": 47628,
+ "nr_vertices": 30828,
+ "surface_area": 0.4760938492416849,
+ "volume": 0.010220124180526164
+ }
+ },
+ "Black_Elderberry_Syrup_54_oz_Gaia_Herbs": {
+ "asset_type": "FileBasedObject",
+ "id": "Black_Elderberry_Syrup_54_oz_Gaia_Herbs",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02864001390799629,
+ -0.029530632479507032,
+ -0.07203835051383244
+ ],
+ [
+ 0.028491986092003707,
+ 0.029558367520492967,
+ 0.07306764948616758
+ ]
+ ],
+ "mass": 0.0004546201057754602,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Black Elderberry Syrup, 5.4 oz, Gaia Herbs",
+ "nr_faces": 4028,
+ "nr_vertices": 2147,
+ "surface_area": 0.03731509836560498,
+ "volume": 0.0004546201057754602
+ }
+ },
+ "Black_Forest_Fruit_Snacks_28_Pack_Grape": {
+ "asset_type": "FileBasedObject",
+ "id": "Black_Forest_Fruit_Snacks_28_Pack_Grape",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1089817427272656,
+ -0.04354948854799287,
+ -0.12824849062582658
+ ],
+ [
+ 0.1081022572727344,
+ 0.043563511452007125,
+ 0.1291675093741734
+ ]
+ ],
+ "mass": 0.004383046584563181,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Black Forest Fruit Snacks 28 Pack Grape",
+ "nr_faces": 2036,
+ "nr_vertices": 1100,
+ "surface_area": 0.17603920883220053,
+ "volume": 0.004383046584563181
+ }
+ },
+ "Black_Forest_Fruit_Snacks_Juicy_Filled_Centers_10_pouches_9_oz_total": {
+ "asset_type": "FileBasedObject",
+ "id": "Black_Forest_Fruit_Snacks_Juicy_Filled_Centers_10_pouches_9_oz_total",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10593998112544334,
+ -0.028004856175176836,
+ -0.07526877052250165
+ ],
+ [
+ 0.10614701887455666,
+ 0.02817914382482316,
+ 0.07555722947749835
+ ]
+ ],
+ "mass": 0.0016346812791051843,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Black Forest Fruit Snacks, Juicy Filled Centers - 10 pouches, 9 oz total",
+ "nr_faces": 2544,
+ "nr_vertices": 1368,
+ "surface_area": 0.09596723832012591,
+ "volume": 0.0016346812791051843
+ }
+ },
+ "Black_and_Decker_PBJ2000_FusionBlade_Blender_Jars": {
+ "asset_type": "FileBasedObject",
+ "id": "Black_and_Decker_PBJ2000_FusionBlade_Blender_Jars",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08848448063840271,
+ -0.04493232350982756,
+ -0.14996568989679557
+ ],
+ [
+ 0.08632451936159728,
+ 0.045179676490172446,
+ 0.1497483101032044
+ ]
+ ],
+ "mass": 0.004284022752385719,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Black and Decker PBJ2000 FusionBlade Blender Jars",
+ "nr_faces": 4658,
+ "nr_vertices": 2478,
+ "surface_area": 0.17698391287274312,
+ "volume": 0.004284022752385719
+ }
+ },
+ "Black_and_Decker_TR3500SD_2Slice_Toaster": {
+ "asset_type": "FileBasedObject",
+ "id": "Black_and_Decker_TR3500SD_2Slice_Toaster",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08264857781786729,
+ -0.13498129544311405,
+ -0.08926948042590256
+ ],
+ [
+ 0.08513642218213271,
+ 0.16029570455688597,
+ 0.10144951957409744
+ ]
+ ],
+ "mass": 0.005264574536554216,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Black and Decker TR3500SD 2-Slice Toaster",
+ "nr_faces": 31474,
+ "nr_vertices": 18562,
+ "surface_area": 0.258289191769804,
+ "volume": 0.005264574536554216
+ }
+ },
+ "Blackcurrant_Lutein": {
+ "asset_type": "FileBasedObject",
+ "id": "Blackcurrant_Lutein",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.027082813090194068,
+ -0.027036048404132193,
+ -0.04430024101524923
+ ],
+ [
+ 0.027074186909805932,
+ 0.026853951595867807,
+ 0.053011758984750766
+ ]
+ ],
+ "mass": 0.00019092386043151614,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Blackcurrant + Lutein",
+ "nr_faces": 8676,
+ "nr_vertices": 4450,
+ "surface_area": 0.019156671989031857,
+ "volume": 0.00019092386043151614
+ }
+ },
+ "BlueBlack_Nintendo_3DSXL": {
+ "asset_type": "FileBasedObject",
+ "id": "BlueBlack_Nintendo_3DSXL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07822148069097744,
+ -0.06662406069741225,
+ -0.022235841122592446
+ ],
+ [
+ 0.07837751930902256,
+ 0.06703793930258775,
+ 0.07041915887740756
+ ]
+ ],
+ "mass": 0.0002819490926389253,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Blue/Black Nintendo 3DS?XL\nThe Nintendo 3DS XL system combines next-generation portable gaming with eye-popping 3D\nvisuals?without the need for special glasses. Take 3D photos, connect to friends, other players, or wireless hotspots with the wireless StreetPass? and SpotPass? communication modes. From games to photos and beyond, Nintendo 3DS XL is the ultimate 3D entertainment system. It comes bundled with a 4GB SD card, making it perfect for downloading content from the Nintendo eShop.\n\nThe Nintendo 3DS XL system plays all Nintendo DS games. Nintendo DS games will not appear in 3D.",
+ "nr_faces": 5932,
+ "nr_vertices": 3100,
+ "surface_area": 0.06082552731493379,
+ "volume": 0.0002819490926389253
+ }
+ },
+ "Blue_Jasmine_Includes_Digital_Copy_UltraViolet_DVD": {
+ "asset_type": "FileBasedObject",
+ "id": "Blue_Jasmine_Includes_Digital_Copy_UltraViolet_DVD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06641327326595076,
+ -0.09676788697040438,
+ -0.008156789496993317
+ ],
+ [
+ 0.07125972673404923,
+ 0.09620711302959563,
+ 0.00877421050300668
+ ]
+ ],
+ "mass": 0.00037641398934354153,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Blue Jasmine [Includes Digital Copy] [UltraViolet] [DVD]",
+ "nr_faces": 6068,
+ "nr_vertices": 3502,
+ "surface_area": 0.0611137068536199,
+ "volume": 0.00037641398934354153
+ }
+ },
+ "Borage_GLA240Gamma_Tocopherol": {
+ "asset_type": "FileBasedObject",
+ "id": "Borage_GLA240Gamma_Tocopherol",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03123946725545999,
+ -0.030940636689005912,
+ -0.051016936662545094
+ ],
+ [
+ 0.03090953274454001,
+ 0.030725363310994087,
+ 0.059932063337454905
+ ]
+ ],
+ "mass": 0.00028931765395795564,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Borage GLA-240+Gamma Tocopherol",
+ "nr_faces": 9132,
+ "nr_vertices": 4677,
+ "surface_area": 0.02505265764152293,
+ "volume": 0.00028931765395795564
+ }
+ },
+ "Bradshaw_International_11642_7_Qt_MP_Plastic_Bowl": {
+ "asset_type": "FileBasedObject",
+ "id": "Bradshaw_International_11642_7_Qt_MP_Plastic_Bowl",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1428660812338982,
+ -0.14125361334742131,
+ -0.07929400655477596
+ ],
+ [
+ 0.1397479187661018,
+ 0.1438363866525787,
+ 0.07520999344522404
+ ]
+ ],
+ "mass": 0.0001703447483178306,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Bradshaw International 11642 7 Qt MP Plastic Bowl\n\"Good Cook - Assorted Colors.\"",
+ "nr_faces": 15502,
+ "nr_vertices": 7951,
+ "surface_area": 0.2720735548373275,
+ "volume": 0.0001703447483178306
+ }
+ },
+ "Breyer_Horse_Of_The_Year_2015": {
+ "asset_type": "FileBasedObject",
+ "id": "Breyer_Horse_Of_The_Year_2015",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11118072060027692,
+ -0.030483308834254305,
+ -0.09719479137330748
+ ],
+ [
+ 0.11996027939972308,
+ 0.027208691165745695,
+ 0.0559882086266925
+ ]
+ ],
+ "mass": 0.0003062815563977941,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Breyer Horse Of The Year, 2015",
+ "nr_faces": 13840,
+ "nr_vertices": 7438,
+ "surface_area": 0.04403434159971018,
+ "volume": 0.0003062815563977941
+ }
+ },
+ "Brisk_Iced_Tea_Lemon_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": {
+ "asset_type": "FileBasedObject",
+ "id": "Brisk_Iced_Tea_Lemon_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20199284135984408,
+ -0.07052935267137059,
+ -0.06463161709015579
+ ],
+ [
+ 0.2008571586401559,
+ 0.07060264732862942,
+ 0.0648853829098442
+ ]
+ ],
+ "mass": 0.0067852253131189325,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Brisk Iced Tea, Lemon - 12 - 12 fl oz (355 ml) cans [144 fl oz (426 lt)]\ndescription 377",
+ "nr_faces": 3634,
+ "nr_vertices": 1927,
+ "surface_area": 0.23282266604190405,
+ "volume": 0.0067852253131189325
+ }
+ },
+ "Brother_Ink_Cartridge_Magenta_LC75M": {
+ "asset_type": "FileBasedObject",
+ "id": "Brother_Ink_Cartridge_Magenta_LC75M",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04387097228437593,
+ -0.015441616522312672,
+ -0.06292252530126258
+ ],
+ [
+ 0.043941027715624074,
+ 0.015438383477687327,
+ 0.0842364746987374
+ ]
+ ],
+ "mass": 0.00026972853507103983,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Brother Ink Cartridge, Magenta LC75M",
+ "nr_faces": 4782,
+ "nr_vertices": 2594,
+ "surface_area": 0.03443387960655497,
+ "volume": 0.00026972853507103983
+ }
+ },
+ "Brother_LC_1053PKS_Ink_Cartridge_CyanMagentaYellow_1pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Brother_LC_1053PKS_Ink_Cartridge_CyanMagentaYellow_1pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.049636397603023116,
+ -0.027313625878473993,
+ -0.061341645686591346
+ ],
+ [
+ 0.049235602396976885,
+ 0.028007374121526006,
+ 0.08357835431340865
+ ]
+ ],
+ "mass": 0.0006007857644915722,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Brother LC 1053PKS Ink Cartridge, Cyan/Magenta/Yellow - 1-pack",
+ "nr_faces": 5762,
+ "nr_vertices": 3144,
+ "surface_area": 0.0458012569897827,
+ "volume": 0.0006007857644915722
+ }
+ },
+ "Brother_Printing_Cartridge_PC501": {
+ "asset_type": "FileBasedObject",
+ "id": "Brother_Printing_Cartridge_PC501",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12765734633704148,
+ -0.02838541364989975,
+ -0.06030032813104966
+ ],
+ [
+ 0.1282176536629585,
+ 0.028187586350100248,
+ 0.05998467186895034
+ ]
+ ],
+ "mass": 0.0015950699736461803,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Brother Printing Cartridge, PC-501",
+ "nr_faces": 4816,
+ "nr_vertices": 2657,
+ "surface_area": 0.09728338302739897,
+ "volume": 0.0015950699736461803
+ }
+ },
+ "CARSII": {
+ "asset_type": "FileBasedObject",
+ "id": "CARSII",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06055619201263321,
+ -0.07061080305303266,
+ -0.011577664441223226
+ ],
+ [
+ 0.0622568079873668,
+ 0.04495719694696734,
+ 0.01581133555877677
+ ]
+ ],
+ "mass": 6.436470272329917e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CARS-II",
+ "nr_faces": 11652,
+ "nr_vertices": 6295,
+ "surface_area": 0.014801343946200895,
+ "volume": 6.436470272329917e-05
+ }
+ },
+ "CAR_CARRIER_TRAIN": {
+ "asset_type": "FileBasedObject",
+ "id": "CAR_CARRIER_TRAIN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.019980055690781463,
+ -0.10753494355410244,
+ -0.02418972008267831
+ ],
+ [
+ 0.018050944309218536,
+ 0.11541905644589756,
+ 0.02687027991732169
+ ]
+ ],
+ "mass": 0.00015926485367403817,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CAR CARRIER TRAIN\nThe Car Carrier Train is a great eco-friendly addition to any rail set. This item is compatible with the rest of the PlanCity line.",
+ "nr_faces": 25266,
+ "nr_vertices": 14745,
+ "surface_area": 0.036178784715920724,
+ "volume": 0.00015926485367403817
+ }
+ },
+ "CASTLE_BLOCKS": {
+ "asset_type": "FileBasedObject",
+ "id": "CASTLE_BLOCKS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.150952102856997,
+ -0.11947983324662154,
+ -0.051798969446260425
+ ],
+ [
+ 0.15145089714300297,
+ 0.08259016675337846,
+ 0.09006803055373959
+ ]
+ ],
+ "mass": 0.0012517551016540066,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CASTLE BLOCKS\nExplore your imaginative side with this 35-piece castle-themed block set.",
+ "nr_faces": 22108,
+ "nr_vertices": 13101,
+ "surface_area": 0.19855611375246973,
+ "volume": 0.0012517551016540066
+ }
+ },
+ "CHICKEN_NESTING": {
+ "asset_type": "FileBasedObject",
+ "id": "CHICKEN_NESTING",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07275431007645879,
+ -0.0715672764905147,
+ -0.0638580304071875
+ ],
+ [
+ 0.06968268992354121,
+ 0.07073872350948529,
+ 0.1311309695928125
+ ]
+ ],
+ "mass": 0.0012148971717183797,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CHICKEN NESTING\nThis basic nesting toy comes with a chicken theme. It consists of 4 pieces and a circle base. Children are able to learn about the sequencing, life cycle of a chicken and play in various styles.",
+ "nr_faces": 11022,
+ "nr_vertices": 5806,
+ "surface_area": 0.0773014190600174,
+ "volume": 0.0012148971717183797
+ }
+ },
+ "CHICKEN_RACER": {
+ "asset_type": "FileBasedObject",
+ "id": "CHICKEN_RACER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04586947561122872,
+ -0.04544574442367795,
+ -0.028911118322620683
+ ],
+ [
+ 0.04580152438877128,
+ 0.042521255576322046,
+ 0.07054588167737932
+ ]
+ ],
+ "mass": 0.0002322223734989215,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CHICKEN RACER\nHave great fun with Chicken 3cars. They have gently curve design which is easy for children to hold and push",
+ "nr_faces": 12808,
+ "nr_vertices": 7116,
+ "surface_area": 0.031775975711623994,
+ "volume": 0.0002322223734989215
+ }
+ },
+ "CHILDRENS_ROOM_NEO": {
+ "asset_type": "FileBasedObject",
+ "id": "CHILDRENS_ROOM_NEO",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08209143576772815,
+ -0.13688802365195774,
+ -0.05581257735087325
+ ],
+ [
+ 0.060061564232271845,
+ 0.06481197634804227,
+ 0.08552442264912674
+ ]
+ ],
+ "mass": 0.0007715812783360692,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CHILDREN'S ROOM - NEO\nThe set consists of a children?s bunk bed which can be split into 2 beds, a cupboard that can be transformed into a desk, and a chair.",
+ "nr_faces": 16054,
+ "nr_vertices": 9615,
+ "surface_area": 0.1282333348904209,
+ "volume": 0.0007715812783360692
+ }
+ },
+ "CHILDREN_BEDROOM_CLASSIC": {
+ "asset_type": "FileBasedObject",
+ "id": "CHILDREN_BEDROOM_CLASSIC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.143430190583517,
+ -0.14027272129750357,
+ -0.04839269279026202
+ ],
+ [
+ 0.081251809416483,
+ 0.05843727870249643,
+ 0.07652430720973799
+ ]
+ ],
+ "mass": 0.0007014206469293475,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CHILDREN BEDROOM - CLASSIC\nChildren can enjoy decorating their dollhouse with the Classic set of furniture while developing their imagination and creating more interest time.",
+ "nr_faces": 12712,
+ "nr_vertices": 7567,
+ "surface_area": 0.12327473774174494,
+ "volume": 0.0007014206469293475
+ }
+ },
+ "CITY_TAXI_POLICE_CAR": {
+ "asset_type": "FileBasedObject",
+ "id": "CITY_TAXI_POLICE_CAR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.028394022171411196,
+ -0.06376839729546649,
+ -0.009947399318637635
+ ],
+ [
+ 0.028241977828588807,
+ 0.0625696027045335,
+ 0.018025600681362365
+ ]
+ ],
+ "mass": 4.5192947523936655e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CITY TAXI & POLICE CAR",
+ "nr_faces": 11192,
+ "nr_vertices": 6148,
+ "surface_area": 0.01136517242772298,
+ "volume": 4.5192947523936655e-05
+ }
+ },
+ "CLIMACOOL_BOAT_BREEZE_IE6CyqSaDwN": {
+ "asset_type": "FileBasedObject",
+ "id": "CLIMACOOL_BOAT_BREEZE_IE6CyqSaDwN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05754995594183877,
+ -0.1361333127459915,
+ -0.03201984729912494
+ ],
+ [
+ 0.04730104405816123,
+ 0.1571386872540085,
+ 0.08370515270087506
+ ]
+ ],
+ "mass": 0.0010148619682053524,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "CLIMACOOL BOAT BREEZE\nFW-SHOES",
+ "nr_faces": 41832,
+ "nr_vertices": 24951,
+ "surface_area": 0.12730316751048146,
+ "volume": 0.0010148619682053524
+ }
+ },
+ "COAST_GUARD_BOAT": {
+ "asset_type": "FileBasedObject",
+ "id": "COAST_GUARD_BOAT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03765993646555458,
+ -0.05781443316314227,
+ -0.020691449951071902
+ ],
+ [
+ 0.038155063534445414,
+ 0.058361566836857726,
+ 0.055247550048928104
+ ]
+ ],
+ "mass": 0.00023919220640884997,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "COAST GUARD BOAT\nProtect the shores and rescue those stuck out at sea! Stimulate interactive and imaginative play.",
+ "nr_faces": 9562,
+ "nr_vertices": 5041,
+ "surface_area": 0.027269856264249957,
+ "volume": 0.00023919220640884997
+ }
+ },
+ "CONE_SORTING": {
+ "asset_type": "FileBasedObject",
+ "id": "CONE_SORTING",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12549227559890383,
+ -0.07789823022015498,
+ -0.029419809346183996
+ ],
+ [
+ 0.14417072440109618,
+ 0.08413876977984502,
+ 0.08127119065381601
+ ]
+ ],
+ "mass": 0.000824881448449137,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CONE SORTING\nLearn about height, depth, size, patterns and ?the sequence of sorting and stacking with this ?nine-piece set.",
+ "nr_faces": 21962,
+ "nr_vertices": 13928,
+ "surface_area": 0.14750852590662267,
+ "volume": 0.000824881448449137
+ }
+ },
+ "CONE_SORTING_kg5fbARBwts": {
+ "asset_type": "FileBasedObject",
+ "id": "CONE_SORTING_kg5fbARBwts",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15587226607923008,
+ -0.06774611472974258,
+ -0.03414826018604775
+ ],
+ [
+ 0.23503373392076993,
+ 0.06779088527025742,
+ 0.10047873981395225
+ ]
+ ],
+ "mass": 0.0012121870467020342,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CONE SORTING\nLearn about height, depth, size, patterns and ?the sequence of sorting and stacking with this ?nine-piece set.",
+ "nr_faces": 5406,
+ "nr_vertices": 2903,
+ "surface_area": 0.10590387656306774,
+ "volume": 0.0012121870467020342
+ }
+ },
+ "CREATIVE_BLOCKS_35_MM": {
+ "asset_type": "FileBasedObject",
+ "id": "CREATIVE_BLOCKS_35_MM",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14289383507173933,
+ -0.07162828264064688,
+ -0.0725681807868385
+ ],
+ [
+ 0.13888216492826067,
+ 0.06917671735935312,
+ 0.1200468192131615
+ ]
+ ],
+ "mass": 0.0022804499459014634,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "CREATIVE BLOCKS (35 MM.)\nBuild a castle or a city! Let your creativity take over!",
+ "nr_faces": 14610,
+ "nr_vertices": 9608,
+ "surface_area": 0.1530237516483346,
+ "volume": 0.0022804499459014634
+ }
+ },
+ "California_Navy_Tieks_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "California_Navy_Tieks_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04314704247617854,
+ -0.12060277611203028,
+ -0.029178686209028228
+ ],
+ [
+ 0.03981295752382146,
+ 0.12106822388796973,
+ 0.052592313790971776
+ ]
+ ],
+ "mass": 0.0005234290046318411,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "California Navy Tieks - Italian Leather Ballet Flats\nThese California Navy ballet flats provide an effortless, elegant look for a day on the boat or an evening on the town. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 23540,
+ "nr_vertices": 13117,
+ "surface_area": 0.0733163040986484,
+ "volume": 0.0005234290046318411
+ }
+ },
+ "Calphalon_Kitchen_Essentials_12_Cast_Iron_Fry_Pan_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Calphalon_Kitchen_Essentials_12_Cast_Iron_Fry_Pan_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15876170549687363,
+ -0.15848167523094914,
+ -0.0738412285483276
+ ],
+ [
+ 0.16359329450312637,
+ 0.16514632476905086,
+ 0.0723977714516724
+ ]
+ ],
+ "mass": 0.0010474480962675977,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Calphalon Kitchen Essentials 12\" Cast Iron Fry Pan, Black",
+ "nr_faces": 8262,
+ "nr_vertices": 4278,
+ "surface_area": 0.29734820919719024,
+ "volume": 0.0010474480962675977
+ }
+ },
+ "Canon_225226_Ink_Cartridges_BlackColor_Cyan_Magenta_Yellow_6_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Canon_225226_Ink_Cartridges_BlackColor_Cyan_Magenta_Yellow_6_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08489851029242429,
+ -0.03560925628044404,
+ -0.05585680713554872
+ ],
+ [
+ 0.08424848970757572,
+ 0.03531674371955596,
+ 0.09264319286445127
+ ]
+ ],
+ "mass": 0.0012577995499645032,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Canon 225/226 Ink Cartridges - Black/Color (Cyan, Magenta, Yellow) - 6 count",
+ "nr_faces": 6292,
+ "nr_vertices": 3375,
+ "surface_area": 0.08356179383737394,
+ "volume": 0.0012577995499645032
+ }
+ },
+ "Canon_Ink_Cartridge_Green_6": {
+ "asset_type": "FileBasedObject",
+ "id": "Canon_Ink_Cartridge_Green_6",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.019101850820721564,
+ -0.03975490700066837,
+ -0.05151664223856319
+ ],
+ [
+ 0.017679149179278437,
+ 0.03983709299933163,
+ 0.09456035776143681
+ ]
+ ],
+ "mass": 0.00027432590518974603,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Canon Ink Cartridge, Green 6",
+ "nr_faces": 6052,
+ "nr_vertices": 3250,
+ "surface_area": 0.03348691676563259,
+ "volume": 0.00027432590518974603
+ }
+ },
+ "Canon_Pixma_Chromalife_100_Magenta_8": {
+ "asset_type": "FileBasedObject",
+ "id": "Canon_Pixma_Chromalife_100_Magenta_8",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.015693532549412973,
+ -0.04623382297663096,
+ -0.03287534415540722
+ ],
+ [
+ 0.016848467450587025,
+ 0.04646617702336905,
+ 0.08117865584459277
+ ]
+ ],
+ "mass": 0.00013553064072944286,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Canon Pixma Chromalife 100, Magenta 8",
+ "nr_faces": 5132,
+ "nr_vertices": 2847,
+ "surface_area": 0.025244786493756464,
+ "volume": 0.00013553064072944286
+ }
+ },
+ "Canon_Pixma_Ink_Cartridge_251_M": {
+ "asset_type": "FileBasedObject",
+ "id": "Canon_Pixma_Ink_Cartridge_251_M",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.012194584755580965,
+ -0.05603893113545375,
+ -0.027690189060971617
+ ],
+ [
+ 0.012166415244419035,
+ 0.05582806886454625,
+ 0.06940081093902839
+ ]
+ ],
+ "mass": 0.0001253057706781858,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Canon Pixma Ink Cartridge, 251 M",
+ "nr_faces": 6536,
+ "nr_vertices": 3494,
+ "surface_area": 0.027146504242919693,
+ "volume": 0.0001253057706781858
+ }
+ },
+ "Canon_Pixma_Ink_Cartridge_8": {
+ "asset_type": "FileBasedObject",
+ "id": "Canon_Pixma_Ink_Cartridge_8",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.014749518116880004,
+ -0.04623216102561468,
+ -0.032708772011415914
+ ],
+ [
+ 0.012338481883119996,
+ 0.045501838974385325,
+ 0.08189422798858409
+ ]
+ ],
+ "mass": 0.00013621243087647017,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Canon Pixma Ink Cartridge, 8",
+ "nr_faces": 5612,
+ "nr_vertices": 2986,
+ "surface_area": 0.025375835186025417,
+ "volume": 0.00013621243087647017
+ }
+ },
+ "Canon_Pixma_Ink_Cartridge_8_Green": {
+ "asset_type": "FileBasedObject",
+ "id": "Canon_Pixma_Ink_Cartridge_8_Green",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.014713978980308642,
+ -0.046358178869732064,
+ -0.03262481167610089
+ ],
+ [
+ 0.014052021019691358,
+ 0.04606882113026793,
+ 0.08223118832389911
+ ]
+ ],
+ "mass": 0.00013708660868697547,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Canon Pixma Ink Cartridge, 8 Green",
+ "nr_faces": 5722,
+ "nr_vertices": 3358,
+ "surface_area": 0.025300648779708612,
+ "volume": 0.00013708660868697547
+ }
+ },
+ "Canon_Pixma_Ink_Cartridge_8_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Canon_Pixma_Ink_Cartridge_8_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.015088365350122479,
+ -0.04735441193948832,
+ -0.0328677817129072
+ ],
+ [
+ 0.013638634649877523,
+ 0.04557558806051168,
+ 0.0817162182870928
+ ]
+ ],
+ "mass": 0.00013734244053295833,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Canon Pixma Ink Cartridge, 8 Red",
+ "nr_faces": 6218,
+ "nr_vertices": 3322,
+ "surface_area": 0.02534692936487922,
+ "volume": 0.00013734244053295833
+ }
+ },
+ "Canon_Pixma_Ink_Cartridge_Cyan_251": {
+ "asset_type": "FileBasedObject",
+ "id": "Canon_Pixma_Ink_Cartridge_Cyan_251",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.012248000240069685,
+ -0.05528773161988965,
+ -0.028482597935678818
+ ],
+ [
+ 0.012577999759930316,
+ 0.055751268380110346,
+ 0.06934540206432117
+ ]
+ ],
+ "mass": 0.00013004038180095966,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Canon Pixma Ink Cartridge, Cyan 251",
+ "nr_faces": 5756,
+ "nr_vertices": 3072,
+ "surface_area": 0.02722878852140924,
+ "volume": 0.00013004038180095966
+ }
+ },
+ "Cascadia_8_Color_AquariusHibscsBearingSeaBlk_Size_50": {
+ "asset_type": "FileBasedObject",
+ "id": "Cascadia_8_Color_AquariusHibscsBearingSeaBlk_Size_50",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05775757686761554,
+ -0.13841947988189326,
+ -0.03638641907757598
+ ],
+ [
+ 0.04313742313238446,
+ 0.11599752011810673,
+ 0.08513758092242403
+ ]
+ ],
+ "mass": 0.0007764731597396171,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Cascadia 8, Color: Aquarius/Hibscs/BearingSea/Blk, Size: 5.0\nThe Cascadia 8 was designed from the gritty, wet, and uneven ground up. Engineered to adapt to the surface and your foot, this versatile piece of equipment runs an ultramarathon and then asks for more. We swapped out the midsole for BioMoGo DNA to create a super cohesive transition and deluxe-ified the Segmented Crash Pad on the lateral side to smooth that heel-to-toe even more. The suede geometric pattern on the upper is a shout-out to past Cascadia designs but also serves the function of wrapping the foot for a close fit. Don't just take our word for it: Runner's World named the Cascadia 8 its \"Editor's Choice\" in the Trail Shoe Guide in the April 2013 issue and wrote, \"The Cascadia has that rare combination of road-shoe comfort and trail-shoe ruggedness.\" In short, the Cascadia 8 offers \"A well-cushioned and smooth ride on any surface.\" Please note: The Cascadia is intended as a trail running shoe. It is not pack-rated and may not hold up to the extra weight and demands of long pack hikes. We're your go-to option for trail runs, but a sturdy hiking boot would be better suited for the Pacific Crest Trail, Appalachian Trail, or other long pack trips. Runner's World is a registered trademark of Rodale Inc. 2013 Rodale Inc. All rights reserved. > See the Men's Cascadia 8 Category: Trail/Neutral Weight: 9.8 oz Platform: Universal Sprung Construction: Strobel Brooks DNA: BioMoGo DNA Launch Date: January 1, 2013",
+ "nr_faces": 42288,
+ "nr_vertices": 24364,
+ "surface_area": 0.1278210213698776,
+ "volume": 0.0007764731597396171
+ }
+ },
+ "Central_Garden_Flower_Pot_Goo_425": {
+ "asset_type": "FileBasedObject",
+ "id": "Central_Garden_Flower_Pot_Goo_425",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05861134467376648,
+ -0.05766045534977448,
+ -0.05341876910305363
+ ],
+ [
+ 0.05669965532623352,
+ 0.05607554465022552,
+ 0.047259230896946364
+ ]
+ ],
+ "mass": 0.00016315582293968583,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Central Garden Flower Pot, Goo, 4.25\"",
+ "nr_faces": 7768,
+ "nr_vertices": 4025,
+ "surface_area": 0.060254174552531084,
+ "volume": 0.00016315582293968583
+ }
+ },
+ "Chef_Style_Round_Cake_Pan_9_inch_pan": {
+ "asset_type": "FileBasedObject",
+ "id": "Chef_Style_Round_Cake_Pan_9_inch_pan",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11996029177379422,
+ -0.12155378508259175,
+ -0.012228976703130364
+ ],
+ [
+ 0.12590070822620578,
+ 0.12444621491740826,
+ 0.032943023296869635
+ ]
+ ],
+ "mass": 0.00013249079939078835,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Chef Style Round Cake Pan - 9 inch pan",
+ "nr_faces": 4436,
+ "nr_vertices": 2336,
+ "surface_area": 0.14090820589299208,
+ "volume": 0.00013249079939078835
+ }
+ },
+ "Chefmate_8_Frypan": {
+ "asset_type": "FileBasedObject",
+ "id": "Chefmate_8_Frypan",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15160120651344575,
+ -0.10529620339248748,
+ -0.021911163540821735
+ ],
+ [
+ 0.20417379348655423,
+ 0.09904879660751253,
+ 0.03310883645917827
+ ]
+ ],
+ "mass": 0.00015890219468175484,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Chefmate 8\" Frypan",
+ "nr_faces": 9320,
+ "nr_vertices": 4985,
+ "surface_area": 0.10005900224734401,
+ "volume": 0.00015890219468175484
+ }
+ },
+ "Chelsea_BlkHeelPMP_DwxLtZNxLZZ": {
+ "asset_type": "FileBasedObject",
+ "id": "Chelsea_BlkHeelPMP_DwxLtZNxLZZ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04475200156401923,
+ -0.1472270081453603,
+ -0.05116530743559119
+ ],
+ [
+ 0.04121099843598077,
+ 0.09353299185463972,
+ 0.1204576925644088
+ ]
+ ],
+ "mass": 0.0004136180053381898,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Chelsea Blk.Heel.PMP",
+ "nr_faces": 15226,
+ "nr_vertices": 7861,
+ "surface_area": 0.08672938831616958,
+ "volume": 0.0004136180053381898
+ }
+ },
+ "Chelsea_lo_fl_rdheel_nQ0LPNF1oMw": {
+ "asset_type": "FileBasedObject",
+ "id": "Chelsea_lo_fl_rdheel_nQ0LPNF1oMw",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15046848019666956,
+ -0.04841730035988547,
+ -0.03224106045165838
+ ],
+ [
+ 0.10606051980333042,
+ 0.03797769964011453,
+ 0.09080693954834163
+ ]
+ ],
+ "mass": 0.0003653554490518803,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Chelsea lo fl rd.heel",
+ "nr_faces": 7624,
+ "nr_vertices": 4071,
+ "surface_area": 0.08368057171381099,
+ "volume": 0.0003653554490518803
+ }
+ },
+ "Chelsea_lo_fl_rdheel_zAQrnhlEfw8": {
+ "asset_type": "FileBasedObject",
+ "id": "Chelsea_lo_fl_rdheel_zAQrnhlEfw8",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04743192962525171,
+ -0.15017864637138587,
+ -0.03212455386092476
+ ],
+ [
+ 0.03899607037474829,
+ 0.10618235362861414,
+ 0.09111244613907524
+ ]
+ ],
+ "mass": 0.00036161247563880534,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Chelsea lo fl rd.heel",
+ "nr_faces": 7910,
+ "nr_vertices": 4226,
+ "surface_area": 0.08320469135281719,
+ "volume": 0.00036161247563880534
+ }
+ },
+ "Circo_Fish_Toothbrush_Holder_14995988": {
+ "asset_type": "FileBasedObject",
+ "id": "Circo_Fish_Toothbrush_Holder_14995988",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.052311842196848486,
+ -0.08751392579976032,
+ -0.041889944715419604
+ ],
+ [
+ 0.053456157803151515,
+ 0.06717707420023968,
+ 0.0600030552845804
+ ]
+ ],
+ "mass": 0.00029138063622324395,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Circo Fish Toothbrush Holder 14995988",
+ "nr_faces": 18510,
+ "nr_vertices": 9965,
+ "surface_area": 0.0729319903807746,
+ "volume": 0.00029138063622324395
+ }
+ },
+ "ClimaCool_Aerate_2_W_Wide": {
+ "asset_type": "FileBasedObject",
+ "id": "ClimaCool_Aerate_2_W_Wide",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05303474841148661,
+ -0.13836051995383722,
+ -0.03603392246049701
+ ],
+ [
+ 0.05180925158851339,
+ 0.13007148004616276,
+ 0.08133807753950298
+ ]
+ ],
+ "mass": 0.0010111211085139758,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ClimaCool Aerate 2 W Wide",
+ "nr_faces": 28482,
+ "nr_vertices": 15699,
+ "surface_area": 0.10672483623614987,
+ "volume": 0.0010111211085139758
+ }
+ },
+ "Clorox_Premium_Choice_Gloves_SM_1_pair": {
+ "asset_type": "FileBasedObject",
+ "id": "Clorox_Premium_Choice_Gloves_SM_1_pair",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14678988101817744,
+ -0.16095223576024192,
+ -0.012878060265915188
+ ],
+ [
+ 0.12736611898182257,
+ 0.16537376423975805,
+ 0.05151193973408481
+ ]
+ ],
+ "mass": 0.0004766215125613033,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Clorox Premium Choice Gloves, S/M - 1 pair\n1 pair foam lined latex 13\" cuff gloves. Moisturized with glycerine.",
+ "nr_faces": 10368,
+ "nr_vertices": 5914,
+ "surface_area": 0.1484535419383526,
+ "volume": 0.0004766215125613033
+ }
+ },
+ "Closetmaid_Premium_Fabric_Cube_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Closetmaid_Premium_Fabric_Cube_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17547804194697245,
+ -0.14308830450754648,
+ -0.0734952187028967
+ ],
+ [
+ 0.14619195805302757,
+ 0.13187669549245354,
+ 0.2156597812971033
+ ]
+ ],
+ "mass": 0.0039948222203234265,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Closetmaid Premium Fabric Cube - Red",
+ "nr_faces": 12158,
+ "nr_vertices": 6522,
+ "surface_area": 0.7120293698065384,
+ "volume": 0.0039948222203234265
+ }
+ },
+ "Clue_Board_Game_Classic_Edition": {
+ "asset_type": "FileBasedObject",
+ "id": "Clue_Board_Game_Classic_Edition",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.24749044825540772,
+ -0.0289623752696064,
+ -0.13008906525355007
+ ],
+ [
+ 0.24943655174459228,
+ 0.0293336247303936,
+ 0.13026393474644993
+ ]
+ ],
+ "mass": 0.005730696200223384,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Clue Board Game, Classic Edition",
+ "nr_faces": 4450,
+ "nr_vertices": 2481,
+ "surface_area": 0.3147755235905171,
+ "volume": 0.005730696200223384
+ }
+ },
+ "CoQ10": {
+ "asset_type": "FileBasedObject",
+ "id": "CoQ10",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.023753275077475176,
+ -0.023729836255800465,
+ -0.040030431596159204
+ ],
+ [
+ 0.02364272492252482,
+ 0.023776163744199535,
+ 0.04436856840384079
+ ]
+ ],
+ "mass": 0.0001325323909449515,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Co-Q10",
+ "nr_faces": 10490,
+ "nr_vertices": 5381,
+ "surface_area": 0.01507238200711273,
+ "volume": 0.0001325323909449515
+ }
+ },
+ "CoQ10_BjTLbuRVt1t": {
+ "asset_type": "FileBasedObject",
+ "id": "CoQ10_BjTLbuRVt1t",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.023820159188995847,
+ -0.02377998550263623,
+ -0.039794425356000654
+ ],
+ [
+ 0.023639840811004155,
+ 0.023510014497363767,
+ 0.04393457464399935
+ ]
+ ],
+ "mass": 0.00013227056502668032,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Co-Q10",
+ "nr_faces": 9298,
+ "nr_vertices": 4781,
+ "surface_area": 0.01505283071749244,
+ "volume": 0.00013227056502668032
+ }
+ },
+ "CoQ10_wSSVoxVppVD": {
+ "asset_type": "FileBasedObject",
+ "id": "CoQ10_wSSVoxVppVD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02374102353301634,
+ -0.023659678287346615,
+ -0.03974903263921523
+ ],
+ [
+ 0.023773976466983662,
+ 0.023542321712653382,
+ 0.04427096736078477
+ ]
+ ],
+ "mass": 0.00013181027121564134,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Co-Q10",
+ "nr_faces": 10984,
+ "nr_vertices": 5614,
+ "surface_area": 0.015021057874124713,
+ "volume": 0.00013181027121564134
+ }
+ },
+ "Cole_Hardware_Antislip_Surfacing_Material_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Antislip_Surfacing_Material_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07718003630696586,
+ -0.07698689534383292,
+ -0.05419108815236109
+ ],
+ [
+ 0.07769896369303413,
+ 0.07734310465616709,
+ 0.053582911847638914
+ ]
+ ],
+ "mass": 0.001456871735941057,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Antislip Surfacing Material, White",
+ "nr_faces": 4484,
+ "nr_vertices": 2429,
+ "surface_area": 0.1031235075090455,
+ "volume": 0.001456871735941057
+ }
+ },
+ "Cole_Hardware_Antislip_Surfacing_White_2_x_60": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Antislip_Surfacing_White_2_x_60",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0785860180032721,
+ -0.07950785459693098,
+ -0.027973426469976925
+ ],
+ [
+ 0.0784419819967279,
+ 0.07831914540306902,
+ 0.027896573530023075
+ ]
+ ],
+ "mass": 0.0007711354082737434,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Antislip Surfacing, White, 2\" x 60'",
+ "nr_faces": 5650,
+ "nr_vertices": 2991,
+ "surface_area": 0.06762530006411913,
+ "volume": 0.0007711354082737434
+ }
+ },
+ "Cole_Hardware_Bowl_Scirocco_YellowBlue": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Bowl_Scirocco_YellowBlue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05725897994973049,
+ -0.05840946023731396,
+ -0.032760150515091575
+ ],
+ [
+ 0.05622902005026951,
+ 0.056488539762686044,
+ 0.02910484948490842
+ ]
+ ],
+ "mass": 7.960467964708548e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Bowl Scirocco, Yellow/Blue",
+ "nr_faces": 10342,
+ "nr_vertices": 5328,
+ "surface_area": 0.04030350530642151,
+ "volume": 7.960467964708548e-05
+ }
+ },
+ "Cole_Hardware_Butter_Dish_Square_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Butter_Dish_Square_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.058106512729188924,
+ -0.05759998054439167,
+ -0.03135689182650728
+ ],
+ [
+ 0.05679248727081108,
+ 0.05761701945560833,
+ 0.05380810817349272
+ ]
+ ],
+ "mass": 0.0004431846598460389,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Cole Hardware Butter Dish, Square, Red",
+ "nr_faces": 34140,
+ "nr_vertices": 17333,
+ "surface_area": 0.042034222468047916,
+ "volume": 0.0004431846598460389
+ }
+ },
+ "Cole_Hardware_Deep_Bowl_Good_Earth_1075": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Deep_Bowl_Good_Earth_1075",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1427033890463261,
+ -0.14284991062680238,
+ -0.06652255109870221
+ ],
+ [
+ 0.14099961095367392,
+ 0.14143108937319762,
+ 0.0652484489012978
+ ]
+ ],
+ "mass": 0.0010776639817390828,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Deep Bowl, Good Earth, 10.75\"",
+ "nr_faces": 10364,
+ "nr_vertices": 5361,
+ "surface_area": 0.23699964191134193,
+ "volume": 0.0010776639817390828
+ }
+ },
+ "Cole_Hardware_Dishtowel_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Dishtowel_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08476949888426878,
+ -0.11391571516836645,
+ -0.008831450205743855
+ ],
+ [
+ 0.08707150111573123,
+ 0.12040828483163354,
+ 0.016591549794256144
+ ]
+ ],
+ "mass": 0.0005064619612778919,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Dishtowel, Blue",
+ "nr_faces": 18694,
+ "nr_vertices": 9648,
+ "surface_area": 0.0915018193278802,
+ "volume": 0.0005064619612778919
+ }
+ },
+ "Cole_Hardware_Dishtowel_BlueWhite": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Dishtowel_BlueWhite",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08413166625559998,
+ -0.11645963682046412,
+ -0.010252311960597012
+ ],
+ [
+ 0.08903333374440002,
+ 0.11931836317953588,
+ 0.017812688039402988
+ ]
+ ],
+ "mass": 0.0005800953797131126,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Dishtowel, Blue/White",
+ "nr_faces": 17596,
+ "nr_vertices": 9129,
+ "surface_area": 0.0930631873754546,
+ "volume": 0.0005800953797131126
+ }
+ },
+ "Cole_Hardware_Dishtowel_Multicolors": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Dishtowel_Multicolors",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08755134298334274,
+ -0.12507871493317022,
+ -0.009281596720494811
+ ],
+ [
+ 0.08742265701665726,
+ 0.11855728506682976,
+ 0.01846040327950519
+ ]
+ ],
+ "mass": 0.000538242106823272,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Dishtowel, Multicolors",
+ "nr_faces": 21206,
+ "nr_vertices": 11150,
+ "surface_area": 0.09628957024812482,
+ "volume": 0.000538242106823272
+ }
+ },
+ "Cole_Hardware_Dishtowel_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Dishtowel_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08478380249110204,
+ -0.1153554064172957,
+ -0.009039880098413243
+ ],
+ [
+ 0.08624719750889796,
+ 0.1211505935827043,
+ 0.017552119901586755
+ ]
+ ],
+ "mass": 0.0004985713690511161,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Dishtowel, Red",
+ "nr_faces": 21290,
+ "nr_vertices": 10993,
+ "surface_area": 0.09074133758536303,
+ "volume": 0.0004985713690511161
+ }
+ },
+ "Cole_Hardware_Dishtowel_Stripe": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Dishtowel_Stripe",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08307329916353456,
+ -0.11598094127007269,
+ -0.00899599154097739
+ ],
+ [
+ 0.08576170083646543,
+ 0.11842105872992731,
+ 0.017665008459022608
+ ]
+ ],
+ "mass": 0.0004884462249644442,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Dishtowel, Stripe",
+ "nr_faces": 14942,
+ "nr_vertices": 7844,
+ "surface_area": 0.09160628716739908,
+ "volume": 0.0004884462249644442
+ }
+ },
+ "Cole_Hardware_Electric_Pot_Assortment_55": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Electric_Pot_Assortment_55",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07191148673495526,
+ -0.07104870294087323,
+ -0.06386849629972145
+ ],
+ [
+ 0.07107251326504474,
+ 0.06952229705912677,
+ 0.06411650370027856
+ ]
+ ],
+ "mass": 0.0002876401084304732,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Electric Pot, Assortment, 5.5\"",
+ "nr_faces": 8752,
+ "nr_vertices": 4520,
+ "surface_area": 0.10322042704605154,
+ "volume": 0.0002876401084304732
+ }
+ },
+ "Cole_Hardware_Electric_Pot_Cabana_55": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Electric_Pot_Cabana_55",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0708756290531263,
+ -0.07076771259937815,
+ -0.06646479849054832
+ ],
+ [
+ 0.0707923709468737,
+ 0.07116628740062184,
+ 0.06359120150945168
+ ]
+ ],
+ "mass": 0.0002914750001286222,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Electric Pot, Cabana, 5.5\"",
+ "nr_faces": 7674,
+ "nr_vertices": 3973,
+ "surface_area": 0.10292336814523576,
+ "volume": 0.0002914750001286222
+ }
+ },
+ "Cole_Hardware_Flower_Pot_1025": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Flower_Pot_1025",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12697129089511844,
+ -0.12434955370299003,
+ -0.11482154936911869
+ ],
+ [
+ 0.12289070910488156,
+ 0.12237244629700997,
+ 0.10198345063088132
+ ]
+ ],
+ "mass": 0.001071983471710696,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Flower Pot, 10.25\"",
+ "nr_faces": 5820,
+ "nr_vertices": 3043,
+ "surface_area": 0.2986550359050619,
+ "volume": 0.001071983471710696
+ }
+ },
+ "Cole_Hardware_Hammer_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Hammer_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.2216317450698082,
+ -0.030244448728351636,
+ -0.043222239420462785
+ ],
+ [
+ 0.07007525493019179,
+ 0.029787551271648366,
+ 0.05284376057953722
+ ]
+ ],
+ "mass": 0.0003119507035730278,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Hammer, Black",
+ "nr_faces": 7836,
+ "nr_vertices": 4138,
+ "surface_area": 0.03605439381139773,
+ "volume": 0.0003119507035730278
+ }
+ },
+ "Cole_Hardware_Mini_Honey_Dipper": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Mini_Honey_Dipper",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.010186119740510036,
+ -0.009920478545855321,
+ -0.03337115134696449
+ ],
+ [
+ 0.010578880259489965,
+ 0.01079152145414468,
+ 0.07713584865303552
+ ]
+ ],
+ "mass": 1.0350865223205166e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Cole Hardware Mini Honey Dipper",
+ "nr_faces": 6458,
+ "nr_vertices": 3370,
+ "surface_area": 0.004357231368975889,
+ "volume": 1.0350865223205166e-05
+ }
+ },
+ "Cole_Hardware_Mug_Classic_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Mug_Classic_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07018174522610562,
+ -0.06338103498675275,
+ -0.04588423870832749
+ ],
+ [
+ 0.09548025477389438,
+ 0.06215896501324725,
+ 0.04888476129167252
+ ]
+ ],
+ "mass": 0.0002676739325271065,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Mug, Classic Blue",
+ "nr_faces": 8716,
+ "nr_vertices": 4542,
+ "surface_area": 0.0837773685004435,
+ "volume": 0.0002676739325271065
+ }
+ },
+ "Cole_Hardware_Orchid_Pot_85": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Orchid_Pot_85",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10678346956491538,
+ -0.1054257085629578,
+ -0.07077967617139429
+ ],
+ [
+ 0.10464953043508461,
+ 0.1047632914370422,
+ 0.0772653238286057
+ ]
+ ],
+ "mass": 0.0006670467661239977,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Orchid Pot, 8.5\"",
+ "nr_faces": 6834,
+ "nr_vertices": 3647,
+ "surface_area": 0.19150800095032558,
+ "volume": 0.0006670467661239977
+ }
+ },
+ "Cole_Hardware_Plant_Saucer_Brown_125": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Plant_Saucer_Brown_125",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15525911333361844,
+ -0.1566992968014721,
+ -0.015947705801324864
+ ],
+ [
+ 0.15540888666638156,
+ 0.1528107031985279,
+ 0.029833294198675135
+ ]
+ ],
+ "mass": 0.0007361509162369424,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Plant Saucer, Brown, 12.5\"",
+ "nr_faces": 4302,
+ "nr_vertices": 2261,
+ "surface_area": 0.18841252539651862,
+ "volume": 0.0007361509162369424
+ }
+ },
+ "Cole_Hardware_Plant_Saucer_Glazed_9": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Plant_Saucer_Glazed_9",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11358181697626635,
+ -0.11347806242488662,
+ -0.013661826128571745
+ ],
+ [
+ 0.11498918302373365,
+ 0.11525793757511339,
+ 0.02330917387142825
+ ]
+ ],
+ "mass": 0.00038951854202096283,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Plant Saucer, Glazed, 9\"",
+ "nr_faces": 4126,
+ "nr_vertices": 2143,
+ "surface_area": 0.10572022624846511,
+ "volume": 0.00038951854202096283
+ }
+ },
+ "Cole_Hardware_Saucer_Electric": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Saucer_Electric",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06218899682576802,
+ -0.061907315492487236,
+ -0.013293709136767765
+ ],
+ [
+ 0.06210400317423198,
+ 0.06234068450751277,
+ 0.01829229086323224
+ ]
+ ],
+ "mass": 0.00010731024483229731,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Saucer, Electric",
+ "nr_faces": 6796,
+ "nr_vertices": 3528,
+ "surface_area": 0.035222548022110126,
+ "volume": 0.00010731024483229731
+ }
+ },
+ "Cole_Hardware_Saucer_Glazed_6": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_Saucer_Glazed_6",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08007471605211118,
+ -0.07999385475897182,
+ -0.011988667371859902
+ ],
+ [
+ 0.07982328394788882,
+ 0.07968214524102818,
+ 0.017959332628140097
+ ]
+ ],
+ "mass": 0.000141241934014875,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Cole Hardware Saucer, Glazed, 6\"",
+ "nr_faces": 5248,
+ "nr_vertices": 2724,
+ "surface_area": 0.05270811256920829,
+ "volume": 0.000141241934014875
+ }
+ },
+ "Cole_Hardware_School_Bell_Solid_Brass_38": {
+ "asset_type": "FileBasedObject",
+ "id": "Cole_Hardware_School_Bell_Solid_Brass_38",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0404747333716358,
+ -0.04159287761008378,
+ -0.06567134981218918
+ ],
+ [
+ 0.042524266628364206,
+ 0.04141812238991622,
+ 0.09397765018781082
+ ]
+ ],
+ "mass": 8.03040743954075e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Cole Hardware School Bell, Solid Brass, 3/8\"",
+ "nr_faces": 8752,
+ "nr_vertices": 4502,
+ "surface_area": 0.027215706044734854,
+ "volume": 8.03040743954075e-05
+ }
+ },
+ "Colton_Wntr_Chukka_y4jO0I8JQFW": {
+ "asset_type": "FileBasedObject",
+ "id": "Colton_Wntr_Chukka_y4jO0I8JQFW",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06543793417603441,
+ -0.18091052496619558,
+ -0.040230456174460805
+ ],
+ [
+ 0.05670306582396558,
+ 0.1460354750338044,
+ 0.11823654382553919
+ ]
+ ],
+ "mass": 0.0011574684321887948,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Colton Wntr Chukka",
+ "nr_faces": 26766,
+ "nr_vertices": 15387,
+ "surface_area": 0.2123550264440075,
+ "volume": 0.0011574684321887948
+ }
+ },
+ "Connect_4_Launchers": {
+ "asset_type": "FileBasedObject",
+ "id": "Connect_4_Launchers",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13770778391163868,
+ -0.0386915092888132,
+ -0.1347215176800825
+ ],
+ [
+ 0.1377362160883613,
+ 0.0382814907111868,
+ 0.1349764823199175
+ ]
+ ],
+ "mass": 0.005342789030638418,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Connect 4 Launchers",
+ "nr_faces": 2544,
+ "nr_vertices": 1394,
+ "surface_area": 0.22163504527764438,
+ "volume": 0.005342789030638418
+ }
+ },
+ "Cootie_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Cootie_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1729310721981155,
+ -0.1398331820130442,
+ -0.043712528310990865
+ ],
+ [
+ 0.16825192780188453,
+ 0.1247478179869558,
+ 0.044071471689009135
+ ]
+ ],
+ "mass": 0.0005922205619274449,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Cootie Game",
+ "nr_faces": 28192,
+ "nr_vertices": 16876,
+ "surface_area": 0.11133545678302115,
+ "volume": 0.0005922205619274449
+ }
+ },
+ "Cootie_Game_tDhURNbfU5J": {
+ "asset_type": "FileBasedObject",
+ "id": "Cootie_Game_tDhURNbfU5J",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07086477981943735,
+ -0.06990994677645355,
+ -0.135268994131598
+ ],
+ [
+ 0.07054622018056264,
+ 0.06898605322354645,
+ 0.13439000586840197
+ ]
+ ],
+ "mass": 0.004993452501555958,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Cootie Game",
+ "nr_faces": 2454,
+ "nr_vertices": 1332,
+ "surface_area": 0.17940206528615465,
+ "volume": 0.004993452501555958
+ }
+ },
+ "Copperhead_Snake_Tieks_Brown_Snake_Print_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Copperhead_Snake_Tieks_Brown_Snake_Print_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.044792465400122945,
+ -0.11683272320262086,
+ -0.032350340459981225
+ ],
+ [
+ 0.03867253459987705,
+ 0.12923727679737915,
+ 0.060297659540018776
+ ]
+ ],
+ "mass": 0.0004714389874460349,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Copperhead Snake Tieks - Brown Snake Print Ballet Flats\nAdd exotic elegance to your step in these couture-worthy, Italian leather ballet flats. The metallic shine of copper, pewter and black combine forces with the perfect print to create a breathtaking pair of Tieks. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 30854,
+ "nr_vertices": 16344,
+ "surface_area": 0.07982610397404825,
+ "volume": 0.0004714389874460349
+ }
+ },
+ "Corningware_CW_by_Corningware_3qt_Oblong_Casserole_Dish_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Corningware_CW_by_Corningware_3qt_Oblong_Casserole_Dish_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18533255790518371,
+ -0.10989375148020042,
+ -0.026132659056715017
+ ],
+ [
+ 0.1831664420948163,
+ 0.11330824851979958,
+ 0.04536234094328499
+ ]
+ ],
+ "mass": 0.0006891011057998094,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Corningware CW by Corningware 3-qt. Oblong Casserole Dish (Blue)",
+ "nr_faces": 4612,
+ "nr_vertices": 2419,
+ "surface_area": 0.21644388123099614,
+ "volume": 0.0006891011057998094
+ }
+ },
+ "Court_Attitude": {
+ "asset_type": "FileBasedObject",
+ "id": "Court_Attitude",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056685206120602336,
+ -0.16419430858852282,
+ -0.049265191851654636
+ ],
+ [
+ 0.06461979387939766,
+ 0.12591669141147716,
+ 0.12589780814834536
+ ]
+ ],
+ "mass": 0.0013503589068683364,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Court Attitude",
+ "nr_faces": 37954,
+ "nr_vertices": 20061,
+ "surface_area": 0.18791717638095265,
+ "volume": 0.0013503589068683364
+ }
+ },
+ "Craftsman_Grip_Screwdriver_Phillips_Cushion": {
+ "asset_type": "FileBasedObject",
+ "id": "Craftsman_Grip_Screwdriver_Phillips_Cushion",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20536886260991688,
+ -0.018079593716582753,
+ -0.019642101525516632
+ ],
+ [
+ 0.05506313739008313,
+ 0.018247406283417245,
+ 0.01824889847448337
+ ]
+ ],
+ "mass": 7.015549204836467e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Craftsman Grip Screwdriver, Phillips Cushion",
+ "nr_faces": 5610,
+ "nr_vertices": 3273,
+ "surface_area": 0.013684166800161416,
+ "volume": 7.015549204836467e-05
+ }
+ },
+ "Crayola_Bonus_64_Crayons": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Bonus_64_Crayons",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07375061015785012,
+ -0.021939639548801976,
+ -0.06289556189588805
+ ],
+ [
+ 0.07349638984214987,
+ 0.02098136045119802,
+ 0.06414543810411195
+ ]
+ ],
+ "mass": 0.000740830408983955,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Crayola Bonus 64 Crayons",
+ "nr_faces": 5558,
+ "nr_vertices": 2908,
+ "surface_area": 0.05686329522155961,
+ "volume": 0.000740830408983955
+ }
+ },
+ "Crayola_Crayons_120_crayons": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Crayons_120_crayons",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11521052018525856,
+ -0.033454411820599717,
+ -0.06835920124188964
+ ],
+ [
+ 0.11556747981474144,
+ 0.03377458817940029,
+ 0.06870979875811035
+ ]
+ ],
+ "mass": 0.0020013275168447786,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crayola Crayons - 120 crayons\nNon-toxic. Surprise inside! Conforms to ASTM D-4236. Meets performance standard ANSI Z356.1. ACMI - Arts & Creative Materials Institute certified. Made in U.S.A.",
+ "nr_faces": 3250,
+ "nr_vertices": 1709,
+ "surface_area": 0.10607071781237877,
+ "volume": 0.0020013275168447786
+ }
+ },
+ "Crayola_Crayons_24_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Crayons_24_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.037159078682315716,
+ -0.014740037467530206,
+ -0.04934727983787453
+ ],
+ [
+ 0.03685592131768428,
+ 0.014874962532469792,
+ 0.06724772016212548
+ ]
+ ],
+ "mass": 0.00019700666592782385,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crayola Crayons - 24 count",
+ "nr_faces": 7562,
+ "nr_vertices": 4057,
+ "surface_area": 0.025141176621907728,
+ "volume": 0.00019700666592782385
+ }
+ },
+ "Crayola_Crayons_Washable_24_crayons": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Crayons_Washable_24_crayons",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.036612166291673874,
+ -0.015160046715101,
+ -0.0491685476759128
+ ],
+ [
+ 0.036370833708326125,
+ 0.014777953284899,
+ 0.06691645232408722
+ ]
+ ],
+ "mass": 0.00019915666985987983,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crayola Crayons, Washable - 24 crayons\nNontoxic. World's most washable. Crayola Washable Crayons are designed to easily wash off walls with just warm water and a sponge. Safety Information: ACMI - AP: Arts & Creative Materials Institute Certified. Conforms to ASTM D 4236. Meets performance standard ANSI Z356.1. All Crayola art materials are nontoxic. Made in USA.",
+ "nr_faces": 7522,
+ "nr_vertices": 4032,
+ "surface_area": 0.025114113515981064,
+ "volume": 0.00019915666985987983
+ }
+ },
+ "Crayola_Model_Magic_Modeling_Material_Single_Packs_6_pack_05_oz_packs": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Model_Magic_Modeling_Material_Single_Packs_6_pack_05_oz_packs",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06233490678337447,
+ -0.025930879305284257,
+ -0.09461023205606324
+ ],
+ [
+ 0.06265109321662553,
+ 0.025845120694715742,
+ 0.12292576794393677
+ ]
+ ],
+ "mass": 0.0011050017129092052,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crayola Model Magic Modeling Material, Single Packs - 6 pack, 0.5 oz packs",
+ "nr_faces": 4150,
+ "nr_vertices": 2242,
+ "surface_area": 0.07945999685907551,
+ "volume": 0.0011050017129092052
+ }
+ },
+ "Crayola_Model_Magic_Modeling_Material_White_3_oz": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Model_Magic_Modeling_Material_White_3_oz",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06300240411814048,
+ -0.027003151988857922,
+ -0.09455254753993585
+ ],
+ [
+ 0.0646085958818595,
+ 0.025603848011142075,
+ 0.12294845246006417
+ ]
+ ],
+ "mass": 0.00105777431498294,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crayola Model Magic Modeling Material, White - 3 oz",
+ "nr_faces": 2756,
+ "nr_vertices": 1528,
+ "surface_area": 0.07942387819664261,
+ "volume": 0.00105777431498294
+ }
+ },
+ "Crayola_Washable_Fingerpaint_Red_Blue_Yellow_3_count_8_fl_oz_bottes_each": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Washable_Fingerpaint_Red_Blue_Yellow_3_count_8_fl_oz_bottes_each",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08861647137097735,
+ -0.03489979637587111,
+ -0.07451241581135491
+ ],
+ [
+ 0.08842052862902265,
+ 0.03003520362412889,
+ 0.07318558418864508
+ ]
+ ],
+ "mass": 0.0014654749134590539,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Crayola Washable Fingerpaint, Red, Blue, Yellow - 3 count, 8 fl oz bottes each",
+ "nr_faces": 7342,
+ "nr_vertices": 3977,
+ "surface_area": 0.09530953994208932,
+ "volume": 0.0014654749134590539
+ }
+ },
+ "Crayola_Washable_Sidewalk_Chalk_16_pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Washable_Sidewalk_Chalk_16_pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04576494486542057,
+ -0.046353232447894945,
+ -0.058324840663527694
+ ],
+ [
+ 0.04654205513457943,
+ 0.04549276755210505,
+ 0.09004215933647229
+ ]
+ ],
+ "mass": 0.0008963260697554224,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crayola Washable Sidewalk Chalk - 16 pack",
+ "nr_faces": 5898,
+ "nr_vertices": 3153,
+ "surface_area": 0.057535389920942766,
+ "volume": 0.0008963260697554224
+ }
+ },
+ "Crayola_Washable_Sidewalk_Chalk_16_pack_wDZECiw7J6s": {
+ "asset_type": "FileBasedObject",
+ "id": "Crayola_Washable_Sidewalk_Chalk_16_pack_wDZECiw7J6s",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.046009401713554214,
+ -0.04622871792242518,
+ -0.058275607085824875
+ ],
+ [
+ 0.04645859828644578,
+ 0.04559528207757482,
+ 0.08987239291417512
+ ]
+ ],
+ "mass": 0.0008959274440146143,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crayola Washable Sidewalk Chalk - 16 pack",
+ "nr_faces": 9010,
+ "nr_vertices": 4712,
+ "surface_area": 0.05753638564342713,
+ "volume": 0.0008959274440146143
+ }
+ },
+ "Crazy_8": {
+ "asset_type": "FileBasedObject",
+ "id": "Crazy_8",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06446765759381118,
+ -0.165357457541187,
+ -0.055213371535585774
+ ],
+ [
+ 0.054422342406188824,
+ 0.14049754245881302,
+ 0.15873362846441422
+ ]
+ ],
+ "mass": 0.001797655641484013,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Crazy 8\nFW-HIGH TOP",
+ "nr_faces": 25056,
+ "nr_vertices": 13616,
+ "surface_area": 0.17606505353761173,
+ "volume": 0.001797655641484013
+ }
+ },
+ "Crazy_Shadow_2": {
+ "asset_type": "FileBasedObject",
+ "id": "Crazy_Shadow_2",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06652644560811462,
+ -0.17327472184893486,
+ -0.0496932409385251
+ ],
+ [
+ 0.05161855439188538,
+ 0.12293027815106514,
+ 0.12115975906147491
+ ]
+ ],
+ "mass": 0.0012333166788243313,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Crazy Shadow 2",
+ "nr_faces": 39326,
+ "nr_vertices": 22043,
+ "surface_area": 0.19221393769443468,
+ "volume": 0.0012333166788243313
+ }
+ },
+ "Crazy_Shadow_2_oW4Jd10HFFr": {
+ "asset_type": "FileBasedObject",
+ "id": "Crazy_Shadow_2_oW4Jd10HFFr",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06597874315851536,
+ -0.16548051284466153,
+ -0.05015957191251682
+ ],
+ [
+ 0.05004825684148464,
+ 0.13067248715533847,
+ 0.12091542808748318
+ ]
+ ],
+ "mass": 0.0017423664263929986,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Crazy Shadow 2",
+ "nr_faces": 23866,
+ "nr_vertices": 13045,
+ "surface_area": 0.130843496226435,
+ "volume": 0.0017423664263929986
+ }
+ },
+ "Cream_Tieks_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Cream_Tieks_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04483783993343958,
+ -0.11907507611862404,
+ -0.027738400377142584
+ ],
+ [
+ 0.038725160066560425,
+ 0.12649992388137596,
+ 0.052035599622857406
+ ]
+ ],
+ "mass": 0.0004946519083630998,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Cream Tieks - Italian Leather Ballet Flats\nOld meets new in this stylish, sexy reinvention of the ballet flat. Return to romance in this lovely Cream color, designed to look exquisite with any outfit. A favorite among brides. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 17216,
+ "nr_vertices": 9370,
+ "surface_area": 0.07301432108226684,
+ "volume": 0.0004946519083630998
+ }
+ },
+ "Creatine_Monohydrate": {
+ "asset_type": "FileBasedObject",
+ "id": "Creatine_Monohydrate",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0643286781174494,
+ -0.06431911978813631,
+ -0.08938342014012896
+ ],
+ [
+ 0.06440932188255061,
+ 0.06434288021186368,
+ 0.09443057985987105
+ ]
+ ],
+ "mass": 0.0021836861572908208,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Creatine Monohydrate",
+ "nr_faces": 9888,
+ "nr_vertices": 5067,
+ "surface_area": 0.09448531026235737,
+ "volume": 0.0021836861572908208
+ }
+ },
+ "Crosley_Alarm_Clock_Vintage_Metal": {
+ "asset_type": "FileBasedObject",
+ "id": "Crosley_Alarm_Clock_Vintage_Metal",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05451267120099429,
+ -0.027688353685026257,
+ -0.06449959019714505
+ ],
+ [
+ 0.054951328799005716,
+ 0.02633464631497374,
+ 0.09778740980285494
+ ]
+ ],
+ "mass": 0.00035399915035025506,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crosley Alarm Clock, Vintage Metal",
+ "nr_faces": 10248,
+ "nr_vertices": 5619,
+ "surface_area": 0.03590442460916743,
+ "volume": 0.00035399915035025506
+ }
+ },
+ "Crunch_Girl_Scouts_Candy_Bars_Peanut_Butter_Creme_78_oz_box": {
+ "asset_type": "FileBasedObject",
+ "id": "Crunch_Girl_Scouts_Candy_Bars_Peanut_Butter_Creme_78_oz_box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06921504203161176,
+ -0.031727406426527154,
+ -0.08153371899220026
+ ],
+ [
+ 0.06941895796838823,
+ 0.03142659357347285,
+ 0.08243228100779973
+ ]
+ ],
+ "mass": 0.0013007732022925034,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Crunch Girl Scouts Candy Bars, Peanut Butter Creme - 7.8 oz box",
+ "nr_faces": 3682,
+ "nr_vertices": 1988,
+ "surface_area": 0.07553650195036135,
+ "volume": 0.0013007732022925034
+ }
+ },
+ "Curver_Storage_Bin_Black_Small": {
+ "asset_type": "FileBasedObject",
+ "id": "Curver_Storage_Bin_Black_Small",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14357088418613312,
+ -0.09657684053796593,
+ -0.05633649450165952
+ ],
+ [
+ 0.14229311581386686,
+ 0.09668515946203407,
+ 0.07768150549834048
+ ]
+ ],
+ "mass": 0.00051193746738183,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Curver Storage Bin, Black, Small",
+ "nr_faces": 86044,
+ "nr_vertices": 57099,
+ "surface_area": 0.3381881337825868,
+ "volume": 0.00051193746738183
+ }
+ },
+ "DANCING_ALLIGATOR": {
+ "asset_type": "FileBasedObject",
+ "id": "DANCING_ALLIGATOR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.048249605838323883,
+ -0.18027680072326996,
+ -0.030005568714623274
+ ],
+ [
+ 0.04948439416167612,
+ 0.11459619927673004,
+ 0.04084443128537672
+ ]
+ ],
+ "mass": 0.00045573416959820246,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "DANCING ALLIGATOR\nWhen pulled along, the alligator moves his head and tail up and down making click-clack sound.",
+ "nr_faces": 20484,
+ "nr_vertices": 12018,
+ "surface_area": 0.08413443120559322,
+ "volume": 0.00045573416959820246
+ }
+ },
+ "DANCING_ALLIGATOR_zoWBjc0jbTs": {
+ "asset_type": "FileBasedObject",
+ "id": "DANCING_ALLIGATOR_zoWBjc0jbTs",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.047469578926005944,
+ -0.1966053275765095,
+ -0.033666709372604214
+ ],
+ [
+ 0.04809942107399406,
+ 0.1256926724234905,
+ 0.05377829062739579
+ ]
+ ],
+ "mass": 0.0005899899204931703,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "DANCING ALLIGATOR\nWhile being pulled, the wooden pieces make rhythmic click-clack sounds.",
+ "nr_faces": 16340,
+ "nr_vertices": 9649,
+ "surface_area": 0.09067100864883093,
+ "volume": 0.0005899899204931703
+ }
+ },
+ "DIM_CDG": {
+ "asset_type": "FileBasedObject",
+ "id": "DIM_CDG",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.023934351539242348,
+ -0.023838650876812927,
+ -0.03983373680400286
+ ],
+ [
+ 0.02377464846075765,
+ 0.02378334912318707,
+ 0.044438263195997134
+ ]
+ ],
+ "mass": 0.00013406731768390265,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "DIM + CDG",
+ "nr_faces": 9242,
+ "nr_vertices": 4756,
+ "surface_area": 0.015160911980013932,
+ "volume": 0.00013406731768390265
+ }
+ },
+ "DINING_ROOM_CLASSIC": {
+ "asset_type": "FileBasedObject",
+ "id": "DINING_ROOM_CLASSIC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10758901427144389,
+ -0.12941167827288222,
+ -0.0492800252672541
+ ],
+ [
+ 0.10782998572855611,
+ 0.10510232172711778,
+ 0.1033209747327459
+ ]
+ ],
+ "mass": 0.0008496338135501647,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "DINING ROOM - CLASSIC\nChildren can enjoy decorating their dollhouse with the Classic set of furniture while developing their imagination and creating more interest time.",
+ "nr_faces": 12230,
+ "nr_vertices": 7552,
+ "surface_area": 0.15161384133575123,
+ "volume": 0.0008496338135501647
+ }
+ },
+ "DINING_ROOM_CLASSIC_UJuxQ0hv5XU": {
+ "asset_type": "FileBasedObject",
+ "id": "DINING_ROOM_CLASSIC_UJuxQ0hv5XU",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09975167874128604,
+ -0.09409491307162607,
+ -0.050216014131470144
+ ],
+ [
+ 0.10001632125871396,
+ 0.13383408692837392,
+ 0.10119498586852985
+ ]
+ ],
+ "mass": 0.0007640738402288714,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "DINING ROOM - CLASSIC\nChildren can enjoy decorating their dollhouse with the Classic set of furniture while developing their imagination and creating more interest time.",
+ "nr_faces": 9792,
+ "nr_vertices": 5801,
+ "surface_area": 0.1525608550921559,
+ "volume": 0.0007640738402288714
+ }
+ },
+ "DINNING_ROOM_FURNITURE_SET_1": {
+ "asset_type": "FileBasedObject",
+ "id": "DINNING_ROOM_FURNITURE_SET_1",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09634533858436894,
+ -0.10093003329984329,
+ -0.03494686807609894
+ ],
+ [
+ 0.09442266141563106,
+ 0.08777696670015671,
+ 0.06332713192390108
+ ]
+ ],
+ "mass": 0.0002869315584756276,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "DINNING ROOM (FURNITURE SET 1)\nThis set includes a dining table, a cabinet, and four chairs. Made of Eco-Friendly PlanWood and solid rubber wood.",
+ "nr_faces": 9412,
+ "nr_vertices": 5504,
+ "surface_area": 0.08260249628768238,
+ "volume": 0.0002869315584756276
+ }
+ },
+ "DOLL_FAMILY": {
+ "asset_type": "FileBasedObject",
+ "id": "DOLL_FAMILY",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11848093531132582,
+ -0.04416898905322322,
+ -0.06260605754367947
+ ],
+ [
+ 0.11253606468867418,
+ 0.04647901094677678,
+ 0.07092594245632053
+ ]
+ ],
+ "mass": 0.00030896137567314413,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "DOLL FAMILY",
+ "nr_faces": 35812,
+ "nr_vertices": 20911,
+ "surface_area": 0.07671646623614771,
+ "volume": 0.00030896137567314413
+ }
+ },
+ "DPC_Handmade_Hat_Brown": {
+ "asset_type": "FileBasedObject",
+ "id": "DPC_Handmade_Hat_Brown",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15385138052695493,
+ -0.17624554330359313,
+ -0.075533577311456
+ ],
+ [
+ 0.16452961947304506,
+ 0.17765745669640687,
+ 0.067656422688544
+ ]
+ ],
+ "mass": 0.0007814177439460894,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Hat",
+ "description": "DPC Handmade Hat, Brown",
+ "nr_faces": 22828,
+ "nr_vertices": 12201,
+ "surface_area": 0.3115022412154774,
+ "volume": 0.0007814177439460894
+ }
+ },
+ "DPC_Thinsulate_Isolate_Gloves_Brown": {
+ "asset_type": "FileBasedObject",
+ "id": "DPC_Thinsulate_Isolate_Gloves_Brown",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14637190025267538,
+ -0.12908538363955385,
+ -0.02044412988758686
+ ],
+ [
+ 0.15472209974732462,
+ 0.12693461636044615,
+ 0.032343870112413145
+ ]
+ ],
+ "mass": 0.0012321822120628695,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "DPC Thinsulate Isolate Gloves, Brown",
+ "nr_faces": 34294,
+ "nr_vertices": 18313,
+ "surface_area": 0.14753404067625514,
+ "volume": 0.0012321822120628695
+ }
+ },
+ "DPC_tropical_Trends_Hat": {
+ "asset_type": "FileBasedObject",
+ "id": "DPC_tropical_Trends_Hat",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19134972760546873,
+ -0.1993465046207851,
+ -0.10024388534649989
+ ],
+ [
+ 0.18501627239453128,
+ 0.2045094953792149,
+ 0.07157411465350012
+ ]
+ ],
+ "mass": 0.0010091633966353112,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Hat",
+ "description": "DPC tropical Trends, Hat",
+ "nr_faces": 55206,
+ "nr_vertices": 38820,
+ "surface_area": 0.37721136007398653,
+ "volume": 0.0010091633966353112
+ }
+ },
+ "DRAGON_W": {
+ "asset_type": "FileBasedObject",
+ "id": "DRAGON_W",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04942862386051794,
+ -0.1356972905441838,
+ -0.03112777160802025
+ ],
+ [
+ 0.04275837613948206,
+ 0.1270777094558162,
+ 0.07665222839197974
+ ]
+ ],
+ "mass": 0.0008154752824657861,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "DRAGON W",
+ "nr_faces": 18932,
+ "nr_vertices": 10152,
+ "surface_area": 0.09512994892277883,
+ "volume": 0.0008154752824657861
+ }
+ },
+ "D_ROSE_45": {
+ "asset_type": "FileBasedObject",
+ "id": "D_ROSE_45",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06447386191441386,
+ -0.1514628661252601,
+ -0.04474683291188881
+ ],
+ [
+ 0.051401138085586134,
+ 0.1472571338747399,
+ 0.1226021670881112
+ ]
+ ],
+ "mass": 0.0014025396830189924,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "D ROSE 4.5\nFW-HIGH TOP",
+ "nr_faces": 30974,
+ "nr_vertices": 16936,
+ "surface_area": 0.15930835066208993,
+ "volume": 0.0014025396830189924
+ }
+ },
+ "D_ROSE_773_II_Kqclsph05pE": {
+ "asset_type": "FileBasedObject",
+ "id": "D_ROSE_773_II_Kqclsph05pE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06260603231719848,
+ -0.17099629181857215,
+ -0.047453226404993026
+ ],
+ [
+ 0.04988996768280152,
+ 0.12633570818142784,
+ 0.12428377359500697
+ ]
+ ],
+ "mass": 0.001309741257816023,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "D ROSE 773 II",
+ "nr_faces": 47688,
+ "nr_vertices": 25893,
+ "surface_area": 0.18458207146487873,
+ "volume": 0.001309741257816023
+ }
+ },
+ "D_ROSE_773_II_hvInJwJ5HUD": {
+ "asset_type": "FileBasedObject",
+ "id": "D_ROSE_773_II_hvInJwJ5HUD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06140798424789127,
+ -0.17044203285872275,
+ -0.04715862082421803
+ ],
+ [
+ 0.050338015752108736,
+ 0.12740896714127725,
+ 0.12484437917578195
+ ]
+ ],
+ "mass": 0.0013105537419827165,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "D ROSE 773 II",
+ "nr_faces": 45804,
+ "nr_vertices": 25055,
+ "surface_area": 0.18159516813029725,
+ "volume": 0.0013105537419827165
+ }
+ },
+ "D_ROSE_ENGLEWOOD_II": {
+ "asset_type": "FileBasedObject",
+ "id": "D_ROSE_ENGLEWOOD_II",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0637045605531261,
+ -0.17161656504966247,
+ -0.03863655027193295
+ ],
+ [
+ 0.0506914394468739,
+ 0.13580943495033754,
+ 0.09592044972806707
+ ]
+ ],
+ "mass": 0.001152046730086903,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "D ROSE ENGLEWOOD II\nFW-SHOES",
+ "nr_faces": 35868,
+ "nr_vertices": 19669,
+ "surface_area": 0.16736495235993332,
+ "volume": 0.001152046730086903
+ }
+ },
+ "Dell_Ink_Cartridge": {
+ "asset_type": "FileBasedObject",
+ "id": "Dell_Ink_Cartridge",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.052048277423610095,
+ -0.026503850338386134,
+ -0.036544938008577
+ ],
+ [
+ 0.05137772257638991,
+ 0.026504149661613866,
+ 0.103390061991423
+ ]
+ ],
+ "mass": 0.0003716608269208235,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Dell Ink Cartridge",
+ "nr_faces": 5510,
+ "nr_vertices": 2982,
+ "surface_area": 0.04315438714536285,
+ "volume": 0.0003716608269208235
+ }
+ },
+ "Dell_Ink_Cartridge_Yellow_31": {
+ "asset_type": "FileBasedObject",
+ "id": "Dell_Ink_Cartridge_Yellow_31",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.015388159942204235,
+ -0.050749693068548,
+ -0.03765015145457821
+ ],
+ [
+ 0.018208840057795765,
+ 0.051209306931452,
+ 0.10246684854542179
+ ]
+ ],
+ "mass": 0.0002119658451993835,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Dell Ink Cartridge, Yellow 31",
+ "nr_faces": 3768,
+ "nr_vertices": 2190,
+ "surface_area": 0.03536618211042836,
+ "volume": 0.0002119658451993835
+ }
+ },
+ "Dell_Series_9_Color_Ink_Cartridge_MK993_High_Yield": {
+ "asset_type": "FileBasedObject",
+ "id": "Dell_Series_9_Color_Ink_Cartridge_MK993_High_Yield",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.034987031935408655,
+ -0.020067996815827632,
+ -0.050215674754411965
+ ],
+ [
+ 0.03463696806459134,
+ 0.019700003184172366,
+ 0.08389032524558802
+ ]
+ ],
+ "mass": 0.00026217405291507065,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Dell Series 9 Color Ink Cartridge (MK993), High Yield",
+ "nr_faces": 4150,
+ "nr_vertices": 2262,
+ "surface_area": 0.029370689846429196,
+ "volume": 0.00026217405291507065
+ }
+ },
+ "Design_Ideas_Drawer_Store_Organizer": {
+ "asset_type": "FileBasedObject",
+ "id": "Design_Ideas_Drawer_Store_Organizer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1529664835305029,
+ -0.07600543819159966,
+ -0.019608238208213075
+ ],
+ [
+ 0.1541485164694971,
+ 0.07547056180840034,
+ 0.03725976179178693
+ ]
+ ],
+ "mass": 0.0008006490180531855,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Design Ideas Drawer Store Organizer",
+ "nr_faces": 1936,
+ "nr_vertices": 1093,
+ "surface_area": 0.17089103093683222,
+ "volume": 0.0008006490180531855
+ }
+ },
+ "Deskstar_Desk_Top_Hard_Drive_1_TB": {
+ "asset_type": "FileBasedObject",
+ "id": "Deskstar_Desk_Top_Hard_Drive_1_TB",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0777444631601257,
+ -0.038038817404959395,
+ -0.10032645942226716
+ ],
+ [
+ 0.07764053683987429,
+ 0.03852718259504061,
+ 0.09904954057773283
+ ]
+ ],
+ "mass": 0.002208299972662681,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Deskstar Desk Top Hard Drive, 1 TB",
+ "nr_faces": 2656,
+ "nr_vertices": 1426,
+ "surface_area": 0.10925727026654605,
+ "volume": 0.002208299972662681
+ }
+ },
+ "Diamond_Visions_Scissors_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Diamond_Visions_Scissors_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03713641004725021,
+ -0.14580562912088676,
+ -0.006628176731621006
+ ],
+ [
+ 0.03952558995274978,
+ 0.06376337087911321,
+ 0.007968823268378993
+ ]
+ ],
+ "mass": 3.6651094272566335e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Diamond Visions Scissors, Red",
+ "nr_faces": 6816,
+ "nr_vertices": 3745,
+ "surface_area": 0.015287370402998126,
+ "volume": 3.6651094272566335e-05
+ }
+ },
+ "Diet_Pepsi_Soda_Cola12_Pack_12_oz_Cans": {
+ "asset_type": "FileBasedObject",
+ "id": "Diet_Pepsi_Soda_Cola12_Pack_12_oz_Cans",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20348521659143723,
+ -0.06430142950734198,
+ -0.06924852993070738
+ ],
+ [
+ 0.20290978340856278,
+ 0.06461757049265801,
+ 0.06947447006929261
+ ]
+ ],
+ "mass": 0.006771409743716262,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Diet Pepsi Soda Cola,12 Pack 12 oz Cans",
+ "nr_faces": 1990,
+ "nr_vertices": 1092,
+ "surface_area": 0.23248316858501109,
+ "volume": 0.006771409743716262
+ }
+ },
+ "Digital_Camo_Double_Decker_Lunch_Bag": {
+ "asset_type": "FileBasedObject",
+ "id": "Digital_Camo_Double_Decker_Lunch_Bag",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1325988791412526,
+ -0.09146009119667248,
+ -0.09545034616010968
+ ],
+ [
+ 0.1281421208587474,
+ 0.09021990880332753,
+ 0.12324765383989031
+ ]
+ ],
+ "mass": 0.007036485932556764,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Digital Camo Double Decker Lunch Bag",
+ "nr_faces": 16358,
+ "nr_vertices": 9022,
+ "surface_area": 0.22234129104165673,
+ "volume": 0.007036485932556764
+ }
+ },
+ "Dino_3": {
+ "asset_type": "FileBasedObject",
+ "id": "Dino_3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12115249242245078,
+ -0.033183176986633096,
+ -0.0845378849298547
+ ],
+ [
+ 0.16757650757754922,
+ 0.0353368230133669,
+ 0.042703115070145306
+ ]
+ ],
+ "mass": 0.0002655483320645139,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Dino 3",
+ "nr_faces": 17722,
+ "nr_vertices": 9654,
+ "surface_area": 0.04605837180507018,
+ "volume": 0.0002655483320645139
+ }
+ },
+ "Dino_4": {
+ "asset_type": "FileBasedObject",
+ "id": "Dino_4",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06374980511478953,
+ -0.03209595502793574,
+ -0.04311433286647433
+ ],
+ [
+ 0.07306519488521047,
+ 0.026626044972064264,
+ 0.049610667133525674
+ ]
+ ],
+ "mass": 9.658863262907067e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Dino 4",
+ "nr_faces": 21900,
+ "nr_vertices": 12307,
+ "surface_area": 0.022020139306277484,
+ "volume": 9.658863262907067e-05
+ }
+ },
+ "Dino_5": {
+ "asset_type": "FileBasedObject",
+ "id": "Dino_5",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12120787894831136,
+ -0.03962983220687911,
+ -0.06047994344358244
+ ],
+ [
+ 0.09850212105168864,
+ 0.04493316779312089,
+ 0.05188605655641756
+ ]
+ ],
+ "mass": 0.000313732331887708,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Dino 5",
+ "nr_faces": 16162,
+ "nr_vertices": 8824,
+ "surface_area": 0.04353091665377182,
+ "volume": 0.000313732331887708
+ }
+ },
+ "Dixie_10_ounce_Bowls_35_ct": {
+ "asset_type": "FileBasedObject",
+ "id": "Dixie_10_ounce_Bowls_35_ct",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07614636147875642,
+ -0.07678366104001477,
+ -0.0365835603138595
+ ],
+ [
+ 0.07602263852124358,
+ 0.07529933895998522,
+ 0.0428174396861405
+ ]
+ ],
+ "mass": 0.0007527035923906089,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Dixie 10 ounce Bowls - 35 ct",
+ "nr_faces": 25548,
+ "nr_vertices": 13208,
+ "surface_area": 0.07351609614647527,
+ "volume": 0.0007527035923906089
+ }
+ },
+ "Dog": {
+ "asset_type": "FileBasedObject",
+ "id": "Dog",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11477059174971134,
+ -0.08199730316552181,
+ -0.08032176622850441
+ ],
+ [
+ 0.11722040825028865,
+ 0.10413669683447818,
+ 0.1189392337714956
+ ]
+ ],
+ "mass": 0.002228789587387092,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Dog\nDog",
+ "nr_faces": 67204,
+ "nr_vertices": 48133,
+ "surface_area": 0.17977241571272212,
+ "volume": 0.002228789587387092
+ }
+ },
+ "Don_Franciscos_Gourmet_Coffee_Medium_Decaf_100_Colombian_12_oz_340_g": {
+ "asset_type": "FileBasedObject",
+ "id": "Don_Franciscos_Gourmet_Coffee_Medium_Decaf_100_Colombian_12_oz_340_g",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.051095156069155524,
+ -0.05184626321050742,
+ -0.07122941026457603
+ ],
+ [
+ 0.05196884393084447,
+ 0.05127673678949258,
+ 0.06981158973542397
+ ]
+ ],
+ "mass": 0.0010743788759140557,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Don Francisco's Gourmet Coffee, Medium, Decaf, 100% Colombian - 12 oz (340 g)",
+ "nr_faces": 9452,
+ "nr_vertices": 4867,
+ "surface_area": 0.06071397637526754,
+ "volume": 0.0010743788759140557
+ }
+ },
+ "Down_To_Earth_Ceramic_Orchid_Pot_Asst_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Down_To_Earth_Ceramic_Orchid_Pot_Asst_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06761415535944926,
+ -0.06650435771381896,
+ -0.048243125509283336
+ ],
+ [
+ 0.06511084464055075,
+ 0.06622964228618104,
+ 0.07108887449071667
+ ]
+ ],
+ "mass": 0.0004472563921560347,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Down To Earth Ceramic Orchid Pot, Asst Blue",
+ "nr_faces": 23934,
+ "nr_vertices": 14420,
+ "surface_area": 0.12228538149185741,
+ "volume": 0.0004472563921560347
+ }
+ },
+ "Down_To_Earth_Orchid_Pot_Ceramic_Lime": {
+ "asset_type": "FileBasedObject",
+ "id": "Down_To_Earth_Orchid_Pot_Ceramic_Lime",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0690360812726115,
+ -0.06942475380896418,
+ -0.04864148777921391
+ ],
+ [
+ 0.0710619187273885,
+ 0.06997924619103582,
+ 0.0784875122207861
+ ]
+ ],
+ "mass": 0.00046562127713271185,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Down To Earth Orchid Pot, Ceramic, Lime",
+ "nr_faces": 20260,
+ "nr_vertices": 12461,
+ "surface_area": 0.13706786104343577,
+ "volume": 0.00046562127713271185
+ }
+ },
+ "Down_To_Earth_Orchid_Pot_Ceramic_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Down_To_Earth_Orchid_Pot_Ceramic_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0640474351412764,
+ -0.06666198266645569,
+ -0.045790333365353125
+ ],
+ [
+ 0.06652056485872361,
+ 0.0646970173335443,
+ 0.07407466663464687
+ ]
+ ],
+ "mass": 0.00032872777748361927,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Down To Earth Orchid Pot, Ceramic, Red",
+ "nr_faces": 24492,
+ "nr_vertices": 13918,
+ "surface_area": 0.10062777266917075,
+ "volume": 0.00032872777748361927
+ }
+ },
+ "ENFR_MID_ENFORCER": {
+ "asset_type": "FileBasedObject",
+ "id": "ENFR_MID_ENFORCER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.062281114859687875,
+ -0.17503379441223085,
+ -0.0536783480046478
+ ],
+ [
+ 0.061622885140312125,
+ 0.11804420558776915,
+ 0.1093166519953522
+ ]
+ ],
+ "mass": 0.0013773736614326607,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ENFR MID (ENFORCER)",
+ "nr_faces": 35714,
+ "nr_vertices": 19253,
+ "surface_area": 0.19344811429243497,
+ "volume": 0.0013773736614326607
+ }
+ },
+ "Eat_to_Live_The_Amazing_NutrientRich_Program_for_Fast_and_Sustained_Weight_Loss_Revised_Edition_Book": {
+ "asset_type": "FileBasedObject",
+ "id": "Eat_to_Live_The_Amazing_NutrientRich_Program_for_Fast_and_Sustained_Weight_Loss_Revised_Edition_Book",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0753742159655157,
+ -0.023737380450156373,
+ -0.10985559562268295
+ ],
+ [
+ 0.0651657840344843,
+ 0.026815619549843628,
+ 0.10051240437731705
+ ]
+ ],
+ "mass": 0.0010383088459039191,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Eat to Live: The Amazing Nutrient-Rich Program for Fast and Sustained Weight Loss, Revised Edition [Book]",
+ "nr_faces": 3812,
+ "nr_vertices": 2336,
+ "surface_area": 0.08197604063324822,
+ "volume": 0.0010383088459039191
+ }
+ },
+ "Ecoforms_Cup_B4_SAN": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Cup_B4_SAN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04858789141815681,
+ -0.05035621030900475,
+ -0.03518776036656333
+ ],
+ [
+ 0.05125910858184319,
+ 0.04962978969099525,
+ 0.03642323963343667
+ ]
+ ],
+ "mass": 5.057447379521401e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Cup, B4 SAN",
+ "nr_faces": 7542,
+ "nr_vertices": 3937,
+ "surface_area": 0.040839980575644426,
+ "volume": 5.057447379521401e-05
+ }
+ },
+ "Ecoforms_Garden_Pot_GP16ATurquois": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Garden_Pot_GP16ATurquois",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08476635424564287,
+ -0.08331370657762935,
+ -0.08379027692854552
+ ],
+ [
+ 0.07950164575435714,
+ 0.08065029342237065,
+ 0.07726972307145448
+ ]
+ ],
+ "mass": 0.0001597794837694265,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Garden Pot, GP16A-Turquois",
+ "nr_faces": 9126,
+ "nr_vertices": 4863,
+ "surface_area": 0.15844204715384813,
+ "volume": 0.0001597794837694265
+ }
+ },
+ "Ecoforms_Plant_Bowl_Atlas_Low": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Bowl_Atlas_Low",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15191432379746664,
+ -0.16858942142703634,
+ -0.06840149684169193
+ ],
+ [
+ 0.16999067620253336,
+ 0.15340957857296367,
+ 0.06597150315830808
+ ]
+ ],
+ "mass": 0.0003121043290093866,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Bowl, Atlas Low",
+ "nr_faces": 9524,
+ "nr_vertices": 4993,
+ "surface_area": 0.274247687694566,
+ "volume": 0.0003121043290093866
+ }
+ },
+ "Ecoforms_Plant_Bowl_Turquoise_7": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Bowl_Turquoise_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09245108785167584,
+ -0.08997225739648779,
+ -0.060855204816135336
+ ],
+ [
+ 0.08913491214832416,
+ 0.09199874260351222,
+ 0.06176379518386467
+ ]
+ ],
+ "mass": 0.0001456649296908873,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Bowl, Turquoise, 7\"",
+ "nr_faces": 6254,
+ "nr_vertices": 3297,
+ "surface_area": 0.13226118935577957,
+ "volume": 0.0001456649296908873
+ }
+ },
+ "Ecoforms_Plant_Container_12_Pot_Nova": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_12_Pot_Nova",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1503926752995169,
+ -0.13921159237361413,
+ -0.15104835951119477
+ ],
+ [
+ 0.14667932470048312,
+ 0.15816240762638586,
+ 0.13580064048880525
+ ]
+ ],
+ "mass": 0.0006431110057524749,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, 12 Pot Nova",
+ "nr_faces": 8288,
+ "nr_vertices": 4306,
+ "surface_area": 0.49575980330795644,
+ "volume": 0.0006431110057524749
+ }
+ },
+ "Ecoforms_Plant_Container_B4_Har": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_B4_Har",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04986445956650169,
+ -0.050282237340442404,
+ -0.03624109046053301
+ ],
+ [
+ 0.05090254043349831,
+ 0.0506447626595576,
+ 0.03541090953946698
+ ]
+ ],
+ "mass": 4.990433229721449e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, B4 Har",
+ "nr_faces": 8754,
+ "nr_vertices": 4574,
+ "surface_area": 0.041447094443650766,
+ "volume": 4.990433229721449e-05
+ }
+ },
+ "Ecoforms_Plant_Container_FB6_Tur": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_FB6_Tur",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08188834507835363,
+ -0.08473596493943546,
+ -0.054595132794519934
+ ],
+ [
+ 0.07956465492164637,
+ 0.07692403506056456,
+ 0.053869867205480065
+ ]
+ ],
+ "mass": 0.00013279592641021268,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, FB6 Tur",
+ "nr_faces": 12316,
+ "nr_vertices": 6390,
+ "surface_area": 0.10964758771071959,
+ "volume": 0.00013279592641021268
+ }
+ },
+ "Ecoforms_Plant_Container_GP16AMOCHA": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_GP16AMOCHA",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08239786735277355,
+ -0.0823240571758819,
+ -0.0774685529571804
+ ],
+ [
+ 0.08031313264722646,
+ 0.0792499428241181,
+ 0.0838194470428196
+ ]
+ ],
+ "mass": 0.0001611979968048268,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, GP16A-MOCHA",
+ "nr_faces": 11020,
+ "nr_vertices": 5858,
+ "surface_area": 0.15824556935501158,
+ "volume": 0.0001611979968048268
+ }
+ },
+ "Ecoforms_Plant_Container_GP16A_Coral": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_GP16A_Coral",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08088061701098856,
+ -0.08418495306714661,
+ -0.07906030864523741
+ ],
+ [
+ 0.08386138298901144,
+ 0.08028304693285339,
+ 0.08177469135476258
+ ]
+ ],
+ "mass": 0.000176576249937737,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, GP16A, Coral",
+ "nr_faces": 10040,
+ "nr_vertices": 5342,
+ "surface_area": 0.15931572613243045,
+ "volume": 0.000176576249937737
+ }
+ },
+ "Ecoforms_Plant_Container_QP6CORAL": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_QP6CORAL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08990451159268892,
+ -0.10104501290031255,
+ -0.09227593760752265
+ ],
+ [
+ 0.10134548840731107,
+ 0.09003298709968745,
+ 0.07626406239247736
+ ]
+ ],
+ "mass": 0.00034222558240776577,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, QP6-CORAL",
+ "nr_faces": 5320,
+ "nr_vertices": 2913,
+ "surface_area": 0.24217650025614165,
+ "volume": 0.00034222558240776577
+ }
+ },
+ "Ecoforms_Plant_Container_QP6HARVEST": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_QP6HARVEST",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09666186608578371,
+ -0.09320350867843806,
+ -0.09112426584118585
+ ],
+ [
+ 0.09352913391421629,
+ 0.09697349132156194,
+ 0.07662373415881414
+ ]
+ ],
+ "mass": 0.0003419193762948432,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, QP6-HARVEST",
+ "nr_faces": 3962,
+ "nr_vertices": 2212,
+ "surface_area": 0.24050593695515093,
+ "volume": 0.0003419193762948432
+ }
+ },
+ "Ecoforms_Plant_Container_QP_Harvest": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_QP_Harvest",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04380688983947681,
+ -0.04321277630675868,
+ -0.04966132168146371
+ ],
+ [
+ 0.044162110160523196,
+ 0.04418022369324132,
+ 0.04032767831853628
+ ]
+ ],
+ "mass": 8.049238590667e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, QP, Harvest",
+ "nr_faces": 7442,
+ "nr_vertices": 4012,
+ "surface_area": 0.05569205895609854,
+ "volume": 8.049238590667e-05
+ }
+ },
+ "Ecoforms_Plant_Container_QP_Turquoise": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_QP_Turquoise",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04517016604288305,
+ -0.04389425177140679,
+ -0.04906064699207304
+ ],
+ [
+ 0.04275983395711695,
+ 0.04427774822859321,
+ 0.04075135300792696
+ ]
+ ],
+ "mass": 8.4728784868715e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, QP, Turquoise",
+ "nr_faces": 14776,
+ "nr_vertices": 7670,
+ "surface_area": 0.05571772468930211,
+ "volume": 8.4728784868715e-05
+ }
+ },
+ "Ecoforms_Plant_Container_Quadra_Sand_QP6": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_Quadra_Sand_QP6",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09052707033978469,
+ -0.0957802664487401,
+ -0.08792388106375155
+ ],
+ [
+ 0.09982792966021532,
+ 0.0943507335512599,
+ 0.08060111893624845
+ ]
+ ],
+ "mass": 0.00031804653270977695,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, Quadra, Sand, QP6",
+ "nr_faces": 3844,
+ "nr_vertices": 2121,
+ "surface_area": 0.24099877332286032,
+ "volume": 0.00031804653270977695
+ }
+ },
+ "Ecoforms_Plant_Container_Quadra_Turquoise_QP12": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_Quadra_Turquoise_QP12",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09790652322437056,
+ -0.09806463599768692,
+ -0.14139223230512912
+ ],
+ [
+ 0.10189547677562945,
+ 0.10162936400231308,
+ 0.14130176769487085
+ ]
+ ],
+ "mass": 0.0006280828236533923,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, Quadra, Turquoise, QP12",
+ "nr_faces": 5032,
+ "nr_vertices": 2821,
+ "surface_area": 0.4150295465477283,
+ "volume": 0.0006280828236533923
+ }
+ },
+ "Ecoforms_Plant_Container_S14Turquoise": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_S14Turquoise",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07439210740105238,
+ -0.07430760075513543,
+ -0.008279768991422114
+ ],
+ [
+ 0.07300589259894762,
+ 0.07322139924486457,
+ 0.018240231008577884
+ ]
+ ],
+ "mass": 4.413934120235599e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, S14-Turquoise",
+ "nr_faces": 4592,
+ "nr_vertices": 2391,
+ "surface_area": 0.04319553461250214,
+ "volume": 4.413934120235599e-05
+ }
+ },
+ "Ecoforms_Plant_Container_S24NATURAL": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_S24NATURAL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11980198421619649,
+ -0.11950351873185444,
+ -0.010324666629778663
+ ],
+ [
+ 0.1214670157838035,
+ 0.12128248126814556,
+ 0.02283533337022134
+ ]
+ ],
+ "mass": 0.0001491250684568455,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, S24-NATURAL",
+ "nr_faces": 4256,
+ "nr_vertices": 2209,
+ "surface_area": 0.11156493965831124,
+ "volume": 0.0001491250684568455
+ }
+ },
+ "Ecoforms_Plant_Container_S24Turquoise": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_S24Turquoise",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12064479492844239,
+ -0.1214296642700729,
+ -0.010239105791182127
+ ],
+ [
+ 0.12108820507155761,
+ 0.1204643357299271,
+ 0.022928894208817878
+ ]
+ ],
+ "mass": 0.00015178383876082198,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, S24-Turquoise",
+ "nr_faces": 4244,
+ "nr_vertices": 2199,
+ "surface_area": 0.11199928997614889,
+ "volume": 0.00015178383876082198
+ }
+ },
+ "Ecoforms_Plant_Container_SB9Turquoise": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_SB9Turquoise",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1466377202129449,
+ -0.15187303362565935,
+ -0.12147078531210176
+ ],
+ [
+ 0.1531072797870551,
+ 0.14735096637434064,
+ 0.11977621468789824
+ ]
+ ],
+ "mass": 0.00069092902064263,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, SB9-Turquoise",
+ "nr_faces": 6820,
+ "nr_vertices": 3601,
+ "surface_area": 0.45657489916807703,
+ "volume": 0.00069092902064263
+ }
+ },
+ "Ecoforms_Plant_Container_URN_NAT": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_URN_NAT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07107038850197259,
+ -0.07559508738129248,
+ -0.08728817759151442
+ ],
+ [
+ 0.07779561149802741,
+ 0.07327391261870753,
+ 0.07264382240848559
+ ]
+ ],
+ "mass": 0.00014632984283535766,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Ecoforms Plant Container, URN NAT",
+ "nr_faces": 4926,
+ "nr_vertices": 2593,
+ "surface_area": 0.1265398869123418,
+ "volume": 0.00014632984283535766
+ }
+ },
+ "Ecoforms_Plant_Container_URN_SAN": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_URN_SAN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06978508509439578,
+ -0.07168347574500249,
+ -0.08647707262200094
+ ],
+ [
+ 0.07939391490560421,
+ 0.07700652425499752,
+ 0.07288192737799906
+ ]
+ ],
+ "mass": 0.00014449018893157052,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Ecoforms Plant Container, URN SAN",
+ "nr_faces": 4930,
+ "nr_vertices": 2632,
+ "surface_area": 0.12655193647921092,
+ "volume": 0.00014449018893157052
+ }
+ },
+ "Ecoforms_Plant_Container_Urn_55_Avocado": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_Urn_55_Avocado",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06713234190337984,
+ -0.07206250922325053,
+ -0.08516197487868167
+ ],
+ [
+ 0.08238065809662017,
+ 0.07681249077674947,
+ 0.07475302512131833
+ ]
+ ],
+ "mass": 0.00014584747436457765,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, Urn 5.5, Avocado",
+ "nr_faces": 4978,
+ "nr_vertices": 2639,
+ "surface_area": 0.12761387371836194,
+ "volume": 0.00014584747436457765
+ }
+ },
+ "Ecoforms_Plant_Container_Urn_55_Mocha": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Container_Urn_55_Mocha",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07151241529066278,
+ -0.07068483292027031,
+ -0.08516710418003813
+ ],
+ [
+ 0.07784658470933721,
+ 0.0783891670797297,
+ 0.07474789581996187
+ ]
+ ],
+ "mass": 0.00014352119046963298,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Container, Urn 5.5, Mocha",
+ "nr_faces": 6268,
+ "nr_vertices": 3298,
+ "surface_area": 0.12753458200665616,
+ "volume": 0.00014352119046963298
+ }
+ },
+ "Ecoforms_Plant_Plate_S11Turquoise": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Plate_S11Turquoise",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05938758835865501,
+ -0.05930901481700769,
+ -0.008008590787557505
+ ],
+ [
+ 0.05863941164134499,
+ 0.05883798518299231,
+ 0.014849409212442495
+ ]
+ ],
+ "mass": 2.107591390964633e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Plate, S11-Turquoise",
+ "nr_faces": 4966,
+ "nr_vertices": 2652,
+ "surface_area": 0.026503441847475682,
+ "volume": 2.107591390964633e-05
+ }
+ },
+ "Ecoforms_Plant_Pot_GP9AAvocado": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Pot_GP9AAvocado",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.047340250327691014,
+ -0.04584989603119525,
+ -0.044540001538771426
+ ],
+ [
+ 0.04632074967230899,
+ 0.04838810396880475,
+ 0.04226199846122858
+ ]
+ ],
+ "mass": 2.4184502830819338e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Pot, GP9A-Avocado",
+ "nr_faces": 11092,
+ "nr_vertices": 5832,
+ "surface_area": 0.04566199852169151,
+ "volume": 2.4184502830819338e-05
+ }
+ },
+ "Ecoforms_Plant_Pot_GP9_SAND": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Pot_GP9_SAND",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0467833874366854,
+ -0.04821487035781917,
+ -0.04200986001646943
+ ],
+ [
+ 0.0473246125633146,
+ 0.045998129642180835,
+ 0.04442513998353057
+ ]
+ ],
+ "mass": 2.3748041479670004e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Pot, GP9 SAND",
+ "nr_faces": 15368,
+ "nr_vertices": 7989,
+ "surface_area": 0.045959297269158345,
+ "volume": 2.3748041479670004e-05
+ }
+ },
+ "Ecoforms_Plant_Saucer_S14MOCHA": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Saucer_S14MOCHA",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07439896474011762,
+ -0.0730026723403514,
+ -0.008693645151215157
+ ],
+ [
+ 0.07345203525988238,
+ 0.0749253276596486,
+ 0.018418354848784846
+ ]
+ ],
+ "mass": 4.4446256169875833e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Saucer, S14-MOCHA",
+ "nr_faces": 5174,
+ "nr_vertices": 2696,
+ "surface_area": 0.04355587990889394,
+ "volume": 4.4446256169875833e-05
+ }
+ },
+ "Ecoforms_Plant_Saucer_S14NATURAL": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Saucer_S14NATURAL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07400528050771726,
+ -0.07570836143666058,
+ -0.008172513017725485
+ ],
+ [
+ 0.07358171949228275,
+ 0.0717626385633394,
+ 0.017982486982274514
+ ]
+ ],
+ "mass": 4.004803810613266e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Saucer, S14-NATURAL",
+ "nr_faces": 4974,
+ "nr_vertices": 2581,
+ "surface_area": 0.04305845050952582,
+ "volume": 4.004803810613266e-05
+ }
+ },
+ "Ecoforms_Plant_Saucer_S17MOCHA": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Saucer_S17MOCHA",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08953427463901942,
+ -0.08715511495508052,
+ -0.009169057961774939
+ ],
+ [
+ 0.08728672536098057,
+ 0.08976488504491947,
+ 0.021339942038225063
+ ]
+ ],
+ "mass": 7.644202736089716e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Saucer, S17-MOCHA",
+ "nr_faces": 6504,
+ "nr_vertices": 3361,
+ "surface_area": 0.0628331831790469,
+ "volume": 7.644202736089716e-05
+ }
+ },
+ "Ecoforms_Plant_Saucer_S20MOCHA": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Saucer_S20MOCHA",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10397686922629006,
+ -0.10283540634095607,
+ -0.00982369561580521
+ ],
+ [
+ 0.10243913077370995,
+ 0.10375159365904392,
+ 0.02334030438419479
+ ]
+ ],
+ "mass": 0.0001042166322621525,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Saucer, S20-MOCHA",
+ "nr_faces": 5718,
+ "nr_vertices": 2966,
+ "surface_area": 0.08365218684740235,
+ "volume": 0.0001042166322621525
+ }
+ },
+ "Ecoforms_Plant_Saucer_SQ1HARVEST": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Saucer_SQ1HARVEST",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04332764423626554,
+ -0.04259787890436411,
+ -0.008341429762646312
+ ],
+ [
+ 0.04315935576373446,
+ 0.04390712109563589,
+ 0.012615570237353688
+ ]
+ ],
+ "mass": 2.6488562842276e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Saucer, SQ1-HARVEST",
+ "nr_faces": 7360,
+ "nr_vertices": 3829,
+ "surface_area": 0.020379035631936687,
+ "volume": 2.6488562842276e-05
+ }
+ },
+ "Ecoforms_Plant_Saucer_SQ8COR": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plant_Saucer_SQ8COR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09110921807575156,
+ -0.09150313840724074,
+ -0.011012624860966453
+ ],
+ [
+ 0.08973278192424843,
+ 0.08899486159275927,
+ 0.02217637513903355
+ ]
+ ],
+ "mass": 0.00013781792410548152,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plant Saucer, SQ8-COR",
+ "nr_faces": 7760,
+ "nr_vertices": 3991,
+ "surface_area": 0.08496786537462357,
+ "volume": 0.00013781792410548152
+ }
+ },
+ "Ecoforms_Planter_Bowl_Cole_Hardware": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Planter_Bowl_Cole_Hardware",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09194187603246386,
+ -0.09177989488741065,
+ -0.06009740702042232
+ ],
+ [
+ 0.08832712396753614,
+ 0.08896410511258936,
+ 0.061422592979577674
+ ]
+ ],
+ "mass": 0.00015092717891245085,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Planter Bowl, Cole Hardware",
+ "nr_faces": 6464,
+ "nr_vertices": 3384,
+ "surface_area": 0.1295883009529925,
+ "volume": 0.00015092717891245085
+ }
+ },
+ "Ecoforms_Planter_Pot_GP12AAvocado": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Planter_Pot_GP12AAvocado",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05992398225866493,
+ -0.05857610957952718,
+ -0.05960692960010992
+ ],
+ [
+ 0.05838701774133507,
+ 0.06002289042047282,
+ 0.05304707039989008
+ ]
+ ],
+ "mass": 5.570411049651113e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Planter Pot, GP12A-Avocado",
+ "nr_faces": 10104,
+ "nr_vertices": 5558,
+ "surface_area": 0.07148951909982396,
+ "volume": 5.570411049651113e-05
+ }
+ },
+ "Ecoforms_Planter_Pot_QP6Ebony": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Planter_Pot_QP6Ebony",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09432588549424137,
+ -0.09216147389018109,
+ -0.08708180891907623
+ ],
+ [
+ 0.09532811450575863,
+ 0.09703752610981892,
+ 0.08115919108092376
+ ]
+ ],
+ "mass": 0.000333067089751557,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Planter Pot, QP6-Ebony",
+ "nr_faces": 7618,
+ "nr_vertices": 4046,
+ "surface_area": 0.23866350454933322,
+ "volume": 0.000333067089751557
+ }
+ },
+ "Ecoforms_Plate_S20Avocado": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Plate_S20Avocado",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1037613165557212,
+ -0.10265238286930778,
+ -0.00964501740593506
+ ],
+ [
+ 0.1032496834442788,
+ 0.10386261713069221,
+ 0.022515982594064936
+ ]
+ ],
+ "mass": 0.00010173098964443234,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Plate, S20-Avocado",
+ "nr_faces": 4340,
+ "nr_vertices": 2249,
+ "surface_area": 0.08345539035006086,
+ "volume": 0.00010173098964443234
+ }
+ },
+ "Ecoforms_Pot_Nova_6_Turquoise": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Pot_Nova_6_Turquoise",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08713738005077992,
+ -0.08369137383504646,
+ -0.08450548159019834
+ ],
+ [
+ 0.09365761994922008,
+ 0.09651262616495354,
+ 0.08542051840980167
+ ]
+ ],
+ "mass": 0.00021545955573016603,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Pot, Nova 6, Turquoise",
+ "nr_faces": 8176,
+ "nr_vertices": 4275,
+ "surface_area": 0.1848466943775539,
+ "volume": 0.00021545955573016603
+ }
+ },
+ "Ecoforms_Quadra_Saucer_SQ1_Avocado": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Quadra_Saucer_SQ1_Avocado",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.043257079821558124,
+ -0.04391122555665266,
+ -0.00835266938797578
+ ],
+ [
+ 0.04382592017844188,
+ 0.04304677444334734,
+ 0.012496330612024221
+ ]
+ ],
+ "mass": 2.89656662409525e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Quadra Saucer, SQ1, Avocado",
+ "nr_faces": 4762,
+ "nr_vertices": 2475,
+ "surface_area": 0.020699793977228466,
+ "volume": 2.89656662409525e-05
+ }
+ },
+ "Ecoforms_Saucer_SQ3_Turquoise": {
+ "asset_type": "FileBasedObject",
+ "id": "Ecoforms_Saucer_SQ3_Turquoise",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13277451331175547,
+ -0.04457279770403553,
+ -0.008752498336897039
+ ],
+ [
+ 0.12906548668824455,
+ 0.046966202295964474,
+ 0.016086501663102958
+ ]
+ ],
+ "mass": 8.92777732512165e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ecoforms Saucer, SQ3, Turquoise",
+ "nr_faces": 2358,
+ "nr_vertices": 1226,
+ "surface_area": 0.06272499118052186,
+ "volume": 8.92777732512165e-05
+ }
+ },
+ "Elephant": {
+ "asset_type": "FileBasedObject",
+ "id": "Elephant",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0943184638944332,
+ -0.11035642256572448,
+ -0.09558597130468598
+ ],
+ [
+ 0.0971105361055668,
+ 0.09953857743427554,
+ 0.17496202869531402
+ ]
+ ],
+ "mass": 0.0027175829744432015,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Elephant\nElephant",
+ "nr_faces": 52216,
+ "nr_vertices": 28007,
+ "surface_area": 0.17216910555040596,
+ "volume": 0.0027175829744432015
+ }
+ },
+ "Embark_Lunch_Cooler_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Embark_Lunch_Cooler_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1593235658328105,
+ -0.09971325547773217,
+ -0.08479766177444764
+ ],
+ [
+ 0.1362504341671895,
+ 0.10108874452226783,
+ 0.11075833822555235
+ ]
+ ],
+ "mass": 0.007714632351355817,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Embark Lunch Cooler, Blue",
+ "nr_faces": 25084,
+ "nr_vertices": 13299,
+ "surface_area": 0.24612373443784805,
+ "volume": 0.007714632351355817
+ }
+ },
+ "Envision_Home_Dish_Drying_Mat_Red_6_x_18": {
+ "asset_type": "FileBasedObject",
+ "id": "Envision_Home_Dish_Drying_Mat_Red_6_x_18",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07792359951337931,
+ -0.20784323503964264,
+ -0.016641075269907605
+ ],
+ [
+ 0.07949040048662069,
+ 0.20203876496035736,
+ 0.020659924730092392
+ ]
+ ],
+ "mass": 0.0017504951646002418,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Envision Home Dish Drying Mat, Red, 6\" x 18\"",
+ "nr_faces": 19994,
+ "nr_vertices": 11485,
+ "surface_area": 0.16583403423890525,
+ "volume": 0.0017504951646002418
+ }
+ },
+ "Epson_273XL_Ink_Cartridge_Magenta": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_273XL_Ink_Cartridge_Magenta",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.037762382561522305,
+ -0.01490756865431251,
+ -0.06569802465941367
+ ],
+ [
+ 0.03815361743847769,
+ 0.014823431345687489,
+ 0.09462897534058634
+ ]
+ ],
+ "mass": 0.000234560788791061,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson 273XL Ink Cartridge - Magenta",
+ "nr_faces": 5578,
+ "nr_vertices": 2964,
+ "surface_area": 0.031976669501806304,
+ "volume": 0.000234560788791061
+ }
+ },
+ "Epson_DURABrite_Ultra_786_Black_Ink_Cartridge_T786120S": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_DURABrite_Ultra_786_Black_Ink_Cartridge_T786120S",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.045090963378906106,
+ -0.018147980289178717,
+ -0.0765521776029794
+ ],
+ [
+ 0.045260036621093895,
+ 0.01747401971082128,
+ 0.1051408223970206
+ ]
+ ],
+ "mass": 0.00039793901246097695,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson DURABrite Ultra 786 Black Ink Cartridge (T786120-S)",
+ "nr_faces": 6800,
+ "nr_vertices": 3556,
+ "surface_area": 0.04385087920306867,
+ "volume": 0.00039793901246097695
+ }
+ },
+ "Epson_Ink_Cartridge_126_Yellow": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_Ink_Cartridge_126_Yellow",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0561801101999829,
+ -0.013148955852379338,
+ -0.04360090653206595
+ ],
+ [
+ 0.057129889800017104,
+ 0.013796044147620663,
+ 0.07105709346793405
+ ]
+ ],
+ "mass": 0.00020335019349084383,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson Ink Cartridge, 126 Yellow",
+ "nr_faces": 4032,
+ "nr_vertices": 2204,
+ "surface_area": 0.03181937378621444,
+ "volume": 0.00020335019349084383
+ }
+ },
+ "Epson_Ink_Cartridge_Black_200": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_Ink_Cartridge_Black_200",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.057256781424531104,
+ -0.012516208827562898,
+ -0.04378390006025996
+ ],
+ [
+ 0.056329218575468895,
+ 0.012362791172437103,
+ 0.07087409993974005
+ ]
+ ],
+ "mass": 0.00020802433589276167,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson Ink Cartridge, Black 200",
+ "nr_faces": 5978,
+ "nr_vertices": 3162,
+ "surface_area": 0.03159632195322318,
+ "volume": 0.00020802433589276167
+ }
+ },
+ "Epson_LabelWorks_LC4WBN9_Tape_reel_labels_047_x_295_Roll_Black_on_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_LabelWorks_LC4WBN9_Tape_reel_labels_047_x_295_Roll_Black_on_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.044124507425472276,
+ -0.02091267903924239,
+ -0.04639537074000711
+ ],
+ [
+ 0.04400149257452773,
+ 0.01974732096075761,
+ 0.0766086292599929
+ ]
+ ],
+ "mass": 0.0002961121374241982,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson LabelWorks LC-4WBN9 Tape reel labels, 0.47\" x 29.5' Roll, Black on White",
+ "nr_faces": 4320,
+ "nr_vertices": 2380,
+ "surface_area": 0.03197375370332868,
+ "volume": 0.0002961121374241982
+ }
+ },
+ "Epson_LabelWorks_LC5WBN9_Tape_reel_labels_071_x_295_Roll_Black_on_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_LabelWorks_LC5WBN9_Tape_reel_labels_071_x_295_Roll_Black_on_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04475223810956841,
+ -0.019812196366759436,
+ -0.04600094310203792
+ ],
+ [
+ 0.044199761890431594,
+ 0.019228803633240567,
+ 0.07735505689796207
+ ]
+ ],
+ "mass": 0.0002922230232875125,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson LabelWorks LC-5WBN9 Tape reel labels, 0.71\" x 29.5' Roll, Black on White",
+ "nr_faces": 4454,
+ "nr_vertices": 2448,
+ "surface_area": 0.03207220371848149,
+ "volume": 0.0002922230232875125
+ }
+ },
+ "Epson_T5803_Ink_Cartridge_Magenta_1pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_T5803_Ink_Cartridge_Magenta_1pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05095509202466316,
+ -0.019219313782858443,
+ -0.04225149932440296
+ ],
+ [
+ 0.051167907975336845,
+ 0.019134686217141556,
+ 0.041878500675597036
+ ]
+ ],
+ "mass": 0.0003007809417325735,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson T5803 Ink Cartridge, Magenta - 1-pack",
+ "nr_faces": 4704,
+ "nr_vertices": 2480,
+ "surface_area": 0.028621573017165638,
+ "volume": 0.0003007809417325735
+ }
+ },
+ "Epson_UltraChrome_T0543_Ink_Cartridge_Magenta_1pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_UltraChrome_T0543_Ink_Cartridge_Magenta_1pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05620332531949038,
+ -0.012343388251042012,
+ -0.04459308224400588
+ ],
+ [
+ 0.05675867468050962,
+ 0.012571611748957988,
+ 0.07046191775599413
+ ]
+ ],
+ "mass": 0.0002013046412897583,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson UltraChrome T0543 Ink Cartridge, Magenta - 1-pack",
+ "nr_faces": 3562,
+ "nr_vertices": 1982,
+ "surface_area": 0.031749489351355714,
+ "volume": 0.0002013046412897583
+ }
+ },
+ "Epson_UltraChrome_T0548_Ink_Cartridge_Matte_Black_1pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Epson_UltraChrome_T0548_Ink_Cartridge_Matte_Black_1pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.057233346325366294,
+ -0.01151252292569285,
+ -0.044427170268984316
+ ],
+ [
+ 0.05789665367463371,
+ 0.01190547707430715,
+ 0.07092982973101568
+ ]
+ ],
+ "mass": 0.000198313125638212,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Epson UltraChrome T0548 Ink Cartridge, Matte Black - 1-pack",
+ "nr_faces": 3888,
+ "nr_vertices": 2133,
+ "surface_area": 0.03179228991332979,
+ "volume": 0.000198313125638212
+ }
+ },
+ "F10_TRX_FG_ssscuo9tGxb": {
+ "asset_type": "FileBasedObject",
+ "id": "F10_TRX_FG_ssscuo9tGxb",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04776836095283515,
+ -0.13307221274926842,
+ -0.04095025217462399
+ ],
+ [
+ 0.04644463904716486,
+ 0.14939878725073158,
+ 0.06705374782537601
+ ]
+ ],
+ "mass": 0.0008202508408544987,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "F10 TRX FG",
+ "nr_faces": 14708,
+ "nr_vertices": 8475,
+ "surface_area": 0.10137632920029968,
+ "volume": 0.0008202508408544987
+ }
+ },
+ "F10_TRX_TF_rH7tmKCdUJq": {
+ "asset_type": "FileBasedObject",
+ "id": "F10_TRX_TF_rH7tmKCdUJq",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.051217748891589136,
+ -0.14174949598322725,
+ -0.03710790730829529
+ ],
+ [
+ 0.04757925110841086,
+ 0.14790950401677275,
+ 0.06889509269170471
+ ]
+ ],
+ "mass": 0.0010028084954185734,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "F10 TRX TF",
+ "nr_faces": 19658,
+ "nr_vertices": 11051,
+ "surface_area": 0.10884323194848146,
+ "volume": 0.0010028084954185734
+ }
+ },
+ "F5_TRX_FG": {
+ "asset_type": "FileBasedObject",
+ "id": "F5_TRX_FG",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0527113776595302,
+ -0.14697053610770075,
+ -0.0439333438638947
+ ],
+ [
+ 0.0489376223404698,
+ 0.13605946389229925,
+ 0.0745346561361053
+ ]
+ ],
+ "mass": 0.0010558616440886446,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "F5 TRX FG",
+ "nr_faces": 14248,
+ "nr_vertices": 7810,
+ "surface_area": 0.08971347315329609,
+ "volume": 0.0010558616440886446
+ }
+ },
+ "FAIRY_TALE_BLOCKS": {
+ "asset_type": "FileBasedObject",
+ "id": "FAIRY_TALE_BLOCKS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1271004745962391,
+ -0.14853028217790398,
+ -0.07173162605426847
+ ],
+ [
+ 0.12058852540376087,
+ 0.116508717822096,
+ 0.15137137394573152
+ ]
+ ],
+ "mass": 0.001402324735136398,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FAIRY TALE BLOCKS\nCreate your own version of happily ever after with this fairly tale block set. Includes a prince",
+ "nr_faces": 23734,
+ "nr_vertices": 14195,
+ "surface_area": 0.20302395130896206,
+ "volume": 0.001402324735136398
+ }
+ },
+ "FARM_ANIMAL": {
+ "asset_type": "FileBasedObject",
+ "id": "FARM_ANIMAL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07956537705150721,
+ -0.0976896094302502,
+ -0.040854031399041195
+ ],
+ [
+ 0.09678062294849278,
+ 0.0767143905697498,
+ 0.051092968600958806
+ ]
+ ],
+ "mass": 0.0003266869328806444,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FARM ANIMAL\nThe set includes a cow, a calf, a piglet, a sheep dog that has moveable head, a sheep plus the sheep?s wool is removable to give that sheered look.",
+ "nr_faces": 25032,
+ "nr_vertices": 17078,
+ "surface_area": 0.06027348166851122,
+ "volume": 0.0003266869328806444
+ }
+ },
+ "FARM_ANIMAL_9GyfdcPyESK": {
+ "asset_type": "FileBasedObject",
+ "id": "FARM_ANIMAL_9GyfdcPyESK",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07714126601997609,
+ -0.0818352744575506,
+ -0.040853804206474637
+ ],
+ [
+ 0.10553973398002392,
+ 0.06568172554244942,
+ 0.05100619579352536
+ ]
+ ],
+ "mass": 0.0003257531646352812,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FARM ANIMAL\nThe set includes a cow, a calf, a piglet, a sheep dog that has moveable head, a sheep plus the sheep?s wool is removable to give that sheered look.",
+ "nr_faces": 28266,
+ "nr_vertices": 16101,
+ "surface_area": 0.06006217169215701,
+ "volume": 0.0003257531646352812
+ }
+ },
+ "FIRE_ENGINE": {
+ "asset_type": "FileBasedObject",
+ "id": "FIRE_ENGINE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.016465798654297887,
+ -0.05841967311460584,
+ -0.03239243783502529
+ ],
+ [
+ 0.016957201345702114,
+ 0.07869932688539416,
+ 0.06430356216497471
+ ]
+ ],
+ "mass": 0.000103680306076223,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FIRE ENGINE",
+ "nr_faces": 23904,
+ "nr_vertices": 13095,
+ "surface_area": 0.02712436365324312,
+ "volume": 0.000103680306076223
+ }
+ },
+ "FIRE_TRUCK": {
+ "asset_type": "FileBasedObject",
+ "id": "FIRE_TRUCK",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03512784484076934,
+ -0.06337914811068943,
+ -0.041725043175442546
+ ],
+ [
+ 0.03442215515923066,
+ 0.060663851889310574,
+ 0.062439956824557455
+ ]
+ ],
+ "mass": 0.00023270894659548216,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FIRE TRUCK\nThis little car has been designed to make it easy for small baby hands to push and play with. This series comes with Rescue Car, Fire Truck, and Helicopter.",
+ "nr_faces": 20576,
+ "nr_vertices": 11337,
+ "surface_area": 0.046056766750965,
+ "volume": 0.00023270894659548216
+ }
+ },
+ "FISHING_GAME": {
+ "asset_type": "FileBasedObject",
+ "id": "FISHING_GAME",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18545557313897892,
+ -0.1414063132120651,
+ -0.016857338601031047
+ ],
+ [
+ 0.20802642686102107,
+ 0.14035368678793492,
+ 0.044308661398968954
+ ]
+ ],
+ "mass": 0.00032190866219567024,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FISHING GAME\nGone fishin'! The set includes 6 colorful fish, pond-blue fabric, and 2 fishing rods. Rods can be adjusted from beginner to advanced level.",
+ "nr_faces": 18240,
+ "nr_vertices": 11200,
+ "surface_area": 0.1639189606063908,
+ "volume": 0.00032190866219567024
+ }
+ },
+ "FOOD_BEVERAGE_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "FOOD_BEVERAGE_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11714171587569941,
+ -0.06274441015747945,
+ -0.041131324011746094
+ ],
+ [
+ 0.1499732841243006,
+ 0.06476658984252055,
+ 0.07905667598825392
+ ]
+ ],
+ "mass": 0.0006808412251841277,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FOOD & BEVERAGE SET\nIncludes orange juice, water, milk, ketchup, jam,?and honey.",
+ "nr_faces": 7730,
+ "nr_vertices": 4168,
+ "surface_area": 0.08230855652708814,
+ "volume": 0.0006808412251841277
+ }
+ },
+ "FRACTION_FUN_n4h4qte23QR": {
+ "asset_type": "FileBasedObject",
+ "id": "FRACTION_FUN_n4h4qte23QR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09141569579378628,
+ -0.0915508120653472,
+ -0.016926093518875432
+ ],
+ [
+ 0.08377130420621373,
+ 0.09759418793465281,
+ 0.026861906481124565
+ ]
+ ],
+ "mass": 0.0004534085710317705,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FRACTION FUN\nFeature as two-sided curved base which easy to flip over! Set develops the understanding of geometric fraction from shapes. Kid will learn about the proportional relationships between one section and the whole.",
+ "nr_faces": 6278,
+ "nr_vertices": 3428,
+ "surface_area": 0.09045204560589772,
+ "volume": 0.0004534085710317705
+ }
+ },
+ "FRUIT_VEGGIE_DOMINO_GRADIENT": {
+ "asset_type": "FileBasedObject",
+ "id": "FRUIT_VEGGIE_DOMINO_GRADIENT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12665132555205516,
+ -0.13866400098745885,
+ -0.016501758150607643
+ ],
+ [
+ 0.22105567444794486,
+ 0.13236099901254117,
+ 0.03886024184939235
+ ]
+ ],
+ "mass": 0.0007913791768860345,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FRUIT & VEGGIE DOMINO (GRADIENT)\nLearn about 12 different kinds of fruits and vegetables with this memory game. The 24 pieces consist of raised and intended details to help with matching.",
+ "nr_faces": 12556,
+ "nr_vertices": 7057,
+ "surface_area": 0.1599269062043558,
+ "volume": 0.0007913791768860345
+ }
+ },
+ "FRUIT_VEGGIE_MEMO_GRADIENT": {
+ "asset_type": "FileBasedObject",
+ "id": "FRUIT_VEGGIE_MEMO_GRADIENT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13484959213037756,
+ -0.10061207850591893,
+ -0.010660616229051196
+ ],
+ [
+ 0.13337440786962243,
+ 0.10497292149408108,
+ 0.011856383770948803
+ ]
+ ],
+ "mass": 0.0006132861121121915,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "FRUIT & VEGGIE MEMO (GRADIENT)\nThe 28 appetizing wooden domino tiles will delight any child's mind! Features 7 different kinds of fruits and vegetables.",
+ "nr_faces": 23218,
+ "nr_vertices": 12994,
+ "surface_area": 0.12666745055840603,
+ "volume": 0.0006132861121121915
+ }
+ },
+ "FYW_ALTERNATION": {
+ "asset_type": "FileBasedObject",
+ "id": "FYW_ALTERNATION",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06356736504662283,
+ -0.17690796779019038,
+ -0.058229870639686085
+ ],
+ [
+ 0.056974634953377165,
+ 0.12962403220980961,
+ 0.11790612936031392
+ ]
+ ],
+ "mass": 0.0022606241448213313,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "FYW ALTERNATION\nFW-HIGH TOP",
+ "nr_faces": 33206,
+ "nr_vertices": 17717,
+ "surface_area": 0.15565026459981599,
+ "volume": 0.0022606241448213313
+ }
+ },
+ "FYW_DIVISION": {
+ "asset_type": "FileBasedObject",
+ "id": "FYW_DIVISION",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0632797887765592,
+ -0.16335836148326494,
+ -0.0506689289762114
+ ],
+ [
+ 0.0580332112234408,
+ 0.14292563851673507,
+ 0.12365407102378859
+ ]
+ ],
+ "mass": 0.0016914123302699314,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "FYW DIVISION\nFW-HIGH TOP",
+ "nr_faces": 36812,
+ "nr_vertices": 19988,
+ "surface_area": 0.16627115401094178,
+ "volume": 0.0016914123302699314
+ }
+ },
+ "FemDophilus": {
+ "asset_type": "FileBasedObject",
+ "id": "FemDophilus",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0290304204299725,
+ -0.02944823944534854,
+ -0.05681633922171186
+ ],
+ [
+ 0.028951579570027502,
+ 0.029768760554651462,
+ 0.057765660778288146
+ ]
+ ],
+ "mass": 0.0003616578542501588,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Fem-Dophilus\nFem-dophilus contains two patented and clinically documented probiotic strains, Lactobacillus rhamnosus, GR-1 and Lactobacillus reuteri, RC-14, discovered and developed by Dr. Gregor Reid and Dr. Andrew Bruce at Urex Biotech. Over 20 years of research supports the oral use of GR-1 and RC-14 to colonize and protect the vaginal tract.* Clinical trials have shown that GR-1 and RC-14: Help to maintain or restore healthy vaginal flora that are important in maintaining vaginal health.* Support the health of the urinary tract.* Fem-dophilus is manufactured under pharmaceutical GMP conditions insuring potency and consistency. The probiotic strains in fem-dophilus are in a proprietary polysaccharide matrix, which protects the bacteria from stomach acid and enhances probiotic bacteria survival to the lower intestine.* *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 3272,
+ "nr_vertices": 1785,
+ "surface_area": 0.03087824989391996,
+ "volume": 0.0003616578542501588
+ }
+ },
+ "Final_Fantasy_XIV_A_Realm_Reborn_60Day_Subscription": {
+ "asset_type": "FileBasedObject",
+ "id": "Final_Fantasy_XIV_A_Realm_Reborn_60Day_Subscription",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06727078879039268,
+ -0.008926408799200621,
+ -0.09507985802727113
+ ],
+ [
+ 0.06875121120960732,
+ 0.00913459120079938,
+ 0.09532714197272887
+ ]
+ ],
+ "mass": 0.00037086701617596084,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Final Fantasy XIV: A Realm Reborn, 60-Day Subscription",
+ "nr_faces": 6888,
+ "nr_vertices": 3563,
+ "surface_area": 0.06067403416281487,
+ "volume": 0.00037086701617596084
+ }
+ },
+ "Firefly_Clue_Board_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Firefly_Clue_Board_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20180521426522663,
+ -0.035185241812884314,
+ -0.13644104730991172
+ ],
+ [
+ 0.2022987857347734,
+ 0.03473575818711568,
+ 0.1373259526900883
+ ]
+ ],
+ "mass": 0.007210071940654526,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Firefly Clue Board Game",
+ "nr_faces": 1818,
+ "nr_vertices": 1012,
+ "surface_area": 0.30089342084066967,
+ "volume": 0.007210071940654526
+ }
+ },
+ "FisherPrice_Make_A_Match_Game_Thomas_Friends": {
+ "asset_type": "FileBasedObject",
+ "id": "FisherPrice_Make_A_Match_Game_Thomas_Friends",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10136182833466022,
+ -0.024384885580235396,
+ -0.13384537654067016
+ ],
+ [
+ 0.10120717166533978,
+ 0.024617114419764604,
+ 0.13395662345932982
+ ]
+ ],
+ "mass": 0.00239290372690282,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Fisher-Price Make A Match Game, Thomas & Friends",
+ "nr_faces": 2064,
+ "nr_vertices": 1106,
+ "surface_area": 0.14317632159696944,
+ "volume": 0.00239290372690282
+ }
+ },
+ "Fisher_price_Classic_Toys_Buzzy_Bee": {
+ "asset_type": "FileBasedObject",
+ "id": "Fisher_price_Classic_Toys_Buzzy_Bee",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0777592950265023,
+ -0.06860512589621902,
+ -0.042748086166767126
+ ],
+ [
+ 0.1281437049734977,
+ 0.06618087410378097,
+ 0.06917491383323288
+ ]
+ ],
+ "mass": 0.000338209269993988,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Fisher price Classic Toys, Buzzy Bee",
+ "nr_faces": 12592,
+ "nr_vertices": 8289,
+ "surface_area": 0.04447753585948918,
+ "volume": 0.000338209269993988
+ }
+ },
+ "Focus_8643_Lime_Squeezer_10x35x188_Enamelled_Aluminum_Light": {
+ "asset_type": "FileBasedObject",
+ "id": "Focus_8643_Lime_Squeezer_10x35x188_Enamelled_Aluminum_Light",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1591493911212274,
+ -0.07333867454084574,
+ -0.028861265757572436
+ ],
+ [
+ 0.17642860887877262,
+ 0.04517432545915426,
+ 0.03443573424242756
+ ]
+ ],
+ "mass": 6.973256640253566e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Focus 8643 Lime Squeezer - 10x3.5x1.88, Enamelled Aluminum, Light",
+ "nr_faces": 6770,
+ "nr_vertices": 3731,
+ "surface_area": 0.04353481906563156,
+ "volume": 6.973256640253566e-05
+ }
+ },
+ "Folic_Acid": {
+ "asset_type": "FileBasedObject",
+ "id": "Folic_Acid",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02370087627926147,
+ -0.023974142483424287,
+ -0.03984229486175699
+ ],
+ [
+ 0.02384112372073853,
+ 0.023661857516575714,
+ 0.04401570513824301
+ ]
+ ],
+ "mass": 0.00013247155962731768,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Folic Acid",
+ "nr_faces": 10924,
+ "nr_vertices": 5587,
+ "surface_area": 0.015096698244251059,
+ "volume": 0.00013247155962731768
+ }
+ },
+ "Footed_Bowl_Sand": {
+ "asset_type": "FileBasedObject",
+ "id": "Footed_Bowl_Sand",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07862700056796704,
+ -0.0789819024864759,
+ -0.05463807122823728
+ ],
+ [
+ 0.08230099943203296,
+ 0.08256109751352411,
+ 0.054200928771762726
+ ]
+ ],
+ "mass": 0.0001339563553030363,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Footed Bowl Sand",
+ "nr_faces": 9468,
+ "nr_vertices": 4908,
+ "surface_area": 0.10994228293977526,
+ "volume": 0.0001339563553030363
+ }
+ },
+ "Fresca_Peach_Citrus_Sparkling_Flavored_Soda_12_PK": {
+ "asset_type": "FileBasedObject",
+ "id": "Fresca_Peach_Citrus_Sparkling_Flavored_Soda_12_PK",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20434037587509327,
+ -0.06990003677982894,
+ -0.06465803436573421
+ ],
+ [
+ 0.20354562412490673,
+ 0.06958896322017105,
+ 0.0650089656342658
+ ]
+ ],
+ "mass": 0.006789832180191678,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Fresca Peach Citrus Sparkling Flavored Soda - 12 PK",
+ "nr_faces": 3138,
+ "nr_vertices": 1767,
+ "surface_area": 0.23275165856794594,
+ "volume": 0.006789832180191678
+ }
+ },
+ "Frozen_Olafs_In_Trouble_PopOMatic_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Frozen_Olafs_In_Trouble_PopOMatic_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13640536296960726,
+ -0.029674537222510775,
+ -0.13583316754284686
+ ],
+ [
+ 0.13695463703039273,
+ 0.029617462777489226,
+ 0.13619183245715316
+ ]
+ ],
+ "mass": 0.004021191238257624,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Frozen Olaf's In Trouble Pop-O-Matic Game",
+ "nr_faces": 1428,
+ "nr_vertices": 780,
+ "surface_area": 0.1985368647688938,
+ "volume": 0.004021191238257624
+ }
+ },
+ "Frozen_Olafs_In_Trouble_PopOMatic_Game_OEu83W9T8pD": {
+ "asset_type": "FileBasedObject",
+ "id": "Frozen_Olafs_In_Trouble_PopOMatic_Game_OEu83W9T8pD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13254386394023135,
+ -0.13040114618026905,
+ -0.008047165097226914
+ ],
+ [
+ 0.12804213605976866,
+ 0.13022285381973095,
+ 0.025665834902773084
+ ]
+ ],
+ "mass": 0.0004299058972806716,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Frozen Olaf's In Trouble Pop-O-Matic Game",
+ "nr_faces": 19718,
+ "nr_vertices": 13057,
+ "surface_area": 0.17750907010139516,
+ "volume": 0.0004299058972806716
+ }
+ },
+ "Frozen_Scrabble_Jr": {
+ "asset_type": "FileBasedObject",
+ "id": "Frozen_Scrabble_Jr",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13585447016274263,
+ -0.02806992459189285,
+ -0.13556665268199505
+ ],
+ [
+ 0.13594952983725736,
+ 0.027855075408107152,
+ 0.13558534731800495
+ ]
+ ],
+ "mass": 0.00381069572750661,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Frozen Scrabble Jr.",
+ "nr_faces": 1462,
+ "nr_vertices": 797,
+ "surface_area": 0.19528196873032466,
+ "volume": 0.00381069572750661
+ }
+ },
+ "Fruity_Friends": {
+ "asset_type": "FileBasedObject",
+ "id": "Fruity_Friends",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08122435531204716,
+ -0.042492442074607256,
+ -0.05614776156938879
+ ],
+ [
+ 0.07870464468795284,
+ 0.038443557925392745,
+ 0.1165212384306112
+ ]
+ ],
+ "mass": 0.0005598817690339741,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Fruity Friends",
+ "nr_faces": 17626,
+ "nr_vertices": 9799,
+ "surface_area": 0.0807836425396225,
+ "volume": 0.0005598817690339741
+ }
+ },
+ "Fujifilm_instax_SHARE_SP1_10_photos": {
+ "asset_type": "FileBasedObject",
+ "id": "Fujifilm_instax_SHARE_SP1_10_photos",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.051263496063029476,
+ -0.02157076092524615,
+ -0.058854626460996186
+ ],
+ [
+ 0.051679503936970524,
+ 0.02139623907475385,
+ 0.06487837353900382
+ ]
+ ],
+ "mass": 0.0004443747551685622,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Fujifilm instax SHARE SP-1 - 10 photos",
+ "nr_faces": 6364,
+ "nr_vertices": 3296,
+ "surface_area": 0.03636347568811548,
+ "volume": 0.0004443747551685622
+ }
+ },
+ "Full_Circle_Happy_Scraps_Out_Collector_Gray": {
+ "asset_type": "FileBasedObject",
+ "id": "Full_Circle_Happy_Scraps_Out_Collector_Gray",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10848593443145134,
+ -0.06618957753126606,
+ -0.07187114780826193
+ ],
+ [
+ 0.10456006556854866,
+ 0.08886242246873394,
+ 0.07122085219173808
+ ]
+ ],
+ "mass": 0.00023669386811707083,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Full Circle Happy Scraps Out Collector, Gray",
+ "nr_faces": 7518,
+ "nr_vertices": 3934,
+ "surface_area": 0.18550431353446267,
+ "volume": 0.00023669386811707083
+ }
+ },
+ "GARDEN_SWING": {
+ "asset_type": "FileBasedObject",
+ "id": "GARDEN_SWING",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08282072836801317,
+ -0.048739221497990814,
+ -0.08442453594404797
+ ],
+ [
+ 0.08276227163198684,
+ 0.05926377850200918,
+ 0.08204546405595203
+ ]
+ ],
+ "mass": 0.000324871701039572,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "GARDEN SWING\nThis set includes a swing, a canopy and 2 cushions.",
+ "nr_faces": 31476,
+ "nr_vertices": 17997,
+ "surface_area": 0.11382491214359472,
+ "volume": 0.000324871701039572
+ }
+ },
+ "GEARS_PUZZLES_STANDARD_gcYxhNHhKlI": {
+ "asset_type": "FileBasedObject",
+ "id": "GEARS_PUZZLES_STANDARD_gcYxhNHhKlI",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19061907809770168,
+ -0.07477674505609981,
+ -0.011735697796429842
+ ],
+ [
+ 0.1206149219022983,
+ 0.08642025494390018,
+ 0.029023302203570158
+ ]
+ ],
+ "mass": 0.0005850286592126945,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "GEARS & PUZZLES - STANDARD\nExplore and build endless possibilities by combining the colorful assortment of gears. Place the puzzle pieces together and watch the amazing movement you can create by spinning and twirling the gears. (12 pieces included)",
+ "nr_faces": 25342,
+ "nr_vertices": 15197,
+ "surface_area": 0.10499980542818807,
+ "volume": 0.0005850286592126945
+ }
+ },
+ "GEOMETRIC_PEG_BOARD": {
+ "asset_type": "FileBasedObject",
+ "id": "GEOMETRIC_PEG_BOARD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08761832923068429,
+ -0.0906849155927931,
+ -0.021644001754992617
+ ],
+ [
+ 0.08737067076931572,
+ 0.08357408440720691,
+ 0.06394399824500738
+ ]
+ ],
+ "mass": 0.0007165758450462363,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "GEOMETRIC PEG BOARD\nThese 16 geometrical pegs (4 different sizes,?shapes and colors) can be sorted, counted, and stacked on a sturdy wooden base.",
+ "nr_faces": 11730,
+ "nr_vertices": 6838,
+ "surface_area": 0.12166512101960762,
+ "volume": 0.0007165758450462363
+ }
+ },
+ "GEOMETRIC_SORTING_BOARD": {
+ "asset_type": "FileBasedObject",
+ "id": "GEOMETRIC_SORTING_BOARD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08614397902298224,
+ -0.08401837081654254,
+ -0.021896452818730375
+ ],
+ [
+ 0.08857802097701777,
+ 0.08964962918345747,
+ 0.038906547181269624
+ ]
+ ],
+ "mass": 0.0009069681735054517,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "GEOMETRIC SORTING BOARD\nA set of four geometric shapes which can be stacked together according to the number of holes in the middle of each one.",
+ "nr_faces": 11274,
+ "nr_vertices": 6823,
+ "surface_area": 0.10605463411316696,
+ "volume": 0.0009069681735054517
+ }
+ },
+ "GEOMETRIC_SORTING_BOARD_MNi4Rbuz9vj": {
+ "asset_type": "FileBasedObject",
+ "id": "GEOMETRIC_SORTING_BOARD_MNi4Rbuz9vj",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19339378081506164,
+ -0.07843879592545419,
+ -0.017359302606869728
+ ],
+ [
+ 0.16887121918493833,
+ 0.09620420407454582,
+ 0.04390969739313027
+ ]
+ ],
+ "mass": 0.0008952166675567554,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "GEOMETRIC SORTING BOARD\nA set of four geometric shapes which can be stacked together according to the number of holes in the middle of each one.",
+ "nr_faces": 8370,
+ "nr_vertices": 5385,
+ "surface_area": 0.13064322046832127,
+ "volume": 0.0008952166675567554
+ }
+ },
+ "GIRLS_DECKHAND": {
+ "asset_type": "FileBasedObject",
+ "id": "GIRLS_DECKHAND",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04560083870487125,
+ -0.12093543547272426,
+ -0.019800942451044627
+ ],
+ [
+ 0.043482161295128746,
+ 0.13385756452727576,
+ 0.04820905754895537
+ ]
+ ],
+ "mass": 0.00039954158911602463,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "GIRLS DECKHAND\nReef Bella Costas Girl's Shoe Classic boat shoe styling Hemp and canvas upper Interior suede heel patch for comfort Mattress-inspired PU foam footbed with anatomical arch support Vulcanized construction Durable rubber outsole with jute inlay",
+ "nr_faces": 18796,
+ "nr_vertices": 10132,
+ "surface_area": 0.08861630035359497,
+ "volume": 0.00039954158911602463
+ }
+ },
+ "GRANDFATHER_DOLL": {
+ "asset_type": "FileBasedObject",
+ "id": "GRANDFATHER_DOLL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.041429151911395665,
+ -0.015578461050456117,
+ -0.06680358054295316
+ ],
+ [
+ 0.04661584808860434,
+ 0.01569253894954388,
+ 0.062238419457046834
+ ]
+ ],
+ "mass": 7.562144453947333e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "GRANDFATHER DOLL",
+ "nr_faces": 15920,
+ "nr_vertices": 8596,
+ "surface_area": 0.018371776741225528,
+ "volume": 7.562144453947333e-05
+ }
+ },
+ "GRANDMOTHER": {
+ "asset_type": "FileBasedObject",
+ "id": "GRANDMOTHER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03675736873251591,
+ -0.02000756435570993,
+ -0.06072310959866274
+ ],
+ [
+ 0.04016563126748409,
+ 0.01840643564429007,
+ 0.06612489040133726
+ ]
+ ],
+ "mass": 7.735239818184683e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "GRANDMOTHER",
+ "nr_faces": 15340,
+ "nr_vertices": 8181,
+ "surface_area": 0.017450476943646,
+ "volume": 7.735239818184683e-05
+ }
+ },
+ "Germanium_GE132": {
+ "asset_type": "FileBasedObject",
+ "id": "Germanium_GE132",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.021949940471390327,
+ -0.022036743768970274,
+ -0.035462399598311156
+ ],
+ [
+ 0.021964059528609674,
+ 0.021898256231029724,
+ 0.04191360040168885
+ ]
+ ],
+ "mass": 9.901122248334867e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Germanium GE-132",
+ "nr_faces": 9102,
+ "nr_vertices": 4687,
+ "surface_area": 0.012582135741532649,
+ "volume": 9.901122248334867e-05
+ }
+ },
+ "Ghost_6_Color_BlckWhtLavaSlvrCitrus_Size_80": {
+ "asset_type": "FileBasedObject",
+ "id": "Ghost_6_Color_BlckWhtLavaSlvrCitrus_Size_80",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06511551646070399,
+ -0.16128947515711908,
+ -0.04072728353347647
+ ],
+ [
+ 0.05095348353929601,
+ 0.13690852484288094,
+ 0.08177871646652353
+ ]
+ ],
+ "mass": 0.0011653226680464837,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Ghost 6, Color: Blck/Wht/Lava/Slvr/Citrus, Size: 8.0\nThe light, bouncy, and balanced ride of the Ghost has haunted the dreams of many competitors -- and it's about to get frighteningly good. We've taken the transition from silky to ridiculously smooth by removing the midfoot shank and creating full ground contact from heel to toe. The underfoot gets even more love with a horseshoe Segmented Crash Pad that wraps the heel from medial to lateral sides and articulates the laydown. What does all that mean? Looking as good as it feels, you'll fall in love with this friendly ghost. We're not the only people who have fallen in love: Runner's World named the Ghost 6 \"Editor's Choice\" in the Fall Shoe Guide in their September 2013 issue the fourth straight Ghost to earn the honor. They called out the new forefoot overlays welded on rather than stitched, but really loved \"how fluidly the shoe rolls from heel-strike to toe-off.\" In short, the Ghost 6 offers \"a sweet balance of weight, cushioning, and everyday durability\" - and the editors say \"The lightest Ghost we've seen leaves nothing out.\" Can you say \"Four-peat\"? Spooky good. > See the Women's Ghost 6 Love the Ghost but hate running in the rain? The Ghost 6 GTX is also available. Everything you love about the Ghost, but with a waterproof, breathable GORE-TEX membrane to keep your feet dry and comfortable. No more blaming it on the rain! Runner's World is a registered trademark of Rodale Inc. 2013 Rodale Inc. All rights reserved.Category: Neutral Weight: 10.7 oz Platform: Universal Construction: Strobel DNA: Anatomical Launch Date: June 1, 2013",
+ "nr_faces": 59036,
+ "nr_vertices": 35062,
+ "surface_area": 0.17501058445388107,
+ "volume": 0.0011653226680464837
+ }
+ },
+ "Ghost_6_Color_MdngtDenmPomBrtePnkSlvBlk_Size_50": {
+ "asset_type": "FileBasedObject",
+ "id": "Ghost_6_Color_MdngtDenmPomBrtePnkSlvBlk_Size_50",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06399844107959055,
+ -0.1521348454772792,
+ -0.03737250126522103
+ ],
+ [
+ 0.05053755892040946,
+ 0.1319721545227208,
+ 0.06870449873477896
+ ]
+ ],
+ "mass": 0.0010891242915907439,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Ghost 6, Color: Mdngt/Denm/Pom/BrtePnk/Slv/Blk, Size: 5.0\nThe light, bouncy, and balanced ride of the Ghost has haunted the dreams of many competitors -- and it's about to get frighteningly good. We've taken the transition from silky to ridiculously smooth by removing the midfoot shank and creating full ground contact from heel to toe. The underfoot gets even more love with a horseshoe Segmented Crash Pad that wraps the heel from medial to lateral sides and articulates the laydown. What does all that mean? Looking as good as it feels, you'll fall in love with this friendly ghost. We're not the only people who have fallen in love: Runner's World named the Ghost 6 \"Editor's Choice\" in the Fall Shoe Guide in their September 2013 issue the fourth straight Ghost to earn the honor. They called out the new forefoot overlays welded on rather than stitched, but really loved \"how fluidly the shoe rolls from heel-strike to toe-off.\" In short, the Ghost 6 offers \"a sweet balance of weight, cushioning, and everyday durability\" - and the editors say \"The lightest Ghost we've seen leaves nothing out.\" Can you say \"Four-peat\"? Spooky good. > See the Men's Ghost 6 Love the Ghost but hate running in the rain? The Ghost 6 GTX is also available. Everything you love about the Ghost, but with a waterproof, breathable GORE-TEX membrane to keep your feet dry and comfortable. No more blaming it on the rain! Runner's World is a registered trademark of Rodale Inc. 2013 Rodale Inc. All rights reserved.Category: Neutral Weight: 8.8 oz Platform: Universal Construction: Strobel DNA: Anatomical Launch Date: June 1, 2013",
+ "nr_faces": 57462,
+ "nr_vertices": 33913,
+ "surface_area": 0.15981762694198828,
+ "volume": 0.0010891242915907439
+ }
+ },
+ "Ghost_6_GTX_Color_AnthBlckSlvrFernSulphSprng_Size_80": {
+ "asset_type": "FileBasedObject",
+ "id": "Ghost_6_GTX_Color_AnthBlckSlvrFernSulphSprng_Size_80",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06318648008228922,
+ -0.15773365126698752,
+ -0.041139745922360735
+ ],
+ [
+ 0.05012651991771077,
+ 0.13268434873301246,
+ 0.08257425407763927
+ ]
+ ],
+ "mass": 0.001095420357727211,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Ghost 6 GTX, Color: Anth/Blck/Slvr/Fern/SulphSprng, Size: 8.0\nThe awesomely easy-going ride of the Ghost 6 makes a splash with GORE-TEX protection. Get the same award-winning blend of cushion and balance with the added anti-soggy technology of a waterproof, breathable membrane in the upper. You'll be a fair-weather runner no more! > See the Women's Ghost 6GTXCategory: Neutral Weight: 11.5 oz Platform: Universal Construction: Combination DNALaunch Date: August 1, 2013",
+ "nr_faces": 58118,
+ "nr_vertices": 34366,
+ "surface_area": 0.16805507739418626,
+ "volume": 0.001095420357727211
+ }
+ },
+ "Gigabyte_GA78LMTUSB3_50_Motherboard_Micro_ATX_Socket_AM3": {
+ "asset_type": "FileBasedObject",
+ "id": "Gigabyte_GA78LMTUSB3_50_Motherboard_Micro_ATX_Socket_AM3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1351453113663112,
+ -0.033420462004905824,
+ -0.1339500845576472
+ ],
+ [
+ 0.1364286886336888,
+ 0.034053537995094176,
+ 0.1355959154423528
+ ]
+ ],
+ "mass": 0.004155197885363218,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Gigabyte GA-78LMT-USB3 5.0 Motherboard Micro ATX Socket AM3+",
+ "nr_faces": 12256,
+ "nr_vertices": 6510,
+ "surface_area": 0.19928736681277506,
+ "volume": 0.004155197885363218
+ }
+ },
+ "Gigabyte_GA970AUD3P_10_Motherboard_ATX_Socket_AM3": {
+ "asset_type": "FileBasedObject",
+ "id": "Gigabyte_GA970AUD3P_10_Motherboard_ATX_Socket_AM3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16653927853927372,
+ -0.038239637578358056,
+ -0.13321407096817642
+ ],
+ [
+ 0.1678467214607263,
+ 0.03868136242164194,
+ 0.13257192903182358
+ ]
+ ],
+ "mass": 0.006381129835523712,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Gigabyte GA-970A-UD3P 1.0 Motherboard ATX Socket AM3+",
+ "nr_faces": 4776,
+ "nr_vertices": 2525,
+ "surface_area": 0.252681193235196,
+ "volume": 0.006381129835523712
+ }
+ },
+ "Gigabyte_GAZ97XSLI_10_motherboard_ATX_LGA1150_Socket_Z97": {
+ "asset_type": "FileBasedObject",
+ "id": "Gigabyte_GAZ97XSLI_10_motherboard_ATX_LGA1150_Socket_Z97",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16765031217607834,
+ -0.0413509088566256,
+ -0.1337425567359464
+ ],
+ [
+ 0.16703468782392164,
+ 0.041228091143374404,
+ 0.1335044432640536
+ ]
+ ],
+ "mass": 0.006362521446297027,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Gigabyte GA-Z97X-SLI 1.0 motherboard ATX LGA1150 Socket Z97",
+ "nr_faces": 25798,
+ "nr_vertices": 13426,
+ "surface_area": 0.2583846491870024,
+ "volume": 0.006362521446297027
+ }
+ },
+ "Glycerin_11_Color_AqrsDrsdnBluBlkSlvShckOrng_Size_50": {
+ "asset_type": "FileBasedObject",
+ "id": "Glycerin_11_Color_AqrsDrsdnBluBlkSlvShckOrng_Size_50",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06283685064731809,
+ -0.14380050958195392,
+ -0.040032324898570795
+ ],
+ [
+ 0.05002214935268191,
+ 0.14414549041804608,
+ 0.0894796751014292
+ ]
+ ],
+ "mass": 0.0012655966859797705,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Glycerin 11, Color: Aqrs/DrsdnBlu/Blk/Slv/ShckOrng, Size: 5.0\nThink of the Glycerin 11 as your foot's butler, catering to your every want and need with plush, conformable comfort in every step. The luxury begins with an ultra-comformable upper that uses innovative 3D Fit Print overlays to create structure and reduce weight. We've also removed the midfoot shank to optimize ground contact for a transition that puts the \"oo\" in smooth. Finished with fresh colors and hot looks, Mr. Belvedere's got nothing on this shoe. > See the Men's Glycerin 11Category: Neutral Weight: 9.6 oz Platform: Universal Construction: Strobel DNA: Full-length Launch Date: June 1, 2013",
+ "nr_faces": 36936,
+ "nr_vertices": 20502,
+ "surface_area": 0.12889857735497018,
+ "volume": 0.0012655966859797705
+ }
+ },
+ "Glycerin_11_Color_BrllntBluSkydvrSlvrBlckWht_Size_80": {
+ "asset_type": "FileBasedObject",
+ "id": "Glycerin_11_Color_BrllntBluSkydvrSlvrBlckWht_Size_80",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0649414447443488,
+ -0.16201184669473706,
+ -0.04163604731397748
+ ],
+ [
+ 0.05484455525565119,
+ 0.14296515330526294,
+ 0.09432595268602254
+ ]
+ ],
+ "mass": 0.0012325495304182897,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Glycerin 11, Color: BrllntBlu/Skydvr/Slvr/Blck/Wht, Size: 8.0\nThink of the Glycerin 11 as your foot's butler, catering to your every want and need with plush, conformable comfort in every step. The luxury begins with an ultra-comformable upper that uses innovative 3D Fit Print overlays to create structure and reduce weight. We've also removed the midfoot shank to optimize ground contact for a transition that puts the \"oo\" in smooth. Finished with fresh colors and hot looks, Mr. Belvedere's got nothing on this shoe. > See the Women's Glycerin 11Category: Neutral Weight: 11.8 oz Platform: Universal Construction: Strobel DNA: Full-length Launch Date: June 1, 2013",
+ "nr_faces": 42844,
+ "nr_vertices": 24593,
+ "surface_area": 0.18149647426278848,
+ "volume": 0.0012325495304182897
+ }
+ },
+ "GoPro_HERO3_Composite_Cable": {
+ "asset_type": "FileBasedObject",
+ "id": "GoPro_HERO3_Composite_Cable",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.061017582454927236,
+ -0.020487371540019474,
+ -0.010200897273168127
+ ],
+ [
+ 0.03760541754507277,
+ 0.027409628459980524,
+ 0.014618102726831872
+ ]
+ ],
+ "mass": 1.601577470542217e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "GoPro HERO3 Composite Cable\nConnect your HERO3 camera to your TV with this composite cable (Mini USB to RCA) for standard definition preview + playback of your GoPro videos and photos.",
+ "nr_faces": 22696,
+ "nr_vertices": 12040,
+ "surface_area": 0.008556186417896156,
+ "volume": 1.601577470542217e-05
+ }
+ },
+ "Google_Cardboard_Original_package": {
+ "asset_type": "FileBasedObject",
+ "id": "Google_Cardboard_Original_package",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10734133769045744,
+ -0.08971056814985547,
+ -0.011453857908596632
+ ],
+ [
+ 0.10698766230954257,
+ 0.08549243185014453,
+ 0.01134514209140337
+ ]
+ ],
+ "mass": 0.0006986966651974739,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Google Cardboard Original (package)",
+ "nr_faces": 5108,
+ "nr_vertices": 2802,
+ "surface_area": 0.09107374715549228,
+ "volume": 0.0006986966651974739
+ }
+ },
+ "Grand_Prix": {
+ "asset_type": "FileBasedObject",
+ "id": "Grand_Prix",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.055963999414130675,
+ -0.14760088957146128,
+ -0.03050631110473134
+ ],
+ [
+ 0.050871000585869325,
+ 0.13740511042853873,
+ 0.08993368889526865
+ ]
+ ],
+ "mass": 0.0009449041888776648,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Grand Prix",
+ "nr_faces": 23248,
+ "nr_vertices": 12311,
+ "surface_area": 0.12078546593172163,
+ "volume": 0.0009449041888776648
+ }
+ },
+ "Granimals_20_Wooden_ABC_Blocks_Wagon": {
+ "asset_type": "FileBasedObject",
+ "id": "Granimals_20_Wooden_ABC_Blocks_Wagon",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10213313319790647,
+ -0.02752749993604931,
+ -0.021729596676863
+ ],
+ [
+ 0.08790186680209353,
+ 0.023159500063950688,
+ 0.041809403323137
+ ]
+ ],
+ "mass": 0.0001658105248274175,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Granimals 20 Wooden ABC Blocks & Wagon\n18+ months",
+ "nr_faces": 12556,
+ "nr_vertices": 6944,
+ "surface_area": 0.03624078997889355,
+ "volume": 0.0001658105248274175
+ }
+ },
+ "Granimals_20_Wooden_ABC_Blocks_Wagon_85VdSftGsLi": {
+ "asset_type": "FileBasedObject",
+ "id": "Granimals_20_Wooden_ABC_Blocks_Wagon_85VdSftGsLi",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.015376618427583736,
+ -0.015578260192704977,
+ -0.015277041065699739
+ ],
+ [
+ 0.015249381572416265,
+ 0.015610739807295023,
+ 0.015185958934300262
+ ]
+ ],
+ "mass": 2.5788783600291663e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Granimals 20 Wooden ABC Blocks & Wagon\n18+ months",
+ "nr_faces": 12112,
+ "nr_vertices": 6302,
+ "surface_area": 0.00522796058525952,
+ "volume": 2.5788783600291663e-05
+ }
+ },
+ "Granimals_20_Wooden_ABC_Blocks_Wagon_g2TinmUGGHI": {
+ "asset_type": "FileBasedObject",
+ "id": "Granimals_20_Wooden_ABC_Blocks_Wagon_g2TinmUGGHI",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10068855010520907,
+ -0.02807699888215691,
+ -0.021923838968017865
+ ],
+ [
+ 0.09113544989479093,
+ 0.03567700111784309,
+ 0.028567161031982136
+ ]
+ ],
+ "mass": 0.00017134714625312135,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Granimals 20 Wooden ABC Blocks & Wagon\n18+ months",
+ "nr_faces": 12336,
+ "nr_vertices": 6993,
+ "surface_area": 0.03528025587111064,
+ "volume": 0.00017134714625312135
+ }
+ },
+ "Great_Dinos_Triceratops_Toy": {
+ "asset_type": "FileBasedObject",
+ "id": "Great_Dinos_Triceratops_Toy",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03473815686283302,
+ -0.022628194953167938,
+ -0.03978610080465434
+ ],
+ [
+ 0.034732843137166985,
+ 0.023178805046832063,
+ 0.039397899195345656
+ ]
+ ],
+ "mass": 9.913703585638417e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Great Dinos Triceratops Toy\ntest",
+ "nr_faces": 10310,
+ "nr_vertices": 5544,
+ "surface_area": 0.014073197936228396,
+ "volume": 9.913703585638417e-05
+ }
+ },
+ "Great_Jones_Wingtip": {
+ "asset_type": "FileBasedObject",
+ "id": "Great_Jones_Wingtip",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0605108790770652,
+ -0.15370877293103016,
+ -0.03328885073653515
+ ],
+ [
+ 0.0505881209229348,
+ 0.15843122706896984,
+ 0.07992914926346485
+ ]
+ ],
+ "mass": 0.0010501139732497918,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Great Jones Wingtip",
+ "nr_faces": 18656,
+ "nr_vertices": 9944,
+ "surface_area": 0.14121632467014808,
+ "volume": 0.0010501139732497918
+ }
+ },
+ "Great_Jones_Wingtip_j5NV8GRnitM": {
+ "asset_type": "FileBasedObject",
+ "id": "Great_Jones_Wingtip_j5NV8GRnitM",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.061391990902296294,
+ -0.16635990079247567,
+ -0.03330928757971575
+ ],
+ [
+ 0.05077500909770371,
+ 0.15053709920752434,
+ 0.08366671242028426
+ ]
+ ],
+ "mass": 0.0009797321271830589,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Great Jones Wingtip",
+ "nr_faces": 22786,
+ "nr_vertices": 12483,
+ "surface_area": 0.16702753441121848,
+ "volume": 0.0009797321271830589
+ }
+ },
+ "Great_Jones_Wingtip_kAqSg6EgG0I": {
+ "asset_type": "FileBasedObject",
+ "id": "Great_Jones_Wingtip_kAqSg6EgG0I",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06047972924792778,
+ -0.16398723504683307,
+ -0.031643100839225835
+ ],
+ [
+ 0.05076127075207222,
+ 0.14802976495316694,
+ 0.08209589916077417
+ ]
+ ],
+ "mass": 0.0009155498837398503,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Great Jones Wingtip",
+ "nr_faces": 22530,
+ "nr_vertices": 12447,
+ "surface_area": 0.1626449721332267,
+ "volume": 0.0009155498837398503
+ }
+ },
+ "Great_Jones_Wingtip_wxH3dbtlvBC": {
+ "asset_type": "FileBasedObject",
+ "id": "Great_Jones_Wingtip_wxH3dbtlvBC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06073832853384872,
+ -0.15764911490835562,
+ -0.03422839098843001
+ ],
+ [
+ 0.050909671466151274,
+ 0.15929688509164439,
+ 0.08429860901156999
+ ]
+ ],
+ "mass": 0.0010708634954837853,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Great Jones Wingtip",
+ "nr_faces": 18654,
+ "nr_vertices": 10025,
+ "surface_area": 0.14579831486524408,
+ "volume": 0.0010708634954837853
+ }
+ },
+ "Grreat_Choice_Dog_Double_Dish_Plastic_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Grreat_Choice_Dog_Double_Dish_Plastic_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17012698767892465,
+ -0.09434031881323748,
+ -0.04880428879410223
+ ],
+ [
+ 0.16797501232107534,
+ 0.09411768118676252,
+ 0.03500771120589777
+ ]
+ ],
+ "mass": 0.0009018387652282609,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Grreat Choice Dog Double Dish, Plastic, Blue",
+ "nr_faces": 8194,
+ "nr_vertices": 4484,
+ "surface_area": 0.24093412925752467,
+ "volume": 0.0009018387652282609
+ }
+ },
+ "Grreatv_Choice_Dog_Bowl_Gray_Bones_Plastic_20_fl_oz_total": {
+ "asset_type": "FileBasedObject",
+ "id": "Grreatv_Choice_Dog_Bowl_Gray_Bones_Plastic_20_fl_oz_total",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08648377004514543,
+ -0.08910428062797247,
+ -0.03171278940185552
+ ],
+ [
+ 0.08436922995485457,
+ 0.09442071937202753,
+ 0.022123210598144483
+ ]
+ ],
+ "mass": 0.0002169315831692352,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Grreatv Choice Dog Bowl, Gray Bones, Plastic - 20 fl oz total",
+ "nr_faces": 8862,
+ "nr_vertices": 4836,
+ "surface_area": 0.09960029351419641,
+ "volume": 0.0002169315831692352
+ }
+ },
+ "Guardians_of_the_Galaxy_Galactic_Battlers_Rocket_Raccoon_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Guardians_of_the_Galaxy_Galactic_Battlers_Rocket_Raccoon_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03012494313215018,
+ -0.06083965420278691,
+ -0.05797329370434983
+ ],
+ [
+ 0.02293505686784982,
+ 0.04060334579721309,
+ 0.04015870629565017
+ ]
+ ],
+ "mass": 5.934958591712067e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Guardians of the Galaxy Galactic Battlers Rocket Raccoon Figure",
+ "nr_faces": 25030,
+ "nr_vertices": 13871,
+ "surface_area": 0.01717214961116931,
+ "volume": 5.934958591712067e-05
+ }
+ },
+ "HAMMER_BALL": {
+ "asset_type": "FileBasedObject",
+ "id": "HAMMER_BALL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13087056164751334,
+ -0.11733678639681733,
+ -0.060101643514794405
+ ],
+ [
+ 0.15304943835248666,
+ 0.06779321360318268,
+ 0.060506356485205595
+ ]
+ ],
+ "mass": 0.0009275441243422734,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "HAMMER BALL\nThis toy helps children to improve hand-eye coordination, aligning, slotting and aiming.",
+ "nr_faces": 12474,
+ "nr_vertices": 7510,
+ "surface_area": 0.17984528756006818,
+ "volume": 0.0009275441243422734
+ }
+ },
+ "HAMMER_PEG": {
+ "asset_type": "FileBasedObject",
+ "id": "HAMMER_PEG",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10208862920556602,
+ -0.09887575470259266,
+ -0.0407880305019737
+ ],
+ [
+ 0.15028237079443396,
+ 0.08674724529740735,
+ 0.04820396949802629
+ ]
+ ],
+ "mass": 0.0007286523372987543,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "HAMMER PEG\nA four-hole wooden board with a wooden mallet for hammering practice. Children can turn it over and start the fun all over again.",
+ "nr_faces": 7254,
+ "nr_vertices": 4403,
+ "surface_area": 0.11613850419158316,
+ "volume": 0.0007286523372987543
+ }
+ },
+ "HAPPY_ENGINE": {
+ "asset_type": "FileBasedObject",
+ "id": "HAPPY_ENGINE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07856116287629297,
+ -0.13717744014329494,
+ -0.025250428632668305
+ ],
+ [
+ 0.12398383712370703,
+ 0.13246855985670508,
+ 0.04974157136733169
+ ]
+ ],
+ "mass": 0.0005764546506133693,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "HAPPY ENGINE\nHappy Engine consists of 3 carriages which can be played together or separately as a pull-toy. Each carrier has a different effect while being pulled.",
+ "nr_faces": 15304,
+ "nr_vertices": 9074,
+ "surface_area": 0.09050773197247977,
+ "volume": 0.0005764546506133693
+ }
+ },
+ "HELICOPTER": {
+ "asset_type": "FileBasedObject",
+ "id": "HELICOPTER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.034932586665033946,
+ -0.06109081932892814,
+ -0.0432107297252316
+ ],
+ [
+ 0.03336641333496605,
+ 0.11206218067107185,
+ 0.0713002702747684
+ ]
+ ],
+ "mass": 0.00019471535929640733,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "HELICOPTER\nThis little car has been designed to make it easy for small baby hands to push and play with. This series comes with Rescue Car, Fire Truck, and Helicopter.",
+ "nr_faces": 11472,
+ "nr_vertices": 6481,
+ "surface_area": 0.041018756491396274,
+ "volume": 0.00019471535929640733
+ }
+ },
+ "HP_1800_Tablet_8GB_7": {
+ "asset_type": "FileBasedObject",
+ "id": "HP_1800_Tablet_8GB_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09541338900532675,
+ -0.06196572149017216,
+ -0.006672569694282051
+ ],
+ [
+ 0.09797661099467324,
+ 0.06386727850982783,
+ 0.006533430305717949
+ ]
+ ],
+ "mass": 0.00024876865615703,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "HP 1800 Tablet, 8GB, 7\"",
+ "nr_faces": 1652,
+ "nr_vertices": 908,
+ "surface_area": 0.05129519838184797,
+ "volume": 0.00024876865615703
+ }
+ },
+ "HP_Card_Invitation_Kit": {
+ "asset_type": "FileBasedObject",
+ "id": "HP_Card_Invitation_Kit",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07639929952905311,
+ -0.019847616873373386,
+ -0.09848393925571786
+ ],
+ [
+ 0.07675470047094689,
+ 0.020597383126626616,
+ 0.09796806074428215
+ ]
+ ],
+ "mass": 0.0010663991903473065,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "HP Card & Invitation Kit",
+ "nr_faces": 2586,
+ "nr_vertices": 1377,
+ "surface_area": 0.08207421208218738,
+ "volume": 0.0010663991903473065
+ }
+ },
+ "Hasbro_Cranium_Performance_and_Acting_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Hasbro_Cranium_Performance_and_Acting_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1048962732408955,
+ -0.02763946099396763,
+ -0.13540086501823784
+ ],
+ [
+ 0.1032467267591045,
+ 0.02721553900603237,
+ 0.13663013498176219
+ ]
+ ],
+ "mass": 0.0028040456558702438,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Hasbro Cranium Performance and Acting Game",
+ "nr_faces": 1502,
+ "nr_vertices": 828,
+ "surface_area": 0.1576219054993151,
+ "volume": 0.0028040456558702438
+ }
+ },
+ "Hasbro_Dont_Wake_Daddy_Board_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Hasbro_Dont_Wake_Daddy_Board_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20301034326610248,
+ -0.045630343594415736,
+ -0.1363338337037166
+ ],
+ [
+ 0.20282165673389752,
+ 0.045225656405584264,
+ 0.1365241662962834
+ ]
+ ],
+ "mass": 0.00951946153388933,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Hasbro Don't Wake Daddy Board Game",
+ "nr_faces": 1150,
+ "nr_vertices": 646,
+ "surface_area": 0.3319985916946067,
+ "volume": 0.00951946153388933
+ }
+ },
+ "Hasbro_Dont_Wake_Daddy_Board_Game_NJnjGna4u1a": {
+ "asset_type": "FileBasedObject",
+ "id": "Hasbro_Dont_Wake_Daddy_Board_Game_NJnjGna4u1a",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.2561703796511198,
+ -0.19708704779981256,
+ -0.0260637573872326
+ ],
+ [
+ 0.2442826203488802,
+ 0.19830695220018743,
+ 0.0713742426127674
+ ]
+ ],
+ "mass": 0.002132989775759182,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Hasbro Don't Wake Daddy Board Game",
+ "nr_faces": 8756,
+ "nr_vertices": 5084,
+ "surface_area": 0.44543503580880384,
+ "volume": 0.002132989775759182
+ }
+ },
+ "Hasbro_Life_Board_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Hasbro_Life_Board_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20325703349583307,
+ -0.03586773458989966,
+ -0.1360406422588667
+ ],
+ [
+ 0.20161696650416694,
+ 0.03342726541010034,
+ 0.13615035774113332
+ ]
+ ],
+ "mass": 0.006986260256312991,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Hasbro Life Board Game",
+ "nr_faces": 1260,
+ "nr_vertices": 691,
+ "surface_area": 0.30162139111993513,
+ "volume": 0.006986260256312991
+ }
+ },
+ "Hasbro_Monopoly_Hotels_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Hasbro_Monopoly_Hotels_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1354045516320147,
+ -0.046766839171681895,
+ -0.1129443668315267
+ ],
+ [
+ 0.1443484483679853,
+ 0.039511160828318105,
+ 0.16663863316847333
+ ]
+ ],
+ "mass": 0.004086275429300826,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Hasbro Monopoly Hotels Game",
+ "nr_faces": 4016,
+ "nr_vertices": 2421,
+ "surface_area": 0.1933334162370997,
+ "volume": 0.004086275429300826
+ }
+ },
+ "Hasbro_Trivial_Pursuit_Family_Edition_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Hasbro_Trivial_Pursuit_Family_Edition_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10263104448687267,
+ -0.031691650414377444,
+ -0.135056476228599
+ ],
+ [
+ 0.10198895551312734,
+ 0.03191234958562256,
+ 0.135985523771401
+ ]
+ ],
+ "mass": 0.003249005593352382,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Hasbro Trivial Pursuit Family Edition Game",
+ "nr_faces": 4712,
+ "nr_vertices": 2423,
+ "surface_area": 0.1626896361684049,
+ "volume": 0.003249005593352382
+ }
+ },
+ "HeavyDuty_Flashlight": {
+ "asset_type": "FileBasedObject",
+ "id": "HeavyDuty_Flashlight",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.043458061269770164,
+ -0.04448038135157664,
+ -0.12279160439943294
+ ],
+ [
+ 0.03413893873022984,
+ 0.03340461864842336,
+ 0.10641339560056705
+ ]
+ ],
+ "mass": 0.0005163419459176717,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Heavy-Duty Flashlight",
+ "nr_faces": 17748,
+ "nr_vertices": 9828,
+ "surface_area": 0.05154211373637721,
+ "volume": 0.0005163419459176717
+ }
+ },
+ "Hefty_Waste_Basket_Decorative_Bronze_85_liter": {
+ "asset_type": "FileBasedObject",
+ "id": "Hefty_Waste_Basket_Decorative_Bronze_85_liter",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13963339878433506,
+ -0.10054452968676186,
+ -0.0754847485400074
+ ],
+ [
+ 0.13105260121566495,
+ 0.10362447031323813,
+ 0.2247322514599926
+ ]
+ ],
+ "mass": 0.002782504060032724,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Hefty Waste Basket, Decorative, Bronze - 8.5 liter",
+ "nr_faces": 13430,
+ "nr_vertices": 10705,
+ "surface_area": 0.3732840743653185,
+ "volume": 0.002782504060032724
+ }
+ },
+ "Hey_You_Pikachu_Nintendo_64": {
+ "asset_type": "FileBasedObject",
+ "id": "Hey_You_Pikachu_Nintendo_64",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05835643100679012,
+ -0.01191233977513171,
+ -0.038195301875444475
+ ],
+ [
+ 0.05817856899320988,
+ 0.01167066022486829,
+ 0.03950369812455552
+ ]
+ ],
+ "mass": 0.00015000852875686867,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Hey You, Pikachu!, Nintendo 64",
+ "nr_faces": 6462,
+ "nr_vertices": 3381,
+ "surface_area": 0.02309687747553955,
+ "volume": 0.00015000852875686867
+ }
+ },
+ "Hilary": {
+ "asset_type": "FileBasedObject",
+ "id": "Hilary",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0429437895241988,
+ -0.12793162190303958,
+ -0.055275327685586406
+ ],
+ [
+ 0.0397722104758012,
+ 0.1075673780969604,
+ 0.11689967231441359
+ ]
+ ],
+ "mass": 0.0008443186624464184,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Hilary",
+ "nr_faces": 12072,
+ "nr_vertices": 6532,
+ "surface_area": 0.1064999551688903,
+ "volume": 0.0008443186624464184
+ }
+ },
+ "Home_Fashions_Washcloth_Linen": {
+ "asset_type": "FileBasedObject",
+ "id": "Home_Fashions_Washcloth_Linen",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05921734182830514,
+ -0.09095658765638327,
+ -0.013876834147522783
+ ],
+ [
+ 0.05972565817169486,
+ 0.08853141234361672,
+ 0.017067165852477216
+ ]
+ ],
+ "mass": 0.0004558825427547107,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Home Fashions Washcloth, Linen",
+ "nr_faces": 43926,
+ "nr_vertices": 23262,
+ "surface_area": 0.05607571592215707,
+ "volume": 0.0004558825427547107
+ }
+ },
+ "Home_Fashions_Washcloth_Olive_Green": {
+ "asset_type": "FileBasedObject",
+ "id": "Home_Fashions_Washcloth_Olive_Green",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06383705329930957,
+ -0.09140584411178965,
+ -0.014996218330394143
+ ],
+ [
+ 0.06721994670069042,
+ 0.08524115588821035,
+ 0.01723178166960586
+ ]
+ ],
+ "mass": 0.000502857134678444,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Home Fashions Washcloth, Olive Green",
+ "nr_faces": 48028,
+ "nr_vertices": 25396,
+ "surface_area": 0.05658436215914655,
+ "volume": 0.000502857134678444
+ }
+ },
+ "Horse_Dreams_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Horse_Dreams_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10614439325071143,
+ -0.04175180620373454,
+ -0.042612979343317675
+ ],
+ [
+ 0.11247560674928857,
+ 0.04330019379626546,
+ 0.05516402065668233
+ ]
+ ],
+ "mass": 0.001008929301601279,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Horse Dreams Pencil Case",
+ "nr_faces": 12128,
+ "nr_vertices": 6525,
+ "surface_area": 0.06526370284788495,
+ "volume": 0.001008929301601279
+ }
+ },
+ "Horses_in_Pink_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Horses_in_Pink_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10540619204988101,
+ -0.04945069945769586,
+ -0.041934182503824594
+ ],
+ [
+ 0.10876380795011899,
+ 0.043206300542304135,
+ 0.04672981749617541
+ ]
+ ],
+ "mass": 0.0010119934026987468,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Horses in Pink Pencil Case",
+ "nr_faces": 12696,
+ "nr_vertices": 6713,
+ "surface_area": 0.06523069138880135,
+ "volume": 0.0010119934026987468
+ }
+ },
+ "House_of_Cards_The_Complete_First_Season_4_Discs_DVD": {
+ "asset_type": "FileBasedObject",
+ "id": "House_of_Cards_The_Complete_First_Season_4_Discs_DVD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07112120131162845,
+ -0.011728311872594108,
+ -0.09560556659819276
+ ],
+ [
+ 0.07237179868837154,
+ 0.011883688127405893,
+ 0.09532443340180723
+ ]
+ ],
+ "mass": 0.0005640719384319516,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "House of Cards: The Complete First Season [4 Discs] [DVD]",
+ "nr_faces": 3506,
+ "nr_vertices": 1900,
+ "surface_area": 0.06576670789013112,
+ "volume": 0.0005640719384319516
+ }
+ },
+ "Hyaluronic_Acid": {
+ "asset_type": "FileBasedObject",
+ "id": "Hyaluronic_Acid",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02714200837620299,
+ -0.027037716332560174,
+ -0.04453359121760254
+ ],
+ [
+ 0.02702499162379701,
+ 0.027167283667439826,
+ 0.05344740878239746
+ ]
+ ],
+ "mass": 0.00019205245006323016,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Hyaluronic Acid",
+ "nr_faces": 8834,
+ "nr_vertices": 4527,
+ "surface_area": 0.019208953719166685,
+ "volume": 0.00019205245006323016
+ }
+ },
+ "HyperX_Cloud_II_Headset_Gun_Metal": {
+ "asset_type": "FileBasedObject",
+ "id": "HyperX_Cloud_II_Headset_Gun_Metal",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12268092972353922,
+ -0.06310659259494196,
+ -0.14928254113779701
+ ],
+ [
+ 0.12256007027646078,
+ 0.06415440740505804,
+ 0.18026145886220296
+ ]
+ ],
+ "mass": 0.008529056418484712,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Headphones",
+ "description": "HyperX Cloud II Headset - Gun Metal\nHyperXR Cloud II features a redesigned USB sound card audio control box that amplifies audio and voice for an optimal Hi-Fi gaming experience, so you can hear what you?ve been missing. Open up a world of detail other gamers will never know ? the rustle of a camper?s boot, the scuttle in a distant vent. Its independent audio and microphone volume control lets you adjust not only sound volume but also mic volume and easily toggle Surround Sound 7.1 or the mic sound on and off. This next-generation headset generates virtual 7.1 surround sound with distance and depth to enhance your gaming, movie or music experience. Pinpoint your opponents? location in the game and strike before he sees you coming. It?s hardware driven and plug and play, with no driver needed. HyperX Cloud II has a digitally enhanced, noise-cancelling microphone with automatic gain control functionality and echo cancellation enabled through the USB sound card. The result is clearer voice quality and reduced background noise, with voice volume automatically increasing as in-game sound gets louder, to optimize team communication and in-game chat in intense battles. HyperX Cloud II is certified by TeamSpeak and optimized for Skype and other leading chat programs. HyperX Cloud II is Hi-Fi capable, with 53mm drivers for superior audio performance and rich sound quality with crystal-clear low, mid and high tones and enhanced bass via the sound card. Pro-gaming optimized, HyperX Cloud II is USB-powered for PCs and Macs and 3.5mm stereo-compatible for PS4 and Xbox One1. Its closed cup design helps with noise cancellation in gaming tournaments and other loud environments so players can obliterate the enemy in peace.",
+ "nr_faces": 4036,
+ "nr_vertices": 2171,
+ "surface_area": 0.2665133083502608,
+ "volume": 0.008529056418484712
+ }
+ },
+ "HyperX_Cloud_II_Headset_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "HyperX_Cloud_II_Headset_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12361024356092776,
+ -0.06202874886869679,
+ -0.1490140303770177
+ ],
+ [
+ 0.12261275643907225,
+ 0.06223425113130321,
+ 0.18226596962298233
+ ]
+ ],
+ "mass": 0.008585862366429588,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Headphones",
+ "description": "HyperX Cloud II Headset - Red\nHyperXR Cloud II features a redesigned USB sound card audio control box that amplifies audio and voice for an optimal Hi-Fi gaming experience, so you can hear what you?ve been missing. Open up a world of detail other gamers will never know ? the rustle of a camper?s boot, the scuttle in a distant vent. Its independent audio and microphone volume control lets you adjust not only sound volume but also mic volume and easily toggle Surround Sound 7.1 or the mic sound on and off. This next-generation headset generates virtual 7.1 surround sound with distance and depth to enhance your gaming, movie or music experience. Pinpoint your opponents? location in the game and strike before he sees you coming. It?s hardware driven and plug and play, with no driver needed. HyperX Cloud II has a digitally enhanced, noise-cancelling microphone with automatic gain control functionality and echo cancellation enabled through the USB sound card. The result is clearer voice quality and reduced background noise, with voice volume automatically increasing as in-game sound gets louder, to optimize team communication and in-game chat in intense battles. HyperX Cloud II is certified by TeamSpeak and optimized for Skype and other leading chat programs. HyperX Cloud II is Hi-Fi capable, with 53mm drivers for superior audio performance and rich sound quality with crystal-clear low, mid and high tones and enhanced bass via the sound card. Pro-gaming optimized, HyperX Cloud II is USB-powered for PCs and Macs and 3.5mm stereo-compatible for PS4 and Xbox One1. Its closed cup design helps with noise cancellation in gaming tournaments and other loud environments so players can obliterate the enemy in peace.",
+ "nr_faces": 3990,
+ "nr_vertices": 2190,
+ "surface_area": 0.26707837992208605,
+ "volume": 0.008585862366429588
+ }
+ },
+ "INTERNATIONAL_PAPER_Willamette_4_Brown_Bag_500Count": {
+ "asset_type": "FileBasedObject",
+ "id": "INTERNATIONAL_PAPER_Willamette_4_Brown_Bag_500Count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1338566800156357,
+ -0.12956747451454564,
+ -0.069262877011538
+ ],
+ [
+ 0.1362183199843643,
+ 0.12785652548545434,
+ 0.070458122988462
+ ]
+ ],
+ "mass": 0.00861315284520299,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "INTERNATIONAL PAPER Willamette #4 Brown Bag 500-Count",
+ "nr_faces": 5168,
+ "nr_vertices": 2756,
+ "surface_area": 0.25272675022161906,
+ "volume": 0.00861315284520299
+ }
+ },
+ "Imaginext_Castle_Ogre": {
+ "asset_type": "FileBasedObject",
+ "id": "Imaginext_Castle_Ogre",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20382888858827294,
+ -0.09829246623687499,
+ -0.12712647224943288
+ ],
+ [
+ 0.19182611141172703,
+ 0.09582753376312501,
+ 0.11008152775056712
+ ]
+ ],
+ "mass": 0.003303524291762162,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Imaginext Castle Ogre",
+ "nr_faces": 27334,
+ "nr_vertices": 15552,
+ "surface_area": 0.26586530718234036,
+ "volume": 0.003303524291762162
+ }
+ },
+ "In_Green_Company_Surface_Saver_Ring_10_Terra_Cotta": {
+ "asset_type": "FileBasedObject",
+ "id": "In_Green_Company_Surface_Saver_Ring_10_Terra_Cotta",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1260784042781735,
+ -0.12717480116684374,
+ -0.018050525129341407
+ ],
+ [
+ 0.1273565957218265,
+ 0.12599419883315627,
+ 0.006317474870658594
+ ]
+ ],
+ "mass": 0.00011286808663217016,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "In Green Company Surface Saver Ring, 10\", Terra Cotta",
+ "nr_faces": 18272,
+ "nr_vertices": 10234,
+ "surface_area": 0.09009091668735378,
+ "volume": 0.00011286808663217016
+ }
+ },
+ "Inositol": {
+ "asset_type": "FileBasedObject",
+ "id": "Inositol",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03131206642506374,
+ -0.030968842936311598,
+ -0.050927534555527586
+ ],
+ [
+ 0.030946933574936265,
+ 0.030875157063688402,
+ 0.05930446544447241
+ ]
+ ],
+ "mass": 0.0002881936182673328,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Inositol",
+ "nr_faces": 9522,
+ "nr_vertices": 4879,
+ "surface_area": 0.02493077407612758,
+ "volume": 0.0002881936182673328
+ }
+ },
+ "InterDesign_Over_Door": {
+ "asset_type": "FileBasedObject",
+ "id": "InterDesign_Over_Door",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10774084114708819,
+ -0.09409390996911553,
+ -0.03903191403252004
+ ],
+ [
+ 0.10742015885291181,
+ 0.1971470900308845,
+ 0.05797108596747996
+ ]
+ ],
+ "mass": 7.084698283716902e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "InterDesign Over Door",
+ "nr_faces": 9408,
+ "nr_vertices": 5438,
+ "surface_area": 0.045093703942214174,
+ "volume": 7.084698283716902e-05
+ }
+ },
+ "IsoRich_Soy": {
+ "asset_type": "FileBasedObject",
+ "id": "IsoRich_Soy",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.061169631460878525,
+ -0.06101891926759451,
+ -0.08208371279024622
+ ],
+ [
+ 0.06120936853912148,
+ 0.06096108073240549,
+ 0.08675528720975378
+ ]
+ ],
+ "mass": 0.0017761954620257032,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Iso-Rich Soy",
+ "nr_faces": 9094,
+ "nr_vertices": 4733,
+ "surface_area": 0.0836953052904678,
+ "volume": 0.0017761954620257032
+ }
+ },
+ "JA_Henckels_International_Premio_Cutlery_Block_Set_14Piece": {
+ "asset_type": "FileBasedObject",
+ "id": "JA_Henckels_International_Premio_Cutlery_Block_Set_14Piece",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05725272950153978,
+ -0.18323614652092934,
+ -0.09752184662786906
+ ],
+ [
+ 0.055469270498460226,
+ 0.16908785347907065,
+ 0.21176615337213095
+ ]
+ ],
+ "mass": 0.004245646236010839,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "J.A. Henckels International Premio Cutlery Block Set, 14-Piece",
+ "nr_faces": 15856,
+ "nr_vertices": 9574,
+ "surface_area": 0.24730500146741718,
+ "volume": 0.004245646236010839
+ }
+ },
+ "JBL_Charge_Speaker_portable_wireless_wired_Green": {
+ "asset_type": "FileBasedObject",
+ "id": "JBL_Charge_Speaker_portable_wireless_wired_Green",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08808514811961526,
+ -0.036458312184157904,
+ -0.037595938769034366
+ ],
+ [
+ 0.08761385188038474,
+ 0.0363616878158421,
+ 0.03763106123096563
+ ]
+ ],
+ "mass": 0.0006489222979706253,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "JBL Charge Speaker - portable - wireless, wired, Green",
+ "nr_faces": 6928,
+ "nr_vertices": 3585,
+ "surface_area": 0.048138256882099884,
+ "volume": 0.0006489222979706253
+ }
+ },
+ "JS_WINGS_20_BLACK_FLAG": {
+ "asset_type": "FileBasedObject",
+ "id": "JS_WINGS_20_BLACK_FLAG",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07174442214765432,
+ -0.17526305500257494,
+ -0.05946923590708054
+ ],
+ [
+ 0.05680957785234568,
+ 0.17839494499742506,
+ 0.12482476409291945
+ ]
+ ],
+ "mass": 0.0020969064150878677,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "JS WINGS 2.0 BLACK FLAG",
+ "nr_faces": 34798,
+ "nr_vertices": 19264,
+ "surface_area": 0.1698412049256084,
+ "volume": 0.0020969064150878677
+ }
+ },
+ "JUICER_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "JUICER_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12169692978508179,
+ -0.10493795668062965,
+ -0.027566661675973183
+ ],
+ [
+ 0.16481007021491823,
+ 0.07732604331937036,
+ 0.050395338324026824
+ ]
+ ],
+ "mass": 0.0006015222114350194,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "JUICER SET\nHave fresh fruit juice with friends with this Juicer Set! Includes juicer, cup, orange, lemon, and knife.",
+ "nr_faces": 9760,
+ "nr_vertices": 5493,
+ "surface_area": 0.08713094081725953,
+ "volume": 0.0006015222114350194
+ }
+ },
+ "JUNGLE_HEIGHT": {
+ "asset_type": "FileBasedObject",
+ "id": "JUNGLE_HEIGHT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13103599410925698,
+ -0.19489473112230982,
+ -0.014847872604731664
+ ],
+ [
+ 0.13872800589074302,
+ 0.1778882688776902,
+ 0.01821012739526833
+ ]
+ ],
+ "mass": 0.0005486638070260877,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "JUNGLE HEIGHT\nChoose Jungle printed canvas growth charts for your kids! This set comes complete with 4 animal measuring clips, which is movable from height to height. Measures heights from 40-160 cm and hangs easily from the attached rope at the top of the chart.",
+ "nr_faces": 18494,
+ "nr_vertices": 12047,
+ "surface_area": 0.19375033782383905,
+ "volume": 0.0005486638070260877
+ }
+ },
+ "Jansport_School_Backpack_Blue_Streak": {
+ "asset_type": "FileBasedObject",
+ "id": "Jansport_School_Backpack_Blue_Streak",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16723961841756949,
+ -0.2000380058386344,
+ -0.20060084255806282
+ ],
+ [
+ 0.19041638158243052,
+ 0.1693079941613656,
+ 0.23954715744193716
+ ]
+ ],
+ "mass": 0.03569940360098656,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Jansport School Backpack, Blue Streak",
+ "nr_faces": 30092,
+ "nr_vertices": 16542,
+ "surface_area": 0.66079039031397,
+ "volume": 0.03569940360098656
+ }
+ },
+ "JarroDophilusFOS_Value_Size": {
+ "asset_type": "FileBasedObject",
+ "id": "JarroDophilusFOS_Value_Size",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0335515271041601,
+ -0.03321482692759389,
+ -0.058510194540149316
+ ],
+ [
+ 0.0333824728958399,
+ 0.033080173072406106,
+ 0.07000180545985069
+ ]
+ ],
+ "mass": 0.00038158945622898265,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Jarro-Dophilus+FOS - Value Size",
+ "nr_faces": 8406,
+ "nr_vertices": 4332,
+ "surface_area": 0.030212812402666274,
+ "volume": 0.00038158945622898265
+ }
+ },
+ "JarroSil_Activated_Silicon": {
+ "asset_type": "FileBasedObject",
+ "id": "JarroSil_Activated_Silicon",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.030084957280255526,
+ -0.023408185653583245,
+ -0.05445359639204272
+ ],
+ [
+ 0.030071042719744475,
+ 0.023284814346416757,
+ 0.05456840360795729
+ ]
+ ],
+ "mass": 0.00029083779879215764,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "JarroSil, Activated Silicon\nJarroSil is a synergistic formulation of highly bioavailable silicon. A patent pending Activated Silicon formula, JarroSil contains stabilized molecular clusters of silicic acid, which provide a biologically active form of silicon upon dissolution into liquids. JarroSil is manufactured in the USA using the latest technology for enhanced bioavailability, stability and improved taste. Stabilized silicic acid is converted to highly bioavailable ortho- and disilicic acids upon dissolution in liquids and in the stomach. JarroSil?s Activated Silicon improves the strength and elasticity of collagen by stimulating collagen production. Stronger collagen means healthier, more elastic skin, and fewer and shallower wrinkles.* The outer shaft of hair is rich in silicon. Adequate silicon helps hair grow thicker and stronger.* Supplementation with JarroSil also strengthens weak, brittle nails associated with an inadequate silicon intake.* Silicon plays an important role in bone calcification, including during the growth of new bone.* Bone building cells (osteoblasts) start by constructing a connective tissue matrix. When this is done, the osteoblasts switch their function and begin to fill in this matrix with minerals. This process requires silicon.* JarroSil is an essential partner of calcium for bones and antioxidants for supple and healthy arteries.* *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 7268,
+ "nr_vertices": 3784,
+ "surface_area": 0.026905487148242698,
+ "volume": 0.00029083779879215764
+ }
+ },
+ "JarroSil_Activated_Silicon_5exdZHIeLAp": {
+ "asset_type": "FileBasedObject",
+ "id": "JarroSil_Activated_Silicon_5exdZHIeLAp",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02999385555156232,
+ -0.023852531250575987,
+ -0.046324422409122455
+ ],
+ [
+ 0.03044214444843768,
+ 0.023791468749424012,
+ 0.04599957759087754
+ ]
+ ],
+ "mass": 0.0002453522776219693,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "JarroSil, Activated Silicon\nJarroSil is a synergistic formulation of highly bioavailable silicon. A patent pending Activated Silicon formula, JarroSil contains stabilized molecular clusters of silicic acid, which provide a biologically active form of silicon upon dissolution into liquids. JarroSil is manufactured in the USA using the latest technology for enhanced bioavailability, stability and improved taste. Stabilized silicic acid is converted to highly bioavailable ortho- and disilicic acids upon dissolution in liquids and in the stomach. JarroSil?s Activated Silicon improves the strength and elasticity of collagen by stimulating collagen production. Stronger collagen means healthier, more elastic skin, and fewer and shallower wrinkles.* The outer shaft of hair is rich in silicon. Adequate silicon helps hair grow thicker and stronger.* Supplementation with JarroSil also strengthens weak, brittle nails associated with an inadequate silicon intake.* Silicon plays an important role in bone calcification, including during the growth of new bone.* Bone building cells (osteoblasts) start by constructing a connective tissue matrix. When this is done, the osteoblasts switch their function and begin to fill in this matrix with minerals. This process requires silicon.* JarroSil is an essential partner of calcium for bones and antioxidants for supple and healthy arteries.* *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 6446,
+ "nr_vertices": 3391,
+ "surface_area": 0.023441207273084717,
+ "volume": 0.0002453522776219693
+ }
+ },
+ "Jarrow_Formulas_Glucosamine_Hci_Mega_1000_100_ct": {
+ "asset_type": "FileBasedObject",
+ "id": "Jarrow_Formulas_Glucosamine_Hci_Mega_1000_100_ct",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.031114781757736416,
+ -0.031044513167961946,
+ -0.05096461454684356
+ ],
+ [
+ 0.030928218242263585,
+ 0.030805486832038056,
+ 0.05949538545315644
+ ]
+ ],
+ "mass": 0.0002879028769740363,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Jarrow Formulas Glucosamine Hci Mega 1000 - 100 ct",
+ "nr_faces": 9234,
+ "nr_vertices": 4729,
+ "surface_area": 0.025002524568491696,
+ "volume": 0.0002879028769740363
+ }
+ },
+ "Jarrow_Glucosamine_Chondroitin_Combination_120_Caps": {
+ "asset_type": "FileBasedObject",
+ "id": "Jarrow_Glucosamine_Chondroitin_Combination_120_Caps",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03255560705520171,
+ -0.03239441117605618,
+ -0.05311958559033265
+ ],
+ [
+ 0.032515392944798285,
+ 0.03235358882394382,
+ 0.06312741440966735
+ ]
+ ],
+ "mass": 0.00032514269715408245,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Jarrow Glucosamine + Chondroitin Combination 120 Caps",
+ "nr_faces": 6406,
+ "nr_vertices": 3315,
+ "surface_area": 0.027079084850169566,
+ "volume": 0.00032514269715408245
+ }
+ },
+ "Jawbone_UP24_Wireless_Activity_Tracker_Pink_Coral_L": {
+ "asset_type": "FileBasedObject",
+ "id": "Jawbone_UP24_Wireless_Activity_Tracker_Pink_Coral_L",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04086089820486661,
+ -0.030110708447596984,
+ -0.007130325515298235
+ ],
+ [
+ 0.04036410179513339,
+ 0.028224291552403018,
+ 0.008070674484701765
+ ]
+ ],
+ "mass": 1.5991214880655163e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Jawbone UP24 Wireless Activity Tracker, Pink Coral, L",
+ "nr_faces": 7654,
+ "nr_vertices": 3981,
+ "surface_area": 0.006970529929371229,
+ "volume": 1.5991214880655163e-05
+ }
+ },
+ "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_Kit_Jet_Black_M60": {
+ "asset_type": "FileBasedObject",
+ "id": "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_Kit_Jet_Black_M60",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03992126348249087,
+ -0.023150649515559313,
+ -0.0719925128094653
+ ],
+ [
+ 0.03983373651750913,
+ 0.022819350484440688,
+ 0.0718214871905347
+ ]
+ ],
+ "mass": 0.0004753639380420256,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Just For Men Mustache & Beard Brush-in Hair Color Gel Kit Jet Black M-60",
+ "nr_faces": 5512,
+ "nr_vertices": 2877,
+ "surface_area": 0.03974612003080969,
+ "volume": 0.0004753639380420256
+ }
+ },
+ "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_MediumDark_Brown_M40": {
+ "asset_type": "FileBasedObject",
+ "id": "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_MediumDark_Brown_M40",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03958270057947262,
+ -0.023628166031905182,
+ -0.07262677685565275
+ ],
+ [
+ 0.039727299420527384,
+ 0.023397833968094816,
+ 0.07247922314434725
+ ]
+ ],
+ "mass": 0.0004818292000420589,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Just For Men Mustache & Beard Brush-in Hair Color Gel Medium-Dark Brown M-40",
+ "nr_faces": 3612,
+ "nr_vertices": 1932,
+ "surface_area": 0.03990916184266601,
+ "volume": 0.0004818292000420589
+ }
+ },
+ "Just_For_Men_ShampooIn_Haircolor_Jet_Black_60": {
+ "asset_type": "FileBasedObject",
+ "id": "Just_For_Men_ShampooIn_Haircolor_Jet_Black_60",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03988252221053346,
+ -0.02398327237956179,
+ -0.07823915630753686
+ ],
+ [
+ 0.03949747778946654,
+ 0.02390872762043821,
+ 0.07815384369246316
+ ]
+ ],
+ "mass": 0.0005452114811632445,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Just For Men Shampoo-In Haircolor Jet Black 60",
+ "nr_faces": 4644,
+ "nr_vertices": 2462,
+ "surface_area": 0.0435037169581641,
+ "volume": 0.0005452114811632445
+ }
+ },
+ "Just_For_Men_ShampooIn_Haircolor_Light_Brown_25": {
+ "asset_type": "FileBasedObject",
+ "id": "Just_For_Men_ShampooIn_Haircolor_Light_Brown_25",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.039410416026598775,
+ -0.023778015443150176,
+ -0.07841241454630875
+ ],
+ [
+ 0.039138583973401225,
+ 0.023755984556849824,
+ 0.07865958545369126
+ ]
+ ],
+ "mass": 0.000548003489478559,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Just For Men Shampoo-In Haircolor Light Brown 25",
+ "nr_faces": 4056,
+ "nr_vertices": 2162,
+ "surface_area": 0.043582393751954995,
+ "volume": 0.000548003489478559
+ }
+ },
+ "Just_For_Men_Shampoo_In_Haircolor_Darkest_Brown_50": {
+ "asset_type": "FileBasedObject",
+ "id": "Just_For_Men_Shampoo_In_Haircolor_Darkest_Brown_50",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.038834907311167156,
+ -0.02383522871482438,
+ -0.0782255615353718
+ ],
+ [
+ 0.03876609268883284,
+ 0.023689771285175618,
+ 0.07853343846462821
+ ]
+ ],
+ "mass": 0.0005423441161801588,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Just For Men Shampoo In Haircolor Darkest Brown 50",
+ "nr_faces": 3382,
+ "nr_vertices": 1783,
+ "surface_area": 0.043586261781956126,
+ "volume": 0.0005423441161801588
+ }
+ },
+ "Justified_The_Complete_Fourth_Season_3_Discs_DVD": {
+ "asset_type": "FileBasedObject",
+ "id": "Justified_The_Complete_Fourth_Season_3_Discs_DVD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07075085870880927,
+ -0.010490035376780388,
+ -0.09625960361991515
+ ],
+ [
+ 0.07090714129119073,
+ 0.010867964623219612,
+ 0.09779339638008487
+ ]
+ ],
+ "mass": 0.0004622478436809457,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Justified: The Complete Fourth Season [3 Discs] [DVD]",
+ "nr_faces": 4702,
+ "nr_vertices": 2462,
+ "surface_area": 0.06404013350840622,
+ "volume": 0.0004622478436809457
+ }
+ },
+ "KID_ROOM_FURNITURE_SET_1": {
+ "asset_type": "FileBasedObject",
+ "id": "KID_ROOM_FURNITURE_SET_1",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06851783221264482,
+ -0.15364123317743283,
+ -0.04167076119562537
+ ],
+ [
+ 0.05716016778735517,
+ 0.07989776682256718,
+ 0.053306238804374635
+ ]
+ ],
+ "mass": 0.00042332393472141515,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "KID ROOM (FURNITURE SET 1)\nThe set includes a bunk bed, shelf , table, and chair. Made of Eco-Friendly PlanWood and solid rubber wood.",
+ "nr_faces": 15210,
+ "nr_vertices": 8543,
+ "surface_area": 0.09058960709673025,
+ "volume": 0.00042332393472141515
+ }
+ },
+ "KITCHEN_FURNITURE_SET_1": {
+ "asset_type": "FileBasedObject",
+ "id": "KITCHEN_FURNITURE_SET_1",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08977910490721644,
+ -0.10232635255840025,
+ -0.04043797567707747
+ ],
+ [
+ 0.09024789509278355,
+ 0.041899647441599755,
+ 0.06561502432292252
+ ]
+ ],
+ "mass": 0.00041681486700752377,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "KITCHEN (FURNITURE SET 1)\nThe set includes refrigerator, a freestanding range, corner storage, and a sink with bottom shlef. Made of Eco-Friendly PlanWood and solid rubber wood.",
+ "nr_faces": 7812,
+ "nr_vertices": 4214,
+ "surface_area": 0.06146830342534524,
+ "volume": 0.00041681486700752377
+ }
+ },
+ "KITCHEN_SET_CLASSIC_40HwCHfeG0H": {
+ "asset_type": "FileBasedObject",
+ "id": "KITCHEN_SET_CLASSIC_40HwCHfeG0H",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11387175836677431,
+ -0.11903203245032175,
+ -0.04643507706994499
+ ],
+ [
+ 0.0715632416332257,
+ 0.04826896754967826,
+ 0.104858922930055
+ ]
+ ],
+ "mass": 0.0008434135924361482,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "KITCHEN SET - CLASSIC\nChildren can enjoy decorating their dollhouse with the Classic set of furniture while developing their imagination and creating more interest time.",
+ "nr_faces": 7274,
+ "nr_vertices": 4181,
+ "surface_area": 0.10235941324385076,
+ "volume": 0.0008434135924361482
+ }
+ },
+ "KS_Chocolate_Cube_Box_Assortment_By_Neuhaus_2010_Ounces": {
+ "asset_type": "FileBasedObject",
+ "id": "KS_Chocolate_Cube_Box_Assortment_By_Neuhaus_2010_Ounces",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07910252173203022,
+ -0.10544758915900845,
+ -0.0780040801911731
+ ],
+ [
+ 0.09112047826796978,
+ 0.07902641084099155,
+ 0.0942529198088269
+ ]
+ ],
+ "mass": 0.0030831104433949636,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "KS Chocolate Cube Box Assortment By Neuhaus 20.10 Ounces",
+ "nr_faces": 13200,
+ "nr_vertices": 7568,
+ "surface_area": 0.14063627251208,
+ "volume": 0.0030831104433949636
+ }
+ },
+ "Kanex_MultiSync_Wireless_Keyboard": {
+ "asset_type": "FileBasedObject",
+ "id": "Kanex_MultiSync_Wireless_Keyboard",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.220725448697555,
+ -0.07136645972643305,
+ -0.01126512977607799
+ ],
+ [
+ 0.22109355130244498,
+ 0.052978540273566944,
+ 0.012289870223922009
+ ]
+ ],
+ "mass": 0.000597715529436611,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Keyboard",
+ "description": "Kanex Multi-Sync - Wireless Keyboard",
+ "nr_faces": 8556,
+ "nr_vertices": 4364,
+ "surface_area": 0.127347053481039,
+ "volume": 0.000597715529436611
+ }
+ },
+ "Kid_Icarus_Uprising_Nintendo_3DS_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Kid_Icarus_Uprising_Nintendo_3DS_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07131027246005821,
+ -0.016225719400231025,
+ -0.06422867592716246
+ ],
+ [
+ 0.0707877275399418,
+ 0.016066280599768973,
+ 0.06456832407283754
+ ]
+ ],
+ "mass": 0.0005398738828071158,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Kid Icarus Uprising [Nintendo 3DS Game]",
+ "nr_faces": 2978,
+ "nr_vertices": 1636,
+ "surface_area": 0.050259326488077266,
+ "volume": 0.0005398738828071158
+ }
+ },
+ "Kingston_DT4000MR_G2_Management_Ready_USB_64GB": {
+ "asset_type": "FileBasedObject",
+ "id": "Kingston_DT4000MR_G2_Management_Ready_USB_64GB",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03973936996495398,
+ -0.011187861358116039,
+ -0.0063664959656425674
+ ],
+ [
+ 0.03973763003504602,
+ 0.010851138641883962,
+ 0.006591504034357433
+ ]
+ ],
+ "mass": 1.6151148037159833e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Kingston DT4000M-R G2 Management Ready USB - 64GB\nKingston?s DataTraveler? 4000 G2 offers high-end security with FIPS 140-2 Level 3 certification and a tamper-evident seal for physical security to detect and respond to attempts at access, use or modification of the cryptographic module. It safeguards 100 percent of even the most sensitive data with 256-bit AES hardware-based encryption in XTS mode. For added peace of mind, the drive locks down and reformats after ten failed intrusion attempts and functions in read-only access mode to avoid malware risks. The drive is available with SafeConsole* management, which allows IT professionals to centrally manage it to meet compliance requirements and provide a higher level of internal support. Activation is easy and can be done manually or with mass deployment tools. DT4000 G2?s industry-leading NAND and controller design allows for NAND to be interchanged without requalification and certification, so customers can add it to their standards list with confidence. DT4000 G2 offers impressive SuperSpeed USB 3.0 technology so users don?t have to compromise speed for security. It?s customizable and available with serial numbering, custom Product Identifier (PID) and other options to meet most frequently requested corporate IT requirements. DataTraveler 4000 G2 is backed by a five-year warranty, free technical support and legendary Kingston? reliability.",
+ "nr_faces": 11596,
+ "nr_vertices": 5984,
+ "surface_area": 0.004594239361515047,
+ "volume": 1.6151148037159833e-05
+ }
+ },
+ "Kong_Puppy_Teething_Rubber_Small_Pink": {
+ "asset_type": "FileBasedObject",
+ "id": "Kong_Puppy_Teething_Rubber_Small_Pink",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.022099787616453162,
+ -0.0222526921282118,
+ -0.03022665839100163
+ ],
+ [
+ 0.022411212383546836,
+ 0.0222033078717882,
+ 0.041430341608998375
+ ]
+ ],
+ "mass": 6.565263907606784e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Kong Puppy Teething Rubber, Small, Pink",
+ "nr_faces": 8772,
+ "nr_vertices": 4516,
+ "surface_area": 0.009479627470326537,
+ "volume": 6.565263907606784e-05
+ }
+ },
+ "Kotex_U_Barely_There_Liners_Thin_60_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Kotex_U_Barely_There_Liners_Thin_60_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04000821931158071,
+ -0.0347722430249036,
+ -0.06546232954546487
+ ],
+ [
+ 0.04001978068841929,
+ 0.034661756975096394,
+ 0.06545667045453513
+ ]
+ ],
+ "mass": 0.0006819278507318758,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Kotex U Barely There Liners, Thin - 60 count",
+ "nr_faces": 8782,
+ "nr_vertices": 4593,
+ "surface_area": 0.046061444575017166,
+ "volume": 0.0006819278507318758
+ }
+ },
+ "Kotex_U_Tween_Pads_16_pads": {
+ "asset_type": "FileBasedObject",
+ "id": "Kotex_U_Tween_Pads_16_pads",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07669824673707262,
+ -0.05194679656484234,
+ -0.04347841641553671
+ ],
+ [
+ 0.07789775326292737,
+ 0.05020420343515766,
+ 0.045213583584463285
+ ]
+ ],
+ "mass": 0.0012679825011666231,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Kotex U Tween Pads - 16 pads\nProtection for smaller sizes. Extra absorbent! Absorbs like our heavy flow pad. Designed to fit smaller bodies for serious protection. Ultra-thin and flexible - bye-bye bulk! Made in China.",
+ "nr_faces": 29600,
+ "nr_vertices": 15128,
+ "surface_area": 0.07151089860857802,
+ "volume": 0.0012679825011666231
+ }
+ },
+ "Kotobuki_Saucer_Dragon_Fly": {
+ "asset_type": "FileBasedObject",
+ "id": "Kotobuki_Saucer_Dragon_Fly",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.048142954881327193,
+ -0.048222326825670424,
+ -0.011939835124993211
+ ],
+ [
+ 0.04842404511867281,
+ 0.04845267317432958,
+ 0.012338164875006788
+ ]
+ ],
+ "mass": 3.408735634835649e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Kotobuki Saucer, Dragon Fly",
+ "nr_faces": 8746,
+ "nr_vertices": 4491,
+ "surface_area": 0.01923350085914944,
+ "volume": 3.408735634835649e-05
+ }
+ },
+ "Krill_Oil": {
+ "asset_type": "FileBasedObject",
+ "id": "Krill_Oil",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.027535192293148356,
+ -0.0270064694432894,
+ -0.044424390924804526
+ ],
+ [
+ 0.027222807706851645,
+ 0.0268535305567106,
+ 0.05314560907519548
+ ]
+ ],
+ "mass": 0.00019161117183995834,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Krill Oil",
+ "nr_faces": 8476,
+ "nr_vertices": 4385,
+ "surface_area": 0.01918544519906131,
+ "volume": 0.00019161117183995834
+ }
+ },
+ "LACING_SHEEP": {
+ "asset_type": "FileBasedObject",
+ "id": "LACING_SHEEP",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.042381970085650894,
+ -0.06339957909322798,
+ -0.047057771558065606
+ ],
+ [
+ 0.042617029914349104,
+ 0.07236342090677202,
+ 0.04218922844193439
+ ]
+ ],
+ "mass": 0.0003554790446895443,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "LACING SHEEP\nChildren can lace corresponding colors together to form a sheep. The toy helps them learn basic colors and sequence.",
+ "nr_faces": 14590,
+ "nr_vertices": 7767,
+ "surface_area": 0.03399919281067769,
+ "volume": 0.0003554790446895443
+ }
+ },
+ "LADYBUG_BEAD": {
+ "asset_type": "FileBasedObject",
+ "id": "LADYBUG_BEAD",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02876000108956623,
+ -0.04165182250442793,
+ -0.01489930407826509
+ ],
+ [
+ 0.02840099891043377,
+ 0.04255917749557207,
+ 0.015392695921734909
+ ]
+ ],
+ "mass": 7.082610871705516e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "LADYBUG BEAD\nThis cute grasping toy features rainbow-colored beads which spin and rattle.",
+ "nr_faces": 10888,
+ "nr_vertices": 5714,
+ "surface_area": 0.013560319658314706,
+ "volume": 7.082610871705516e-05
+ }
+ },
+ "LEGO_5887_Dino_Defense_HQ": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_5887_Dino_Defense_HQ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.23113482376211336,
+ -0.17991925824565536,
+ -0.07697592079442823
+ ],
+ [
+ 0.22058217623788662,
+ 0.16742174175434463,
+ 0.18473407920557178
+ ]
+ ],
+ "mass": 0.002285033061737521,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "LEGO 5887 Dino Defense HQ",
+ "nr_faces": 82396,
+ "nr_vertices": 56832,
+ "surface_area": 0.5192364395857534,
+ "volume": 0.002285033061737521
+ }
+ },
+ "LEGO_Bricks_More_Creative_Suitcase": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_Bricks_More_Creative_Suitcase",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1900605082417752,
+ -0.07309823582995525,
+ -0.14162117027661886
+ ],
+ [
+ 0.1910354917582248,
+ 0.07394976417004476,
+ 0.14218482972338112
+ ]
+ ],
+ "mass": 0.014978032153396202,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "LEGO Bricks & More Creative Suitcase",
+ "nr_faces": 5138,
+ "nr_vertices": 3070,
+ "surface_area": 0.39550681402822807,
+ "volume": 0.014978032153396202
+ }
+ },
+ "LEGO_City_Advent_Calendar": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_City_Advent_Calendar",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19180960043140682,
+ -0.036245660577050184,
+ -0.13139790381939415
+ ],
+ [
+ 0.19165539956859318,
+ 0.03602033942294981,
+ 0.13049409618060584
+ ]
+ ],
+ "mass": 0.006936754338982564,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "LEGO City Advent Calendar",
+ "nr_faces": 1950,
+ "nr_vertices": 1097,
+ "surface_area": 0.2808797164054704,
+ "volume": 0.006936754338982564
+ }
+ },
+ "LEGO_Creationary_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_Creationary_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17199587699193558,
+ -0.10636608629063883,
+ -0.02028303201581177
+ ],
+ [
+ 0.11049112300806442,
+ 0.10465591370936117,
+ 0.04905096798418822
+ ]
+ ],
+ "mass": 0.0002326867173513453,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "LEGO Creationary Game",
+ "nr_faces": 18654,
+ "nr_vertices": 11195,
+ "surface_area": 0.07946510847343863,
+ "volume": 0.0002326867173513453
+ }
+ },
+ "LEGO_Creationary_Game_ZJa163wlWp2": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_Creationary_Game_ZJa163wlWp2",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.21755359259911858,
+ -0.03783125088813823,
+ -0.13714633504589635
+ ],
+ [
+ 0.21815340740088143,
+ 0.03757174911186177,
+ 0.13790366495410364
+ ]
+ ],
+ "mass": 0.00843218639483778,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "LEGO Creationary Game",
+ "nr_faces": 2896,
+ "nr_vertices": 1545,
+ "surface_area": 0.32694185929619124,
+ "volume": 0.00843218639483778
+ }
+ },
+ "LEGO_Duplo_Build_and_Play_Box_4629": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_Duplo_Build_and_Play_Box_4629",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.22129199930656,
+ -0.1389906789479083,
+ -0.0723650919000666
+ ],
+ [
+ 0.21834200069344,
+ 0.1049123210520917,
+ 0.1446689080999334
+ ]
+ ],
+ "mass": 0.0018560516880803282,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "LEGO Duplo Build and Play Box (4629)",
+ "nr_faces": 51030,
+ "nr_vertices": 38460,
+ "surface_area": 0.33248677820790795,
+ "volume": 0.0018560516880803282
+ }
+ },
+ "LEGO_Duplo_Creative_Animals_10573": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_Duplo_Creative_Animals_10573",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19385941285035152,
+ -0.06357293807770076,
+ -0.051094189086150744
+ ],
+ [
+ 0.1953645871496485,
+ 0.08488806192229925,
+ 0.10862781091384927
+ ]
+ ],
+ "mass": 0.0008310205151719682,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "LEGO Duplo Creative Animals (10573)",
+ "nr_faces": 22284,
+ "nr_vertices": 13998,
+ "surface_area": 0.1502215741435866,
+ "volume": 0.0008310205151719682
+ }
+ },
+ "LEGO_Fusion_Set_Town_Master": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_Fusion_Set_Town_Master",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17722849642636965,
+ -0.030398260009777647,
+ -0.09734621849711145
+ ],
+ [
+ 0.17635150357363036,
+ 0.030986739990222355,
+ 0.09724278150288855
+ ]
+ ],
+ "mass": 0.0038286568189349534,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "LEGO Fusion Set Town Master",
+ "nr_faces": 4726,
+ "nr_vertices": 2468,
+ "surface_area": 0.19489186432258612,
+ "volume": 0.0038286568189349534
+ }
+ },
+ "LEGO_Star_Wars_Advent_Calendar": {
+ "asset_type": "FileBasedObject",
+ "id": "LEGO_Star_Wars_Advent_Calendar",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19306037962271613,
+ -0.03865430570769258,
+ -0.1320273900974838
+ ],
+ [
+ 0.19212262037728386,
+ 0.038160694292307416,
+ 0.1316836099025162
+ ]
+ ],
+ "mass": 0.0071722071626507695,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "LEGO Star Wars Advent Calendar",
+ "nr_faces": 2554,
+ "nr_vertices": 1479,
+ "surface_area": 0.281768441236661,
+ "volume": 0.0071722071626507695
+ }
+ },
+ "LEUCIPPUS_ADIPURE": {
+ "asset_type": "FileBasedObject",
+ "id": "LEUCIPPUS_ADIPURE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05686343120069882,
+ -0.13223620595390057,
+ -0.033522276868350194
+ ],
+ [
+ 0.04687556879930119,
+ 0.13697479404609944,
+ 0.0767167231316498
+ ]
+ ],
+ "mass": 0.0009275758934399514,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "LEUCIPPUS ADIPURE",
+ "nr_faces": 24908,
+ "nr_vertices": 14519,
+ "surface_area": 0.1038504882391879,
+ "volume": 0.0009275758934399514
+ }
+ },
+ "LTyrosine": {
+ "asset_type": "FileBasedObject",
+ "id": "LTyrosine",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.031024060212879304,
+ -0.030656020995386522,
+ -0.05105019458608415
+ ],
+ [
+ 0.031018939787120694,
+ 0.030668979004613475,
+ 0.05952980541391585
+ ]
+ ],
+ "mass": 0.00028770773355592515,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "L-Tyrosine",
+ "nr_faces": 10370,
+ "nr_vertices": 5305,
+ "surface_area": 0.024986352559975195,
+ "volume": 0.00028770773355592515
+ }
+ },
+ "Lactoferrin": {
+ "asset_type": "FileBasedObject",
+ "id": "Lactoferrin",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.028741617855650752,
+ -0.02846123021542153,
+ -0.04652271996992003
+ ],
+ [
+ 0.028657382144349246,
+ 0.02866476978457847,
+ 0.05306628003007997
+ ]
+ ],
+ "mass": 0.00022366924072572585,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Lactoferrin",
+ "nr_faces": 7738,
+ "nr_vertices": 3976,
+ "surface_area": 0.021045727266831106,
+ "volume": 0.00022366924072572585
+ }
+ },
+ "Lalaloopsy_Peanut_Big_Top_Tricycle": {
+ "asset_type": "FileBasedObject",
+ "id": "Lalaloopsy_Peanut_Big_Top_Tricycle",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05784649011346441,
+ -0.04223580867396261,
+ -0.03805083322065567
+ ],
+ [
+ 0.06055650988653559,
+ 0.046654191326037396,
+ 0.07092716677934433
+ ]
+ ],
+ "mass": 5.954256217736851e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Lalaloopsy Peanut Big Top Tricycle",
+ "nr_faces": 35664,
+ "nr_vertices": 20156,
+ "surface_area": 0.043658696973675824,
+ "volume": 5.954256217736851e-05
+ }
+ },
+ "Lavender_Snake_Tieks_Snake_Print_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Lavender_Snake_Tieks_Snake_Print_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04700656085491903,
+ -0.12131856738539983,
+ -0.0285761977832774
+ ],
+ [
+ 0.04126343914508097,
+ 0.12025843261460017,
+ 0.05289180221672261
+ ]
+ ],
+ "mass": 0.0004962050468986659,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Lavender Snake Tieks - Snake Print Ballet Flats\nAttract envious stares with these one-of-a-kind, snake print ballet flats. The lustrous combination of lavender, black, gold and pewter is sure to turn heads. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 27246,
+ "nr_vertices": 14541,
+ "surface_area": 0.07394614573009263,
+ "volume": 0.0004962050468986659
+ }
+ },
+ "Leap_Frog_Paint_Dabber_Dot_Art_5_paint_bottles": {
+ "asset_type": "FileBasedObject",
+ "id": "Leap_Frog_Paint_Dabber_Dot_Art_5_paint_bottles",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11698007394224641,
+ -0.02858417876152468,
+ -0.11544860033897664
+ ],
+ [
+ 0.11873692605775359,
+ 0.028597821238475322,
+ 0.11734739966102335
+ ]
+ ],
+ "mass": 0.0023422297076494012,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Leap Frog Paint Dabber Dot Art - 5 paint bottles",
+ "nr_faces": 1764,
+ "nr_vertices": 972,
+ "surface_area": 0.14592876297240936,
+ "volume": 0.0023422297076494012
+ }
+ },
+ "Lego_Friends_Advent_Calendar": {
+ "asset_type": "FileBasedObject",
+ "id": "Lego_Friends_Advent_Calendar",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19277275049288445,
+ -0.037922084646339484,
+ -0.13196294756258944
+ ],
+ [
+ 0.19226424950711557,
+ 0.037357915353660516,
+ 0.13150105243741056
+ ]
+ ],
+ "mass": 0.007118114423675312,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "Lego Friends Advent Calendar",
+ "nr_faces": 1880,
+ "nr_vertices": 1087,
+ "surface_area": 0.2814474159219249,
+ "volume": 0.007118114423675312
+ }
+ },
+ "Lego_Friends_Mia": {
+ "asset_type": "FileBasedObject",
+ "id": "Lego_Friends_Mia",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0446255424894343,
+ -0.10388220979679162,
+ -0.018206324403193426
+ ],
+ [
+ 0.0468594575105657,
+ 0.09500179020320837,
+ 0.05581467559680658
+ ]
+ ],
+ "mass": 0.00010012159577964732,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "Lego Friends, Mia",
+ "nr_faces": 36812,
+ "nr_vertices": 22524,
+ "surface_area": 0.0385989870955799,
+ "volume": 0.00010012159577964732
+ }
+ },
+ "Lenovo_Yoga_2_11": {
+ "asset_type": "FileBasedObject",
+ "id": "Lenovo_Yoga_2_11",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15002495162153004,
+ -0.1372425672937982,
+ -0.028198364594408387
+ ],
+ [
+ 0.14952704837846997,
+ 0.18267843270620182,
+ 0.1572086354055916
+ ]
+ ],
+ "mass": 0.0008747575511484342,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Lenovo Yoga 2 11",
+ "nr_faces": 5790,
+ "nr_vertices": 3124,
+ "surface_area": 0.25552352952280116,
+ "volume": 0.0008747575511484342
+ }
+ },
+ "Little_Big_Planet_3_Plush_Edition": {
+ "asset_type": "FileBasedObject",
+ "id": "Little_Big_Planet_3_Plush_Edition",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07160243485987998,
+ -0.04339753311206031,
+ -0.09057537891167367
+ ],
+ [
+ 0.07179456514012003,
+ 0.04370546688793969,
+ 0.08929162108832633
+ ]
+ ],
+ "mass": 0.002144704761178049,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Little Big Planet 3 Plush Edition",
+ "nr_faces": 4664,
+ "nr_vertices": 2459,
+ "surface_area": 0.10304398666401639,
+ "volume": 0.002144704761178049
+ }
+ },
+ "Little_Debbie_Chocolate_Cupcakes_8_ct": {
+ "asset_type": "FileBasedObject",
+ "id": "Little_Debbie_Chocolate_Cupcakes_8_ct",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14955171071888465,
+ -0.027788810053051904,
+ -0.08665452412017124
+ ],
+ [
+ 0.14887828928111535,
+ 0.027572189946948097,
+ 0.08671647587982877
+ ]
+ ],
+ "mass": 0.0026623663601850842,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Little Debbie Chocolate Cupcakes 8 ct",
+ "nr_faces": 3054,
+ "nr_vertices": 1614,
+ "surface_area": 0.14499243911471887,
+ "volume": 0.0026623663601850842
+ }
+ },
+ "Little_Debbie_Cloud_Cakes_10_ct": {
+ "asset_type": "FileBasedObject",
+ "id": "Little_Debbie_Cloud_Cakes_10_ct",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12118424046578184,
+ -0.04074732339666935,
+ -0.06888160240390528
+ ],
+ [
+ 0.12139575953421816,
+ 0.04075667660333065,
+ 0.07061939759609472
+ ]
+ ],
+ "mass": 0.0025475884081161315,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Little Debbie Cloud Cakes 10 ct",
+ "nr_faces": 2544,
+ "nr_vertices": 1393,
+ "surface_area": 0.1209194941086568,
+ "volume": 0.0025475884081161315
+ }
+ },
+ "Little_Debbie_Donut_Sticks_6_cake_donuts_10_oz_total": {
+ "asset_type": "FileBasedObject",
+ "id": "Little_Debbie_Donut_Sticks_6_cake_donuts_10_oz_total",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1559161717791286,
+ -0.018786273077336293,
+ -0.05627050399742694
+ ],
+ [
+ 0.1565398282208714,
+ 0.019201726922663708,
+ 0.05605949600257305
+ ]
+ ],
+ "mass": 0.0012259908541741643,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Little Debbie Donut, Sticks - 6 cake donuts, 10 oz total",
+ "nr_faces": 2364,
+ "nr_vertices": 1288,
+ "surface_area": 0.09503774769778085,
+ "volume": 0.0012259908541741643
+ }
+ },
+ "Little_House_on_the_Prairie_Season_Two_5_Discs_Includes_Digital": {
+ "asset_type": "FileBasedObject",
+ "id": "Little_House_on_the_Prairie_Season_Two_5_Discs_Includes_Digital",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07005772466974534,
+ -0.014445812856773346,
+ -0.09689515663957476
+ ],
+ [
+ 0.07159327533025465,
+ 0.014018187143226654,
+ 0.09670884336042523
+ ]
+ ],
+ "mass": 0.0006783695946413175,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Little House on the Prairie: Season Two (5 Discs) (Includes Digital",
+ "nr_faces": 5066,
+ "nr_vertices": 3050,
+ "surface_area": 0.069006550690217,
+ "volume": 0.0006783695946413175
+ }
+ },
+ "Logitech_Ultimate_Ears_Boom_Wireless_Speaker_Night_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Logitech_Ultimate_Ears_Boom_Wireless_Speaker_Night_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.053208533622137434,
+ -0.05118844611496599,
+ -0.12724479770759883
+ ],
+ [
+ 0.05263646637786256,
+ 0.05281355388503401,
+ 0.13342120229240118
+ ]
+ ],
+ "mass": 0.002062186000539533,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Logitech Ultimate Ears Boom Wireless Speaker - Night Black",
+ "nr_faces": 4594,
+ "nr_vertices": 2620,
+ "surface_area": 0.09975570203724045,
+ "volume": 0.002062186000539533
+ }
+ },
+ "Lovable_Huggable_Cuddly_Boutique_Teddy_Bear_Beige": {
+ "asset_type": "FileBasedObject",
+ "id": "Lovable_Huggable_Cuddly_Boutique_Teddy_Bear_Beige",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12412737148698154,
+ -0.20105785289992653,
+ -0.05004333435126369
+ ],
+ [
+ 0.1445776285130185,
+ 0.16955414710007347,
+ 0.07368666564873631
+ ]
+ ],
+ "mass": 0.003321233573745786,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Stuffed Toys",
+ "description": "Lovable Huggable Cuddly Boutique Teddy Bear Beige",
+ "nr_faces": 97684,
+ "nr_vertices": 84950,
+ "surface_area": 0.3288710000439184,
+ "volume": 0.003321233573745786
+ }
+ },
+ "Lovestruck_Tieks_Glittery_Rose_Gold_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Lovestruck_Tieks_Glittery_Rose_Gold_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04573241982018506,
+ -0.11813570373222414,
+ -0.027804613090808037
+ ],
+ [
+ 0.037892580179814936,
+ 0.1275442962677759,
+ 0.054809386909191966
+ ]
+ ],
+ "mass": 0.0005045579906081228,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Lovestruck Tieks - Glittery Rose Gold Italian Leather Ballet Flats\nCupid's latest creation comes in the form of glittery Lovestruck Tieks! These beautiful, rose gold ballet flats provide a sophisticated sparkle that brings any outfit to life. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 30450,
+ "nr_vertices": 16260,
+ "surface_area": 0.07784652201627078,
+ "volume": 0.0005045579906081228
+ }
+ },
+ "Luigis_Mansion_Dark_Moon_Nintendo_3DS_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Luigis_Mansion_Dark_Moon_Nintendo_3DS_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06691802032726414,
+ -0.06280853119664535,
+ -0.007593263230730815
+ ],
+ [
+ 0.07096297967273586,
+ 0.06254446880335464,
+ 0.008508736769269186
+ ]
+ ],
+ "mass": 0.00023191764718673218,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Luigi's Mansion: Dark Moon [Nintendo 3DS Game]",
+ "nr_faces": 4116,
+ "nr_vertices": 2163,
+ "surface_area": 0.04057374739673031,
+ "volume": 0.00023191764718673218
+ }
+ },
+ "Lutein": {
+ "asset_type": "FileBasedObject",
+ "id": "Lutein",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.027045689998751517,
+ -0.02698818817384661,
+ -0.04424479336657836
+ ],
+ [
+ 0.026893310001248484,
+ 0.02689581182615339,
+ 0.052954206633421645
+ ]
+ ],
+ "mass": 0.00019063812861451034,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Lutein",
+ "nr_faces": 8132,
+ "nr_vertices": 4183,
+ "surface_area": 0.019130260051737853,
+ "volume": 0.00019063812861451034
+ }
+ },
+ "MARTIN_WEDGE_LACE_BOOT": {
+ "asset_type": "FileBasedObject",
+ "id": "MARTIN_WEDGE_LACE_BOOT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06354230462323064,
+ -0.16282195651664316,
+ -0.053037479495657784
+ ],
+ [
+ 0.051450695376769356,
+ 0.13407104348335683,
+ 0.15231952050434222
+ ]
+ ],
+ "mass": 0.0015271647263694547,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "MARTIN WEDGE LACE BOOT\n*Lace boot in waterproof leather upper. *Fully lined. *Leather welt. *Vibram bottom for traction and comfort.",
+ "nr_faces": 27128,
+ "nr_vertices": 15675,
+ "surface_area": 0.2088128468945048,
+ "volume": 0.0015271647263694547
+ }
+ },
+ "MEAT_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "MEAT_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1273371931070816,
+ -0.07646814892862529,
+ -0.014349023809673131
+ ],
+ [
+ 0.1294378068929184,
+ 0.0867558510713747,
+ 0.026091976190326868
+ ]
+ ],
+ "mass": 0.00036735351184437196,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MEAT SET\nThis set includes steak, fish, sausage, a chicken drumstick, salami, bologna and a knife.",
+ "nr_faces": 9520,
+ "nr_vertices": 5459,
+ "surface_area": 0.06310556658304993,
+ "volume": 0.00036735351184437196
+ }
+ },
+ "MINI_EXCAVATOR": {
+ "asset_type": "FileBasedObject",
+ "id": "MINI_EXCAVATOR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04362476793370897,
+ -0.10155404215578229,
+ -0.05611332961138354
+ ],
+ [
+ 0.042103232066291026,
+ 0.06533095784421772,
+ 0.11552067038861646
+ ]
+ ],
+ "mass": 0.0005395213802542848,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MINI EXCAVATOR\nFeatures an adjustable arm and realistic shovel to make tough digging jobs easy.",
+ "nr_faces": 14226,
+ "nr_vertices": 8007,
+ "surface_area": 0.06290603387666184,
+ "volume": 0.0005395213802542848
+ }
+ },
+ "MINI_FIRE_ENGINE": {
+ "asset_type": "FileBasedObject",
+ "id": "MINI_FIRE_ENGINE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04350491962702511,
+ -0.07556802175672399,
+ -0.04913429878009746
+ ],
+ [
+ 0.07020708037297489,
+ 0.08000297824327601,
+ 0.12760970121990256
+ ]
+ ],
+ "mass": 0.0007527931997747796,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MINI FIRE ENGINE\nThis fiery vehicle features a movable ladder and rotatable cab.",
+ "nr_faces": 25254,
+ "nr_vertices": 15148,
+ "surface_area": 0.0830704403507334,
+ "volume": 0.0007527931997747796
+ }
+ },
+ "MINI_ROLLER": {
+ "asset_type": "FileBasedObject",
+ "id": "MINI_ROLLER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.044931743263285806,
+ -0.07404458498944314,
+ -0.04017531137920251
+ ],
+ [
+ 0.04334825673671419,
+ 0.06961641501055688,
+ 0.0646956886207975
+ ]
+ ],
+ "mass": 0.0005461614619924356,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MINI ROLLER\nFlatten out those bumps for a smooth ride! The roller on the front provides easy directional control.",
+ "nr_faces": 15596,
+ "nr_vertices": 8594,
+ "surface_area": 0.06277019350651111,
+ "volume": 0.0005461614619924356
+ }
+ },
+ "MIRACLE_POUNDING": {
+ "asset_type": "FileBasedObject",
+ "id": "MIRACLE_POUNDING",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13112410830622073,
+ -0.11846397082846709,
+ -0.06618356653643012
+ ],
+ [
+ 0.16217289169377927,
+ 0.049784029171532906,
+ 0.10151743346356987
+ ]
+ ],
+ "mass": 0.0012600741777334004,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MIRACLE POUNDING\nAs the ball is pounded with the wooden mallet, a new ball comes up to replace it. Great for developing hand-eye coordination.",
+ "nr_faces": 18824,
+ "nr_vertices": 12576,
+ "surface_area": 0.18467168032288614,
+ "volume": 0.0012600741777334004
+ }
+ },
+ "MK7": {
+ "asset_type": "FileBasedObject",
+ "id": "MK7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02404326281232902,
+ -0.023571736535843782,
+ -0.03984868839718414
+ ],
+ [
+ 0.023911737187670982,
+ 0.023631263464156217,
+ 0.04422131160281586
+ ]
+ ],
+ "mass": 0.000133137995937695,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "MK-7",
+ "nr_faces": 8356,
+ "nr_vertices": 4292,
+ "surface_area": 0.015098840474427812,
+ "volume": 0.000133137995937695
+ }
+ },
+ "MODERN_DOLL_FAMILY": {
+ "asset_type": "FileBasedObject",
+ "id": "MODERN_DOLL_FAMILY",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1133275328107951,
+ -0.03872421850204921,
+ -0.0622243063054518
+ ],
+ [
+ 0.0988384671892049,
+ 0.05688278149795079,
+ 0.0694636936945482
+ ]
+ ],
+ "mass": 0.00031562524595560635,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MODERN DOLL FAMILY\nFashionably clothed dolls scaled to fit PlanDollhouse.",
+ "nr_faces": 43750,
+ "nr_vertices": 25846,
+ "surface_area": 0.07778439408333501,
+ "volume": 0.00031562524595560635
+ }
+ },
+ "MONKEY_BOWLING": {
+ "asset_type": "FileBasedObject",
+ "id": "MONKEY_BOWLING",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14658466218883334,
+ -0.15076825575515815,
+ -0.06847237709986442
+ ],
+ [
+ 0.17764433781116667,
+ 0.07488774424484188,
+ 0.10558562290013558
+ ]
+ ],
+ "mass": 0.0012402581559301953,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MONKEY BOWLING\nThis game features 5 funky monkey pins and a monkey ball. Knock as many of the pins down to win!",
+ "nr_faces": 18946,
+ "nr_vertices": 10739,
+ "surface_area": 0.1390134579898358,
+ "volume": 0.0012402581559301953
+ }
+ },
+ "MOSAIC": {
+ "asset_type": "FileBasedObject",
+ "id": "MOSAIC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13690322633330163,
+ -0.08178043661764102,
+ -0.008642129006560703
+ ],
+ [
+ 0.13970277366669837,
+ 0.08225456338235898,
+ 0.010789870993439296
+ ]
+ ],
+ "mass": 0.00047342280253960344,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MOSAIC\nSay it with a mosaic! The set includes 50 two-toned blocks and a two-sided guide that features animal patterns and other various patterns that children can replicate.",
+ "nr_faces": 2822,
+ "nr_vertices": 1636,
+ "surface_area": 0.07348154892483172,
+ "volume": 0.00047342280253960344
+ }
+ },
+ "MOVING_MOUSE_PW_6PCSSET": {
+ "asset_type": "FileBasedObject",
+ "id": "MOVING_MOUSE_PW_6PCSSET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09266788690456698,
+ -0.06442145376298913,
+ -0.016000243376662206
+ ],
+ [
+ 0.08547111309543301,
+ 0.09389454623701086,
+ 0.018471756623337793
+ ]
+ ],
+ "mass": 0.00012470878405382066,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MOVING MOUSE (PW) - 6PCS/SET\nPropelled by a gear-box mechanism, the mouse can move forward when it is pulled backward and released.",
+ "nr_faces": 15806,
+ "nr_vertices": 9100,
+ "surface_area": 0.030878393314248527,
+ "volume": 0.00012470878405382066
+ }
+ },
+ "MY_MOOD_MEMO": {
+ "asset_type": "FileBasedObject",
+ "id": "MY_MOOD_MEMO",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16737577745178803,
+ -0.16970719717315264,
+ -0.009857564326514554
+ ],
+ [
+ 0.171395222548212,
+ 0.16751680282684736,
+ 0.011910435673485445
+ ]
+ ],
+ "mass": 0.0006283285474680967,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "MY MOOD MEMO\nThe set consists of 24 wooden tiles with 12 different emotions. Children can learn how to match two identical emotions with this fun memory game! Skills include learning about the relationship of colors and emotions. Emotion Color Wheel can help visually group feeling and practice emotion vocabulary.",
+ "nr_faces": 15014,
+ "nr_vertices": 8211,
+ "surface_area": 0.1738529862098238,
+ "volume": 0.0006283285474680967
+ }
+ },
+ "Mad_Gab_Refresh_Card_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Mad_Gab_Refresh_Card_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07807432797852737,
+ -0.07797752481408374,
+ -0.07822314845240484
+ ],
+ [
+ 0.07779167202147262,
+ 0.07802647518591627,
+ 0.07768185154759516
+ ]
+ ],
+ "mass": 0.0036692633414324043,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Mad Gab Refresh Card Game",
+ "nr_faces": 4622,
+ "nr_vertices": 2598,
+ "surface_area": 0.1408770355713348,
+ "volume": 0.0036692633414324043
+ }
+ },
+ "Magnifying_Glassassrt": {
+ "asset_type": "FileBasedObject",
+ "id": "Magnifying_Glassassrt",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07754821235835355,
+ -0.030206946439537218,
+ -0.007896307316434937
+ ],
+ [
+ 0.07428778764164647,
+ 0.030225053560462782,
+ 0.009107692683565063
+ ]
+ ],
+ "mass": 3.17734891241345e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Magnifying Glass-assrt",
+ "nr_faces": 6944,
+ "nr_vertices": 3691,
+ "surface_area": 0.011703552316761765,
+ "volume": 3.17734891241345e-05
+ }
+ },
+ "Marc_Anthony_Skip_Professional_Oil_of_Morocco_Conditioner_with_Argan_Oil": {
+ "asset_type": "FileBasedObject",
+ "id": "Marc_Anthony_Skip_Professional_Oil_of_Morocco_Conditioner_with_Argan_Oil",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0368133085628394,
+ -0.023851891541967082,
+ -0.08086272443539166
+ ],
+ [
+ 0.03758669143716059,
+ 0.024565108458032916,
+ 0.11127027556460832
+ ]
+ ],
+ "mass": 0.00028540773686047476,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Marc Anthony Skip Professional Oil of Morocco Conditioner with Argan Oil",
+ "nr_faces": 2694,
+ "nr_vertices": 1417,
+ "surface_area": 0.03125889943877247,
+ "volume": 0.00028540773686047476
+ }
+ },
+ "Marc_Anthony_Strictly_Curls_Curl_Envy_Perfect_Curl_Cream_6_fl_oz_bottle": {
+ "asset_type": "FileBasedObject",
+ "id": "Marc_Anthony_Strictly_Curls_Curl_Envy_Perfect_Curl_Cream_6_fl_oz_bottle",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.042400455109873135,
+ -0.028147538905083633,
+ -0.11155986870187472
+ ],
+ [
+ 0.04170254489012687,
+ 0.02785346109491637,
+ 0.11190413129812526
+ ]
+ ],
+ "mass": 0.0009183787029902349,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Marc Anthony Strictly Curls Curl Envy Perfect Curl Cream - 6 fl oz bottle",
+ "nr_faces": 4828,
+ "nr_vertices": 2515,
+ "surface_area": 0.06406720431639285,
+ "volume": 0.0009183787029902349
+ }
+ },
+ "Marc_Anthony_True_Professional_Oil_of_Morocco_Argan_Oil_Treatment": {
+ "asset_type": "FileBasedObject",
+ "id": "Marc_Anthony_True_Professional_Oil_of_Morocco_Argan_Oil_Treatment",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03317600033822795,
+ -0.020034282714756,
+ -0.08136807398978645
+ ],
+ [
+ 0.03363899966177205,
+ 0.019874717285244,
+ 0.08101592601021355
+ ]
+ ],
+ "mass": 0.00040643968503630294,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Marc Anthony True Professional Oil of Morocco Argan Oil Treatment",
+ "nr_faces": 6076,
+ "nr_vertices": 3144,
+ "surface_area": 0.037473194997089135,
+ "volume": 0.00040643968503630294
+ }
+ },
+ "Marc_Anthony_True_Professional_Strictly_Curls_Curl_Defining_Lotion": {
+ "asset_type": "FileBasedObject",
+ "id": "Marc_Anthony_True_Professional_Strictly_Curls_Curl_Defining_Lotion",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.029999564832890815,
+ -0.025138004894060147,
+ -0.08459695836592752
+ ],
+ [
+ 0.026661435167109185,
+ 0.025556995105939853,
+ 0.11068904163407246
+ ]
+ ],
+ "mass": 0.00030914984668852234,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Marc Anthony True Professional Strictly Curls Curl Defining Lotion",
+ "nr_faces": 2066,
+ "nr_vertices": 1094,
+ "surface_area": 0.0319268835080303,
+ "volume": 0.00030914984668852234
+ }
+ },
+ "Mario_Luigi_Dream_Team_Nintendo_3DS_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Mario_Luigi_Dream_Team_Nintendo_3DS_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.066937913584159,
+ -0.06206999251175457,
+ -0.0076365586187622505
+ ],
+ [
+ 0.070542086415841,
+ 0.06307000748824543,
+ 0.00864944138123775
+ ]
+ ],
+ "mass": 0.00023380487094804318,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Mario & Luigi: Dream Team [Nintendo 3DS Game]",
+ "nr_faces": 2536,
+ "nr_vertices": 1359,
+ "surface_area": 0.04048916668834618,
+ "volume": 0.00023380487094804318
+ }
+ },
+ "Mario_Party_9_Wii_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Mario_Party_9_Wii_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06631570955757271,
+ -0.09560729718097288,
+ -0.00837546575392635
+ ],
+ [
+ 0.07063329044242728,
+ 0.09564970281902713,
+ 0.00885653424607365
+ ]
+ ],
+ "mass": 0.0003748818857065442,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Mario Party 9 [Wii Game]",
+ "nr_faces": 2802,
+ "nr_vertices": 1523,
+ "surface_area": 0.061900290536406354,
+ "volume": 0.0003748818857065442
+ }
+ },
+ "Markings_Desk_Caddy": {
+ "asset_type": "FileBasedObject",
+ "id": "Markings_Desk_Caddy",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05655135164269577,
+ -0.13702892780395756,
+ -0.03700359648023987
+ ],
+ [
+ 0.04864764835730423,
+ 0.15631507219604243,
+ 0.07593540351976014
+ ]
+ ],
+ "mass": 0.0007400839434684283,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Markings Desk Caddy",
+ "nr_faces": 24970,
+ "nr_vertices": 13173,
+ "surface_area": 0.22017177701296495,
+ "volume": 0.0007400839434684283
+ }
+ },
+ "Markings_Letter_Holder": {
+ "asset_type": "FileBasedObject",
+ "id": "Markings_Letter_Holder",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.046185109272436936,
+ -0.09828536634544979,
+ -0.03771608240317
+ ],
+ [
+ 0.05357189072756307,
+ 0.10008763365455021,
+ 0.10327791759683
+ ]
+ ],
+ "mass": 0.0006004463960396314,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Markings Letter Holder",
+ "nr_faces": 19340,
+ "nr_vertices": 9973,
+ "surface_area": 0.15726421802912122,
+ "volume": 0.0006004463960396314
+ }
+ },
+ "Marvel_Avengers_Titan_Hero_Series_Doctor_Doom": {
+ "asset_type": "FileBasedObject",
+ "id": "Marvel_Avengers_Titan_Hero_Series_Doctor_Doom",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0877709877124793,
+ -0.04459664521705705,
+ -0.16113168465476846
+ ],
+ [
+ 0.0845200122875207,
+ 0.03516735478294295,
+ 0.13055431534523154
+ ]
+ ],
+ "mass": 0.0005990350698236889,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Marvel Avengers Titan Hero Series, Doctor Doom",
+ "nr_faces": 23082,
+ "nr_vertices": 12855,
+ "surface_area": 0.11846561712602596,
+ "volume": 0.0005990350698236889
+ }
+ },
+ "Mastic_Gum": {
+ "asset_type": "FileBasedObject",
+ "id": "Mastic_Gum",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.027215284036615925,
+ -0.027147438828243005,
+ -0.04431016892341639
+ ],
+ [
+ 0.027145715963384075,
+ 0.026924561171756994,
+ 0.05295383107658361
+ ]
+ ],
+ "mass": 0.0001911196362475258,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Mastic Gum",
+ "nr_faces": 7782,
+ "nr_vertices": 4010,
+ "surface_area": 0.01910075105479444,
+ "volume": 0.0001911196362475258
+ }
+ },
+ "Matte_Black_Tieks_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Matte_Black_Tieks_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.045016933014995354,
+ -0.1146054735165816,
+ -0.02972314424164683
+ ],
+ [
+ 0.036883066985004646,
+ 0.12627152648341838,
+ 0.052660855758353164
+ ]
+ ],
+ "mass": 0.000499218652501938,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Matte Black Tieks - Italian Leather Ballet Flats\nThese black ballet flats are a wardrobe essential. Wear them with anything from skinny jeans to your favorite little black dress. Reminiscent of the classic elegance of Jackie O. and Audrey Hepburn, Matte Black Tieks are sure to polish off any look. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 22308,
+ "nr_vertices": 11965,
+ "surface_area": 0.07159687828247827,
+ "volume": 0.000499218652501938
+ }
+ },
+ "Mattel_SKIP_BO_Card_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Mattel_SKIP_BO_Card_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.015170621267131165,
+ -0.04904507314089968,
+ -0.0936582691730197
+ ],
+ [
+ 0.015503378732868835,
+ 0.04869392685910032,
+ 0.11094273082698031
+ ]
+ ],
+ "mass": 0.00041787271878010245,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Mattel SKIP BO Card Game",
+ "nr_faces": 3474,
+ "nr_vertices": 1941,
+ "surface_area": 0.05046637663918489,
+ "volume": 0.00041787271878010245
+ }
+ },
+ "Melissa_Doug_Cart_Turtle_Block": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_Cart_Turtle_Block",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13248869728613505,
+ -0.20699030556231351,
+ -0.04460295776188753
+ ],
+ [
+ 0.14074930271386496,
+ 0.1451746944376865,
+ 0.025074042238112465
+ ]
+ ],
+ "mass": 0.002098273605789126,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Melissa & Doug Cart, Turtle Block",
+ "nr_faces": 9774,
+ "nr_vertices": 5688,
+ "surface_area": 0.21898841682483103,
+ "volume": 0.002098273605789126
+ }
+ },
+ "Melissa_Doug_Chunky_Puzzle_Vehicles": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_Chunky_Puzzle_Vehicles",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1530918010517897,
+ -0.11824593130461605,
+ -0.010273823360164294
+ ],
+ [
+ 0.15176319894821028,
+ 0.11149106869538394,
+ 0.01624917663983571
+ ]
+ ],
+ "mass": 0.0010172950769390943,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Melissa & Doug Chunky Puzzle Vehicles",
+ "nr_faces": 9798,
+ "nr_vertices": 5895,
+ "surface_area": 0.17158551862283966,
+ "volume": 0.0010172950769390943
+ }
+ },
+ "Melissa_Doug_Felt_Food_Pizza_Set": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_Felt_Food_Pizza_Set",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13698877676841187,
+ -0.13961569794577777,
+ -0.016651689735088657
+ ],
+ [
+ 0.14001322323158813,
+ 0.13735430205422225,
+ 0.027279310264911344
+ ]
+ ],
+ "mass": 0.001233858571759922,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Melissa & Doug Felt Food, Pizza Set",
+ "nr_faces": 33188,
+ "nr_vertices": 20268,
+ "surface_area": 0.19562963539314376,
+ "volume": 0.001233858571759922
+ }
+ },
+ "Melissa_Doug_Jumbo_Knob_Puzzles_Barnyard_Animals": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_Jumbo_Knob_Puzzles_Barnyard_Animals",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14500109454339077,
+ -0.12888970514151998,
+ -0.009204774276499766
+ ],
+ [
+ 0.14694590545660924,
+ 0.16637129485848,
+ 0.03576022572350023
+ ]
+ ],
+ "mass": 0.000977403931486499,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Melissa & Doug Jumbo Knob Puzzles, Barnyard Animals",
+ "nr_faces": 3694,
+ "nr_vertices": 2083,
+ "surface_area": 0.15461258995956242,
+ "volume": 0.000977403931486499
+ }
+ },
+ "Melissa_Doug_Pattern_Blocks_and_Boards": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_Pattern_Blocks_and_Boards",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19257335463420797,
+ -0.16556717986819758,
+ -0.013588572432555197
+ ],
+ [
+ 0.18879364536579202,
+ 0.16964782013180243,
+ 0.017318427567444804
+ ]
+ ],
+ "mass": 0.001127835862674217,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Melissa & Doug Pattern Blocks and Boards",
+ "nr_faces": 5376,
+ "nr_vertices": 3247,
+ "surface_area": 0.1450075594214092,
+ "volume": 0.001127835862674217
+ }
+ },
+ "Melissa_Doug_Pound_and_Roll": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_Pound_and_Roll",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14893273738797697,
+ -0.07319808535160283,
+ -0.07890855118025462
+ ],
+ [
+ 0.08054926261202303,
+ 0.06935791464839716,
+ 0.10008644881974538
+ ]
+ ],
+ "mass": 0.0013093126684997156,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Melissa & Doug Pound and Roll",
+ "nr_faces": 13170,
+ "nr_vertices": 7681,
+ "surface_area": 0.21910131911183253,
+ "volume": 0.0013093126684997156
+ }
+ },
+ "Melissa_Doug_See_Spell": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_See_Spell",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18009170519437792,
+ -0.02422702543294789,
+ -0.11912996696613345
+ ],
+ [
+ 0.18119029480562207,
+ 0.021701974567052112,
+ 0.12122603303386656
+ ]
+ ],
+ "mass": 0.003375879217432347,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Melissa & Doug See & Spell",
+ "nr_faces": 7750,
+ "nr_vertices": 4346,
+ "surface_area": 0.22838627265554398,
+ "volume": 0.003375879217432347
+ }
+ },
+ "Melissa_Doug_Shape_Sorting_Clock": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_Shape_Sorting_Clock",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15213860983677527,
+ -0.15827263125479976,
+ -0.02033362567096147
+ ],
+ [
+ 0.15431339016322473,
+ 0.14677336874520025,
+ 0.03978437432903853
+ ]
+ ],
+ "mass": 0.0017114448241657796,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Melissa & Doug Shape Sorting Clock",
+ "nr_faces": 7554,
+ "nr_vertices": 4610,
+ "surface_area": 0.19397000737338216,
+ "volume": 0.0017114448241657796
+ }
+ },
+ "Melissa_Doug_Traffic_Signs_and_Vehicles": {
+ "asset_type": "FileBasedObject",
+ "id": "Melissa_Doug_Traffic_Signs_and_Vehicles",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17018081348946604,
+ -0.025065891893309794,
+ -0.11056734829619405
+ ],
+ [
+ 0.17922418651053396,
+ 0.021254108106690206,
+ 0.10652665170380594
+ ]
+ ],
+ "mass": 0.0021201353322507564,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Melissa & Doug Traffic Signs and Vehicles",
+ "nr_faces": 14714,
+ "nr_vertices": 8660,
+ "surface_area": 0.2924510890827986,
+ "volume": 0.0021201353322507564
+ }
+ },
+ "Mens_ASV_Billfish_Boat_Shoe_in_Dark_Brown_Leather_zdHVHXueI3w": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_ASV_Billfish_Boat_Shoe_in_Dark_Brown_Leather_zdHVHXueI3w",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059200412226600774,
+ -0.14151170829296025,
+ -0.031746853684480485
+ ],
+ [
+ 0.049799587773399226,
+ 0.15111829170703975,
+ 0.07552514631551951
+ ]
+ ],
+ "mass": 0.0010550890862000106,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's ASV Billfish Boat Shoe in Dark Brown Leather\nMen's ASV Billfish Boat Shoe",
+ "nr_faces": 21364,
+ "nr_vertices": 11737,
+ "surface_area": 0.12648246600852836,
+ "volume": 0.0010550890862000106
+ }
+ },
+ "Mens_ASV_Billfish_Boat_Shoe_in_Tan_Leather_wmUJ5PbwANc": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_ASV_Billfish_Boat_Shoe_in_Tan_Leather_wmUJ5PbwANc",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.057800136293852444,
+ -0.13517160697194103,
+ -0.03235096690014493
+ ],
+ [
+ 0.05063986370614756,
+ 0.15147339302805898,
+ 0.07350403309985507
+ ]
+ ],
+ "mass": 0.0010617726221762707,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's ASV Billfish Boat Shoe in Tan Leather\nMen's ASV Billfish Boat Shoe",
+ "nr_faces": 21110,
+ "nr_vertices": 11142,
+ "surface_area": 0.12321613612417077,
+ "volume": 0.0010617726221762707
+ }
+ },
+ "Mens_ASV_Shock_Light_Bungee_in_Light_Grey_xGCOvtLDnQJ": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_ASV_Shock_Light_Bungee_in_Light_Grey_xGCOvtLDnQJ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059784999444663714,
+ -0.1440391549473715,
+ -0.03024262502221511
+ ],
+ [
+ 0.04757900055533629,
+ 0.1432858450526285,
+ 0.0875623749777849
+ ]
+ ],
+ "mass": 0.0008418296685232,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's ASV Shock Light Bungee in Light Grey\nMen's ASV Shock Light Bungee",
+ "nr_faces": 38368,
+ "nr_vertices": 21022,
+ "surface_area": 0.15140945136662629,
+ "volume": 0.0008418296685232
+ }
+ },
+ "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_NHHQddDLQys": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_NHHQddDLQys",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.055939701236136244,
+ -0.1441079327259097,
+ -0.02513303144165963
+ ],
+ [
+ 0.048972298763863754,
+ 0.14467506727409032,
+ 0.06543196855834038
+ ]
+ ],
+ "mass": 0.0006893257909451034,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Authentic Original Boat Shoe in Navy Leather\nMen's Authentic Original Boat Shoe",
+ "nr_faces": 28948,
+ "nr_vertices": 17504,
+ "surface_area": 0.13279931881499768,
+ "volume": 0.0006893257909451034
+ }
+ },
+ "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_RpT4GvUXRRP": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_RpT4GvUXRRP",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1181250213626566,
+ -0.043055001532689874,
+ -0.02495746601648748
+ ],
+ [
+ 0.1316909786373434,
+ 0.04679099846731013,
+ 0.055995533983512515
+ ]
+ ],
+ "mass": 0.0005136538169351742,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Authentic Original Boat Shoe in Navy Leather\nMen's Authentic Original Boat Shoe",
+ "nr_faces": 19030,
+ "nr_vertices": 9946,
+ "surface_area": 0.0866027872954118,
+ "volume": 0.0005136538169351742
+ }
+ },
+ "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_xgoEcZtRNmH": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_xgoEcZtRNmH",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0492598190477087,
+ -0.11763543491230083,
+ -0.02510675484736173
+ ],
+ [
+ 0.0422771809522913,
+ 0.13241456508769917,
+ 0.05592824515263827
+ ]
+ ],
+ "mass": 0.0005293232724506434,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Authentic Original Boat Shoe in Navy Leather\nMen's Authentic Original Boat Shoe",
+ "nr_faces": 19012,
+ "nr_vertices": 9981,
+ "surface_area": 0.08688346688551564,
+ "volume": 0.0005293232724506434
+ }
+ },
+ "Mens_Bahama_in_Black_b4ADzYywRHl": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Bahama_in_Black_b4ADzYywRHl",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.055553349920134845,
+ -0.13082123973890436,
+ -0.028156272399926106
+ ],
+ [
+ 0.04787265007986515,
+ 0.15612376026109565,
+ 0.0735997276000739
+ ]
+ ],
+ "mass": 0.0007670094362488078,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Bahama in Black\nMen's Bahama",
+ "nr_faces": 21270,
+ "nr_vertices": 11056,
+ "surface_area": 0.12074302384422989,
+ "volume": 0.0007670094362488078
+ }
+ },
+ "Mens_Bahama_in_Khaki_Oyster_xU2jeqYwhQJ": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Bahama_in_Khaki_Oyster_xU2jeqYwhQJ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05532286161248069,
+ -0.1298021271395265,
+ -0.028054030917696444
+ ],
+ [
+ 0.048055138387519306,
+ 0.1573638728604735,
+ 0.06101696908230356
+ ]
+ ],
+ "mass": 0.0008329774778321592,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Bahama in Khaki Oyster\nMen's Bahama",
+ "nr_faces": 20600,
+ "nr_vertices": 10724,
+ "surface_area": 0.11809141501458603,
+ "volume": 0.0008329774778321592
+ }
+ },
+ "Mens_Bahama_in_White_vSwvGMCo32f": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Bahama_in_White_vSwvGMCo32f",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05854561811176941,
+ -0.13445094218264086,
+ -0.027433639406143916
+ ],
+ [
+ 0.047091381888230595,
+ 0.15276705781735914,
+ 0.06846536059385608
+ ]
+ ],
+ "mass": 0.0008283797474007227,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Bahama in White\nMen's Bahama",
+ "nr_faces": 23030,
+ "nr_vertices": 12683,
+ "surface_area": 0.11919901167728436,
+ "volume": 0.0008283797474007227
+ }
+ },
+ "Mens_Billfish_3Eye_Boat_Shoe_in_Dark_Tan_wyns9HRcEuH": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Billfish_3Eye_Boat_Shoe_in_Dark_Tan_wyns9HRcEuH",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05936586931148259,
+ -0.14958189802071972,
+ -0.031704949058285
+ ],
+ [
+ 0.05132413068851741,
+ 0.14274010197928028,
+ 0.07323605094171501
+ ]
+ ],
+ "mass": 0.000936555887893302,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Billfish 3-Eye Boat Shoe in Dark Tan\nMen's Billfish 3-Eye Boat Shoe",
+ "nr_faces": 23618,
+ "nr_vertices": 12889,
+ "surface_area": 0.14764212345846944,
+ "volume": 0.000936555887893302
+ }
+ },
+ "Mens_Billfish_Slip_On_in_Coffee_e8bPKE9Lfgo": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Billfish_Slip_On_in_Coffee_e8bPKE9Lfgo",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13738815160194676,
+ -0.06127269501157386,
+ -0.02749107013556806
+ ],
+ [
+ 0.14888584839805324,
+ 0.05718530498842614,
+ 0.07963392986443193
+ ]
+ ],
+ "mass": 0.00084544369783664,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Billfish Slip On in Coffee\nMen's Billfish Slip On",
+ "nr_faces": 21450,
+ "nr_vertices": 11144,
+ "surface_area": 0.12617374816510385,
+ "volume": 0.00084544369783664
+ }
+ },
+ "Mens_Billfish_Slip_On_in_Coffee_nK6AJJAHOae": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Billfish_Slip_On_in_Coffee_nK6AJJAHOae",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0696704519155245,
+ -0.13534418858928976,
+ -0.02822795972883129
+ ],
+ [
+ 0.0508255480844755,
+ 0.15101381141071024,
+ 0.0700660402711687
+ ]
+ ],
+ "mass": 0.0007011065119040549,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Billfish Slip On in Coffee\nMen's Billfish Slip On",
+ "nr_faces": 19276,
+ "nr_vertices": 10246,
+ "surface_area": 0.12552730502994358,
+ "volume": 0.0007011065119040549
+ }
+ },
+ "Mens_Billfish_Slip_On_in_Tan_Beige_aaVUk0tNTv8": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Billfish_Slip_On_in_Tan_Beige_aaVUk0tNTv8",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05583134926003351,
+ -0.13601849555271195,
+ -0.031373906273418996
+ ],
+ [
+ 0.048466650739966484,
+ 0.15504850444728807,
+ 0.079464093726581
+ ]
+ ],
+ "mass": 0.0010924612753183485,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Billfish Slip On in Tan Beige\nMen's Billfish Slip On",
+ "nr_faces": 19680,
+ "nr_vertices": 10281,
+ "surface_area": 0.11029585921984761,
+ "volume": 0.0010924612753183485
+ }
+ },
+ "Mens_Billfish_Ultra_Lite_Boat_Shoe_in_Dark_Brown_Blue_c6zDZTtRJr6": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Billfish_Ultra_Lite_Boat_Shoe_in_Dark_Brown_Blue_c6zDZTtRJr6",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05810358722539398,
+ -0.14067103596839303,
+ -0.03059628695622767
+ ],
+ [
+ 0.04726641277460602,
+ 0.15102196403160698,
+ 0.07497271304377233
+ ]
+ ],
+ "mass": 0.0009151542752758214,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Billfish Ultra Lite Boat Shoe in Dark Brown / Blue\nMen's Billfish Ultra Lite Boat Shoe",
+ "nr_faces": 32020,
+ "nr_vertices": 17167,
+ "surface_area": 0.1333569342564908,
+ "volume": 0.0009151542752758214
+ }
+ },
+ "Mens_Gold_Cup_ASV_2Eye_Boat_Shoe_in_Cognac_Leather": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Gold_Cup_ASV_2Eye_Boat_Shoe_in_Cognac_Leather",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059111665240594406,
+ -0.14205236502273189,
+ -0.031401393388115914
+ ],
+ [
+ 0.0521263347594056,
+ 0.15125063497726815,
+ 0.06768960661188408
+ ]
+ ],
+ "mass": 0.0009296177207696269,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Gold Cup ASV 2-Eye Boat Shoe in Cognac Leather\nMen's Gold Cup ASV 2-Eye Boat Shoe",
+ "nr_faces": 24598,
+ "nr_vertices": 12896,
+ "surface_area": 0.1307173605778142,
+ "volume": 0.0009296177207696269
+ }
+ },
+ "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_EjPnk3E8fCs": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_EjPnk3E8fCs",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05271294045754407,
+ -0.1437794654792543,
+ -0.03130832513729039
+ ],
+ [
+ 0.04881105954245593,
+ 0.1465725345207457,
+ 0.07001067486270962
+ ]
+ ],
+ "mass": 0.000795844145422897,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Gold Cup ASV Capetown Penny Loafer in Black\nMen's Gold Cup ASV Capetown Penny Loafer",
+ "nr_faces": 28192,
+ "nr_vertices": 14432,
+ "surface_area": 0.12045051875819246,
+ "volume": 0.000795844145422897
+ }
+ },
+ "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_GkQBKqABeQN": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_GkQBKqABeQN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05420432030794805,
+ -0.1446658117701587,
+ -0.03167629961170117
+ ],
+ [
+ 0.04929567969205195,
+ 0.1454681882298413,
+ 0.07045470038829883
+ ]
+ ],
+ "mass": 0.0008004139009768608,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Gold Cup ASV Capetown Penny Loafer in Black\nMen's Gold Cup ASV Capetown Penny Loafer",
+ "nr_faces": 25360,
+ "nr_vertices": 13121,
+ "surface_area": 0.1240329802802597,
+ "volume": 0.0008004139009768608
+ }
+ },
+ "Mens_Gold_Cup_ASV_Dress_Casual_Venetian_in_Dark_Brown_Leather": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Gold_Cup_ASV_Dress_Casual_Venetian_in_Dark_Brown_Leather",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.057861581004909825,
+ -0.1567436864769764,
+ -0.0296211680235255
+ ],
+ [
+ 0.049382418995090174,
+ 0.1378823135230236,
+ 0.0768848319764745
+ ]
+ ],
+ "mass": 0.0009065455708502862,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Gold Cup ASV Dress Casual Venetian in Dark Brown Leather\nMen's Gold Cup ASV Dress Casual Venetian",
+ "nr_faces": 20090,
+ "nr_vertices": 10484,
+ "surface_area": 0.12619853810404336,
+ "volume": 0.0009065455708502862
+ }
+ },
+ "Mens_Largo_Slip_On_in_Taupe_gooyS417q4R": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Largo_Slip_On_in_Taupe_gooyS417q4R",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1438812028296203,
+ -0.05687710247099492,
+ -0.027136199284628845
+ ],
+ [
+ 0.1513887971703797,
+ 0.05538189752900508,
+ 0.06231680071537116
+ ]
+ ],
+ "mass": 0.0009246374472292988,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Largo Slip On in Taupe\nMen's Largo Slip On",
+ "nr_faces": 19398,
+ "nr_vertices": 10008,
+ "surface_area": 0.12513058719909473,
+ "volume": 0.0009246374472292988
+ }
+ },
+ "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_9d05GG33QQQ": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_9d05GG33QQQ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05708626078898821,
+ -0.142139277804958,
+ -0.03018663146870482
+ ],
+ [
+ 0.04759073921101179,
+ 0.148831722195042,
+ 0.06873436853129519
+ ]
+ ],
+ "mass": 0.0008372059307146715,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Mako Canoe Moc 2-Eye Boat Shoe in Coffee\nMen's Mako Canoe Moc 2-Eye Boat Shoe",
+ "nr_faces": 20804,
+ "nr_vertices": 11537,
+ "surface_area": 0.12986399462453824,
+ "volume": 0.0008372059307146715
+ }
+ },
+ "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_K9e8FoV73uZ": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_K9e8FoV73uZ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.057353138383805395,
+ -0.14143342522014773,
+ -0.022659521734554957
+ ],
+ [
+ 0.054053861616194604,
+ 0.14579357477985225,
+ 0.07227947826544505
+ ]
+ ],
+ "mass": 0.0005556145719994533,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Mako Canoe Moc 2-Eye Boat Shoe in Coffee\nMen's Mako Canoe Moc 2-Eye Boat Shoe",
+ "nr_faces": 21168,
+ "nr_vertices": 11325,
+ "surface_area": 0.12188199810557974,
+ "volume": 0.0005556145719994533
+ }
+ },
+ "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_OysterTaupe_otyRrfvPMiA": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_OysterTaupe_otyRrfvPMiA",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05666227044005047,
+ -0.13759843003429853,
+ -0.03070571488804509
+ ],
+ [
+ 0.050899729559949536,
+ 0.15022356996570146,
+ 0.0677322851119549
+ ]
+ ],
+ "mass": 0.0009055177507106148,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Mako Canoe Moc 2-Eye Boat Shoe in Oyster/Taupe\nMen's Mako Canoe Moc 2-Eye Boat Shoe",
+ "nr_faces": 17868,
+ "nr_vertices": 9964,
+ "surface_area": 0.1239669119594898,
+ "volume": 0.0009055177507106148
+ }
+ },
+ "Mens_RR_Moc_in_Navy_Suede_vmFfijhBzL3": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_RR_Moc_in_Navy_Suede_vmFfijhBzL3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06608548879545274,
+ -0.13203011041894858,
+ -0.028419839948245994
+ ],
+ [
+ 0.04925151120454725,
+ 0.15462488958105142,
+ 0.06932416005175401
+ ]
+ ],
+ "mass": 0.0007434700433930523,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's R&R Moc in Navy Suede\nMen's R&R Moc",
+ "nr_faces": 19406,
+ "nr_vertices": 10376,
+ "surface_area": 0.12473361899157508,
+ "volume": 0.0007434700433930523
+ }
+ },
+ "Mens_Santa_Cruz_Thong_in_Chocolate_La1fo2mAovE": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Santa_Cruz_Thong_in_Chocolate_La1fo2mAovE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1466275067389479,
+ -0.060739783972917925,
+ -0.0197158674873573
+ ],
+ [
+ 0.14576449326105212,
+ 0.057823216027082076,
+ 0.06445813251264271
+ ]
+ ],
+ "mass": 0.0006182785488924407,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Santa Cruz Thong in Chocolate\nMen's Santa Cruz Thong",
+ "nr_faces": 10358,
+ "nr_vertices": 5664,
+ "surface_area": 0.08593397335513797,
+ "volume": 0.0006182785488924407
+ }
+ },
+ "Mens_Santa_Cruz_Thong_in_Chocolate_lvxYW7lek6B": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Santa_Cruz_Thong_in_Chocolate_lvxYW7lek6B",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07046178231487032,
+ -0.14782450685856513,
+ -0.01973404462797557
+ ],
+ [
+ 0.06368221768512967,
+ 0.14409949314143486,
+ 0.06396595537202443
+ ]
+ ],
+ "mass": 0.0006192902747065314,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Santa Cruz Thong in Chocolate\nMen's Santa Cruz Thong",
+ "nr_faces": 11674,
+ "nr_vertices": 6232,
+ "surface_area": 0.08599261287017447,
+ "volume": 0.0006192902747065314
+ }
+ },
+ "Mens_Santa_Cruz_Thong_in_Tan_r59C69daRPh": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Santa_Cruz_Thong_in_Tan_r59C69daRPh",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05700406665422378,
+ -0.14718312193399663,
+ -0.018942440378126767
+ ],
+ [
+ 0.06296593334577621,
+ 0.14641687806600337,
+ 0.06119355962187324
+ ]
+ ],
+ "mass": 0.0006337420871559593,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Santa Cruz Thong in Tan\nMen's Santa Cruz Thong",
+ "nr_faces": 11918,
+ "nr_vertices": 6420,
+ "surface_area": 0.0858983846890219,
+ "volume": 0.0006337420871559593
+ }
+ },
+ "Mens_Striper_Sneaker_in_White_rnp8HUli59Y": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Striper_Sneaker_in_White_rnp8HUli59Y",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05561552787178468,
+ -0.14685856714155143,
+ -0.030037845776856736
+ ],
+ [
+ 0.048660472128215324,
+ 0.1386854328584486,
+ 0.07105015422314326
+ ]
+ ],
+ "mass": 0.0008065122486304336,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Striper Sneaker in White\nMen's Striper Sneaker",
+ "nr_faces": 27882,
+ "nr_vertices": 15536,
+ "surface_area": 0.13777935433585312,
+ "volume": 0.0008065122486304336
+ }
+ },
+ "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05668949951713033,
+ -0.14261030705085712,
+ -0.025049197771111312
+ ],
+ [
+ 0.04931350048286967,
+ 0.1524166929491429,
+ 0.06774580222888868
+ ]
+ ],
+ "mass": 0.0006575131557636176,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Tremont Kiltie Tassel Loafer in Black Amaretto\nMen's Tremont Kiltie Tassel Loafer",
+ "nr_faces": 29246,
+ "nr_vertices": 15665,
+ "surface_area": 0.1284329847916852,
+ "volume": 0.0006575131557636176
+ }
+ },
+ "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_FT0I9OjSA6O": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_FT0I9OjSA6O",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056064524642256613,
+ -0.14400245975209144,
+ -0.024921705314743775
+ ],
+ [
+ 0.050095475357743384,
+ 0.15129354024790856,
+ 0.06791629468525623
+ ]
+ ],
+ "mass": 0.0006499269608217513,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Tremont Kiltie Tassel Loafer in Black Amaretto\nMen's Tremont Kiltie Tassel Loafer",
+ "nr_faces": 44822,
+ "nr_vertices": 24064,
+ "surface_area": 0.13456803296673206,
+ "volume": 0.0006499269608217513
+ }
+ },
+ "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_rCdzRZqgCnI": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_rCdzRZqgCnI",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056005094490920816,
+ -0.14466028834824105,
+ -0.024254717305406702
+ ],
+ [
+ 0.05009190550907918,
+ 0.15052971165175896,
+ 0.0687132826945933
+ ]
+ ],
+ "mass": 0.0006311213716716742,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Tremont Kiltie Tassel Loafer in Black Amaretto\nMen's Tremont Kiltie Tassel Loafer",
+ "nr_faces": 34070,
+ "nr_vertices": 18268,
+ "surface_area": 0.1282655147538448,
+ "volume": 0.0006311213716716742
+ }
+ },
+ "Mens_Wave_Driver_Kiltie_Moc_in_Tan_Leather": {
+ "asset_type": "FileBasedObject",
+ "id": "Mens_Wave_Driver_Kiltie_Moc_in_Tan_Leather",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13128115946706104,
+ -0.05670746670520323,
+ -0.031871362839885266
+ ],
+ [
+ 0.14711284053293897,
+ 0.05456253329479677,
+ 0.07632763716011473
+ ]
+ ],
+ "mass": 0.0006933997926757224,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Men's Wave Driver Kiltie Moc in Tan Leather\nMen's Wave Driver Kiltie Moc",
+ "nr_faces": 24036,
+ "nr_vertices": 13273,
+ "surface_area": 0.12210531974206443,
+ "volume": 0.0006933997926757224
+ }
+ },
+ "Metallic_Gold_Tieks_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Metallic_Gold_Tieks_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.046608311791303765,
+ -0.12272186798939633,
+ -0.025255753078879926
+ ],
+ [
+ 0.03791868820869623,
+ 0.12356413201060366,
+ 0.052366246921120074
+ ]
+ ],
+ "mass": 0.0004537051023298675,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Metallic Gold Tieks - Italian Leather Ballet Flats\nA softly stunning ballet flat, Metallic Gold Tieks are a basic for any season. Wear these with a fancy dress, or add a fun flash to your everyday look. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 22072,
+ "nr_vertices": 12075,
+ "surface_area": 0.08122123858712996,
+ "volume": 0.0004537051023298675
+ }
+ },
+ "Metallic_Pewter_Tieks_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Metallic_Pewter_Tieks_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.044891065789483944,
+ -0.12433257529087223,
+ -0.026924608770204587
+ ],
+ [
+ 0.038228934210516055,
+ 0.12233342470912778,
+ 0.05163939122979541
+ ]
+ ],
+ "mass": 0.0004878104564951112,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Metallic Pewter Tieks - Italian Leather Ballet Flats\nThese striking, Metallic Pewter ballet flats can jazz up an evening ensemble or add subtle flash to your everyday look. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 20080,
+ "nr_vertices": 10802,
+ "surface_area": 0.07280696728490701,
+ "volume": 0.0004878104564951112
+ }
+ },
+ "Mist_Wipe_Warmer": {
+ "asset_type": "FileBasedObject",
+ "id": "Mist_Wipe_Warmer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13203421654099282,
+ -0.061566564818172125,
+ -0.11652492332670897
+ ],
+ [
+ 0.1321567834590072,
+ 0.06616843518182788,
+ 0.11659107667329102
+ ]
+ ],
+ "mass": 0.007099560941139414,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Mist Wipe Warmer",
+ "nr_faces": 3308,
+ "nr_vertices": 2021,
+ "surface_area": 0.2313508744835512,
+ "volume": 0.007099560941139414
+ }
+ },
+ "My_First_Animal_Tower": {
+ "asset_type": "FileBasedObject",
+ "id": "My_First_Animal_Tower",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1980750251146664,
+ -0.12985489324734395,
+ -0.03478901674901883
+ ],
+ [
+ 0.1550559748853336,
+ 0.13639310675265606,
+ 0.04818298325098117
+ ]
+ ],
+ "mass": 0.0005869634849560292,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "My First Animal Tower",
+ "nr_faces": 6818,
+ "nr_vertices": 3982,
+ "surface_area": 0.09032251690881632,
+ "volume": 0.0005869634849560292
+ }
+ },
+ "My_First_Rolling_Lion": {
+ "asset_type": "FileBasedObject",
+ "id": "My_First_Rolling_Lion",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08244616641878669,
+ -0.02710509693617748,
+ -0.06702698920418654
+ ],
+ [
+ 0.07611983358121331,
+ 0.027333903063822516,
+ 0.08496201079581346
+ ]
+ ],
+ "mass": 0.00036608981133204267,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "My First Rolling Lion",
+ "nr_faces": 7740,
+ "nr_vertices": 4271,
+ "surface_area": 0.051791618168961176,
+ "volume": 0.00036608981133204267
+ }
+ },
+ "My_First_Wiggle_Crocodile": {
+ "asset_type": "FileBasedObject",
+ "id": "My_First_Wiggle_Crocodile",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09892520681194127,
+ -0.0334465263141876,
+ -0.02764964088759628
+ ],
+ [
+ 0.09831779318805874,
+ 0.033133473685812403,
+ 0.03325135911240372
+ ]
+ ],
+ "mass": 0.000246607577438828,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "My First Wiggle Crocodile",
+ "nr_faces": 10056,
+ "nr_vertices": 6824,
+ "surface_area": 0.040197595304094516,
+ "volume": 0.000246607577438828
+ }
+ },
+ "My_Little_Pony_Princess_Celestia": {
+ "asset_type": "FileBasedObject",
+ "id": "My_Little_Pony_Princess_Celestia",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09278990228784792,
+ -0.09482628924546574,
+ -0.11332814224230664
+ ],
+ [
+ 0.10038709771215207,
+ 0.12910871075453426,
+ 0.11864885775769336
+ ]
+ ],
+ "mass": 0.0005400544560188571,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "My Little Pony Princess Celestia",
+ "nr_faces": 39168,
+ "nr_vertices": 24003,
+ "surface_area": 0.1311228319858539,
+ "volume": 0.0005400544560188571
+ }
+ },
+ "My_Monopoly_Board_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "My_Monopoly_Board_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20303633878364663,
+ -0.028994646271431196,
+ -0.136210053186196
+ ],
+ [
+ 0.20189266121635338,
+ 0.0299533537285688,
+ 0.136275946813804
+ ]
+ ],
+ "mass": 0.00580391681009582,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "My Monopoly Board Game",
+ "nr_faces": 1356,
+ "nr_vertices": 742,
+ "surface_area": 0.28430542256573565,
+ "volume": 0.00580391681009582
+ }
+ },
+ "NAPA_VALLEY_NAVAJO_SANDAL": {
+ "asset_type": "FileBasedObject",
+ "id": "NAPA_VALLEY_NAVAJO_SANDAL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07359825964713906,
+ -0.10426321881700878,
+ -0.014746730401119037
+ ],
+ [
+ 0.05415774035286094,
+ 0.12829778118299123,
+ 0.06622826959888096
+ ]
+ ],
+ "mass": 0.00020798848760315896,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "NAPA VALLEY NAVAJO SANDAL\nJack Rogers signature flat sandal",
+ "nr_faces": 12446,
+ "nr_vertices": 6749,
+ "surface_area": 0.05775376782393233,
+ "volume": 0.00020798848760315896
+ }
+ },
+ "NESCAFE_NESCAFE_TC_STKS_DECAF_6_CT": {
+ "asset_type": "FileBasedObject",
+ "id": "NESCAFE_NESCAFE_TC_STKS_DECAF_6_CT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04078195069003221,
+ -0.01463460807959874,
+ -0.06556237833693063
+ ],
+ [
+ 0.03987304930996779,
+ 0.014210391920401261,
+ 0.06561262166306939
+ ]
+ ],
+ "mass": 0.00027033581135326096,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "NESCAFE NESCAFE TC STKS DECAF 6 CT",
+ "nr_faces": 6260,
+ "nr_vertices": 3283,
+ "surface_area": 0.029911463584208032,
+ "volume": 0.00027033581135326096
+ }
+ },
+ "NUTS_BOLTS": {
+ "asset_type": "FileBasedObject",
+ "id": "NUTS_BOLTS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08801691700027249,
+ -0.1068098978804792,
+ -0.05153144428588209
+ ],
+ [
+ 0.09219808299972751,
+ 0.06533510211952079,
+ 0.07346055571411791
+ ]
+ ],
+ "mass": 0.0005485529244079126,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "NUTS & BOLTS\nEncourage children to create forms and imaginary figures. Children will have fun assembling and reassembling the nuts and bolts transforming them into various mixes and matches.",
+ "nr_faces": 18260,
+ "nr_vertices": 9992,
+ "surface_area": 0.07963345713328272,
+ "volume": 0.0005485529244079126
+ }
+ },
+ "NattoMax": {
+ "asset_type": "FileBasedObject",
+ "id": "NattoMax",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.026632039581069716,
+ -0.026183822167302567,
+ -0.04053722038881065
+ ],
+ [
+ 0.026370960418930285,
+ 0.026089177832697433,
+ 0.04829977961118934
+ ]
+ ],
+ "mass": 0.0001642314405403778,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "NattoMax",
+ "nr_faces": 8508,
+ "nr_vertices": 4379,
+ "surface_area": 0.01735333491023175,
+ "volume": 0.0001642314405403778
+ }
+ },
+ "Neat_Solutions_Character_Bib_2_pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Neat_Solutions_Character_Bib_2_pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10327331785801598,
+ -0.10104162228024528,
+ -0.029254305115093155
+ ],
+ [
+ 0.10188168214198402,
+ 0.10382337771975471,
+ 0.047318694884906844
+ ]
+ ],
+ "mass": 0.0003582823881289193,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Neat Solutions Character Bib - 2 pack",
+ "nr_faces": 12082,
+ "nr_vertices": 6165,
+ "surface_area": 0.1362536768606652,
+ "volume": 0.0003582823881289193
+ }
+ },
+ "Nescafe_16Count_Dolce_Gusto_Cappuccino_Capsules": {
+ "asset_type": "FileBasedObject",
+ "id": "Nescafe_16Count_Dolce_Gusto_Cappuccino_Capsules",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06204099924757924,
+ -0.06220571219467868,
+ -0.060542236671773914
+ ],
+ [
+ 0.061741000752420755,
+ 0.06176628780532133,
+ 0.06205176332822608
+ ]
+ ],
+ "mass": 0.0017831974045965425,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nescafe 16-Count Dolce Gusto Cappuccino Capsules",
+ "nr_faces": 3024,
+ "nr_vertices": 1639,
+ "surface_area": 0.08561358962943322,
+ "volume": 0.0017831974045965425
+ }
+ },
+ "Nescafe_Memento_Latte_Caramel_8_08_oz_23_g_packets_64_oz_184_g": {
+ "asset_type": "FileBasedObject",
+ "id": "Nescafe_Memento_Latte_Caramel_8_08_oz_23_g_packets_64_oz_184_g",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04631695800895645,
+ -0.03201273579595887,
+ -0.08033823038192413
+ ],
+ [
+ 0.04554804199104355,
+ 0.03202226420404113,
+ 0.08030376961807587
+ ]
+ ],
+ "mass": 0.0008823516108587967,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nescafe Memento Latte, Caramel - 8 - 0.8 oz (23 g) packets [6.4 oz (184 g)]\nSpecialty coffee beverage. Good food, good life. Good Question: How can I get coffeehouse quality foam that lasts until the final sip? Good to Know: By using real nonfat milk infused with airy bubbles NesCafe Memento brings you the frothy, foamy goodness you love. Natural source of antioxidants. 269 mg of antioxidants per serving. Product of Mexico.",
+ "nr_faces": 3992,
+ "nr_vertices": 2109,
+ "surface_area": 0.057424150384485714,
+ "volume": 0.0008823516108587967
+ }
+ },
+ "Nescafe_Momento_Mocha_Specialty_Coffee_Mix_8_ct": {
+ "asset_type": "FileBasedObject",
+ "id": "Nescafe_Momento_Mocha_Specialty_Coffee_Mix_8_ct",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04571236864778312,
+ -0.03233834909853319,
+ -0.08054396376758764
+ ],
+ [
+ 0.045503631352216876,
+ 0.032075650901466815,
+ 0.08084203623241236
+ ]
+ ],
+ "mass": 0.0008873374508255481,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nescafe Momento Mocha Specialty Coffee Mix 8 ct",
+ "nr_faces": 4312,
+ "nr_vertices": 2263,
+ "surface_area": 0.05753855659565028,
+ "volume": 0.0008873374508255481
+ }
+ },
+ "Nescafe_Tasters_Choice_Instant_Coffee_Decaf_House_Blend_Light_7_oz": {
+ "asset_type": "FileBasedObject",
+ "id": "Nescafe_Tasters_Choice_Instant_Coffee_Decaf_House_Blend_Light_7_oz",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04839729876962015,
+ -0.03994098650051752,
+ -0.09002928459809698
+ ],
+ [
+ 0.04845670123037985,
+ 0.03930001349948248,
+ 0.09570271540190303
+ ]
+ ],
+ "mass": 0.001054154490372136,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Nescafe Taster's Choice Instant Coffee, Decaf House Blend, Light - 7 oz",
+ "nr_faces": 9214,
+ "nr_vertices": 4727,
+ "surface_area": 0.0600023605790232,
+ "volume": 0.001054154490372136
+ }
+ },
+ "Nestl_Crunch_Girl_Scouts_Cookie_Flavors_Caramel_Coconut_78_oz_box": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestl_Crunch_Girl_Scouts_Cookie_Flavors_Caramel_Coconut_78_oz_box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07010148133206508,
+ -0.03070289530310762,
+ -0.08109021543927183
+ ],
+ [
+ 0.06936451866793492,
+ 0.03056410469689238,
+ 0.08195278456072816
+ ]
+ ],
+ "mass": 0.0012805824565990404,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestl? Crunch Girl Scouts Cookie Flavors, Caramel & Coconut - 7.8 oz box",
+ "nr_faces": 3320,
+ "nr_vertices": 1794,
+ "surface_area": 0.07562474162755708,
+ "volume": 0.0012805824565990404
+ }
+ },
+ "Nestl_Skinny_Cow_Heavenly_Crisp_Candy_Bar_Chocolate_Raspberry_6_pack_462_oz_total": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestl_Skinny_Cow_Heavenly_Crisp_Candy_Bar_Chocolate_Raspberry_6_pack_462_oz_total",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05589665329122152,
+ -0.025227564286587123,
+ -0.08199137723230665
+ ],
+ [
+ 0.05601434670877848,
+ 0.024831435713412876,
+ 0.08212362276769335
+ ]
+ ],
+ "mass": 0.0008487545471703049,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestl? Skinny Cow Heavenly Crisp Candy Bar ,Chocolate Raspberry - 6 pack, 4.62 oz total",
+ "nr_faces": 4904,
+ "nr_vertices": 2625,
+ "surface_area": 0.05930087166100612,
+ "volume": 0.0008487545471703049
+ }
+ },
+ "Nestle_Candy_19_oz_Butterfinger_Singles_116567": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestle_Candy_19_oz_Butterfinger_Singles_116567",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07974047137024017,
+ -0.021639458158302607,
+ -0.008825064055775739
+ ],
+ [
+ 0.08848552862975984,
+ 0.020305541841697392,
+ 0.009816935944224262
+ ]
+ ],
+ "mass": 6.866134614817132e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestle Candy 1.9 oz. Butterfinger Singles 116567",
+ "nr_faces": 6496,
+ "nr_vertices": 3893,
+ "surface_area": 0.015102753701311537,
+ "volume": 6.866134614817132e-05
+ }
+ },
+ "Nestle_Carnation_Cinnamon_Coffeecake_Kit_1913OZ": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestle_Carnation_Cinnamon_Coffeecake_Kit_1913OZ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07505644971143964,
+ -0.03550503961426584,
+ -0.09715532117730748
+ ],
+ [
+ 0.07469355028856035,
+ 0.03577096038573416,
+ 0.09793467882269252
+ ]
+ ],
+ "mass": 0.0019705380956440777,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestle Carnation Cinnamon Coffeecake Kit 19.13OZ",
+ "nr_faces": 2068,
+ "nr_vertices": 1141,
+ "surface_area": 0.10120449379457389,
+ "volume": 0.0019705380956440777
+ }
+ },
+ "Nestle_Nesquik_Chocolate_Powder_Flavored_Milk_Additive_109_Oz_Canister": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestle_Nesquik_Chocolate_Powder_Flavored_Milk_Additive_109_Oz_Canister",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03112254316845772,
+ -0.05362985496389256,
+ -0.07239494080620214
+ ],
+ [
+ 0.03108545683154228,
+ 0.05312214503610744,
+ 0.07134305919379787
+ ]
+ ],
+ "mass": 0.0007204803277452614,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestle Nesquik Chocolate Powder Flavored Milk Additive 10.9 Oz Canister\n25% less sugar than the leading syrup brand (13 g vs. 20 g sugar/svg in the leading syrup brand. This product contains 25 g of sugar when mixed with 1 cup of milk). 19 servings. Good to compare: 8 fl oz beverage: Nesquik, 25 g total sugars (sugar content is based on mixing Nesquik and the leading syrup brand with 1% milk. Milk contributes 12 g of sugar), 40% DV calcium (percent represents daily value), no high fructose corn syrup; leading chocolate syrup brand (sugar content is based on mixing Nesquik and the leading syrup brand with 1% milk. Milk contributes 12 g of sugar), 32 g total sugars (sugar content is based on mixing Nesquik and the leading syrup brand with 1% milk. Milk contributes 12 g of sugar), 30-40% DV calcium (percent represents daily value), yes high fructose corn syrup; leading juice drinks for kids (average sugar level of kids' juice drink brands. If you compare to 6.75 fl oz of juice drink vs. 6.75 fl oz of Nesquik in milk, the sugar levels are 25 g sugar vs. 21 g respectively), 30 g total sugars (sugar content is based on mixing Nesquik and the leading syrup brand with 1% milk. Milk contributes 12 g of sugar), 0-15% DV calcium (percent represents daily value), yes high fructose corn syrup. Good for active play: Nesquik when mixed with 1 cup lowfat milk is filled with protein, carbs & happiness - to help build strong bodies & fuel active minds. Contains no artificial sweeteners. 99.9% caffeine free.",
+ "nr_faces": 14756,
+ "nr_vertices": 7741,
+ "surface_area": 0.051045706505503385,
+ "volume": 0.0007204803277452614
+ }
+ },
+ "Nestle_Nips_Hard_Candy_Peanut_Butter": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestle_Nips_Hard_Candy_Peanut_Butter",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.044273992099539604,
+ -0.021134830338954396,
+ -0.07687808902268288
+ ],
+ [
+ 0.0442330079004604,
+ 0.021269169661045605,
+ 0.07645991097731711
+ ]
+ ],
+ "mass": 0.0005352262339063743,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestle Nips Hard Candy Peanut Butter",
+ "nr_faces": 4852,
+ "nr_vertices": 2559,
+ "surface_area": 0.04398118655891999,
+ "volume": 0.0005352262339063743
+ }
+ },
+ "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1367710195368098,
+ -0.06530202777122536,
+ -0.06804662362842814
+ ],
+ [
+ 0.13619698046319018,
+ 0.06501297222877464,
+ 0.06802737637157187
+ ]
+ ],
+ "mass": 0.004531628338435322,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestle Pure Life Exotics Sparkling Water, Strawberry Dragon Fruit - 8 count, 12 fl oz can",
+ "nr_faces": 3938,
+ "nr_vertices": 2129,
+ "surface_area": 0.16544191458155008,
+ "volume": 0.004531628338435322
+ }
+ },
+ "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can_aX0ygjh3bxi": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can_aX0ygjh3bxi",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1354646158011743,
+ -0.06416185808332954,
+ -0.06859528700015549
+ ],
+ [
+ 0.1355523841988257,
+ 0.06412914191667046,
+ 0.07047371299984449
+ ]
+ ],
+ "mass": 0.004467279634076719,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestle Pure Life Exotics Sparkling Water, Strawberry Dragon Fruit - 8 count, 12 fl oz can",
+ "nr_faces": 3240,
+ "nr_vertices": 1738,
+ "surface_area": 0.16560559779154121,
+ "volume": 0.004467279634076719
+ }
+ },
+ "Nestle_Raisinets_Milk_Chocolate_35_oz_992_g": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestle_Raisinets_Milk_Chocolate_35_oz_992_g",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08085445580798821,
+ -0.010689618278293607,
+ -0.04103645904046832
+ ],
+ [
+ 0.08127454419201179,
+ 0.010722381721706394,
+ 0.04183454095953169
+ ]
+ ],
+ "mass": 0.000244472442331944,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestle Raisinets, Milk Chocolate - 3.5 oz (99.2 g)\nNestle Classic milk chocolate California raisins. Natural source of fruit antioxidants. 30% less fat than the leading chocolate brands. Chocolate covered sunshine. 8 g fat vs 11.4 g fat (average) of the leading chocolate brands. Good food, good life. Good to connect. Gluten free.",
+ "nr_faces": 3828,
+ "nr_vertices": 2003,
+ "surface_area": 0.0336786455671091,
+ "volume": 0.000244472442331944
+ }
+ },
+ "Nestle_Skinny_Cow_Dreamy_Clusters_Candy_Dark_Chocolate_6_pack_1_oz_pouches": {
+ "asset_type": "FileBasedObject",
+ "id": "Nestle_Skinny_Cow_Dreamy_Clusters_Candy_Dark_Chocolate_6_pack_1_oz_pouches",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06894102301196839,
+ -0.02966881276386585,
+ -0.08240888554063909
+ ],
+ [
+ 0.06912297698803162,
+ 0.029210187236134152,
+ 0.08218611445936091
+ ]
+ ],
+ "mass": 0.0012486996114298632,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nestle Skinny Cow Dreamy Clusters Candy, Dark Chocolate - 6 pack, 1 oz pouches",
+ "nr_faces": 4764,
+ "nr_vertices": 2575,
+ "surface_area": 0.07551500214438156,
+ "volume": 0.0012486996114298632
+ }
+ },
+ "Netgear_Ac1750_Router_Wireless_Dual_Band_Gigabit_Router": {
+ "asset_type": "FileBasedObject",
+ "id": "Netgear_Ac1750_Router_Wireless_Dual_Band_Gigabit_Router",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17511041074167386,
+ -0.04435761321253101,
+ -0.12982972669357148
+ ],
+ [
+ 0.17300558925832615,
+ 0.044531386787468985,
+ 0.12982027330642854
+ ]
+ ],
+ "mass": 0.007382254993053611,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Netgear Ac1750 Router Wireless Dual Band Gigabit Router",
+ "nr_faces": 38524,
+ "nr_vertices": 31216,
+ "surface_area": 0.27483005209268063,
+ "volume": 0.007382254993053611
+ }
+ },
+ "Netgear_N750_Wireless_Dual_Band_Gigabit_Router": {
+ "asset_type": "FileBasedObject",
+ "id": "Netgear_N750_Wireless_Dual_Band_Gigabit_Router",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14926190482069804,
+ -0.03698423071007987,
+ -0.13250920167375582
+ ],
+ [
+ 0.14699809517930196,
+ 0.035385769289920134,
+ 0.1333817983262442
+ ]
+ ],
+ "mass": 0.005277736150794469,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Netgear N750 Wireless Dual Band Gigabit Router",
+ "nr_faces": 2044,
+ "nr_vertices": 1096,
+ "surface_area": 0.22773693037938217,
+ "volume": 0.005277736150794469
+ }
+ },
+ "Netgear_Nighthawk_X6_AC3200_TriBand_Gigabit_Wireless_Router": {
+ "asset_type": "FileBasedObject",
+ "id": "Netgear_Nighthawk_X6_AC3200_TriBand_Gigabit_Wireless_Router",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18662073110912544,
+ -0.048813871107511876,
+ -0.1470945717973663
+ ],
+ [
+ 0.18778926889087455,
+ 0.04897212889248812,
+ 0.1472824282026337
+ ]
+ ],
+ "mass": 0.010166461804406697,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Netgear Nighthawk X6 AC3200 Tri-Band Gigabit Wireless Router",
+ "nr_faces": 3170,
+ "nr_vertices": 1768,
+ "surface_area": 0.32934251012656235,
+ "volume": 0.010166461804406697
+ }
+ },
+ "New_Super_Mario_BrosWii_Wii_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "New_Super_Mario_BrosWii_Wii_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06663624654128765,
+ -0.09614170532339697,
+ -0.008176617257802922
+ ],
+ [
+ 0.07044275345871236,
+ 0.09557929467660303,
+ 0.008550382742197079
+ ]
+ ],
+ "mass": 0.00036542879761347234,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "New Super Mario Bros.Wii [Wii Game]",
+ "nr_faces": 3312,
+ "nr_vertices": 1750,
+ "surface_area": 0.06188731613196464,
+ "volume": 0.00036542879761347234
+ }
+ },
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Leonardo": {
+ "asset_type": "FileBasedObject",
+ "id": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Leonardo",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05451345248423444,
+ -0.07888782235348203,
+ -0.05825782481201748
+ ],
+ [
+ 0.029883547515765555,
+ 0.038389177646517975,
+ 0.05545617518798252
+ ]
+ ],
+ "mass": 7.64543837593535e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Nickelodeon Teenage Mutant Ninja Turtles Leonardo",
+ "nr_faces": 21724,
+ "nr_vertices": 12223,
+ "surface_area": 0.022867415735093745,
+ "volume": 7.64543837593535e-05
+ }
+ },
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Michelangelo": {
+ "asset_type": "FileBasedObject",
+ "id": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Michelangelo",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07810394055035146,
+ -0.02254922081599484,
+ -0.05518621860722304
+ ],
+ [
+ 0.06361505944964854,
+ 0.02308977918400516,
+ 0.05909578139277696
+ ]
+ ],
+ "mass": 6.332832182044783e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Nickelodeon Teenage Mutant Ninja Turtles Michelangelo",
+ "nr_faces": 18996,
+ "nr_vertices": 10552,
+ "surface_area": 0.01901081359754383,
+ "volume": 6.332832182044783e-05
+ }
+ },
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Raphael": {
+ "asset_type": "FileBasedObject",
+ "id": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Raphael",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04579719061464154,
+ -0.03939113774804859,
+ -0.05822759250858681
+ ],
+ [
+ 0.05119980938535846,
+ 0.025837862251951414,
+ 0.07133440749141318
+ ]
+ ],
+ "mass": 7.7398721834272e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Nickelodeon Teenage Mutant Ninja Turtles Raphael",
+ "nr_faces": 21666,
+ "nr_vertices": 12103,
+ "surface_area": 0.020820200324941338,
+ "volume": 7.7398721834272e-05
+ }
+ },
+ "Nickelodeon_The_Spongebob_Movie_PopAPart_Spongebob": {
+ "asset_type": "FileBasedObject",
+ "id": "Nickelodeon_The_Spongebob_Movie_PopAPart_Spongebob",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12252333498292398,
+ -0.043964572607547735,
+ -0.05979311068943425
+ ],
+ [
+ 0.10013666501707602,
+ 0.07348342739245227,
+ 0.07360088931056574
+ ]
+ ],
+ "mass": 0.00020323054802811065,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Nickelodeon The Spongebob Movie Pop-A-Part Spongebob",
+ "nr_faces": 23990,
+ "nr_vertices": 16278,
+ "surface_area": 0.06193331607938604,
+ "volume": 0.00020323054802811065
+ }
+ },
+ "Nightmare_Before_Christmas_Collectors_Edition_Operation": {
+ "asset_type": "FileBasedObject",
+ "id": "Nightmare_Before_Christmas_Collectors_Edition_Operation",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.2229679130614948,
+ -0.0358576140823614,
+ -0.13336269792600816
+ ],
+ [
+ 0.2215330869385052,
+ 0.0359273859176386,
+ 0.1334253020739918
+ ]
+ ],
+ "mass": 0.005677265266711784,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Nightmare Before Christmas Collector's Edition Operation",
+ "nr_faces": 2728,
+ "nr_vertices": 1793,
+ "surface_area": 0.29928356256126765,
+ "volume": 0.005677265266711784
+ }
+ },
+ "Nikon_1_AW1_w11275mm_Lens_Silver": {
+ "asset_type": "FileBasedObject",
+ "id": "Nikon_1_AW1_w11275mm_Lens_Silver",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03132516800651553,
+ -0.03142067011143299,
+ -0.03896135436215128
+ ],
+ [
+ 0.03150483199348447,
+ 0.03143432988856701,
+ 0.03967064563784872
+ ]
+ ],
+ "mass": 0.00022204336302448984,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Camera",
+ "description": "Nikon 1 AW1 w/11-27.5mm Lens (Silver)\nOne-Lens-Kit, Nikon 1 AW1 Camera Body, AN-N1000 Strap, UC-E15 USB Cable, EN-EL20 Rechargeable Li-ion Battery, MH-27 Battery Charger, BF-N2000 Body Cap, WP-O2000 O-Ring, PA-N1000 O-Ring Protector, ViewNX 2, Short Movie Creator CD, User's Manual, Reference Manual CD",
+ "nr_faces": 9566,
+ "nr_vertices": 4910,
+ "surface_area": 0.020097281997442765,
+ "volume": 0.00022204336302448984
+ }
+ },
+ "Nintendo_2DS_Crimson_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Nintendo_2DS_Crimson_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07216552426852549,
+ -0.06923964778291834,
+ -0.009315038740180626
+ ],
+ [
+ 0.07211147573147451,
+ 0.05835635221708165,
+ 0.013078961259819373
+ ]
+ ],
+ "mass": 0.00026534175219858716,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Nintendo 2DS? ? Crimson Red\nThe Best of Two Worlds. The Nintendo 2DS system brings the \npower of two systems together into a single, affordable package. Play all games?both Nintendo DS and Nintendo 3DS?in 2D. Connect with friends, other players, and wireless hotspots using the wireless StreetPass? and SpotPass? communication modes to unlock exclusive content for games and download other entertainment. From games to photos and beyond, Nintendo 2DS is the ultimate 2D gaming experience. \n\nNintendo 2DS is a 2D system that plays all Nintendo DS and Nintendo 3DS games. Nintendo 2DS is only capable of 2D display.",
+ "nr_faces": 6254,
+ "nr_vertices": 3227,
+ "surface_area": 0.042157548129160394,
+ "volume": 0.00026534175219858716
+ }
+ },
+ "Nintendo_Mario_Action_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Nintendo_Mario_Action_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03871184031939118,
+ -0.03342085791544587,
+ -0.05545890048046655
+ ],
+ [
+ 0.024484159680608825,
+ 0.02084314208455413,
+ 0.04691809951953345
+ ]
+ ],
+ "mass": 6.521531846194816e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Nintendo Mario Action Figure",
+ "nr_faces": 20116,
+ "nr_vertices": 10737,
+ "surface_area": 0.015866124131562416,
+ "volume": 6.521531846194816e-05
+ }
+ },
+ "Nintendo_Wii_Party_U_with_Controller_Wii_U_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Nintendo_Wii_Party_U_with_Controller_Wii_U_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0728125415388704,
+ -0.03182704856540939,
+ -0.09844094365983273
+ ],
+ [
+ 0.0726074584611296,
+ 0.03152495143459061,
+ 0.09867105634016728
+ ]
+ ],
+ "mass": 0.0016039295624640428,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Nintendo Wii Party U with Controller [Wii U Game]",
+ "nr_faces": 2510,
+ "nr_vertices": 1348,
+ "surface_area": 0.09286271834769812,
+ "volume": 0.0016039295624640428
+ }
+ },
+ "Nintendo_Yoshi_Action_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Nintendo_Yoshi_Action_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03175047437901181,
+ -0.032256863374798425,
+ -0.05709734046589189
+ ],
+ [
+ 0.037018525620988195,
+ 0.03284813662520158,
+ 0.05594365953410811
+ ]
+ ],
+ "mass": 0.00010109660963817433,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Nintendo Yoshi Action Figure",
+ "nr_faces": 16498,
+ "nr_vertices": 8865,
+ "surface_area": 0.020398213346192347,
+ "volume": 0.00010109660963817433
+ }
+ },
+ "Nips_Hard_Candy_Rich_Creamy_Butter_Rum_4_oz_1133_g": {
+ "asset_type": "FileBasedObject",
+ "id": "Nips_Hard_Candy_Rich_Creamy_Butter_Rum_4_oz_1133_g",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04490495499793378,
+ -0.021515878371014804,
+ -0.0762783416023126
+ ],
+ [
+ 0.04417704500206622,
+ 0.021593121628985194,
+ 0.07641165839768739
+ ]
+ ],
+ "mass": 0.0005236288544176942,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Nips Hard Candy, Rich & Creamy, Butter Rum - 4 oz (113.3 g)\n30 Calories per piece. Value pack! Artificially flavored. Good to Remember: Reward yourself with a smooth indulgent treat. Good to Know: Each delicious piece has 30 calories! Enjoy the long-lasting, rich and creamy taste of Nips.",
+ "nr_faces": 4398,
+ "nr_vertices": 2328,
+ "surface_area": 0.04384958361443924,
+ "volume": 0.0005236288544176942
+ }
+ },
+ "Nordic_Ware_Original_Bundt_Pan": {
+ "asset_type": "FileBasedObject",
+ "id": "Nordic_Ware_Original_Bundt_Pan",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13515920795503156,
+ -0.13242984624212656,
+ -0.050374462311556185
+ ],
+ [
+ 0.12871179204496844,
+ 0.13100215375787344,
+ 0.04959153768844381
+ ]
+ ],
+ "mass": 0.00032023308374524024,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Nordic Ware Original Bundt Pan",
+ "nr_faces": 16052,
+ "nr_vertices": 8221,
+ "surface_area": 0.24210548170797455,
+ "volume": 0.00032023308374524024
+ }
+ },
+ "Now_Designs_Bowl_Akita_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Now_Designs_Bowl_Akita_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07992283298487692,
+ -0.07850709097020524,
+ -0.03660400976329214
+ ],
+ [
+ 0.07976016701512309,
+ 0.08043590902979476,
+ 0.03860999023670786
+ ]
+ ],
+ "mass": 0.00015408228545274433,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Now Designs Bowl, Akita, Black",
+ "nr_faces": 42522,
+ "nr_vertices": 21546,
+ "surface_area": 0.0719066718196679,
+ "volume": 0.00015408228545274433
+ }
+ },
+ "Now_Designs_Dish_Towel_Mojave_18_x_28": {
+ "asset_type": "FileBasedObject",
+ "id": "Now_Designs_Dish_Towel_Mojave_18_x_28",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08088231061961204,
+ -0.17492262712864837,
+ -0.00957813494331635
+ ],
+ [
+ 0.07298868938038797,
+ 0.18262137287135163,
+ 0.022705865056683653
+ ]
+ ],
+ "mass": 0.0007488078334419472,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Now Designs Dish Towel, Mojave, 18\" x 28\"",
+ "nr_faces": 20548,
+ "nr_vertices": 10813,
+ "surface_area": 0.12520917360979955,
+ "volume": 0.0007488078334419472
+ }
+ },
+ "Now_Designs_Snack_Bags_Bicycle_2_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Now_Designs_Snack_Bags_Bicycle_2_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09260820208709335,
+ -0.08720224506908877,
+ -0.008043312119752323
+ ],
+ [
+ 0.09786479791290664,
+ 0.11480875493091124,
+ 0.013579687880247677
+ ]
+ ],
+ "mass": 0.00040376388211201474,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Now Designs Snack Bags, Bicycle - 2 count",
+ "nr_faces": 9702,
+ "nr_vertices": 5484,
+ "surface_area": 0.08191290281761138,
+ "volume": 0.00040376388211201474
+ }
+ },
+ "OVAL_XYLOPHONE": {
+ "asset_type": "FileBasedObject",
+ "id": "OVAL_XYLOPHONE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12488246012153606,
+ -0.13885542097010664,
+ -0.035979717316601836
+ ],
+ [
+ 0.08283553987846395,
+ 0.14485657902989338,
+ 0.03529928268339816
+ ]
+ ],
+ "mass": 0.0005242332458823017,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "OVAL XYLOPHONE\nThis xylophone will help develop hand-eye coordination and reinforce children?s natural sense of harmony and rhythm.",
+ "nr_faces": 8862,
+ "nr_vertices": 5334,
+ "surface_area": 0.14534721339612938,
+ "volume": 0.0005242332458823017
+ }
+ },
+ "OWL_SORTER": {
+ "asset_type": "FileBasedObject",
+ "id": "OWL_SORTER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09931311055254642,
+ -0.044744612642660525,
+ -0.05967904748361526
+ ],
+ [
+ 0.09788188944745357,
+ 0.06060138735733948,
+ 0.11783495251638473
+ ]
+ ],
+ "mass": 0.00038876510677323994,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "OWL SORTER\nGreat fun for children to sort 4 different shapes in the Owl. It also encourages children?s recognition of colors and shapes as well as the development of hand-eye coordination.",
+ "nr_faces": 11398,
+ "nr_vertices": 6759,
+ "surface_area": 0.11257653492279251,
+ "volume": 0.00038876510677323994
+ }
+ },
+ "OXO_Cookie_Spatula": {
+ "asset_type": "FileBasedObject",
+ "id": "OXO_Cookie_Spatula",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09796850705616585,
+ -0.03242701995306046,
+ -0.012563399006807918
+ ],
+ [
+ 0.14215249294383414,
+ 0.03543498004693954,
+ 0.012109600993192082
+ ]
+ ],
+ "mass": 3.9423941987004484e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "OXO Cookie Spatula",
+ "nr_faces": 4494,
+ "nr_vertices": 2469,
+ "surface_area": 0.01855185222418121,
+ "volume": 3.9423941987004484e-05
+ }
+ },
+ "OXO_Soft_Works_Can_Opener_SnapLock": {
+ "asset_type": "FileBasedObject",
+ "id": "OXO_Soft_Works_Can_Opener_SnapLock",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0689002579806568,
+ -0.03518659994537335,
+ -0.02398741544098033
+ ],
+ [
+ 0.10846074201934319,
+ 0.03453940005462665,
+ 0.03223058455901967
+ ]
+ ],
+ "mass": 0.00015663432718115218,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "OXO Soft Works Can Opener, Snap-Lock",
+ "nr_faces": 20568,
+ "nr_vertices": 11084,
+ "surface_area": 0.03085983971217264,
+ "volume": 0.00015663432718115218
+ }
+ },
+ "Object": {
+ "asset_type": "FileBasedObject",
+ "id": "Object",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06266311654850512,
+ -0.025360704996646034,
+ -0.044220083195780156
+ ],
+ [
+ 0.055188883451494884,
+ 0.025373295003353967,
+ 0.07077091680421985
+ ]
+ ],
+ "mass": 0.00018103074003106,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Object\nObject",
+ "nr_faces": 26276,
+ "nr_vertices": 13505,
+ "surface_area": 0.02896352921168778,
+ "volume": 0.00018103074003106
+ }
+ },
+ "Object_REmvBDJStub": {
+ "asset_type": "FileBasedObject",
+ "id": "Object_REmvBDJStub",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11745909709492888,
+ -0.13970568172656905,
+ -0.0791548906887691
+ ],
+ [
+ 0.11833290290507112,
+ 0.14496631827343093,
+ 0.1714251093112309
+ ]
+ ],
+ "mass": 0.0003556599484839476,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Object\nObject",
+ "nr_faces": 8694,
+ "nr_vertices": 4761,
+ "surface_area": 0.17961495511725029,
+ "volume": 0.0003556599484839476
+ }
+ },
+ "Ocedar_Snap_On_Dust_Pan_And_Brush_1_ct": {
+ "asset_type": "FileBasedObject",
+ "id": "Ocedar_Snap_On_Dust_Pan_And_Brush_1_ct",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11499976399955619,
+ -0.1369611993561957,
+ -0.03579272448207032
+ ],
+ [
+ 0.1157922360004438,
+ 0.19373180064380432,
+ 0.05884427551792968
+ ]
+ ],
+ "mass": 0.0004559530806668732,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ocedar Snap On Dust Pan And Brush - 1 ct",
+ "nr_faces": 14656,
+ "nr_vertices": 8499,
+ "surface_area": 0.15464664537390488,
+ "volume": 0.0004559530806668732
+ }
+ },
+ "Office_Depot_Canon_CL211XL_Remanufactured_Ink_Cartridge_TriColor": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_CL211XL_Remanufactured_Ink_Cartridge_TriColor",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04338014502254157,
+ -0.02450738061610472,
+ -0.05825000205707406
+ ],
+ [
+ 0.04250885497745843,
+ 0.024298619383895277,
+ 0.059607997942925935
+ ]
+ ],
+ "mass": 0.0004641886232401791,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Canon CL-211XL) Remanufactured Ink Cartridge - Tri-Color",
+ "nr_faces": 6088,
+ "nr_vertices": 3233,
+ "surface_area": 0.0374836929985436,
+ "volume": 0.0004641886232401791
+ }
+ },
+ "Office_Depot_Canon_CLI36_Remanufactured_Ink_Cartridge_TriColor": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_CLI36_Remanufactured_Ink_Cartridge_TriColor",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04295608068940937,
+ -0.025499156826309634,
+ -0.06031575831706326
+ ],
+ [
+ 0.04276691931059063,
+ 0.024174843173690366,
+ 0.08687124168293672
+ ]
+ ],
+ "mass": 0.00046196723754925964,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Canon CLI-36) Remanufactured Ink Cartridge - Tri-Color",
+ "nr_faces": 3980,
+ "nr_vertices": 2166,
+ "surface_area": 0.04193768341459135,
+ "volume": 0.00046196723754925964
+ }
+ },
+ "Office_Depot_Canon_CLI_221BK_Ink_Cartridge_Black_2946B001": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_CLI_221BK_Ink_Cartridge_Black_2946B001",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04262866785228085,
+ -0.024910960453452848,
+ -0.05845069233011852
+ ],
+ [
+ 0.04273633214771915,
+ 0.02463103954654715,
+ 0.05986230766988148
+ ]
+ ],
+ "mass": 0.000468669488406684,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot Canon CLI 221BK Ink Cartridge, Black (2946B001)",
+ "nr_faces": 5926,
+ "nr_vertices": 3107,
+ "surface_area": 0.03755543456015214,
+ "volume": 0.000468669488406684
+ }
+ },
+ "Office_Depot_Canon_CLI_8CMY_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_CLI_8CMY_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04303262388620368,
+ -0.04285113851573125,
+ -0.05822561582732042
+ ],
+ [
+ 0.04301337611379632,
+ 0.04279786148426875,
+ 0.06019838417267958
+ ]
+ ],
+ "mass": 0.0008157617525500892,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Canon CLI 8CMY) Remanufactured Ink Cartridges - Color (Cyan, Magenta, Yellow) - 3 count",
+ "nr_faces": 4876,
+ "nr_vertices": 2609,
+ "surface_area": 0.051111753110706294,
+ "volume": 0.0008157617525500892
+ }
+ },
+ "Office_Depot_Canon_CLI_8Y_Ink_Cartridge_Yellow_0623B002": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_CLI_8Y_Ink_Cartridge_Yellow_0623B002",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04340621884472031,
+ -0.024839554415595873,
+ -0.058520331773833485
+ ],
+ [
+ 0.04248178115527969,
+ 0.024516445584404127,
+ 0.05981666822616651
+ ]
+ ],
+ "mass": 0.0004671204607648598,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot Canon CLI 8Y Ink Cartridge, Yellow (0623B002)",
+ "nr_faces": 4732,
+ "nr_vertices": 2522,
+ "surface_area": 0.03753906421993059,
+ "volume": 0.0004671204607648598
+ }
+ },
+ "Office_Depot_Canon_CL_41_Remanufactured_Ink_Cartridge_TriColor": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_CL_41_Remanufactured_Ink_Cartridge_TriColor",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.043768757580651844,
+ -0.025300010983877963,
+ -0.05897378924810845
+ ],
+ [
+ 0.043431242419348155,
+ 0.025283989016122034,
+ 0.05917721075189155
+ ]
+ ],
+ "mass": 0.000472225959661657,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Canon CL 41) Remanufactured Ink Cartridge - Tri-Color",
+ "nr_faces": 4276,
+ "nr_vertices": 2277,
+ "surface_area": 0.03737516921675211,
+ "volume": 0.000472225959661657
+ }
+ },
+ "Office_Depot_Canon_PG21XL_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_PG21XL_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04268344122698766,
+ -0.02500599737101386,
+ -0.05846073866849066
+ ],
+ [
+ 0.04265055877301234,
+ 0.02470700262898614,
+ 0.059420261331509336
+ ]
+ ],
+ "mass": 0.00047062760934120265,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Canon PG-21XL) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 4780,
+ "nr_vertices": 2532,
+ "surface_area": 0.037401621356369576,
+ "volume": 0.00047062760934120265
+ }
+ },
+ "Office_Depot_Canon_PGI22_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_PGI22_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04319814695566338,
+ -0.025233333017636205,
+ -0.05897713467819815
+ ],
+ [
+ 0.04344185304433662,
+ 0.025209666982363797,
+ 0.059981865321801844
+ ]
+ ],
+ "mass": 0.0004742434541720746,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Canon PGI-22) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 4614,
+ "nr_vertices": 2448,
+ "surface_area": 0.037740912051528366,
+ "volume": 0.0004742434541720746
+ }
+ },
+ "Office_Depot_Canon_PGI35_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_PGI35_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.043786674774483406,
+ -0.02457152040101547,
+ -0.058692889204805365
+ ],
+ [
+ 0.042900325225516595,
+ 0.024407479598984528,
+ 0.05963411079519463
+ ]
+ ],
+ "mass": 0.0004703862197664925,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Canon PGI-35) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 4446,
+ "nr_vertices": 2360,
+ "surface_area": 0.037453527803283634,
+ "volume": 0.0004703862197664925
+ }
+ },
+ "Office_Depot_Canon_PGI5BK_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_PGI5BK_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04356731981138218,
+ -0.024597994758424807,
+ -0.05837208023617634
+ ],
+ [
+ 0.042932680188617824,
+ 0.024242005241575194,
+ 0.05948091976382365
+ ]
+ ],
+ "mass": 0.0004632194189327721,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Canon PGI-5BK) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 6472,
+ "nr_vertices": 3512,
+ "surface_area": 0.037535888758541594,
+ "volume": 0.0004632194189327721
+ }
+ },
+ "Office_Depot_Canon_PG_240XL_Ink_Cartridge_Black_5206B001": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Canon_PG_240XL_Ink_Cartridge_Black_5206B001",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04314799447631856,
+ -0.024892653039872675,
+ -0.05839559841915232
+ ],
+ [
+ 0.042865005523681436,
+ 0.024486346960127324,
+ 0.06004340158084768
+ ]
+ ],
+ "mass": 0.00046954814224721837,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot Canon PG 240XL Ink Cartridge, Black (5206B001)",
+ "nr_faces": 6584,
+ "nr_vertices": 3500,
+ "surface_area": 0.03755916304548221,
+ "volume": 0.00046954814224721837
+ }
+ },
+ "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04363687520103072,
+ -0.024796602982657127,
+ -0.05860836872680198
+ ],
+ [
+ 0.04343712479896928,
+ 0.024540397017342876,
+ 0.06017463127319802
+ ]
+ ],
+ "mass": 0.00047168291461989085,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Dell Series 11) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 5694,
+ "nr_vertices": 3015,
+ "surface_area": 0.037588011993792504,
+ "volume": 0.00047168291461989085
+ }
+ },
+ "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_TriColor": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_TriColor",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04329747015373071,
+ -0.025303030332383993,
+ -0.0593984187681227
+ ],
+ [
+ 0.04325552984626929,
+ 0.024444969667616008,
+ 0.08839558123187731
+ ]
+ ],
+ "mass": 0.0004744458762168034,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Dell Series 11) Remanufactured Ink Cartridge - Tri-Color",
+ "nr_faces": 3676,
+ "nr_vertices": 2003,
+ "surface_area": 0.0419812976270503,
+ "volume": 0.0004744458762168034
+ }
+ },
+ "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04328883954503792,
+ -0.024998342166987885,
+ -0.058337551115364907
+ ],
+ [
+ 0.04304216045496208,
+ 0.024836657833012112,
+ 0.0598474488846351
+ ]
+ ],
+ "mass": 0.0004696488363502816,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Dell Series 1) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 5394,
+ "nr_vertices": 2867,
+ "surface_area": 0.03730987888599904,
+ "volume": 0.0004696488363502816
+ }
+ },
+ "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_TriColor": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_TriColor",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04273573235906576,
+ -0.02490118820671743,
+ -0.05844115951325045
+ ],
+ [
+ 0.04264526764093424,
+ 0.024608811793282573,
+ 0.059468840486749545
+ ]
+ ],
+ "mass": 0.000470142720826504,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Dell Series 1) Remanufactured Ink Cartridge - Tri-Color",
+ "nr_faces": 5722,
+ "nr_vertices": 3119,
+ "surface_area": 0.037456296682006424,
+ "volume": 0.000470142720826504
+ }
+ },
+ "Office_Depot_Dell_Series_5_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Dell_Series_5_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0429629954808636,
+ -0.024861020176599594,
+ -0.05849245116823794
+ ],
+ [
+ 0.042770004519136394,
+ 0.024644979823400408,
+ 0.059349548831762064
+ ]
+ ],
+ "mass": 0.0004713370062244881,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (Dell Series 5) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 4108,
+ "nr_vertices": 2179,
+ "surface_area": 0.037496012127972655,
+ "volume": 0.0004713370062244881
+ }
+ },
+ "Office_Depot_Dell_Series_9_Color_Ink_Ink_Cartridge_MK991_MK993": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Dell_Series_9_Color_Ink_Ink_Cartridge_MK991_MK993",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04267601820507008,
+ -0.025828814541610973,
+ -0.058404713124820075
+ ],
+ [
+ 0.04319198179492992,
+ 0.025879185458389027,
+ 0.05977128687517992
+ ]
+ ],
+ "mass": 0.00047748975423248896,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot Dell Series 9 Color Ink Ink Cartridge (MK991, MK993)",
+ "nr_faces": 4846,
+ "nr_vertices": 2586,
+ "surface_area": 0.03773760824049793,
+ "volume": 0.00047748975423248896
+ }
+ },
+ "Office_Depot_Dell_Series_9_Ink_Cartridge_Black_MK992": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_Dell_Series_9_Ink_Cartridge_Black_MK992",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04360032615530069,
+ -0.02489287181034286,
+ -0.058283337210439386
+ ],
+ [
+ 0.04261367384469931,
+ 0.02475812818965714,
+ 0.059848662789560615
+ ]
+ ],
+ "mass": 0.00046978153339110413,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot Dell Series 9 Ink Cartridge, Black (MK992)",
+ "nr_faces": 5162,
+ "nr_vertices": 2759,
+ "surface_area": 0.037425238704994764,
+ "volume": 0.00046978153339110413
+ }
+ },
+ "Office_Depot_HP_2_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_2_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04253957437616345,
+ -0.025353529367824045,
+ -0.05914018867663749
+ ],
+ [
+ 0.04237442562383655,
+ 0.024683470632175953,
+ 0.0883538113233625
+ ]
+ ],
+ "mass": 0.00047246553465283203,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (HP 2) Remanufactured Ink Cartridges - Color (Cyan, Magenta, Yellow) - 3 count",
+ "nr_faces": 4236,
+ "nr_vertices": 2313,
+ "surface_area": 0.04202206647992337,
+ "volume": 0.00047246553465283203
+ }
+ },
+ "Office_Depot_HP_564XL_Ink_Cartridge_Black_CN684WN": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_564XL_Ink_Cartridge_Black_CN684WN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04308456135341125,
+ -0.024897652881669115,
+ -0.05836552068968934
+ ],
+ [
+ 0.04286143864658875,
+ 0.024732347118330885,
+ 0.05936447931031066
+ ]
+ ],
+ "mass": 0.0004666954757019618,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot HP 564XL Ink Cartridge, Black (CN684WN)",
+ "nr_faces": 4212,
+ "nr_vertices": 2256,
+ "surface_area": 0.03723528071871231,
+ "volume": 0.0004666954757019618
+ }
+ },
+ "Office_Depot_HP_564XL_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_564XL_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04335009080293183,
+ -0.042050048052723284,
+ -0.05826315936748349
+ ],
+ [
+ 0.042807909197068165,
+ 0.041887951947276715,
+ 0.07577984063251653
+ ]
+ ],
+ "mass": 0.0008033768692462456,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (HP 564XL) Remanufactured Ink Cartridges - Color (Cyan, Magenta, Yellow) - 3 count",
+ "nr_faces": 4126,
+ "nr_vertices": 2387,
+ "surface_area": 0.05422807687234542,
+ "volume": 0.0008033768692462456
+ }
+ },
+ "Office_Depot_HP_61Tricolor_Ink_Cartridge": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_61Tricolor_Ink_Cartridge",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04298019935852919,
+ -0.02519134353543428,
+ -0.05831991553560114
+ ],
+ [
+ 0.04257980064147081,
+ 0.02492065646456572,
+ 0.060072084464398864
+ ]
+ ],
+ "mass": 0.00046909730266332965,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot HP 61Tricolor Ink Cartridge",
+ "nr_faces": 4438,
+ "nr_vertices": 2384,
+ "surface_area": 0.03741690385344773,
+ "volume": 0.00046909730266332965
+ }
+ },
+ "Office_Depot_HP_71_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_71_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04316220083206327,
+ -0.024949381161511356,
+ -0.05859234930601681
+ ],
+ [
+ 0.042847799167936726,
+ 0.02548961883848864,
+ 0.058869650693983186
+ ]
+ ],
+ "mass": 0.0004681209012705811,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (HP 71) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 5972,
+ "nr_vertices": 3296,
+ "surface_area": 0.037446833504971175,
+ "volume": 0.0004681209012705811
+ }
+ },
+ "Office_Depot_HP_74XL75_Remanufactured_Ink_Cartridges_BlackTriColor_2_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_74XL75_Remanufactured_Ink_Cartridges_BlackTriColor_2_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0428389118930438,
+ -0.04259271821076881,
+ -0.05772976257177234
+ ],
+ [
+ 0.0426490881069562,
+ 0.0424952817892312,
+ 0.058796237428227656
+ ]
+ ],
+ "mass": 0.0008054018230407181,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (HP 74XL/75) Remanufactured Ink Cartridges - Black/Tri-Color - 2 count",
+ "nr_faces": 3634,
+ "nr_vertices": 1969,
+ "surface_area": 0.05101308625202873,
+ "volume": 0.0008054018230407181
+ }
+ },
+ "Office_Depot_HP_75_Remanufactured_Ink_Cartridge_TriColor": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_75_Remanufactured_Ink_Cartridge_TriColor",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04259961198939457,
+ -0.02485943649692341,
+ -0.05972339072606632
+ ],
+ [
+ 0.042694388010605426,
+ 0.024508563503076588,
+ 0.0870906092739337
+ ]
+ ],
+ "mass": 0.0004722291342393886,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (HP 75) Remanufactured Ink Cartridge - Tri-Color",
+ "nr_faces": 5498,
+ "nr_vertices": 2980,
+ "surface_area": 0.04186563623428311,
+ "volume": 0.0004722291342393886
+ }
+ },
+ "Office_Depot_HP_920XL_920_High_Yield_Black_and_Standard_CMY_Color_Ink_Cartridges": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_920XL_920_High_Yield_Black_and_Standard_CMY_Color_Ink_Cartridges",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.043265260900213376,
+ -0.042470472680878946,
+ -0.05796076410668626
+ ],
+ [
+ 0.04295373909978662,
+ 0.042240527319121056,
+ 0.05915623589331374
+ ]
+ ],
+ "mass": 0.0008077949139250848,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot HP 920XL /920 High Yield Black and Standard C/M/Y Color Ink Cartridges",
+ "nr_faces": 4314,
+ "nr_vertices": 2315,
+ "surface_area": 0.050918552665582185,
+ "volume": 0.0008077949139250848
+ }
+ },
+ "Office_Depot_HP_932XL_Ink_Cartridge_Black_CN053A": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_932XL_Ink_Cartridge_Black_CN053A",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.042618226748805554,
+ -0.02479807420547248,
+ -0.05841429577945968
+ ],
+ [
+ 0.04274077325119445,
+ 0.02445492579452752,
+ 0.059241704220540314
+ ]
+ ],
+ "mass": 0.00046614913424208914,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot HP 932XL Ink Cartridge, Black (CN053A)",
+ "nr_faces": 5168,
+ "nr_vertices": 2737,
+ "surface_area": 0.03738050789302182,
+ "volume": 0.00046614913424208914
+ }
+ },
+ "Office_Depot_HP_950XL_Ink_Cartridge_Black_CN045AN": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_950XL_Ink_Cartridge_Black_CN045AN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.042789411839949894,
+ -0.02492945451592077,
+ -0.058408002356212414
+ ],
+ [
+ 0.04251158816005011,
+ 0.02475254548407923,
+ 0.05956599764378758
+ ]
+ ],
+ "mass": 0.0004675951447109186,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot HP 950XL Ink Cartridge, Black (CN045AN)",
+ "nr_faces": 5454,
+ "nr_vertices": 2990,
+ "surface_area": 0.03736362625961647,
+ "volume": 0.0004675951447109186
+ }
+ },
+ "Office_Depot_HP_96_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_96_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04271946693135565,
+ -0.025276001865541044,
+ -0.0590881480739775
+ ],
+ [
+ 0.04263653306864435,
+ 0.024639998134458954,
+ 0.08805585192602251
+ ]
+ ],
+ "mass": 0.00047222605838248175,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (HP 96) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 4640,
+ "nr_vertices": 2504,
+ "surface_area": 0.041961173945186475,
+ "volume": 0.00047222605838248175
+ }
+ },
+ "Office_Depot_HP_98_Remanufactured_Ink_Cartridge_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Office_Depot_HP_98_Remanufactured_Ink_Cartridge_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04302100581438678,
+ -0.0249485154798537,
+ -0.059764529447406345
+ ],
+ [
+ 0.04250599418561322,
+ 0.0243024845201463,
+ 0.08790447055259366
+ ]
+ ],
+ "mass": 0.0004712332553745876,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Office Depot (HP 98) Remanufactured Ink Cartridge - Black",
+ "nr_faces": 4046,
+ "nr_vertices": 2214,
+ "surface_area": 0.04221651085537938,
+ "volume": 0.0004712332553745876
+ }
+ },
+ "Olive_Kids_Birdie_Lunch_Box": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Birdie_Lunch_Box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13891914066788533,
+ -0.05300604547365136,
+ -0.09980151578613093
+ ],
+ [
+ 0.12815385933211465,
+ 0.04993695452634864,
+ 0.11438748421386907
+ ]
+ ],
+ "mass": 0.0043024453022764055,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Birdie Lunch Box",
+ "nr_faces": 13760,
+ "nr_vertices": 7440,
+ "surface_area": 0.17165275482835735,
+ "volume": 0.0043024453022764055
+ }
+ },
+ "Olive_Kids_Birdie_Munch_n_Lunch": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Birdie_Munch_n_Lunch",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.114635745505303,
+ -0.08540938132626301,
+ -0.11501543677122014
+ ],
+ [
+ 0.114884254494697,
+ 0.078884618673737,
+ 0.15442756322877987
+ ]
+ ],
+ "mass": 0.006175978424380883,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Birdie Munch 'n Lunch",
+ "nr_faces": 15898,
+ "nr_vertices": 8310,
+ "surface_area": 0.2395827515462841,
+ "volume": 0.006175978424380883
+ }
+ },
+ "Olive_Kids_Birdie_Pack_n_Snack": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Birdie_Pack_n_Snack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14093100996455601,
+ -0.12962478308365694,
+ -0.14634221864741256
+ ],
+ [
+ 0.141041990035444,
+ 0.11626721691634306,
+ 0.17442278135258743
+ ]
+ ],
+ "mass": 0.013229390033623022,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Birdie Pack 'n Snack",
+ "nr_faces": 27676,
+ "nr_vertices": 15028,
+ "surface_area": 0.34138041253650653,
+ "volume": 0.013229390033623022
+ }
+ },
+ "Olive_Kids_Birdie_Sidekick_Backpack": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Birdie_Sidekick_Backpack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15399146343638032,
+ -0.12171877185903296,
+ -0.18043282204506986
+ ],
+ [
+ 0.16788853656361968,
+ 0.12242822814096704,
+ 0.20529117795493013
+ ]
+ ],
+ "mass": 0.016400848795675306,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Birdie Sidekick Backpack",
+ "nr_faces": 28666,
+ "nr_vertices": 15926,
+ "surface_area": 0.44322862453753564,
+ "volume": 0.016400848795675306
+ }
+ },
+ "Olive_Kids_Butterfly_Garden_Munch_n_Lunch_Bag": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Butterfly_Garden_Munch_n_Lunch_Bag",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11479261764183651,
+ -0.09060392482018625,
+ -0.11601986269159947
+ ],
+ [
+ 0.11001838235816348,
+ 0.07793007517981375,
+ 0.1490851373084005
+ ]
+ ],
+ "mass": 0.00629864792816009,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Butterfly Garden Munch 'n Lunch Bag",
+ "nr_faces": 18968,
+ "nr_vertices": 9862,
+ "surface_area": 0.23894937708805777,
+ "volume": 0.00629864792816009
+ }
+ },
+ "Olive_Kids_Butterfly_Garden_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Butterfly_Garden_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10521692698208207,
+ -0.04302521288453099,
+ -0.04365419475465964
+ ],
+ [
+ 0.10400207301791793,
+ 0.043942787115469006,
+ 0.051245805245340365
+ ]
+ ],
+ "mass": 0.0010600924772142626,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Butterfly Garden Pencil Case",
+ "nr_faces": 11022,
+ "nr_vertices": 5918,
+ "surface_area": 0.06515418067910138,
+ "volume": 0.0010600924772142626
+ }
+ },
+ "Olive_Kids_Dinosaur_Land_Lunch_Box": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Dinosaur_Land_Lunch_Box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1315302478332494,
+ -0.05374599578795668,
+ -0.09929132722008706
+ ],
+ [
+ 0.1290707521667506,
+ 0.05369700421204332,
+ 0.11018967277991294
+ ]
+ ],
+ "mass": 0.004422823848884554,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Dinosaur Land Lunch Box",
+ "nr_faces": 15204,
+ "nr_vertices": 8268,
+ "surface_area": 0.17185919748428213,
+ "volume": 0.004422823848884554
+ }
+ },
+ "Olive_Kids_Dinosaur_Land_Munch_n_Lunch": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Dinosaur_Land_Munch_n_Lunch",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1117898807850179,
+ -0.08744132939232463,
+ -0.10921893432979504
+ ],
+ [
+ 0.11016111921498209,
+ 0.07889567060767538,
+ 0.15181806567020495
+ ]
+ ],
+ "mass": 0.005664041852135185,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Dinosaur Land Munch 'n Lunch",
+ "nr_faces": 18202,
+ "nr_vertices": 9379,
+ "surface_area": 0.2376402526522547,
+ "volume": 0.005664041852135185
+ }
+ },
+ "Olive_Kids_Dinosaur_Land_Pack_n_Snack": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Dinosaur_Land_Pack_n_Snack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14006789053503013,
+ -0.12487134281012185,
+ -0.14564914895012207
+ ],
+ [
+ 0.14756310946496987,
+ 0.10611065718987815,
+ 0.16866785104987794
+ ]
+ ],
+ "mass": 0.013164268473114938,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Dinosaur Land Pack 'n Snack",
+ "nr_faces": 29314,
+ "nr_vertices": 16016,
+ "surface_area": 0.3448363903015679,
+ "volume": 0.013164268473114938
+ }
+ },
+ "Olive_Kids_Dinosaur_Land_Sidekick_Backpack": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Dinosaur_Land_Sidekick_Backpack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15447286657193426,
+ -0.1519081768965303,
+ -0.1728585704149945
+ ],
+ [
+ 0.15565413342806572,
+ 0.14037382310346969,
+ 0.2073024295850055
+ ]
+ ],
+ "mass": 0.016121657366049584,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Dinosaur Land Sidekick Backpack",
+ "nr_faces": 22640,
+ "nr_vertices": 12095,
+ "surface_area": 0.3896301285230108,
+ "volume": 0.016121657366049584
+ }
+ },
+ "Olive_Kids_Game_On_Lunch_Box": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Game_On_Lunch_Box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14336828924596906,
+ -0.053285378682719445,
+ -0.10106842453927133
+ ],
+ [
+ 0.13137271075403095,
+ 0.05051962131728056,
+ 0.11908157546072866
+ ]
+ ],
+ "mass": 0.004224809599156481,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Game On Lunch Box",
+ "nr_faces": 14212,
+ "nr_vertices": 7636,
+ "surface_area": 0.1723083870860785,
+ "volume": 0.004224809599156481
+ }
+ },
+ "Olive_Kids_Game_On_Munch_n_Lunch": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Game_On_Munch_n_Lunch",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11462344188992359,
+ -0.08738825878491684,
+ -0.1152817261054462
+ ],
+ [
+ 0.11298355811007642,
+ 0.07840174121508316,
+ 0.1524532738945538
+ ]
+ ],
+ "mass": 0.006255926970675358,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Game On Munch 'n Lunch",
+ "nr_faces": 17356,
+ "nr_vertices": 8971,
+ "surface_area": 0.24196095079483346,
+ "volume": 0.006255926970675358
+ }
+ },
+ "Olive_Kids_Game_On_Pack_n_Snack": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Game_On_Pack_n_Snack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16778361417545326,
+ -0.12581393756337156,
+ -0.14316860413567326
+ ],
+ [
+ 0.16215938582454675,
+ 0.12835906243662845,
+ 0.17110739586432672
+ ]
+ ],
+ "mass": 0.01250149911109744,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Game On Pack 'n Snack",
+ "nr_faces": 30086,
+ "nr_vertices": 16481,
+ "surface_area": 0.3847943854143493,
+ "volume": 0.01250149911109744
+ }
+ },
+ "Olive_Kids_Mermaids_Pack_n_Snack_Backpack": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Mermaids_Pack_n_Snack_Backpack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14299687963942867,
+ -0.12441364836881764,
+ -0.1464327467132661
+ ],
+ [
+ 0.14196912036057133,
+ 0.11725735163118235,
+ 0.1745732532867339
+ ]
+ ],
+ "mass": 0.012658697078179945,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Mermaids Pack 'n Snack Backpack",
+ "nr_faces": 27022,
+ "nr_vertices": 14549,
+ "surface_area": 0.3379816425396069,
+ "volume": 0.012658697078179945
+ }
+ },
+ "Olive_Kids_Paisley_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Paisley_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10934174560251024,
+ -0.0452193840945487,
+ -0.04229850029298781
+ ],
+ [
+ 0.10457625439748977,
+ 0.0461346159054513,
+ 0.048049499707012194
+ ]
+ ],
+ "mass": 0.0010403545808113804,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Paisley Pencil Case",
+ "nr_faces": 12444,
+ "nr_vertices": 6621,
+ "surface_area": 0.06507394818388547,
+ "volume": 0.0010403545808113804
+ }
+ },
+ "Olive_Kids_Robots_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Robots_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11187550655258122,
+ -0.04353920783838537,
+ -0.043079014533580234
+ ],
+ [
+ 0.10848549344741878,
+ 0.04244579216161463,
+ 0.05262298546641977
+ ]
+ ],
+ "mass": 0.001024302573666241,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Robots Pencil Case",
+ "nr_faces": 12574,
+ "nr_vertices": 6728,
+ "surface_area": 0.0661555631216704,
+ "volume": 0.001024302573666241
+ }
+ },
+ "Olive_Kids_Trains_Planes_Trucks_Bogo_Backpack": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Trains_Planes_Trucks_Bogo_Backpack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17138281430392233,
+ -0.13253319801012867,
+ -0.1592689071890491
+ ],
+ [
+ 0.17209718569607768,
+ 0.12057880198987134,
+ 0.2169730928109509
+ ]
+ ],
+ "mass": 0.019547156176227407,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Trains, Planes, Trucks Bogo Backpack",
+ "nr_faces": 43896,
+ "nr_vertices": 24860,
+ "surface_area": 0.4844441655860341,
+ "volume": 0.019547156176227407
+ }
+ },
+ "Olive_Kids_Trains_Planes_Trucks_Munch_n_Lunch_Bag": {
+ "asset_type": "FileBasedObject",
+ "id": "Olive_Kids_Trains_Planes_Trucks_Munch_n_Lunch_Bag",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1066557545956003,
+ -0.06576160029808296,
+ -0.10908052621567833
+ ],
+ [
+ 0.1105112454043997,
+ 0.06993239970191704,
+ 0.17939047378432166
+ ]
+ ],
+ "mass": 0.004315066968109261,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Olive Kids Trains, Planes & Trucks Munch 'n Lunch Bag",
+ "nr_faces": 19022,
+ "nr_vertices": 9921,
+ "surface_area": 0.22699674466578645,
+ "volume": 0.004315066968109261
+ }
+ },
+ "Orbit_Bubblemint_Mini_Bottle_6_ct": {
+ "asset_type": "FileBasedObject",
+ "id": "Orbit_Bubblemint_Mini_Bottle_6_ct",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11011086689162596,
+ -0.03467206262300043,
+ -0.055156482852187966
+ ],
+ [
+ 0.10029513310837404,
+ 0.03490493737699957,
+ 0.06425251714781205
+ ]
+ ],
+ "mass": 0.0014424073811670074,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Orbit Bubblemint Mini Bottle - 6 ct",
+ "nr_faces": 11374,
+ "nr_vertices": 6325,
+ "surface_area": 0.10236959059760634,
+ "volume": 0.0014424073811670074
+ }
+ },
+ "Organic_Whey_Protein_Unflavored": {
+ "asset_type": "FileBasedObject",
+ "id": "Organic_Whey_Protein_Unflavored",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06106878313187676,
+ -0.06102542192739091,
+ -0.08213519026002516
+ ],
+ [
+ 0.060800216868123244,
+ 0.06098357807260909,
+ 0.08692780973997484
+ ]
+ ],
+ "mass": 0.0017820933753479292,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Organic Whey Protein, Unflavored",
+ "nr_faces": 9014,
+ "nr_vertices": 4743,
+ "surface_area": 0.08350381188045132,
+ "volume": 0.0017820933753479292
+ }
+ },
+ "Organic_Whey_Protein_Vanilla": {
+ "asset_type": "FileBasedObject",
+ "id": "Organic_Whey_Protein_Vanilla",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06135849743736643,
+ -0.060568158468930516,
+ -0.08224575611974834
+ ],
+ [
+ 0.06122250256263356,
+ 0.06067784153106948,
+ 0.08764824388025165
+ ]
+ ],
+ "mass": 0.0017896934630004387,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Organic Whey Protein, Vanilla",
+ "nr_faces": 9416,
+ "nr_vertices": 4881,
+ "surface_area": 0.08363096700039553,
+ "volume": 0.0017896934630004387
+ }
+ },
+ "Ortho_Forward_Facing": {
+ "asset_type": "FileBasedObject",
+ "id": "Ortho_Forward_Facing",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09900638797243201,
+ -0.10652872807901068,
+ -0.06955272400272504
+ ],
+ [
+ 0.10352461202756799,
+ 0.1281922719209893,
+ 0.12078427599727497
+ ]
+ ],
+ "mass": 0.0019889490543929635,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ortho Forward Facing",
+ "nr_faces": 31238,
+ "nr_vertices": 16916,
+ "surface_area": 0.14524380229363648,
+ "volume": 0.0019889490543929635
+ }
+ },
+ "Ortho_Forward_Facing_3Q6J2oKJD92": {
+ "asset_type": "FileBasedObject",
+ "id": "Ortho_Forward_Facing_3Q6J2oKJD92",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08351309191385553,
+ -0.10725427142954534,
+ -0.077465089171702
+ ],
+ [
+ 0.11060890808614447,
+ 0.13645572857045465,
+ 0.118484910828298
+ ]
+ ],
+ "mass": 0.0021544463889636547,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ortho Forward Facing",
+ "nr_faces": 27166,
+ "nr_vertices": 14495,
+ "surface_area": 0.14350877827974637,
+ "volume": 0.0021544463889636547
+ }
+ },
+ "Ortho_Forward_Facing_CkAW6rL25xH": {
+ "asset_type": "FileBasedObject",
+ "id": "Ortho_Forward_Facing_CkAW6rL25xH",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1260460471556728,
+ -0.1599956877862534,
+ -0.14129261309963018
+ ],
+ [
+ 0.1251439528443272,
+ 0.1188053122137466,
+ 0.12453838690036986
+ ]
+ ],
+ "mass": 0.005941297774642517,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ortho Forward Facing",
+ "nr_faces": 26568,
+ "nr_vertices": 14277,
+ "surface_area": 0.34576718961351394,
+ "volume": 0.005941297774642517
+ }
+ },
+ "Ortho_Forward_Facing_QCaor9ImJ2G": {
+ "asset_type": "FileBasedObject",
+ "id": "Ortho_Forward_Facing_QCaor9ImJ2G",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08729786633366925,
+ -0.08940582541691035,
+ -0.07110751945816164
+ ],
+ [
+ 0.08607913366633074,
+ 0.09026317458308965,
+ 0.12440248054183836
+ ]
+ ],
+ "mass": 0.0017810139450583006,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Ortho Forward Facing",
+ "nr_faces": 99980,
+ "nr_vertices": 65190,
+ "surface_area": 0.14104946091437934,
+ "volume": 0.0017810139450583006
+ }
+ },
+ "PARENT_ROOM_FURNITURE_SET_1": {
+ "asset_type": "FileBasedObject",
+ "id": "PARENT_ROOM_FURNITURE_SET_1",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11632808319297368,
+ -0.08163000285865676,
+ -0.0321578836648166
+ ],
+ [
+ 0.10329891680702633,
+ 0.06224999714134323,
+ 0.0780611163351834
+ ]
+ ],
+ "mass": 0.0005699148452517913,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "PARENT ROOM (FURNITURE SET 1)\nThe set includes a bed with blanket, an armoire, a vanity and a stool. Made of Eco-Friendly PlanWood and solid rubber wood.",
+ "nr_faces": 13184,
+ "nr_vertices": 7667,
+ "surface_area": 0.09806896561589035,
+ "volume": 0.0005699148452517913
+ }
+ },
+ "PARENT_ROOM_FURNITURE_SET_1_DLKEy8H4mwK": {
+ "asset_type": "FileBasedObject",
+ "id": "PARENT_ROOM_FURNITURE_SET_1_DLKEy8H4mwK",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07447470019493149,
+ -0.14262391519841827,
+ -0.032574751734478546
+ ],
+ [
+ 0.07001029980506851,
+ 0.14648008480158173,
+ 0.07903924826552144
+ ]
+ ],
+ "mass": 0.0005736495633984615,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "PARENT ROOM (FURNITURE SET 1)\nThe set includes a bed with blanket, an armoire, a vanity and a stool. Made of Eco-Friendly PlanWood and solid rubber wood.",
+ "nr_faces": 9406,
+ "nr_vertices": 5452,
+ "surface_area": 0.09658104073855346,
+ "volume": 0.0005736495633984615
+ }
+ },
+ "PEEKABOO_ROLLER": {
+ "asset_type": "FileBasedObject",
+ "id": "PEEKABOO_ROLLER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02435812881180793,
+ -0.03130067722303224,
+ -0.028172056287876605
+ ],
+ [
+ 0.020298871188192073,
+ 0.032604322776967766,
+ 0.030123943712123395
+ ]
+ ],
+ "mass": 0.0001032368791088315,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "PEEK-A-BOO ROLLER\nWatch the colored pieces peek in and out when rolled.",
+ "nr_faces": 11438,
+ "nr_vertices": 5982,
+ "surface_area": 0.01322598418813853,
+ "volume": 0.0001032368791088315
+ }
+ },
+ "PEPSI_NEXT_CACRV": {
+ "asset_type": "FileBasedObject",
+ "id": "PEPSI_NEXT_CACRV",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20150900463938606,
+ -0.06850396032390253,
+ -0.06465800551409577
+ ],
+ [
+ 0.20133999536061395,
+ 0.06813703967609748,
+ 0.06459699448590424
+ ]
+ ],
+ "mass": 0.006673908692576823,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "PEPSI NEXT (CA+CRV)",
+ "nr_faces": 2388,
+ "nr_vertices": 1305,
+ "surface_area": 0.23152282759011472,
+ "volume": 0.006673908692576823
+ }
+ },
+ "PETS_ACCESSORIES": {
+ "asset_type": "FileBasedObject",
+ "id": "PETS_ACCESSORIES",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09208286062410252,
+ -0.04818680133713395,
+ -0.03688985966988789
+ ],
+ [
+ 0.07077113937589748,
+ 0.10386519866286605,
+ 0.049593140330112105
+ ]
+ ],
+ "mass": 0.00016647496320103364,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "PETS & ACCESSORIES\nThis set includes a dog and kennel, a cat, a rabbit and feeding bowls.",
+ "nr_faces": 10614,
+ "nr_vertices": 6124,
+ "surface_area": 0.04490012221524109,
+ "volume": 0.00016647496320103364
+ }
+ },
+ "PHEEHAN_RUN": {
+ "asset_type": "FileBasedObject",
+ "id": "PHEEHAN_RUN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05815867855227256,
+ -0.1305665176824499,
+ -0.036334551156409094
+ ],
+ [
+ 0.04734832144772744,
+ 0.1320804823175501,
+ 0.0770574488435909
+ ]
+ ],
+ "mass": 0.0010055532432952656,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "PHEEHAN RUN\nFootwear",
+ "nr_faces": 33016,
+ "nr_vertices": 19516,
+ "surface_area": 0.10525025165676917,
+ "volume": 0.0010055532432952656
+ }
+ },
+ "PINEAPPLE_MARACA_6_PCSSET": {
+ "asset_type": "FileBasedObject",
+ "id": "PINEAPPLE_MARACA_6_PCSSET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03454173378994785,
+ -0.041060141338638445,
+ -0.026834451669642705
+ ],
+ [
+ 0.03425226621005215,
+ 0.05927885866136155,
+ 0.026841548330357297
+ ]
+ ],
+ "mass": 0.0001348082771540065,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "PINEAPPLE MARACA (6 PCS/SET)\nShake up your next musical adventure with this tropical maraca. Combine with other PlanToys musical items to form a rockstar band !",
+ "nr_faces": 11476,
+ "nr_vertices": 6055,
+ "surface_area": 0.015895592472214795,
+ "volume": 0.0001348082771540065
+ }
+ },
+ "POUNDING_MUSHROOMS": {
+ "asset_type": "FileBasedObject",
+ "id": "POUNDING_MUSHROOMS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08476188045004639,
+ -0.1232601930771072,
+ -0.026482583309341754
+ ],
+ [
+ 0.0800711195499536,
+ 0.09028780692289279,
+ 0.07261241669065824
+ ]
+ ],
+ "mass": 0.0009878761330822646,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "POUNDING MUSHROOMS\nPound the mushroom down and another one continuously comes up. Mushrooms can also be pressed down by hand. Helps develop hand-eye coordination.",
+ "nr_faces": 7946,
+ "nr_vertices": 4294,
+ "surface_area": 0.080859976599058,
+ "volume": 0.0009878761330822646
+ }
+ },
+ "PUNCH_DROP": {
+ "asset_type": "FileBasedObject",
+ "id": "PUNCH_DROP",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09928610632433188,
+ -0.15240129341013267,
+ -0.05602915348221272
+ ],
+ [
+ 0.15093589367566815,
+ 0.08940970658986733,
+ 0.05785484651778727
+ ]
+ ],
+ "mass": 0.001594815680927839,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "PUNCH & DROP\nGreat fun for children to pound the balls until they drop and slide out.",
+ "nr_faces": 11554,
+ "nr_vertices": 6921,
+ "surface_area": 0.1648609828197691,
+ "volume": 0.001594815680927839
+ }
+ },
+ "PUNCH_DROP_TjicLPMqLvz": {
+ "asset_type": "FileBasedObject",
+ "id": "PUNCH_DROP_TjicLPMqLvz",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07745314830825507,
+ -0.11740483362463328,
+ -0.05614999067864549
+ ],
+ [
+ 0.10333285169174493,
+ 0.0789821663753667,
+ 0.08346800932135451
+ ]
+ ],
+ "mass": 0.0019079500260679848,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "PUNCH & DROP\nGreat fun for children to pound the balls until they drop and slide out.",
+ "nr_faces": 15420,
+ "nr_vertices": 9953,
+ "surface_area": 0.14332383226678003,
+ "volume": 0.0019079500260679848
+ }
+ },
+ "Paint_Maker": {
+ "asset_type": "FileBasedObject",
+ "id": "Paint_Maker",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11967927832458894,
+ -0.07241918294421967,
+ -0.11499776212501098
+ ],
+ [
+ 0.12015372167541107,
+ 0.07388481705578033,
+ 0.11600323787498903
+ ]
+ ],
+ "mass": 0.007658922050100232,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Paint Maker\nCreate your own custom paint colors in minutes! Use the mixing guide to create your color or make up your own. This interactive kit provides everything you need to make 15 unique paint colors. Whether you experiment with colors or keep things simple this kit guides you through every step of the process! Available at Walmart.",
+ "nr_faces": 2158,
+ "nr_vertices": 1195,
+ "surface_area": 0.23534185932536306,
+ "volume": 0.007658922050100232
+ }
+ },
+ "Paper_Mario_Sticker_Star_Nintendo_3DS_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Paper_Mario_Sticker_Star_Nintendo_3DS_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06694350621933672,
+ -0.062354009299656836,
+ -0.007509806889630665
+ ],
+ [
+ 0.07064249378066328,
+ 0.06285699070034316,
+ 0.008236193110369336
+ ]
+ ],
+ "mass": 0.00023029766597482235,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Paper Mario: Sticker Star [Nintendo 3DS Game]",
+ "nr_faces": 2950,
+ "nr_vertices": 1559,
+ "surface_area": 0.04050680582587923,
+ "volume": 0.00023029766597482235
+ }
+ },
+ "Pass_The_Popcorn_Movie_Guessing_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Pass_The_Popcorn_Movie_Guessing_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10241006619383602,
+ -0.030901954561757226,
+ -0.13489508384965337
+ ],
+ [
+ 0.10245393380616398,
+ 0.03171904543824277,
+ 0.1355469161503466
+ ]
+ ],
+ "mass": 0.00322191705051575,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Pass The Popcorn Movie Guessing Game",
+ "nr_faces": 4568,
+ "nr_vertices": 2389,
+ "surface_area": 0.15972453938371917,
+ "volume": 0.00322191705051575
+ }
+ },
+ "Paul_Frank_Dot_Lunch_Box": {
+ "asset_type": "FileBasedObject",
+ "id": "Paul_Frank_Dot_Lunch_Box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13095042382407537,
+ -0.05096030701572675,
+ -0.09814661606003681
+ ],
+ [
+ 0.13247557617592462,
+ 0.05696369298427325,
+ 0.13388838393996316
+ ]
+ ],
+ "mass": 0.004283261675168991,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Paul Frank Dot Lunch Box",
+ "nr_faces": 16336,
+ "nr_vertices": 8853,
+ "surface_area": 0.17666693609255613,
+ "volume": 0.004283261675168991
+ }
+ },
+ "Pennington_Electric_Pot_Cabana_4": {
+ "asset_type": "FileBasedObject",
+ "id": "Pennington_Electric_Pot_Cabana_4",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05269700413266161,
+ -0.051665951583200184,
+ -0.04970874770658539
+ ],
+ [
+ 0.05088399586733839,
+ 0.05176704841679981,
+ 0.048117252293414604
+ ]
+ ],
+ "mass": 0.00015916385913089634,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Pennington Electric Pot, Cabana, 4\"",
+ "nr_faces": 13700,
+ "nr_vertices": 7016,
+ "surface_area": 0.05601167914844342,
+ "volume": 0.00015916385913089634
+ }
+ },
+ "Pepsi_Caffeine_Free_Diet_12_CT": {
+ "asset_type": "FileBasedObject",
+ "id": "Pepsi_Caffeine_Free_Diet_12_CT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.202635512900642,
+ -0.06927877163923801,
+ -0.06411370880798695
+ ],
+ [
+ 0.202618487099358,
+ 0.068743228360762,
+ 0.06489729119201307
+ ]
+ ],
+ "mass": 0.006708723757293875,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Pepsi Caffeine Free Diet - 12 CT\n0 calories per can. Sugar free. Very low sodium, 35 mg or less per 8 fl oz (240 ml). Please recycle.",
+ "nr_faces": 2354,
+ "nr_vertices": 1275,
+ "surface_area": 0.23215248661321347,
+ "volume": 0.006708723757293875
+ }
+ },
+ "Pepsi_Cola_Caffeine_Free_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": {
+ "asset_type": "FileBasedObject",
+ "id": "Pepsi_Cola_Caffeine_Free_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20171065254437573,
+ -0.0684162846454746,
+ -0.06476504574221469
+ ],
+ [
+ 0.20230034745562425,
+ 0.0684157153545254,
+ 0.0645519542577853
+ ]
+ ],
+ "mass": 0.0066243751466349855,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Pepsi Cola, Caffeine Free - 12 - 12 fl oz (355 ml) cans [144 fl oz (4.26 lt)]\n150 calories per can. Very low sodium. Please recycle.",
+ "nr_faces": 3718,
+ "nr_vertices": 1980,
+ "surface_area": 0.23195427652429162,
+ "volume": 0.0066243751466349855
+ }
+ },
+ "Pepsi_Cola_Wild_Cherry_Diet_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": {
+ "asset_type": "FileBasedObject",
+ "id": "Pepsi_Cola_Wild_Cherry_Diet_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20297863694270468,
+ -0.07131703801938331,
+ -0.06406865336357637
+ ],
+ [
+ 0.2024213630572953,
+ 0.07060296198061669,
+ 0.06447334663642362
+ ]
+ ],
+ "mass": 0.006807439028353807,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Pepsi Cola, Wild Cherry, Diet - 12 - 12 fl oz (355 ml) cans [144 fl oz (4.26 lt)]\nWith other natural flavors. 0 calories per can. Contains no juice. Sugar free. Very low sodium, 35 mg or less per 8 fl oz (240 ml). Caffeine content: 38 mg /12 fl oz.",
+ "nr_faces": 3760,
+ "nr_vertices": 1991,
+ "surface_area": 0.23215207782795177,
+ "volume": 0.006807439028353807
+ }
+ },
+ "Pepsi_Max_Cola_Zero_Calorie_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": {
+ "asset_type": "FileBasedObject",
+ "id": "Pepsi_Max_Cola_Zero_Calorie_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.2029035827815415,
+ -0.07225214581818096,
+ -0.06420302989177895
+ ],
+ [
+ 0.20189341721845852,
+ 0.07098185418181904,
+ 0.06398697010822105
+ ]
+ ],
+ "mass": 0.006800549535556534,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Pepsi Max Cola, Zero Calorie - 12 - 12 fl oz (355 ml) cans [144 fl oz (4.26 lt)]\n0 calorie cola. 0 calories per can. Maximum taste. Sugar free. Very low sodium, 35 mg or less per 240 ml (8 fl oz). Caffeine Content: 69 ml/12 fl oz. www.pepsi.com. Please recycle.",
+ "nr_faces": 9826,
+ "nr_vertices": 5630,
+ "surface_area": 0.23293276981663555,
+ "volume": 0.006800549535556534
+ }
+ },
+ "Perricoen_MD_No_Concealer_Concealer": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricoen_MD_No_Concealer_Concealer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.026366559139735395,
+ -0.021490929352809225,
+ -0.055373289936953035
+ ],
+ [
+ 0.026263440860264605,
+ 0.021599070647190775,
+ 0.05547071006304696
+ ]
+ ],
+ "mass": 0.0002306615377552238,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricoen MD No Concealer Concealer\nA universal concealer, brightener, and illuminator with anti-aging and hydrating benefits for the eye area.",
+ "nr_faces": 3144,
+ "nr_vertices": 1733,
+ "surface_area": 0.023503228688402558,
+ "volume": 0.0002306615377552238
+ }
+ },
+ "Perricone_MD_AcylGlutathione_Deep_Crease_Serum": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_AcylGlutathione_Deep_Crease_Serum",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0391820268286267,
+ -0.028244676640605874,
+ -0.05301649466376159
+ ],
+ [
+ 0.039318973171373305,
+ 0.028381323359394126,
+ 0.05275250533623841
+ ]
+ ],
+ "mass": 0.0004430729393189246,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Acyl-Glutathione Deep Crease Serum\nA targeted treatment for the appearance of expression lines and creases. With patent-pending Acyl-Glutathione.",
+ "nr_faces": 9406,
+ "nr_vertices": 4922,
+ "surface_area": 0.03499218375567425,
+ "volume": 0.0004430729393189246
+ }
+ },
+ "Perricone_MD_AcylGlutathione_Eye_Lid_Serum": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_AcylGlutathione_Eye_Lid_Serum",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04009717582085809,
+ -0.02797573888527228,
+ -0.05384932959074406
+ ],
+ [
+ 0.03969482417914191,
+ 0.02827326111472772,
+ 0.053983670409255946
+ ]
+ ],
+ "mass": 0.00044703119082379115,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Acyl-Glutathione Eye Lid Serum\nA targeted eye treatment to tighten and firm the upper eye lid while smoothing fine lines and creases around the entire eye area. With patent-pending Acyl Glutathione.",
+ "nr_faces": 15466,
+ "nr_vertices": 8077,
+ "surface_area": 0.03531354433397206,
+ "volume": 0.00044703119082379115
+ }
+ },
+ "Perricone_MD_Best_of_Perricone_7Piece_Collection_MEGsO6GIsyL": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Best_of_Perricone_7Piece_Collection_MEGsO6GIsyL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1488611083104241,
+ -0.03764818036007522,
+ -0.06078347982292141
+ ],
+ [
+ 0.1479068916895759,
+ 0.03749481963992478,
+ 0.06170752017707858
+ ]
+ ],
+ "mass": 0.0024191708308973353,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Best of Perricone 7-Piece Collection\nSeven of Dr. Perricone's best selling products in one collection.",
+ "nr_faces": 1406,
+ "nr_vertices": 777,
+ "surface_area": 0.12313367931544451,
+ "volume": 0.0024191708308973353
+ }
+ },
+ "Perricone_MD_Blue_Plasma_Orbital": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Blue_Plasma_Orbital",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.046762029898762145,
+ -0.027486492050951904,
+ -0.0475876925186021
+ ],
+ [
+ 0.04656197010123786,
+ 0.0282345079490481,
+ 0.0473103074813979
+ ]
+ ],
+ "mass": 0.000453649788036571,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Blue Plasma Orbital\nA eye treatment to reduce dark circles, puffiness, wrinkles and crowsfeet, and also brighten the eye.",
+ "nr_faces": 17356,
+ "nr_vertices": 8915,
+ "surface_area": 0.03564623295718419,
+ "volume": 0.000453649788036571
+ }
+ },
+ "Perricone_MD_Chia_Serum": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Chia_Serum",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.030217597039943627,
+ -0.02130444161041178,
+ -0.05991655073612988
+ ],
+ [
+ 0.030534402960056373,
+ 0.02137455838958822,
+ 0.05986544926387012
+ ]
+ ],
+ "mass": 0.000289635664528143,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Chia Serum\nA luxurious serum that delivers superior nourishment and hydration. With Chia Oil.",
+ "nr_faces": 2346,
+ "nr_vertices": 1287,
+ "surface_area": 0.0277556125737958,
+ "volume": 0.000289635664528143
+ }
+ },
+ "Perricone_MD_Cold_Plasma": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Cold_Plasma",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.052927404084199436,
+ -0.03232629560992688,
+ -0.05211677700529029
+ ],
+ [
+ 0.05322359591580056,
+ 0.033463704390073123,
+ 0.05223622299470971
+ ]
+ ],
+ "mass": 0.000664812999458937,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Cold Plasma\nA revolutionary anti-aging product, Cold Plasma helps correct the ten most visible signs of aging: wrinkles, enlarged pores, dryness, redness, discoloration, uneven skin tone, impurities, loss of firmness, loss of smoothness, and loss of radiance.",
+ "nr_faces": 15706,
+ "nr_vertices": 8134,
+ "surface_area": 0.04586327307271498,
+ "volume": 0.000664812999458937
+ }
+ },
+ "Perricone_MD_Cold_Plasma_Body": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Cold_Plasma_Body",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0421358816203709,
+ -0.03575508067373916,
+ -0.07823446128452541
+ ],
+ [
+ 0.042478118379629094,
+ 0.03568191932626084,
+ 0.08017653871547457
+ ]
+ ],
+ "mass": 0.0007869633724093257,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Cold Plasma Body\nAn anti-aging body moisturizer formulated with Dr. Perricone's Cold Plasma delivery system.",
+ "nr_faces": 1890,
+ "nr_vertices": 1049,
+ "surface_area": 0.052405055107816644,
+ "volume": 0.0007869633724093257
+ }
+ },
+ "Perricone_MD_Face_Finishing_Moisturizer": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Face_Finishing_Moisturizer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.030376615603031516,
+ -0.03050765868107982,
+ -0.03684853049132277
+ ],
+ [
+ 0.030385384396968484,
+ 0.03031134131892018,
+ 0.03686746950867723
+ ]
+ ],
+ "mass": 0.000258568407980334,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Face Finishing Moisturizer\nA bestselling and performance-driven moisturizer rich in corrective antioxidants to hydrate, nourish and impart a glow.",
+ "nr_faces": 2846,
+ "nr_vertices": 1569,
+ "surface_area": 0.023501068671986154,
+ "volume": 0.000258568407980334
+ }
+ },
+ "Perricone_MD_Face_Finishing_Moisturizer_4_oz": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Face_Finishing_Moisturizer_4_oz",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03918203469980958,
+ -0.039358952000555954,
+ -0.0256501532605247
+ ],
+ [
+ 0.03894396530019042,
+ 0.039180047999444044,
+ 0.0256808467394753
+ ]
+ ],
+ "mass": 0.0002962960258752415,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Face Finishing Moisturizer 4 oz\nFace Finishing moisturizer is an anti-aging moisturizer to hydrate dry skin while correcting fine lines and wrinkles.",
+ "nr_faces": 2968,
+ "nr_vertices": 1609,
+ "surface_area": 0.026028299460753117,
+ "volume": 0.0002962960258752415
+ }
+ },
+ "Perricone_MD_Firming_Neck_Therapy_Treatment": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Firming_Neck_Therapy_Treatment",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.030808288182620224,
+ -0.030506735781548524,
+ -0.03675551911673934
+ ],
+ [
+ 0.030520711817379777,
+ 0.030450264218451473,
+ 0.03653248088326066
+ ]
+ ],
+ "mass": 0.0002588151977006968,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Firming Neck Therapy Treatment\nA targeted treatment to firm, tighten and tone the neck while reducing wrinkles and creases. With Phospholipids and Tocotrienols",
+ "nr_faces": 2968,
+ "nr_vertices": 1636,
+ "surface_area": 0.023579283717736772,
+ "volume": 0.0002588151977006968
+ }
+ },
+ "Perricone_MD_Health_Weight_Management_Supplements": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Health_Weight_Management_Supplements",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08632882041512438,
+ -0.06695783679949718,
+ -0.08975128643296679
+ ],
+ [
+ 0.08660517958487562,
+ 0.06604416320050281,
+ 0.09109671356703322
+ ]
+ ],
+ "mass": 0.003884697386992729,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Health & Weight Management Supplements\nA dietary supplement designed to promote healthy weight loss and maintenance.",
+ "nr_faces": 2272,
+ "nr_vertices": 1208,
+ "surface_area": 0.14646588189927878,
+ "volume": 0.003884697386992729
+ }
+ },
+ "Perricone_MD_High_Potency_Evening_Repair": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_High_Potency_Evening_Repair",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.030740924139897804,
+ -0.02275042051656635,
+ -0.06018847721611187
+ ],
+ [
+ 0.030895075860102195,
+ 0.02213557948343365,
+ 0.061050522783888124
+ ]
+ ],
+ "mass": 0.0002901000522886163,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD High Potency Evening Repair\nA retinol based treatment to correct sun damage, dark spots, and uneven skin tone.",
+ "nr_faces": 2532,
+ "nr_vertices": 1364,
+ "surface_area": 0.027837356239046946,
+ "volume": 0.0002901000522886163
+ }
+ },
+ "Perricone_MD_Hypoallergenic_Firming_Eye_Cream_05_oz": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Hypoallergenic_Firming_Eye_Cream_05_oz",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.028386856938073655,
+ -0.028791545109669567,
+ -0.02443883394903711
+ ],
+ [
+ 0.028585143061926346,
+ 0.028463454890330434,
+ 0.02460716605096289
+ ]
+ ],
+ "mass": 0.0001491723897932825,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Hypoallergenic Firming Eye Cream 0.5 oz",
+ "nr_faces": 3436,
+ "nr_vertices": 1859,
+ "surface_area": 0.01600979301434468,
+ "volume": 0.0001491723897932825
+ }
+ },
+ "Perricone_MD_Hypoallergenic_Gentle_Cleanser": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Hypoallergenic_Gentle_Cleanser",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0420182600283087,
+ -0.03254061264542757,
+ -0.07776709899089437
+ ],
+ [
+ 0.04182873997169131,
+ 0.033564387354572435,
+ 0.07806190100910564
+ ]
+ ],
+ "mass": 0.0007771314597063234,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Hypoallergenic Gentle Cleanser\nA mild cleanser that is safe and effective for sensitive skin. With Olive Polyphenols, Tocotrienols, Neuropeptides and Green Tea Extract.",
+ "nr_faces": 1906,
+ "nr_vertices": 1028,
+ "surface_area": 0.05185503238798142,
+ "volume": 0.0007771314597063234
+ }
+ },
+ "Perricone_MD_Neuropeptide_Facial_Conformer": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Neuropeptide_Facial_Conformer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.029761141411751218,
+ -0.022594407031941235,
+ -0.06038024003906734
+ ],
+ [
+ 0.030528858588248782,
+ 0.022523592968058764,
+ 0.060021759960932654
+ ]
+ ],
+ "mass": 0.00028262556203886217,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Neuropeptide Facial Conformer\nThe most advanced formulation of anti-aging ingredients to completely rejuvenate and restore the appearance of younger looking skin. With Neuropeptides, DMAE and Phospholipids. 1 fl oz / 30 mL",
+ "nr_faces": 6770,
+ "nr_vertices": 3569,
+ "surface_area": 0.027507822480012992,
+ "volume": 0.00028262556203886217
+ }
+ },
+ "Perricone_MD_Neuropeptide_Firming_Moisturizer": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Neuropeptide_Firming_Moisturizer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03048726397321995,
+ -0.03019436786916884,
+ -0.03693658828999789
+ ],
+ [
+ 0.03036973602678005,
+ 0.03004063213083116,
+ 0.03641941171000211
+ ]
+ ],
+ "mass": 0.00025406045278589934,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Neuropeptide Firming Moisturizer\nAn anti-aging moisturizer to repair severe loss of elasticity and deliver antioxidant protection. With Alpha Lipoic Acid, DMAE and Vitamin C Ester.",
+ "nr_faces": 12250,
+ "nr_vertices": 6457,
+ "surface_area": 0.023340858405388784,
+ "volume": 0.00025406045278589934
+ }
+ },
+ "Perricone_MD_No_Bronzer_Bronzer": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_No_Bronzer_Bronzer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.025956960910192953,
+ -0.02220606085975773,
+ -0.05018525796328461
+ ],
+ [
+ 0.026099039089807048,
+ 0.02173393914024227,
+ 0.050524742036715385
+ ]
+ ],
+ "mass": 0.00020787358488010316,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD No Bronzer Bronzer\nPerricone MD's No Bronzer Bronzer protects the skin with broad spectrum SPF 30 while instantly reviving the complexion with warm radiance.",
+ "nr_faces": 4374,
+ "nr_vertices": 2370,
+ "surface_area": 0.02174735020742232,
+ "volume": 0.00020787358488010316
+ }
+ },
+ "Perricone_MD_No_Foundation_Foundation_No_1": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_No_Foundation_Foundation_No_1",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.031416476181485006,
+ -0.02214506854162474,
+ -0.060637328543385764
+ ],
+ [
+ 0.031525523818515,
+ 0.022294931458375262,
+ 0.06094567145661424
+ ]
+ ],
+ "mass": 0.000307078325079302,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD No Foundation Foundation No. 1\nA lightweight foundation designed to restore the natural color and radiance of youthful skin while delivering powerfulanti-aging benefits and sun protection with a dewy, glowing finish.",
+ "nr_faces": 3228,
+ "nr_vertices": 1791,
+ "surface_area": 0.029057653113708816,
+ "volume": 0.000307078325079302
+ }
+ },
+ "Perricone_MD_No_Foundation_Serum": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_No_Foundation_Serum",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03210212835383203,
+ -0.021870138594836233,
+ -0.06092923598005402
+ ],
+ [
+ 0.03220487164616797,
+ 0.02158286140516377,
+ 0.061321764019945976
+ ]
+ ],
+ "mass": 0.00031178687265565166,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD No Foundation Serum\nPerricone MD's No Foundation Serum is a multitasking makeup foundation scientifically formulated to deliver flawless coverage, powerful anti-aging benefits, and sun protection.",
+ "nr_faces": 3198,
+ "nr_vertices": 1773,
+ "surface_area": 0.029095241835717614,
+ "volume": 0.00031178687265565166
+ }
+ },
+ "Perricone_MD_No_Lipstick_Lipstick": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_No_Lipstick_Lipstick",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.025231643190311247,
+ -0.02164873892690697,
+ -0.03955358404837485
+ ],
+ [
+ 0.025290356809688753,
+ 0.02140326107309303,
+ 0.03946741595162515
+ ]
+ ],
+ "mass": 0.000162292048529251,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD No Lipstick Lipstick\nAn anti-aging lipstick designed to restore the natural rosy color of youthful lips while doubling as a lip treatment for lip lines and wrinkles. ?",
+ "nr_faces": 4902,
+ "nr_vertices": 2662,
+ "surface_area": 0.017721331238723083,
+ "volume": 0.000162292048529251
+ }
+ },
+ "Perricone_MD_No_Mascara_Mascara": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_No_Mascara_Mascara",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.026388864119489232,
+ -0.02213623404178219,
+ -0.06439011013611301
+ ],
+ [
+ 0.026495135880510768,
+ 0.02187276595821781,
+ 0.06432288986388698
+ ]
+ ],
+ "mass": 0.0002690235439263718,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD No Mascara Mascara\nA mascara by Perricone MD scientifically formulated for longer, stronger, healthier eye lashes.",
+ "nr_faces": 3432,
+ "nr_vertices": 1828,
+ "surface_area": 0.026573202611032177,
+ "volume": 0.0002690235439263718
+ }
+ },
+ "Perricone_MD_Nutritive_Cleanser": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Nutritive_Cleanser",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04193936930447424,
+ -0.030368611882383365,
+ -0.07397603042979099
+ ],
+ [
+ 0.04199263069552576,
+ 0.029979388117616634,
+ 0.074761969570209
+ ]
+ ],
+ "mass": 0.0006596097088712295,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Nutritive Cleanser\nA nourishing facial wash that removes impurities while delivering superior anti-aging benefits.",
+ "nr_faces": 1980,
+ "nr_vertices": 1089,
+ "surface_area": 0.04722953029352731,
+ "volume": 0.0006596097088712295
+ }
+ },
+ "Perricone_MD_OVM": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_OVM",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05224023505255805,
+ -0.03223351826085098,
+ -0.05231619382305198
+ ],
+ [
+ 0.05247076494744195,
+ 0.032339481739149016,
+ 0.05272680617694802
+ ]
+ ],
+ "mass": 0.0006644122821897669,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD OVM\nBio-matrix technology harnessed from the Eggshell Membrane to deliver the appearance of youthful volume, cushion and firmness.",
+ "nr_faces": 1890,
+ "nr_vertices": 1059,
+ "surface_area": 0.04529615297891426,
+ "volume": 0.0006644122821897669
+ }
+ },
+ "Perricone_MD_Omega_3_Supplements": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Omega_3_Supplements",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03688101392176286,
+ -0.03718787506954818,
+ -0.06319952903134214
+ ],
+ [
+ 0.03700298607823714,
+ 0.036950124930451814,
+ 0.06318847096865786
+ ]
+ ],
+ "mass": 0.0006512669141487227,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Omega 3 Supplements\nA dietary supplement that helps elevate mood, regulate weight and support cardiovascular health. 30 day supply.",
+ "nr_faces": 2198,
+ "nr_vertices": 1208,
+ "surface_area": 0.044718841755573197,
+ "volume": 0.0006512669141487227
+ }
+ },
+ "Perricone_MD_Photo_Plasma": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Photo_Plasma",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.053360115532213294,
+ -0.03256036140907752,
+ -0.05233094922794414
+ ],
+ [
+ 0.052482884467786706,
+ 0.03266463859092249,
+ 0.05265705077205587
+ ]
+ ],
+ "mass": 0.0006603591044164224,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Photo Plasma\nAn anti-aging moisturizer luxurious in texture, oil-free and with broad spectrum SPF 30.",
+ "nr_faces": 12342,
+ "nr_vertices": 6348,
+ "surface_area": 0.04507788012804635,
+ "volume": 0.0006603591044164224
+ }
+ },
+ "Perricone_MD_Skin_Clear_Supplements": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Skin_Clear_Supplements",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0845110135580303,
+ -0.06589111545069716,
+ -0.04681653197357991
+ ],
+ [
+ 0.08444398644196971,
+ 0.06569288454930283,
+ 0.046861468026420085
+ ]
+ ],
+ "mass": 0.001980234936269448,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Skin Clear Supplements\nA comprehensive vitamin supplement that works from the inside out to help clear skin and prevent breakouts.",
+ "nr_faces": 2294,
+ "nr_vertices": 1271,
+ "surface_area": 0.09483060470270029,
+ "volume": 0.001980234936269448
+ }
+ },
+ "Perricone_MD_Skin_Total_Body_Supplements": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Skin_Total_Body_Supplements",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06661169270388206,
+ -0.06614618979233952,
+ -0.08744706477432301
+ ],
+ [
+ 0.06618730729611794,
+ 0.06567781020766049,
+ 0.08753793522567699
+ ]
+ ],
+ "mass": 0.002943962992664656,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Skin & Total Body Supplements\nSkin & Total Body Dietary Supplements are targeted nutritional supplements and an essential part of Dr. Perricone's 3-Tier Approach for a healthy body and beautiful skin.",
+ "nr_faces": 1690,
+ "nr_vertices": 919,
+ "surface_area": 0.12054998270251892,
+ "volume": 0.002943962992664656
+ }
+ },
+ "Perricone_MD_Super_Berry_Powder_with_Acai_Supplements": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Super_Berry_Powder_with_Acai_Supplements",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.045501430547218336,
+ -0.04508961916319542,
+ -0.07502820757221729
+ ],
+ [
+ 0.04534656945278166,
+ 0.04464038083680458,
+ 0.07481179242778273
+ ]
+ ],
+ "mass": 0.0011553494513661547,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Super Berry Powder with Acai Supplements\nA dietary supplement powder that provides antioxidant protection to help defer the visible signs of aging.",
+ "nr_faces": 2198,
+ "nr_vertices": 1186,
+ "surface_area": 0.06539992002656997,
+ "volume": 0.0011553494513661547
+ }
+ },
+ "Perricone_MD_The_Cold_Plasma_Face_Eyes_Duo": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_The_Cold_Plasma_Face_Eyes_Duo",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.066064776145767,
+ -0.034215937661292106,
+ -0.05981279316603007
+ ],
+ [
+ 0.065541223854233,
+ 0.03429606233870789,
+ 0.06002320683396993
+ ]
+ ],
+ "mass": 0.001011422742830388,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD The Cold Plasma Face & Eyes Duo\nTwo best selling products to treat the 10 most visible signs of aging. With proprietary Cold Plasma delivery system.",
+ "nr_faces": 8922,
+ "nr_vertices": 4666,
+ "surface_area": 0.061494907525475664,
+ "volume": 0.001011422742830388
+ }
+ },
+ "Perricone_MD_The_Crease_Cure_Duo": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_The_Crease_Cure_Duo",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08445688047377883,
+ -0.0329725346241186,
+ -0.05952902902321509
+ ],
+ [
+ 0.08499711952622116,
+ 0.0338494653758814,
+ 0.06006697097678492
+ ]
+ ],
+ "mass": 0.0012047616713304656,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD The Crease Cure Duo\nThe perfect duo to combat deep lines, creases and advanced signs of aging. With patent-pending Acyl Glutathione.",
+ "nr_faces": 6712,
+ "nr_vertices": 3576,
+ "surface_area": 0.0724259589000533,
+ "volume": 0.0012047616713304656
+ }
+ },
+ "Perricone_MD_The_Metabolic_Formula_Supplements": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_The_Metabolic_Formula_Supplements",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.048114571018457314,
+ -0.04598901260691788,
+ -0.0836904579981645
+ ],
+ [
+ 0.047708428981542685,
+ 0.04627998739308212,
+ 0.08478054200183549
+ ]
+ ],
+ "mass": 0.00139794857245231,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD The Metabolic Formula Supplements\nA 10-day dietary supplement program to promote healthy weight maintenance.",
+ "nr_faces": 2158,
+ "nr_vertices": 1165,
+ "surface_area": 0.07523782693338092,
+ "volume": 0.00139794857245231
+ }
+ },
+ "Perricone_MD_The_Power_Treatments": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_The_Power_Treatments",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10564054097956709,
+ -0.026833127839747777,
+ -0.07896150992197461
+ ],
+ [
+ 0.1052154590204329,
+ 0.027646872160252224,
+ 0.0800184900780254
+ ]
+ ],
+ "mass": 0.0016263561070943514,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD The Power Treatments\nA collection of Dr. Perricone's most powerful and effective anti-aging treatments.",
+ "nr_faces": 1252,
+ "nr_vertices": 691,
+ "surface_area": 0.09865851912445384,
+ "volume": 0.0016263561070943514
+ }
+ },
+ "Perricone_MD_Vitamin_C_Ester_15": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Vitamin_C_Ester_15",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04040107050722139,
+ -0.03183525485003063,
+ -0.06524260458438558
+ ],
+ [
+ 0.040673929492778614,
+ 0.03169874514996937,
+ 0.06510539541561443
+ ]
+ ],
+ "mass": 0.0006394643437332647,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Vitamin C Ester 15\nAn anti-aging treatment to address sun damage, loss of firmness, wrinkles, and boost collagen production.",
+ "nr_faces": 1776,
+ "nr_vertices": 998,
+ "surface_area": 0.04517845775935379,
+ "volume": 0.0006394643437332647
+ }
+ },
+ "Perricone_MD_Vitamin_C_Ester_Serum": {
+ "asset_type": "FileBasedObject",
+ "id": "Perricone_MD_Vitamin_C_Ester_Serum",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04019980593361755,
+ -0.027966706594972364,
+ -0.05268732096924492
+ ],
+ [
+ 0.03995319406638245,
+ 0.028011293405027636,
+ 0.052586679030755076
+ ]
+ ],
+ "mass": 0.0004497185027785426,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Perricone MD Vitamin C Ester Serum\nA vitamin c ester serum formulated to diminish the appearance of melasma, age spots, and brown spots.",
+ "nr_faces": 2260,
+ "nr_vertices": 1247,
+ "surface_area": 0.03522732358036998,
+ "volume": 0.0004497185027785426
+ }
+ },
+ "Persona_Q_Shadow_of_the_Labyrinth_Nintendo_3DS": {
+ "asset_type": "FileBasedObject",
+ "id": "Persona_Q_Shadow_of_the_Labyrinth_Nintendo_3DS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07115944982233569,
+ -0.012727825537173755,
+ -0.06431725179486648
+ ],
+ [
+ 0.07117955017766431,
+ 0.012759174462826244,
+ 0.06469974820513352
+ ]
+ ],
+ "mass": 0.0004210466101356217,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Persona Q: Shadow of the Labyrinth [Nintendo 3DS]",
+ "nr_faces": 7168,
+ "nr_vertices": 3741,
+ "surface_area": 0.04650285990239815,
+ "volume": 0.0004210466101356217
+ }
+ },
+ "Pet_Dophilus_powder": {
+ "asset_type": "FileBasedObject",
+ "id": "Pet_Dophilus_powder",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.027870877183274977,
+ -0.027879421667531146,
+ -0.04736499477888397
+ ],
+ [
+ 0.027928122816725024,
+ 0.027736578332468856,
+ 0.05490700522111603
+ ]
+ ],
+ "mass": 0.00021593626767127866,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Pet Dophilus, powder",
+ "nr_faces": 9120,
+ "nr_vertices": 4675,
+ "surface_area": 0.020738229754106663,
+ "volume": 0.00021593626767127866
+ }
+ },
+ "Philips_60ct_Warm_White_LED_Smooth_Mini_String_Lights": {
+ "asset_type": "FileBasedObject",
+ "id": "Philips_60ct_Warm_White_LED_Smooth_Mini_String_Lights",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06658078046734626,
+ -0.037527423480755585,
+ -0.12862546847273246
+ ],
+ [
+ 0.06599821953265374,
+ 0.03854157651924441,
+ 0.12938853152726754
+ ]
+ ],
+ "mass": 0.002436831082218998,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Philips 60ct Warm White LED Smooth Mini String Lights",
+ "nr_faces": 1504,
+ "nr_vertices": 816,
+ "surface_area": 0.11874206084022276,
+ "volume": 0.002436831082218998
+ }
+ },
+ "Philips_EcoVantage_43_W_Light_Bulbs_Natural_Light_2_pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Philips_EcoVantage_43_W_Light_Bulbs_Natural_Light_2_pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0534237756908235,
+ -0.03365938757653393,
+ -0.05391838341856539
+ ],
+ [
+ 0.0534832243091765,
+ 0.033647612423466075,
+ 0.0539376165814346
+ ]
+ ],
+ "mass": 0.0007204367408784748,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Philips EcoVantage 43 W Light Bulbs, Natural Light - 2 pack",
+ "nr_faces": 4484,
+ "nr_vertices": 2376,
+ "surface_area": 0.04780904142947405,
+ "volume": 0.0007204367408784748
+ }
+ },
+ "Philips_Sonicare_Tooth_Brush_2_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Philips_Sonicare_Tooth_Brush_2_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08806046453707715,
+ -0.05174089194396521,
+ -0.12074859742037977
+ ],
+ [
+ 0.08785953546292286,
+ 0.05226210805603479,
+ 0.12086240257962022
+ ]
+ ],
+ "mass": 0.004095569336245056,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Philips Sonicare Tooth Brush - 2 count",
+ "nr_faces": 2180,
+ "nr_vertices": 1194,
+ "surface_area": 0.15918739023050227,
+ "volume": 0.004095569336245056
+ }
+ },
+ "Phillips_Caplets_Size_24": {
+ "asset_type": "FileBasedObject",
+ "id": "Phillips_Caplets_Size_24",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.039529966509634924,
+ -0.02251001823673516,
+ -0.04283934746477854
+ ],
+ [
+ 0.039323033490365075,
+ 0.02247398176326484,
+ 0.04290065253522146
+ ]
+ ],
+ "mass": 0.0002848301770994458,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Phillips Caplets Size: 24\nLaxative Dietary Supplement. Genuine. Comfortable relief. Convenient. Easy-to-swallow. Stimulant free. Cramp free. Comfortable, cramp-free relief of occasional constipation. Is the only line of stimulant-free laxatives for overnight relief. Nothing's been proven more effective and gentle than Phillips. Please visit our website at www.bayercare.com. (This statement has not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.) Made in USA.",
+ "nr_faces": 3724,
+ "nr_vertices": 2015,
+ "surface_area": 0.02612826444222044,
+ "volume": 0.0002848301770994458
+ }
+ },
+ "Phillips_Colon_Health_Probiotic_Capsule": {
+ "asset_type": "FileBasedObject",
+ "id": "Phillips_Colon_Health_Probiotic_Capsule",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05172964758072801,
+ -0.02871348372673953,
+ -0.05934637355899172
+ ],
+ [
+ 0.05220535241927199,
+ 0.02841051627326047,
+ 0.05881462644100827
+ ]
+ ],
+ "mass": 0.0006626993474137503,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Phillips Colon Health Probiotic Capsule",
+ "nr_faces": 3166,
+ "nr_vertices": 1717,
+ "surface_area": 0.047229772262240635,
+ "volume": 0.0006626993474137503
+ }
+ },
+ "Phillips_Milk_of_Magnesia_Saline_Laxative_Liquid_Original": {
+ "asset_type": "FileBasedObject",
+ "id": "Phillips_Milk_of_Magnesia_Saline_Laxative_Liquid_Original",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03624156309345779,
+ -0.028593514464098815,
+ -0.07619057060376586
+ ],
+ [
+ 0.03649443690654221,
+ 0.028256485535901186,
+ 0.09795042939623413
+ ]
+ ],
+ "mass": 0.0004683770354062362,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Phillips Milk of Magnesia Saline Laxative Liquid Original",
+ "nr_faces": 9778,
+ "nr_vertices": 5016,
+ "surface_area": 0.03655311745292876,
+ "volume": 0.0004683770354062362
+ }
+ },
+ "Phillips_Stool_Softener_Liquid_Gels_30_liquid_gels": {
+ "asset_type": "FileBasedObject",
+ "id": "Phillips_Stool_Softener_Liquid_Gels_30_liquid_gels",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03950438352934151,
+ -0.022128218475772475,
+ -0.043269952920357006
+ ],
+ [
+ 0.03946361647065849,
+ 0.022493781524227527,
+ 0.043426047079643
+ ]
+ ],
+ "mass": 0.0002900269584232543,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Phillips Stool Softener, Liquid Gels - 30 liquid gels\nOther Information: Each Softgel Contains: sodium 6 mg. Very low sodium. Store at room temperature. Avoid excessive heat 104 degrees F (40 degrees C). Misc: Docusate sodium. Genuine. Gentle, dependable relief. No. 1 doctor recommended among stool softener ingredients. Stimulant free. Cramp free. Phillips' Milk of Magnesia has provided stimulant-free relief of constipation for over 125 years. Easy-to-swallow Phillips' Liquid Gels contain the No. 1 doctor recommended stool softening ingredient and provide effective relief of occasional constipation. Unlike some other laxatives, Phillips' Liquid Gels do not contain the harsh stimulants that can cause pain and cramping. Liquid Gels help you feel your best by gently drawing water into the stool making it more comfortable to pass. As with any laxative, your dose should be adjusted within the label directions to meet your own body's needs. Many people find 2 liquid gels to be an effective starting adult dosage. Phillips' comfortable, cramp-free relief. www.bayercare.com. Made in USA.",
+ "nr_faces": 3534,
+ "nr_vertices": 1887,
+ "surface_area": 0.02648886280812595,
+ "volume": 0.0002900269584232543
+ }
+ },
+ "PhosphOmega": {
+ "asset_type": "FileBasedObject",
+ "id": "PhosphOmega",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.030291247952473777,
+ -0.030579708338942364,
+ -0.05189568111751792
+ ],
+ [
+ 0.030362752047526222,
+ 0.030429291661057636,
+ 0.060508318882482086
+ ]
+ ],
+ "mass": 0.0002816827226040713,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "PhosphOmega",
+ "nr_faces": 9488,
+ "nr_vertices": 4930,
+ "surface_area": 0.024939561191795002,
+ "volume": 0.0002816827226040713
+ }
+ },
+ "Pinwheel_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Pinwheel_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11116496978590741,
+ -0.04954771059766817,
+ -0.04215377020806541
+ ],
+ [
+ 0.10633403021409259,
+ 0.044531289402331836,
+ 0.04812222979193459
+ ]
+ ],
+ "mass": 0.0010679544986401017,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Pinwheel Pencil Case",
+ "nr_faces": 11852,
+ "nr_vertices": 6263,
+ "surface_area": 0.0658934321104529,
+ "volume": 0.0010679544986401017
+ }
+ },
+ "Playmates_Industrial_CoSplinter_Teenage_Mutant_Ninja_Turtle_Action_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Playmates_Industrial_CoSplinter_Teenage_Mutant_Ninja_Turtle_Action_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0374900855464806,
+ -0.04274985707699834,
+ -0.0577343951639523
+ ],
+ [
+ 0.0453779144535194,
+ 0.04936914292300166,
+ 0.0659786048360477
+ ]
+ ],
+ "mass": 8.68598814899555e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Playmates Industrial Co.Splinter Teenage Mutant Ninja Turtle Action Figure",
+ "nr_faces": 22342,
+ "nr_vertices": 12434,
+ "surface_area": 0.027264846748944048,
+ "volume": 8.68598814899555e-05
+ }
+ },
+ "Playmates_nickelodeon_teenage_mutant_ninja_turtles_shredder": {
+ "asset_type": "FileBasedObject",
+ "id": "Playmates_nickelodeon_teenage_mutant_ninja_turtles_shredder",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.044106282943281346,
+ -0.027478738309529214,
+ -0.06660033008291255
+ ],
+ [
+ 0.04800171705671866,
+ 0.021628261690470784,
+ 0.07495966991708745
+ ]
+ ],
+ "mass": 8.039806955812383e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Playmates nickelodeon teenage mutant ninja turtles, shredder",
+ "nr_faces": 31290,
+ "nr_vertices": 17948,
+ "surface_area": 0.026371479569682374,
+ "volume": 8.039806955812383e-05
+ }
+ },
+ "Poise_Ultimate_Pads_Long": {
+ "asset_type": "FileBasedObject",
+ "id": "Poise_Ultimate_Pads_Long",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18867080481415288,
+ -0.07046788163121451,
+ -0.11029406377378896
+ ],
+ [
+ 0.1836541951858471,
+ 0.07040511836878549,
+ 0.11404693622621104
+ ]
+ ],
+ "mass": 0.009701699709206257,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Poise Ultimate Pads Long\nDiscreet bladder protection. Leak-block sides. Absorb-loc core. Secure overnight protection. Fresh new look & dry-touch layer. Discreet and worry-free protection. Our most coverage Poise pad! Individually wrapped. Absorb-loc core quickly locks away wetness and odor. Dry-touch layer for your comfort. Leak-block sides for outstanding protection. Distributed in the USA. Made in the USA from domestic and imported material.",
+ "nr_faces": 9030,
+ "nr_vertices": 4861,
+ "surface_area": 0.2792803343095374,
+ "volume": 0.009701699709206257
+ }
+ },
+ "Pokmon_Conquest_Nintendo_DS_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Pokmon_Conquest_Nintendo_DS_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06681423007315598,
+ -0.062261701386043776,
+ -0.008532241036015112
+ ],
+ [
+ 0.07094476992684401,
+ 0.062232298613956225,
+ 0.009033758963984888
+ ]
+ ],
+ "mass": 0.00026504395008527013,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Pok?mon Conquest [Nintendo DS Game]",
+ "nr_faces": 3964,
+ "nr_vertices": 2099,
+ "surface_area": 0.04151890622353906,
+ "volume": 0.00026504395008527013
+ }
+ },
+ "Pokmon_X_Nintendo_3DS_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Pokmon_X_Nintendo_3DS_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06682714904754948,
+ -0.06228466729381637,
+ -0.007237561175634308
+ ],
+ [
+ 0.07018885095245052,
+ 0.06261133270618363,
+ 0.00783843882436569
+ ]
+ ],
+ "mass": 0.00022712271304441497,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Pok?mon X [Nintendo 3DS Game]",
+ "nr_faces": 2328,
+ "nr_vertices": 1260,
+ "surface_area": 0.040028879773241564,
+ "volume": 0.00022712271304441497
+ }
+ },
+ "Pokmon_Y_Nintendo_3DS_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Pokmon_Y_Nintendo_3DS_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0665877644650445,
+ -0.06263333830498878,
+ -0.007505797275072796
+ ],
+ [
+ 0.0709292355349555,
+ 0.06266866169501123,
+ 0.008297202724927205
+ ]
+ ],
+ "mass": 0.00023018405896814897,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Pok?mon Y [Nintendo 3DS Game]",
+ "nr_faces": 2680,
+ "nr_vertices": 1446,
+ "surface_area": 0.0403472131276783,
+ "volume": 0.00023018405896814897
+ }
+ },
+ "Pok\u00e9mon_Omega_Ruby_Alpha_Sapphire_Dual_Pack_Nintendo_3DS": {
+ "asset_type": "FileBasedObject",
+ "id": "Pok\u00e9mon_Omega_Ruby_Alpha_Sapphire_Dual_Pack_Nintendo_3DS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07131471377397437,
+ -0.016672737910896806,
+ -0.06514961006709555
+ ],
+ [
+ 0.07214728622602563,
+ 0.016908262089103194,
+ 0.06555038993290446
+ ]
+ ],
+ "mass": 0.0005377133390661974,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Pok\u00e9mon: Omega Ruby + Alpha Sapphire Dual Pack [Nintendo 3DS]",
+ "nr_faces": 2486,
+ "nr_vertices": 1347,
+ "surface_area": 0.05033677211325851,
+ "volume": 0.0005377133390661974
+ }
+ },
+ "Pok\u00e9mon_Yellow_Special_Pikachu_Edition_Nintendo_Game_Boy_Color": {
+ "asset_type": "FileBasedObject",
+ "id": "Pok\u00e9mon_Yellow_Special_Pikachu_Edition_Nintendo_Game_Boy_Color",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.028849546058619686,
+ -0.005812545047636779,
+ -0.031993024680631955
+ ],
+ [
+ 0.029104453941380316,
+ 0.004851454952363221,
+ 0.03375097531936804
+ ]
+ ],
+ "mass": 3.113093480536833e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Pok\u00e9mon Yellow: Special Pikachu Edition, Nintendo Game Boy Color",
+ "nr_faces": 7498,
+ "nr_vertices": 3898,
+ "surface_area": 0.009391065812682557,
+ "volume": 3.113093480536833e-05
+ }
+ },
+ "Polar_Herring_Fillets_Smoked_Peppered_705_oz_total": {
+ "asset_type": "FileBasedObject",
+ "id": "Polar_Herring_Fillets_Smoked_Peppered_705_oz_total",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07573533934436522,
+ -0.016653700851637834,
+ -0.04098804983379381
+ ],
+ [
+ 0.07480466065563478,
+ 0.014864299148362167,
+ 0.04330395016620619
+ ]
+ ],
+ "mass": 0.00021703985540994566,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Polar Herring Fillets, Smoked Peppered - 7.05 oz total",
+ "nr_faces": 7338,
+ "nr_vertices": 3773,
+ "surface_area": 0.03196437518594257,
+ "volume": 0.00021703985540994566
+ }
+ },
+ "Pony_C_Clamp_1440": {
+ "asset_type": "FileBasedObject",
+ "id": "Pony_C_Clamp_1440",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1035262294882226,
+ -0.06971504082245195,
+ -0.010657198728643005
+ ],
+ [
+ 0.0986907705117774,
+ 0.10304395917754806,
+ 0.016729801271356995
+ ]
+ ],
+ "mass": 8.869907120732216e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Pony C Clamp, 1440",
+ "nr_faces": 16180,
+ "nr_vertices": 8575,
+ "surface_area": 0.034306552543272084,
+ "volume": 8.869907120732216e-05
+ }
+ },
+ "Poppin_File_Sorter_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Poppin_File_Sorter_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12540166601906377,
+ -0.08651235899102758,
+ -0.018018541534829038
+ ],
+ [
+ 0.1249233339809362,
+ 0.08718864100897242,
+ 0.13555245846517097
+ ]
+ ],
+ "mass": 0.0007330209180376958,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Poppin File Sorter, Blue",
+ "nr_faces": 6188,
+ "nr_vertices": 3487,
+ "surface_area": 0.13606617132137672,
+ "volume": 0.0007330209180376958
+ }
+ },
+ "Poppin_File_Sorter_Pink": {
+ "asset_type": "FileBasedObject",
+ "id": "Poppin_File_Sorter_Pink",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08681994183999421,
+ -0.12521264094247264,
+ -0.01714483901481081
+ ],
+ [
+ 0.08710205816000578,
+ 0.12506135905752735,
+ 0.1398091609851892
+ ]
+ ],
+ "mass": 0.0007234951272719047,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Poppin File Sorter, Pink",
+ "nr_faces": 6834,
+ "nr_vertices": 3823,
+ "surface_area": 0.13701518356740575,
+ "volume": 0.0007234951272719047
+ }
+ },
+ "Poppin_File_Sorter_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Poppin_File_Sorter_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1251588476092332,
+ -0.08698348004797339,
+ -0.018667033292982322
+ ],
+ [
+ 0.1254811523907668,
+ 0.08693251995202661,
+ 0.13739496670701767
+ ]
+ ],
+ "mass": 0.0007415628229421657,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Poppin File Sorter, White",
+ "nr_faces": 6440,
+ "nr_vertices": 3617,
+ "surface_area": 0.1380666838116782,
+ "volume": 0.0007415628229421657
+ }
+ },
+ "Predator_LZ_TRX_FG": {
+ "asset_type": "FileBasedObject",
+ "id": "Predator_LZ_TRX_FG",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04977448301447712,
+ -0.1315008521231232,
+ -0.04302534203675097
+ ],
+ [
+ 0.04751151698552288,
+ 0.1520221478768768,
+ 0.07774265796324903
+ ]
+ ],
+ "mass": 0.0007559910084305321,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Predator LZ TRX FG",
+ "nr_faces": 22122,
+ "nr_vertices": 12489,
+ "surface_area": 0.11256952559975007,
+ "volume": 0.0007559910084305321
+ }
+ },
+ "Predito_LZ_TRX_FG_W": {
+ "asset_type": "FileBasedObject",
+ "id": "Predito_LZ_TRX_FG_W",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.050917314129331474,
+ -0.13885641824738615,
+ -0.042350178703481844
+ ],
+ [
+ 0.04024768587066853,
+ 0.12214158175261383,
+ 0.07032682129651815
+ ]
+ ],
+ "mass": 0.0007012814518141755,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Predito LZ TRX FG W",
+ "nr_faces": 24280,
+ "nr_vertices": 13776,
+ "surface_area": 0.11750271524767442,
+ "volume": 0.0007012814518141755
+ }
+ },
+ "ProSport_Harness_to_Booster_Seat": {
+ "asset_type": "FileBasedObject",
+ "id": "ProSport_Harness_to_Booster_Seat",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11586140469412057,
+ -0.11343631530470635,
+ -0.019896696495982243
+ ],
+ [
+ 0.11127259530587942,
+ 0.11380868469529365,
+ 0.03469930350401776
+ ]
+ ],
+ "mass": 0.0005901642766282428,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Car Seat",
+ "description": "ProSport Harness to Booster Seat",
+ "nr_faces": 32868,
+ "nr_vertices": 20015,
+ "surface_area": 0.11713405311466865,
+ "volume": 0.0005901642766282428
+ }
+ },
+ "Progressive_Rubber_Spatulas_3_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Progressive_Rubber_Spatulas_3_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08987918501385013,
+ -0.16144209665826875,
+ -0.00781380354462845
+ ],
+ [
+ 0.09068381498614987,
+ 0.09824090334173126,
+ 0.013040196455371552
+ ]
+ ],
+ "mass": 0.00012489017780324316,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Progressive Rubber Spatulas - 3 count",
+ "nr_faces": 4212,
+ "nr_vertices": 2410,
+ "surface_area": 0.046516832785265916,
+ "volume": 0.00012489017780324316
+ }
+ },
+ "Prostate_Optimizer": {
+ "asset_type": "FileBasedObject",
+ "id": "Prostate_Optimizer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.030865289040386996,
+ -0.030433462930218192,
+ -0.05081976305601525
+ ],
+ [
+ 0.030797710959613006,
+ 0.03062853706978181,
+ 0.05951023694398475
+ ]
+ ],
+ "mass": 0.00027921402030766214,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Prostate Optimizer",
+ "nr_faces": 18954,
+ "nr_vertices": 9639,
+ "surface_area": 0.024589788087003937,
+ "volume": 0.00027921402030766214
+ }
+ },
+ "Provence_Bath_Towel_Royal_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Provence_Bath_Towel_Royal_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1346122480569644,
+ -0.1808958327642534,
+ -0.0359871913845198
+ ],
+ [
+ 0.1283837519430356,
+ 0.1752651672357466,
+ 0.052251808615480205
+ ]
+ ],
+ "mass": 0.005404254030308144,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Provence Bath Towel, Royal Blue",
+ "nr_faces": 101142,
+ "nr_vertices": 53409,
+ "surface_area": 0.2707362499030643,
+ "volume": 0.005404254030308144
+ }
+ },
+ "PureCadence_2_Color_HiRskRedNghtlfeSlvrBlckWht_Size_70": {
+ "asset_type": "FileBasedObject",
+ "id": "PureCadence_2_Color_HiRskRedNghtlfeSlvrBlckWht_Size_70",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06531659354434786,
+ -0.16415730227144085,
+ -0.03784427806160624
+ ],
+ [
+ 0.05255540645565213,
+ 0.14195369772855915,
+ 0.09213172193839375
+ ]
+ ],
+ "mass": 0.0011226589915657359,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "PureCadence 2, Color: HiRskRed/Nghtlf/eSlvr/Blck/Wht, Size: 7.0\nWith lean construction and a responsive fit, the PureCadence 2 rethinks how support technology is engineered. Features like the internal PDRB help prevent overpronation without added parts and the wide Nav Band holds your foot like an endless hug. Add fresh looks and some street cred, and this featherweight friend will run footloose and fancy-free with you. Just like our core line, we hold PureProject to the industry's highest weartest and durability standards. Because of their lightweight construction and fewer materials, runners should generally expect shoes from the PureProject line to last approximately 250-300 miles. > See the Women's PureCadence 2Category: Support Weight: 9.3 oz Platform: Anatomical Last Construction: Stroebel Launch Date: December 1, 2012 Technologies • BioMoGo DNA Midsole • IDEAL Heel • Toe Flex • Nav Band • Anatomical Last",
+ "nr_faces": 37382,
+ "nr_vertices": 20859,
+ "surface_area": 0.16839072130756372,
+ "volume": 0.0011226589915657359
+ }
+ },
+ "PureCadence_2_Color_TleBluLmePnchSlvMoodIndgWh_Size_50_EEzAfcBfHHO": {
+ "asset_type": "FileBasedObject",
+ "id": "PureCadence_2_Color_TleBluLmePnchSlvMoodIndgWh_Size_50_EEzAfcBfHHO",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.061377399120067073,
+ -0.15397806868549815,
+ -0.036348630703539574
+ ],
+ [
+ 0.049785600879932924,
+ 0.13285093131450185,
+ 0.07788636929646042
+ ]
+ ],
+ "mass": 0.0009516723010773404,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "PureCadence 2, Color: TleBlu/LmePnch/Slv/MoodIndg/Wh, Size: 5.0\nWith lean construction and a responsive fit, the PureCadence 2 rethinks how support technology is engineered. Features like the internal PDRB help prevent overpronation without added parts and the wide Nav Band holds your foot like an endless hug. Add fresh looks and some street cred, and this featherweight friend will run footloose and fancy-free with you. Just like our core line, we hold PureProject to the industry's highest weartest and durability standards. Because of their lightweight construction and fewer materials, runners should generally expect shoes from the PureProject line to last approximately 250-300 miles. > See the Men's PureCadence 2Category: Support Weight: 7.7 oz Platform: Anatomical Last Construction: Stroebel Launch Date: December 1, 2012 Technologies • BioMoGo DNA Midsole • IDEAL Heel • Toe Flex • Nav Band • Anatomical Last",
+ "nr_faces": 35224,
+ "nr_vertices": 19938,
+ "surface_area": 0.14294016510861485,
+ "volume": 0.0009516723010773404
+ }
+ },
+ "PureConnect_2_Color_AnthrcteKnckoutPnkGrnGecko_Size_50": {
+ "asset_type": "FileBasedObject",
+ "id": "PureConnect_2_Color_AnthrcteKnckoutPnkGrnGecko_Size_50",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05547754603736002,
+ -0.13431079983100314,
+ -0.037340513276876625
+ ],
+ [
+ 0.04845545396263998,
+ 0.13651720016899685,
+ 0.07611148672312337
+ ]
+ ],
+ "mass": 0.0008392262300388625,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "PureConnect 2, Color: Anthrcte/KnckoutPnk/GrnGecko, Size: 5.0\nEmbrace the ground beneath you with the featherweight feel and pliable flex of the PureConnect 2. This slim and nimble turn-hugger is the perfect fit when you crave less shoe and more freedom. A split toe groove extends toward the midfoot, engaging the natural movement of the foot and letting you feel every nuance of the run. With rad looks, the baby is ready to run, right out of the box. Just like our core line, we hold PureProject to the industry's highest weartest and durability standards. Because of their lightweight construction and fewer materials, runners should generally expect shoes from the PureProject line to last approximately 250-300 miles. > See the Men's PureConnect 2Category: Neutral Weight: 5.9 oz Platform: Anatomical Last Construction: Stroebel Launch Date: January 1, 2013 Technologies • BioMoGo DNA Midsole • IDEAL Heel • Toe Flex • Nav Band • Anatomical Last",
+ "nr_faces": 29120,
+ "nr_vertices": 15693,
+ "surface_area": 0.11390737812558685,
+ "volume": 0.0008392262300388625
+ }
+ },
+ "PureConnect_2_Color_BlckBrllntBluNghtlfeAnthrct_Size_70": {
+ "asset_type": "FileBasedObject",
+ "id": "PureConnect_2_Color_BlckBrllntBluNghtlfeAnthrct_Size_70",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06270930577642848,
+ -0.17026184975797232,
+ -0.04205011692568606
+ ],
+ [
+ 0.056626694223571514,
+ 0.1525781502420277,
+ 0.09146988307431393
+ ]
+ ],
+ "mass": 0.0011877738116361752,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "PureConnect 2, Color: Blck/BrllntBlu/Nghtlfe/Anthrct, Size: 7.0\nEmbrace the ground beneath you with the featherweight feel and pliable flex of the PureConnect 2. This slim and nimble turn-hugger is the perfect fit when you crave less shoe and more freedom. A split toe groove extends toward the midfoot, engaging the natural movement of the foot and letting you feel every nuance of the run. With rad looks, the baby is ready to run, right out of the box. Just like our core line, we hold PureProject to the industry's highest weartest and durability standards. Because of their lightweight construction and fewer materials, runners should generally expect shoes from the PureProject line to last approximately 250-300 miles. > See the Women's PureConnect 2Category: Neutral Weight: 7.2 oz Platform: Anatomical Last Construction: Stroebel Launch Date: January 1, 2013 Technologies • BioMoGo DNA Midsole • IDEAL Heel • Toe Flex • Nav Band • Anatomical Last",
+ "nr_faces": 33976,
+ "nr_vertices": 18611,
+ "surface_area": 0.18290632819654448,
+ "volume": 0.0011877738116361752
+ }
+ },
+ "PureConnect_2_Color_FernNightlifeSilverBlack_Size_70_5w0BYsiogeV": {
+ "asset_type": "FileBasedObject",
+ "id": "PureConnect_2_Color_FernNightlifeSilverBlack_Size_70_5w0BYsiogeV",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05829588818767737,
+ -0.15283050851546168,
+ -0.03896862924571222
+ ],
+ [
+ 0.05097611181232263,
+ 0.14219749148453834,
+ 0.08432237075428778
+ ]
+ ],
+ "mass": 0.0009558999392583752,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "PureConnect 2, Color: Fern/Nightlife/Silver/Black, Size: 7.0\nEmbrace the ground beneath you with the featherweight feel and pliable flex of the PureConnect 2. This slim and nimble turn-hugger is the perfect fit when you crave less shoe and more freedom. A split toe groove extends toward the midfoot, engaging the natural movement of the foot and letting you feel every nuance of the run. With rad looks, the baby is ready to run, right out of the box. Just like our core line, we hold PureProject to the industry's highest weartest and durability standards. Because of their lightweight construction and fewer materials, runners should generally expect shoes from the PureProject line to last approximately 250-300 miles. > See the Women's PureConnect 2Category: Neutral Weight: 7.2 oz Platform: Anatomical Last Construction: Stroebel Launch Date: January 1, 2013 Technologies • BioMoGo DNA Midsole • IDEAL Heel • Toe Flex • Nav Band • Anatomical Last",
+ "nr_faces": 30128,
+ "nr_vertices": 16985,
+ "surface_area": 0.1508043343956083,
+ "volume": 0.0009558999392583752
+ }
+ },
+ "PureFlow_2_Color_RylPurHibiscusBlkSlvrWht_Size_50": {
+ "asset_type": "FileBasedObject",
+ "id": "PureFlow_2_Color_RylPurHibiscusBlkSlvrWht_Size_50",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06399754504255364,
+ -0.14056944136709226,
+ -0.03807123175902643
+ ],
+ [
+ 0.05162045495744635,
+ 0.14619255863290773,
+ 0.08155976824097357
+ ]
+ ],
+ "mass": 0.0012001350428794272,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "PureFlow 2, Color: RylPur/Hibiscus/Blk/Slvr/Wht, Size: 5.0\nLike peanut butter and jelly or water and energy gels, the lightweight construction and lush cushioning of the PureFlow 2 are a perfect match. The key to blending the two is engineering comfort features in a lean way like a shaped BioMoGo DNA midsole that gives your feet a cushy feel without added materials. It's a match your feet will hunger for. Just like our core line, we hold PureProject to the industry's highest weartest and durability standards. Because of their lightweight construction and fewer materials, runners should generally expect shoes from the PureProject line to last approximately 250-300 miles. > See the Men's PureFlow 2Category: Guidance Weight: 7.2 oz Platform: Anatomical Last Construction: Stroebel Launch Date: December 1, 2012 Technologies • BioMoGo DNA Midsole • IDEAL Heel • Toe Flex • Nav Band • Anatomical Last",
+ "nr_faces": 26280,
+ "nr_vertices": 14536,
+ "surface_area": 0.11588625575896261,
+ "volume": 0.0012001350428794272
+ }
+ },
+ "QAbsorb_CoQ10": {
+ "asset_type": "FileBasedObject",
+ "id": "QAbsorb_CoQ10",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.028876443497031206,
+ -0.028408024617712076,
+ -0.04657236043916698
+ ],
+ [
+ 0.028550556502968793,
+ 0.028457975382287923,
+ 0.052736639560833014
+ ]
+ ],
+ "mass": 0.00022381714067970933,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Q-Absorb Co-Q10",
+ "nr_faces": 8558,
+ "nr_vertices": 4401,
+ "surface_area": 0.021065114849130064,
+ "volume": 0.00022381714067970933
+ }
+ },
+ "QAbsorb_CoQ10_53iUqjWjW3O": {
+ "asset_type": "FileBasedObject",
+ "id": "QAbsorb_CoQ10_53iUqjWjW3O",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02854787341991807,
+ -0.028591787701729387,
+ -0.04667939506687309
+ ],
+ [
+ 0.028406126580081927,
+ 0.028716212298270614,
+ 0.052638604933126915
+ ]
+ ],
+ "mass": 0.00022275379235971748,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Q-Absorb Co-Q10",
+ "nr_faces": 9584,
+ "nr_vertices": 4924,
+ "surface_area": 0.020917503045616154,
+ "volume": 0.00022275379235971748
+ }
+ },
+ "QHPomegranate": {
+ "asset_type": "FileBasedObject",
+ "id": "QHPomegranate",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.027020372489915807,
+ -0.026886958870045448,
+ -0.04459716240747094
+ ],
+ [
+ 0.027039627510084194,
+ 0.026888041129954552,
+ 0.05324683759252906
+ ]
+ ],
+ "mass": 0.00019072434753093065,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "QH-Pomegranate",
+ "nr_faces": 10176,
+ "nr_vertices": 5212,
+ "surface_area": 0.01911047199047119,
+ "volume": 0.00019072434753093065
+ }
+ },
+ "Quercetin_500": {
+ "asset_type": "FileBasedObject",
+ "id": "Quercetin_500",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.040550011227372396,
+ -0.0402881377165262,
+ -0.0665702733418895
+ ],
+ [
+ 0.040420988772627606,
+ 0.0401038622834738,
+ 0.07757672665811048
+ ]
+ ],
+ "mass": 0.0006387812007745929,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Quercetin 500",
+ "nr_faces": 7850,
+ "nr_vertices": 4021,
+ "surface_area": 0.04170984890875663,
+ "volume": 0.0006387812007745929
+ }
+ },
+ "REEF_BANTU": {
+ "asset_type": "FileBasedObject",
+ "id": "REEF_BANTU",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05800675577956929,
+ -0.14890688186105322,
+ -0.03695222941479892
+ ],
+ [
+ 0.04706324422043071,
+ 0.13203211813894677,
+ 0.11227577058520108
+ ]
+ ],
+ "mass": 0.0008770162993284688,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "REEF BANTU\nReef RESRV collection Premium leather full grain upper with distressed and vintage finishes Medial side zipper for fast removal at airport security lines Slammed cup sole construction Molded wax texture cushion insole Removable and washable insole for function and travel EVA compounds for odor management on the insole Reef molded rubber swellular traction out sole Reef die cut leather labels inlay on the out sole Custom dust bag Laced box system",
+ "nr_faces": 25130,
+ "nr_vertices": 14149,
+ "surface_area": 0.17510082018634057,
+ "volume": 0.0008770162993284688
+ }
+ },
+ "REEF_BRAIDED_CUSHION": {
+ "asset_type": "FileBasedObject",
+ "id": "REEF_BRAIDED_CUSHION",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04999691059722425,
+ -0.12740135298240893,
+ -0.01230498643889145
+ ],
+ [
+ 0.04451008940277575,
+ 0.1242506470175911,
+ 0.04440701356110856
+ ]
+ ],
+ "mass": 0.00028790599754640364,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "REEF BRAIDED CUSHION\nGirl's Essentials Sandal. Ultra soft, woven strap lined with polyester webbing. Featuring super soft Reef cushion EVA with anatomical arch support. Durable, rubber outsole",
+ "nr_faces": 22626,
+ "nr_vertices": 11679,
+ "surface_area": 0.05687270994279256,
+ "volume": 0.00028790599754640364
+ }
+ },
+ "REEF_ZENFUN": {
+ "asset_type": "FileBasedObject",
+ "id": "REEF_ZENFUN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05047034438873186,
+ -0.1177688741608081,
+ -0.013160709467718659
+ ],
+ [
+ 0.05690265561126814,
+ 0.1322271258391919,
+ 0.04680329053228134
+ ]
+ ],
+ "mass": 0.00031409750961727085,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "REEF ZENFUN\nGirl's Sporty sandal. Synthetic upper featuring mesh detailing. Zen garden inspired molded PU foam footbed with anatomical arch support. Durable rubber outsole",
+ "nr_faces": 26068,
+ "nr_vertices": 13414,
+ "surface_area": 0.05995653340148064,
+ "volume": 0.00031409750961727085
+ }
+ },
+ "RESCUE_CREW": {
+ "asset_type": "FileBasedObject",
+ "id": "RESCUE_CREW",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04156224095501745,
+ -0.044542587768667846,
+ -0.02892613426580023
+ ],
+ [
+ 0.046395759044982554,
+ 0.044803412231332156,
+ 0.03323086573419977
+ ]
+ ],
+ "mass": 6.827002706548299e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "RESCUE CREW\nPlanCity professional figures will help your children understand and learn about different occupations, and develop their social skills.",
+ "nr_faces": 22066,
+ "nr_vertices": 12156,
+ "surface_area": 0.01939198491833671,
+ "volume": 6.827002706548299e-05
+ }
+ },
+ "RJ_Rabbit_Easter_Basket_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "RJ_Rabbit_Easter_Basket_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09998765728025949,
+ -0.07871649384328819,
+ -0.08015945224171257
+ ],
+ [
+ 0.1073653427197405,
+ 0.08485750615671181,
+ 0.15500654775828743
+ ]
+ ],
+ "mass": 0.00025864836532396834,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "R.J Rabbit Easter Basket, Blue",
+ "nr_faces": 39616,
+ "nr_vertices": 24489,
+ "surface_area": 0.18168659822446578,
+ "volume": 0.00025864836532396834
+ }
+ },
+ "ROAD_CONSTRUCTION_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "ROAD_CONSTRUCTION_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07006832802871708,
+ -0.082392874348981,
+ -0.020153363821753333
+ ],
+ [
+ 0.06865367197128293,
+ 0.07694312565101899,
+ 0.03595963617824667
+ ]
+ ],
+ "mass": 0.0001423982945939318,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "ROAD CONSTRUCTION SET",
+ "nr_faces": 22310,
+ "nr_vertices": 13091,
+ "surface_area": 0.0432196389343459,
+ "volume": 0.0001423982945939318
+ }
+ },
+ "Racoon": {
+ "asset_type": "FileBasedObject",
+ "id": "Racoon",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08272849982065816,
+ -0.11895566255032586,
+ -0.07376918108395615
+ ],
+ [
+ 0.06974250017934186,
+ 0.19619133744967415,
+ 0.13738581891604384
+ ]
+ ],
+ "mass": 0.002310074467988978,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Racoon\nRacoon",
+ "nr_faces": 70952,
+ "nr_vertices": 54773,
+ "surface_area": 0.19305008232279106,
+ "volume": 0.002310074467988978
+ }
+ },
+ "Ravenna_4_Color_WhtOlyBluBlkShkOrngSlvRdO_Size_70": {
+ "asset_type": "FileBasedObject",
+ "id": "Ravenna_4_Color_WhtOlyBluBlkShkOrngSlvRdO_Size_70",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06708428724274881,
+ -0.17404940268804492,
+ -0.04126106276768729
+ ],
+ [
+ 0.05403471275725118,
+ 0.1474775973119551,
+ 0.08484293723231273
+ ]
+ ],
+ "mass": 0.0013186057156339532,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Ravenna 4, Color: Wht/OlyBlu/Blk/ShkOrng/Slv/RdO, Size: 7.0\nA middle child to neutral and support, the Ravenna 4 is leading the charge for in-between feet. This season, this shoe is bringing a little more cushion, a bit more flex, and a whole lot of swagger with sleek design lines and fast colors. We've also honed in on midfoot capture and engineered a saddle that envelops the foot with an adjustable band. Not too Neutral and not too Support, the Ravenna 4 is juuuust right. Don't take our word for it: Runner's World named the Ravenna 4 its \"Best Buy\" in the Spring Shoe Guide in the March 2013 issue. Their bottom line? \"For the price, it's awfully hard to beat this balance of features and ride.\" > See the Women's Ravenna 4 Runner's World is a registered trademark of Rodale Inc. 2013 Rodale Inc. All rights reserved.Category: Guidance Weight: 10.8 oz Platform: Universal Construction: Strobel DNA: Anatomical Launch Date: February 1, 2013",
+ "nr_faces": 65146,
+ "nr_vertices": 42689,
+ "surface_area": 0.1917619917434647,
+ "volume": 0.0013186057156339532
+ }
+ },
+ "Rayna_BootieWP": {
+ "asset_type": "FileBasedObject",
+ "id": "Rayna_BootieWP",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0473878796240877,
+ -0.1415750578179809,
+ -0.06509452073724589
+ ],
+ [
+ 0.039913120375912305,
+ 0.0997279421820191,
+ 0.1356274792627541
+ ]
+ ],
+ "mass": 0.0013177850894826823,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Rayna Bootie.WP",
+ "nr_faces": 12754,
+ "nr_vertices": 6656,
+ "surface_area": 0.10782492980667012,
+ "volume": 0.0013177850894826823
+ }
+ },
+ "Razer_Abyssus_Ambidextrous_Gaming_Mouse": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_Abyssus_Ambidextrous_Gaming_Mouse",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0530922919335782,
+ -0.06369897455187891,
+ -0.015418251927293871
+ ],
+ [
+ 0.0478847080664218,
+ 0.08211702544812109,
+ 0.023020748072706126
+ ]
+ ],
+ "mass": 0.00018330112851777533,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Mouse",
+ "description": "Razer Abyssus - Ambidextrous Gaming Mouse\nThe Razer Abyssus is armed with ultra-responsive buttons tuned for maximum tactile feedback. With an uncompromising 3500 DPI Razer optical sensor at its core, take full control of your every aim with perfect tracking so you outgun your competition.",
+ "nr_faces": 33292,
+ "nr_vertices": 18214,
+ "surface_area": 0.028906498709978454,
+ "volume": 0.00018330112851777533
+ }
+ },
+ "Razer_BlackWidow_Stealth_2014_Keyboard_07VFzIVabgh": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_BlackWidow_Stealth_2014_Keyboard_07VFzIVabgh",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.24123014621885788,
+ -0.10651749423352447,
+ -0.02027351687556756
+ ],
+ [
+ 0.23085585378114212,
+ 0.13919050576647554,
+ 0.07326748312443244
+ ]
+ ],
+ "mass": 0.0021831804407557833,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Keyboard",
+ "description": "Razer BlackWidow Stealth 2014 - Keyboard\nThe Razer BlackWidow features the all-new Razer? Mechanical Switches that have been designed from the ground up with the aim of elevating the speed and responsiveness of the Razer BlackWidow gaming keyboard beyond the capabilities of current-gen mechanical switches. Tested and validated by the world?s top eSports athletes, we have identified the optimal actuation distance and reduced the tolerance for faster commands and greater precision when compared to standard mechanical switches.",
+ "nr_faces": 26614,
+ "nr_vertices": 16819,
+ "surface_area": 0.27467587487213935,
+ "volume": 0.0021831804407557833
+ }
+ },
+ "Razer_BlackWidow_Ultimate_2014_Mechanical_Gaming_Keyboard": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_BlackWidow_Ultimate_2014_Mechanical_Gaming_Keyboard",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.236555032665146,
+ -0.1084520289660594,
+ -0.018961726610948127
+ ],
+ [
+ 0.23472796733485402,
+ 0.1910269710339406,
+ 0.02958027338905187
+ ]
+ ],
+ "mass": 0.0022554325781066796,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Keyboard",
+ "description": "Razer BlackWidow Ultimate 2014 - Mechanical Gaming Keyboard\nThe Razer BlackWidow features the all-new Razer? Mechanical Switches that have been designed from the ground up with the aim of elevating the speed and responsiveness of the Razer BlackWidow gaming keyboard beyond the capabilities of current-gen mechanical switches. Tested and validated by the world?s top eSports athletes, we have identified the optimal actuation distance and reduced the tolerance for faster commands and greater precision when compared to standard mechanical switches.",
+ "nr_faces": 24792,
+ "nr_vertices": 16031,
+ "surface_area": 0.2628509707813156,
+ "volume": 0.0022554325781066796
+ }
+ },
+ "Razer_Blackwidow_Tournament_Edition_Keyboard": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_Blackwidow_Tournament_Edition_Keyboard",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18218373598011275,
+ -0.08860071416256379,
+ -0.01910693425463073
+ ],
+ [
+ 0.18379726401988725,
+ 0.1311572858374362,
+ 0.02784106574536927
+ ]
+ ],
+ "mass": 0.0015699787402798598,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Keyboard",
+ "description": "Razer Blackwidow Tournament Edition Keyboard",
+ "nr_faces": 25702,
+ "nr_vertices": 15999,
+ "surface_area": 0.18522387969060777,
+ "volume": 0.0015699787402798598
+ }
+ },
+ "Razer_Goliathus_Control_Edition_Small_Soft_Gaming_Mouse_Mat": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_Goliathus_Control_Edition_Small_Soft_Gaming_Mouse_Mat",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1409954893641346,
+ -0.10620845013433117,
+ -0.004738087470338026
+ ],
+ [
+ 0.1319005106358654,
+ 0.11338454986566883,
+ 0.005535912529661974
+ ]
+ ],
+ "mass": 0.0001723461521633005,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Razer Goliathus Control Edition - Small - Soft Gaming Mouse Mat\nEngineered to exceed the exacting demands of the world's top professional gamers, the highly-adaptable Razer Goliathus Control Edition gaming mouse mat is optimized for all mouse sensitivity settings and sensor types, with a rubber base for secure grip on smooth surfaces.",
+ "nr_faces": 3868,
+ "nr_vertices": 2124,
+ "surface_area": 0.11939484666937222,
+ "volume": 0.0001723461521633005
+ }
+ },
+ "Razer_Kraken_71_Chroma_headset_Full_size_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_Kraken_71_Chroma_headset_Full_size_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.111356302925563,
+ -0.06057069810386643,
+ -0.1199446354122964
+ ],
+ [
+ 0.11377069707443699,
+ 0.059374301896133574,
+ 0.1386213645877036
+ ]
+ ],
+ "mass": 0.00601732914410971,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Headphones",
+ "description": "Razer Kraken 7.1 Chroma - headset - Full size - Black\nGet the complete 7.1 surround sound gaming experience with the Razer Kraken 7.1 Chroma USB gaming headset. This headset adopts the comfortable form factor of the Razer Kraken Pro, tested by numerous professional gamers to determine the optimal ergonomics for extended gaming sessions. - Advanced 7.1 virtual surround sound engine - True-to-life positional audio. The Razer Kraken 7.1 Chroma comes equipped with an advanced 7.1 virtual surround sound engine that immerses you deeper into the game. The engine is capable of ultra-low latency audio processing and modulates the audio source to simulate a 360 surround sound experience that is usually achievable only by incorporating more than one positional driver in each ear cup.",
+ "nr_faces": 8206,
+ "nr_vertices": 4371,
+ "surface_area": 0.20825033373237478,
+ "volume": 0.00601732914410971
+ }
+ },
+ "Razer_Kraken_Pro_headset_Full_size_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_Kraken_Pro_headset_Full_size_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0905501364755341,
+ -0.0489077317519407,
+ -0.16067840669342767
+ ],
+ [
+ 0.0886498635244659,
+ 0.0874382682480593,
+ 0.12950759330657233
+ ]
+ ],
+ "mass": 0.0007679669246305313,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Headphones",
+ "description": "Razer Kraken Pro - headset - Full size- Black\nThe Razer Kraken Pro gaming headset can extend gaming sessions as well as for unparalleled comfort on the go. The Razer Kraken Pro's large neodymium magnet drivers are tuned for clear high- and mid-ranges as well as deep bass for powerful lows. A closed ear cup deign with plush circumlunar padding creates superior sound isolation so you can focus on your game or conversation uninterrupted by outside noise.",
+ "nr_faces": 29666,
+ "nr_vertices": 16135,
+ "surface_area": 0.11069594235426139,
+ "volume": 0.0007679669246305313
+ }
+ },
+ "Razer_Naga_MMO_Gaming_Mouse": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_Naga_MMO_Gaming_Mouse",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03483884223849924,
+ -0.0724992594362707,
+ -0.01711760746295267
+ ],
+ [
+ 0.039968157761500755,
+ 0.1827087405637293,
+ 0.026315392537047327
+ ]
+ ],
+ "mass": 0.00022832624755860268,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Mouse",
+ "description": "Razer Naga - MMO Gaming Mouse\nThe Razer Naga MMO gaming mouse comes with 12 mechanical thumb-grid buttons for faster in-game actuations and assured tactile feedback. The improved button design also allows for blind-find so you stay focused on the game, letting your instincts lead you to victory. The all-new Razer Naga comes with refined ergonomics for a comfortable feel in hand, while an intuitive in-game overlay support can be activated via RazerSynapse.",
+ "nr_faces": 19384,
+ "nr_vertices": 10448,
+ "surface_area": 0.032930914308646295,
+ "volume": 0.00022832624755860268
+ }
+ },
+ "Razer_Taipan_Black_Ambidextrous_Gaming_Mouse": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_Taipan_Black_Ambidextrous_Gaming_Mouse",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08423340146120839,
+ -0.07167028865911884,
+ -0.015656835644736758
+ ],
+ [
+ 0.038309598538791616,
+ 0.10285571134088116,
+ 0.024515164355263238
+ ]
+ ],
+ "mass": 0.00019517699904980832,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Mouse",
+ "description": "Razer Taipan Black - Ambidextrous Gaming Mouse\nThe Razer Taipan offers 9 Hyperesponse buttons and is ergonomically designed for both right and left handed users. The 8200dpi 4G laser sensor also offers exceptional tracking precision with zero interpolation for high-performance wired gameplay.",
+ "nr_faces": 31596,
+ "nr_vertices": 17455,
+ "surface_area": 0.033416584368758995,
+ "volume": 0.00019517699904980832
+ }
+ },
+ "Razer_Taipan_White_Ambidextrous_Gaming_Mouse": {
+ "asset_type": "FileBasedObject",
+ "id": "Razer_Taipan_White_Ambidextrous_Gaming_Mouse",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.047033053903849854,
+ -0.0749287721333991,
+ -0.016006129813253403
+ ],
+ [
+ 0.05280994609615015,
+ 0.10715322786660092,
+ 0.023938870186746595
+ ]
+ ],
+ "mass": 0.00019978488526462132,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Mouse",
+ "description": "Razer Taipan White - Ambidextrous Gaming Mouse\nThe Razer Taipan offers 9 Hyperesponse buttons and is ergonomically designed for both right and left handed users. The 8200dpi 4G laser sensor also offers exceptional tracking precision with zero interpolation for high-performance wired gameplay.",
+ "nr_faces": 23000,
+ "nr_vertices": 12527,
+ "surface_area": 0.03181596699457426,
+ "volume": 0.00019978488526462132
+ }
+ },
+ "ReadytoUse_Rolled_Fondant_Pure_White_24_oz_box": {
+ "asset_type": "FileBasedObject",
+ "id": "ReadytoUse_Rolled_Fondant_Pure_White_24_oz_box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.061058322757127054,
+ -0.02461560104668025,
+ -0.08437518482023847
+ ],
+ [
+ 0.06062067724287295,
+ 0.02450839895331975,
+ 0.08428381517976154
+ ]
+ ],
+ "mass": 0.0009282984456978214,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Ready-to-Use Rolled Fondant, Pure White - 24 oz box",
+ "nr_faces": 1744,
+ "nr_vertices": 948,
+ "surface_area": 0.06480561944248536,
+ "volume": 0.0009282984456978214
+ }
+ },
+ "Real_Deal_1nIwCHX1MTh": {
+ "asset_type": "FileBasedObject",
+ "id": "Real_Deal_1nIwCHX1MTh",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06347915829691093,
+ -0.17159319249812488,
+ -0.052362762303728765
+ ],
+ [
+ 0.05112184170308906,
+ 0.13102480750187512,
+ 0.10659123769627124
+ ]
+ ],
+ "mass": 0.0013604620733007255,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Real Deal",
+ "nr_faces": 37872,
+ "nr_vertices": 20631,
+ "surface_area": 0.1889092311990624,
+ "volume": 0.0013604620733007255
+ }
+ },
+ "RedBlack_Nintendo_3DSXL": {
+ "asset_type": "FileBasedObject",
+ "id": "RedBlack_Nintendo_3DSXL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0778611102329585,
+ -0.06748235977195445,
+ -0.02226579885287301
+ ],
+ [
+ 0.0781158897670415,
+ 0.06693764022804555,
+ 0.07030620114712699
+ ]
+ ],
+ "mass": 0.0002840952885325022,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Red/Black Nintendo 3DS?XL\nThe Nintendo 3DS XL system combines next-generation portable gaming with eye-popping 3D\nvisuals?without the need for special glasses. Take 3D photos, connect to friends, other players, or wireless hotspots with the wireless StreetPass? and SpotPass? communication modes. From games to photos and beyond, Nintendo 3DS XL is the ultimate 3D entertainment system. It comes bundled with a 4GB SD card, making it perfect for downloading content from the Nintendo eShop.\n\nThe Nintendo 3DS XL system plays all Nintendo DS games. Nintendo DS games will not appear in 3D.",
+ "nr_faces": 6834,
+ "nr_vertices": 3623,
+ "surface_area": 0.0608266422730656,
+ "volume": 0.0002840952885325022
+ }
+ },
+ "Reebok_ALLYLYNN": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_ALLYLYNN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.047054436691931836,
+ -0.12688877880598864,
+ -0.042104890626103494
+ ],
+ [
+ 0.03975656330806816,
+ 0.09139022119401137,
+ 0.1003961093738965
+ ]
+ ],
+ "mass": 0.0006509644518357107,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok ALLYLYNN",
+ "nr_faces": 30270,
+ "nr_vertices": 16428,
+ "surface_area": 0.11363751329831291,
+ "volume": 0.0006509644518357107
+ }
+ },
+ "Reebok_BREAKPOINT_LO_2V": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_BREAKPOINT_LO_2V",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0452593595543519,
+ -0.11753672102236923,
+ -0.031233299591305014
+ ],
+ [
+ 0.0398216404456481,
+ 0.09940127897763076,
+ 0.05490570040869499
+ ]
+ ],
+ "mass": 0.0005114667902249206,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok BREAKPOINT LO 2V",
+ "nr_faces": 32522,
+ "nr_vertices": 17279,
+ "surface_area": 0.09027776363892553,
+ "volume": 0.0005114667902249206
+ }
+ },
+ "Reebok_BREAKPOINT_MID": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_BREAKPOINT_MID",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05060260596632763,
+ -0.1334729676924699,
+ -0.04258394265155453
+ ],
+ [
+ 0.04343839403367237,
+ 0.1141610323075301,
+ 0.09892905734844545
+ ]
+ ],
+ "mass": 0.0009463468051154242,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok BREAKPOINT MID",
+ "nr_faces": 25834,
+ "nr_vertices": 13707,
+ "surface_area": 0.10474754950030876,
+ "volume": 0.0009463468051154242
+ }
+ },
+ "Reebok_CLASSIC_JOGGER": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_CLASSIC_JOGGER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.043296429927077135,
+ -0.10836192764469493,
+ -0.03236325132542083
+ ],
+ [
+ 0.03867457007292287,
+ 0.10589807235530507,
+ 0.05417374867457917
+ ]
+ ],
+ "mass": 0.0005757209932546909,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok CLASSIC JOGGER",
+ "nr_faces": 20090,
+ "nr_vertices": 10693,
+ "surface_area": 0.0690941543492149,
+ "volume": 0.0005757209932546909
+ }
+ },
+ "Reebok_CLASSIC_LEGACY_II": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_CLASSIC_LEGACY_II",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059462307554351376,
+ -0.11570759190981783,
+ -0.06955904635794083
+ ],
+ [
+ 0.07172369244564862,
+ 0.17543440809018215,
+ 0.14325395364205917
+ ]
+ ],
+ "mass": 0.002168797961719624,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok CLASSIC LEGACY II",
+ "nr_faces": 24810,
+ "nr_vertices": 13926,
+ "surface_area": 0.1618282716481826,
+ "volume": 0.002168797961719624
+ }
+ },
+ "Reebok_CL_DIBELLO_II": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_CL_DIBELLO_II",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06335736690626671,
+ -0.16791658358225792,
+ -0.048156624990273754
+ ],
+ [
+ 0.04923863309373329,
+ 0.1177354164177421,
+ 0.12068137500972625
+ ]
+ ],
+ "mass": 0.0012378213521314616,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok CL DIBELLO II",
+ "nr_faces": 31018,
+ "nr_vertices": 17807,
+ "surface_area": 0.1815590409311264,
+ "volume": 0.0012378213521314616
+ }
+ },
+ "Reebok_CL_LTHR_R12": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_CL_LTHR_R12",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05953263960541832,
+ -0.16187801036590888,
+ -0.04116116879561241
+ ],
+ [
+ 0.05100536039458168,
+ 0.12747498963409115,
+ 0.0753068312043876
+ ]
+ ],
+ "mass": 0.001061409162732489,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok CL LTHR R12",
+ "nr_faces": 25680,
+ "nr_vertices": 14547,
+ "surface_area": 0.1580333053517595,
+ "volume": 0.001061409162732489
+ }
+ },
+ "Reebok_CL_RAYEN": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_CL_RAYEN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05419537372843287,
+ -0.16728583693958513,
+ -0.038161423668776145
+ ],
+ [
+ 0.048729626271567135,
+ 0.12638716306041486,
+ 0.07702357633122386
+ ]
+ ],
+ "mass": 0.0009648316090365365,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok CL RAYEN",
+ "nr_faces": 24400,
+ "nr_vertices": 13046,
+ "surface_area": 0.14570852745536308,
+ "volume": 0.0009648316090365365
+ }
+ },
+ "Reebok_COMFORT_REEFRESH_FLIP": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_COMFORT_REEFRESH_FLIP",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05039571507097489,
+ -0.1278317855043946,
+ -0.015294581663726162
+ ],
+ [
+ 0.06259628492902511,
+ 0.12909721449560538,
+ 0.048681418336273846
+ ]
+ ],
+ "mass": 0.00045577483065212346,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok COMFORT REEFRESH FLIP",
+ "nr_faces": 14902,
+ "nr_vertices": 7936,
+ "surface_area": 0.06828119189257223,
+ "volume": 0.00045577483065212346
+ }
+ },
+ "Reebok_DMX_MAX_MANIA_WD_D": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_DMX_MAX_MANIA_WD_D",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05809285646569372,
+ -0.13915396603853925,
+ -0.04349179523792132
+ ],
+ [
+ 0.04817814353430628,
+ 0.13361303396146076,
+ 0.09204220476207868
+ ]
+ ],
+ "mass": 0.0012300589927479433,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok DMX MAX MANIA WD D",
+ "nr_faces": 22114,
+ "nr_vertices": 11915,
+ "surface_area": 0.11060268447295266,
+ "volume": 0.0012300589927479433
+ }
+ },
+ "Reebok_DMX_MAX_PLUS_ATHLETIC": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_DMX_MAX_PLUS_ATHLETIC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06159850114106015,
+ -0.16467454693091113,
+ -0.04542659517511353
+ ],
+ [
+ 0.05056549885893985,
+ 0.1363814530690889,
+ 0.08569040482488646
+ ]
+ ],
+ "mass": 0.0012094867470418959,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok DMX MAX PLUS ATHLETIC",
+ "nr_faces": 27920,
+ "nr_vertices": 15453,
+ "surface_area": 0.16452906489679506,
+ "volume": 0.0012094867470418959
+ }
+ },
+ "Reebok_DMX_MAX_PLUS_RAINWALKER": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_DMX_MAX_PLUS_RAINWALKER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06200423235051712,
+ -0.1542656584539388,
+ -0.04940651686682112
+ ],
+ [
+ 0.05223776764948288,
+ 0.1465833415460612,
+ 0.08713948313317887
+ ]
+ ],
+ "mass": 0.0016142106119380808,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok DMX MAX PLUS RAINWALKER",
+ "nr_faces": 27446,
+ "nr_vertices": 15221,
+ "surface_area": 0.12603890012740868,
+ "volume": 0.0016142106119380808
+ }
+ },
+ "Reebok_EASYTONE_CL_LEATHER": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_EASYTONE_CL_LEATHER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05593165037841962,
+ -0.1373136689290602,
+ -0.0458286766034738
+ ],
+ [
+ 0.04335034962158038,
+ 0.12787233107093982,
+ 0.08626432339652622
+ ]
+ ],
+ "mass": 0.0011560432128583271,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok EASYTONE CL LEATHER",
+ "nr_faces": 17784,
+ "nr_vertices": 9430,
+ "surface_area": 0.10042196836714214,
+ "volume": 0.0011560432128583271
+ }
+ },
+ "Reebok_FS_HI_INT_R12": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_FS_HI_INT_R12",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05712546071437581,
+ -0.153218918040126,
+ -0.04603002192174196
+ ],
+ [
+ 0.04833053928562418,
+ 0.106828081959874,
+ 0.09430197807825805
+ ]
+ ],
+ "mass": 0.0009064431720712557,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok F/S HI INT R12",
+ "nr_faces": 30106,
+ "nr_vertices": 16146,
+ "surface_area": 0.14321190799892397,
+ "volume": 0.0009064431720712557
+ }
+ },
+ "Reebok_FS_HI_MINI": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_FS_HI_MINI",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.050307104522459456,
+ -0.1438523351333459,
+ -0.03826311934183266
+ ],
+ [
+ 0.04646689547754054,
+ 0.11579466486665414,
+ 0.09051388065816733
+ ]
+ ],
+ "mass": 0.0009162991138388445,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok F/S HI MINI",
+ "nr_faces": 25484,
+ "nr_vertices": 13585,
+ "surface_area": 0.10027382642561661,
+ "volume": 0.0009162991138388445
+ }
+ },
+ "Reebok_FUELTRAIN": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_FUELTRAIN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05789649825334184,
+ -0.14165288161153447,
+ -0.03967579868755868
+ ],
+ [
+ 0.046985501746658165,
+ 0.13068411838846553,
+ 0.07850720131244132
+ ]
+ ],
+ "mass": 0.001136888441047578,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok FUELTRAIN",
+ "nr_faces": 27552,
+ "nr_vertices": 15020,
+ "surface_area": 0.10582667193951428,
+ "volume": 0.001136888441047578
+ }
+ },
+ "Reebok_GL_6000": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_GL_6000",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06177177747439238,
+ -0.15555900828294617,
+ -0.040559888530200316
+ ],
+ [
+ 0.04916822252560762,
+ 0.13740199171705383,
+ 0.08770611146979969
+ ]
+ ],
+ "mass": 0.0014623069153033125,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok GL 6000",
+ "nr_faces": 24766,
+ "nr_vertices": 14243,
+ "surface_area": 0.12496510383863553,
+ "volume": 0.0014623069153033125
+ }
+ },
+ "Reebok_HIMARA_LTR": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_HIMARA_LTR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.060155499020873596,
+ -0.1530309740696776,
+ -0.04252237666925657
+ ],
+ [
+ 0.0518335009791264,
+ 0.14279802593032237,
+ 0.09354962333074343
+ ]
+ ],
+ "mass": 0.0014451921537215388,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok HIMARA LTR",
+ "nr_faces": 28674,
+ "nr_vertices": 15526,
+ "surface_area": 0.1263664687876638,
+ "volume": 0.0014451921537215388
+ }
+ },
+ "Reebok_JR_ZIG_COOPERSTOWN_MR": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_JR_ZIG_COOPERSTOWN_MR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.047057273087053784,
+ -0.12659065648680284,
+ -0.045990263768448496
+ ],
+ [
+ 0.04545272691294621,
+ 0.11387234351319714,
+ 0.0717347362315515
+ ]
+ ],
+ "mass": 0.0008308264904079653,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok JR ZIG COOPERSTOWN MR",
+ "nr_faces": 40952,
+ "nr_vertices": 22302,
+ "surface_area": 0.08971992639077767,
+ "volume": 0.0008308264904079653
+ }
+ },
+ "Reebok_KAMIKAZE_II_MID": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_KAMIKAZE_II_MID",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06392728745851145,
+ -0.16200828700813438,
+ -0.05541180383424552
+ ],
+ [
+ 0.06516571254148855,
+ 0.1313057129918656,
+ 0.1346481961657545
+ ]
+ ],
+ "mass": 0.0018192361621908403,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok KAMIKAZE II MID",
+ "nr_faces": 23646,
+ "nr_vertices": 13115,
+ "surface_area": 0.15835788904739578,
+ "volume": 0.0018192361621908403
+ }
+ },
+ "Reebok_PUMP_OMNI_LITE_HLS": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_PUMP_OMNI_LITE_HLS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06421950656022013,
+ -0.17431478766693376,
+ -0.055784801343377204
+ ],
+ [
+ 0.05858449343977986,
+ 0.11781421233306624,
+ 0.11107119865662281
+ ]
+ ],
+ "mass": 0.0013431236816374313,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok PUMP OMNI LITE HLS",
+ "nr_faces": 49318,
+ "nr_vertices": 28731,
+ "surface_area": 0.19343589918776263,
+ "volume": 0.0013431236816374313
+ }
+ },
+ "Reebok_REALFLEX_SELECT": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_REALFLEX_SELECT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06008964163080142,
+ -0.15213612099087595,
+ -0.04015000185991065
+ ],
+ [
+ 0.052409358369198585,
+ 0.14798187900912405,
+ 0.08989699814008936
+ ]
+ ],
+ "mass": 0.001183295047384883,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok REALFLEX SELECT",
+ "nr_faces": 26914,
+ "nr_vertices": 15270,
+ "surface_area": 0.13730506702168183,
+ "volume": 0.001183295047384883
+ }
+ },
+ "Reebok_REESCULPT_TRAINER_II": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_REESCULPT_TRAINER_II",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05306396635328423,
+ -0.13724157058136197,
+ -0.03824987499828586
+ ],
+ [
+ 0.04508603364671577,
+ 0.12974342941863803,
+ 0.06887412500171414
+ ]
+ ],
+ "mass": 0.0009637301508712984,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok REESCULPT TRAINER II",
+ "nr_faces": 22258,
+ "nr_vertices": 11999,
+ "surface_area": 0.09577024582673686,
+ "volume": 0.0009637301508712984
+ }
+ },
+ "Reebok_RETRO_RUSH_2V": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_RETRO_RUSH_2V",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04170773686529708,
+ -0.10951147671408772,
+ -0.03271176107972842
+ ],
+ [
+ 0.03834726313470292,
+ 0.10700052328591228,
+ 0.056335238920271584
+ ]
+ ],
+ "mass": 0.000577036647924912,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok RETRO RUSH 2V",
+ "nr_faces": 19990,
+ "nr_vertices": 10588,
+ "surface_area": 0.06854306497234869,
+ "volume": 0.000577036647924912
+ }
+ },
+ "Reebok_R_CROSSFIT_OLY_UFORM": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_R_CROSSFIT_OLY_UFORM",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0578584830983944,
+ -0.1611726973517124,
+ -0.04211050249112237
+ ],
+ [
+ 0.0502835169016056,
+ 0.1307073026482876,
+ 0.08706249750887764
+ ]
+ ],
+ "mass": 0.0009985822463132517,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok R CROSSFIT OLY U-FORM",
+ "nr_faces": 32096,
+ "nr_vertices": 17287,
+ "surface_area": 0.15793420955397774,
+ "volume": 0.0009985822463132517
+ }
+ },
+ "Reebok_R_DANCE_FLASH": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_R_DANCE_FLASH",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.054551167438013144,
+ -0.14908537274521277,
+ -0.037395764204219376
+ ],
+ [
+ 0.04221183256198686,
+ 0.11522762725478722,
+ 0.07086223579578063
+ ]
+ ],
+ "mass": 0.000843502299593172,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok R DANCE FLASH",
+ "nr_faces": 34902,
+ "nr_vertices": 19203,
+ "surface_area": 0.12607021700900733,
+ "volume": 0.000843502299593172
+ }
+ },
+ "Reebok_SH_COURT_MID_II": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_SH_COURT_MID_II",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059099617877055005,
+ -0.16761187245856177,
+ -0.04965146961092308
+ ],
+ [
+ 0.047556382122944996,
+ 0.12431712754143823,
+ 0.11365553038907691
+ ]
+ ],
+ "mass": 0.0013366630957219107,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok SH COURT MID II",
+ "nr_faces": 28546,
+ "nr_vertices": 15818,
+ "surface_area": 0.17646190975785506,
+ "volume": 0.0013366630957219107
+ }
+ },
+ "Reebok_SH_NEWPORT_LOW": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_SH_NEWPORT_LOW",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056958691052639496,
+ -0.13757518386491566,
+ -0.03561808693991026
+ ],
+ [
+ 0.0473913089473605,
+ 0.14903881613508435,
+ 0.08572191306008975
+ ]
+ ],
+ "mass": 0.0009004615043985654,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok SH NEWPORT LOW",
+ "nr_faces": 19432,
+ "nr_vertices": 10570,
+ "surface_area": 0.12663460243007865,
+ "volume": 0.0009004615043985654
+ }
+ },
+ "Reebok_SH_PRIME_COURT_LOW": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_SH_PRIME_COURT_LOW",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05109818924780885,
+ -0.1290919138783638,
+ -0.0314962630993563
+ ],
+ [
+ 0.04453781075219115,
+ 0.1296450861216362,
+ 0.0745137369006437
+ ]
+ ],
+ "mass": 0.0007880776789182182,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok SH PRIME COURT LOW",
+ "nr_faces": 24708,
+ "nr_vertices": 12851,
+ "surface_area": 0.09659860095374391,
+ "volume": 0.0007880776789182182
+ }
+ },
+ "Reebok_SH_PRIME_COURT_MID": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_SH_PRIME_COURT_MID",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04562678022927738,
+ -0.1228021381801511,
+ -0.03807990659646413
+ ],
+ [
+ 0.04126621977072262,
+ 0.09438686181984891,
+ 0.07557309340353587
+ ]
+ ],
+ "mass": 0.0005590918365447448,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok SH PRIME COURT MID",
+ "nr_faces": 33582,
+ "nr_vertices": 18197,
+ "surface_area": 0.10196212268582665,
+ "volume": 0.0005590918365447448
+ }
+ },
+ "Reebok_SL_FLIP_UPDATE": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_SL_FLIP_UPDATE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05744397768254896,
+ -0.15317419574100405,
+ -0.04894425591647551
+ ],
+ [
+ 0.04879002231745104,
+ 0.13519580425899594,
+ 0.11770374408352448
+ ]
+ ],
+ "mass": 0.0013790211194163607,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok SL FLIP UPDATE",
+ "nr_faces": 22734,
+ "nr_vertices": 12400,
+ "surface_area": 0.14677269791513453,
+ "volume": 0.0013790211194163607
+ }
+ },
+ "Reebok_SMOOTHFLEX_CUSHRUN_20": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_SMOOTHFLEX_CUSHRUN_20",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05591146902735633,
+ -0.1464205065463054,
+ -0.03891563149922491
+ ],
+ [
+ 0.04795353097264367,
+ 0.12130149345369463,
+ 0.08320236850077509
+ ]
+ ],
+ "mass": 0.0008921776064042333,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok SMOOTHFLEX CUSHRUN 2.0",
+ "nr_faces": 55096,
+ "nr_vertices": 30707,
+ "surface_area": 0.1396502413636751,
+ "volume": 0.0008921776064042333
+ }
+ },
+ "Reebok_SOMERSET_RUN": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_SOMERSET_RUN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059631725181303843,
+ -0.1623657867713978,
+ -0.04001106687048365
+ ],
+ [
+ 0.053232274818696156,
+ 0.1302842132286022,
+ 0.07608793312951635
+ ]
+ ],
+ "mass": 0.0010393353275774593,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok SOMERSET RUN",
+ "nr_faces": 32926,
+ "nr_vertices": 18280,
+ "surface_area": 0.15404437886044187,
+ "volume": 0.0010393353275774593
+ }
+ },
+ "Reebok_STUDIO_BEAT_LOW_V": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_STUDIO_BEAT_LOW_V",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056280664264855715,
+ -0.14937010079035373,
+ -0.037366609060517
+ ],
+ [
+ 0.04421533573514429,
+ 0.11717189920964625,
+ 0.068275390939483
+ ]
+ ],
+ "mass": 0.0008081496433454416,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok STUDIO BEAT LOW V",
+ "nr_faces": 33052,
+ "nr_vertices": 17548,
+ "surface_area": 0.12708346782104746,
+ "volume": 0.0008081496433454416
+ }
+ },
+ "Reebok_TRIPLE_BREAK_LITE": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_TRIPLE_BREAK_LITE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05304930466400695,
+ -0.13473838654921452,
+ -0.03671257737700069
+ ],
+ [
+ 0.047011695335993045,
+ 0.13119161345078548,
+ 0.08095142262299931
+ ]
+ ],
+ "mass": 0.0009881384601672675,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok TRIPLE BREAK LITE",
+ "nr_faces": 14528,
+ "nr_vertices": 7916,
+ "surface_area": 0.09393346822702733,
+ "volume": 0.0009881384601672675
+ }
+ },
+ "Reebok_TURBO_RC": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_TURBO_RC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06124309507847069,
+ -0.1621903050604904,
+ -0.04145695912799035
+ ],
+ [
+ 0.04919690492152931,
+ 0.1343906949395096,
+ 0.08403604087200964
+ ]
+ ],
+ "mass": 0.0011425366504369883,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok TURBO RC",
+ "nr_faces": 28818,
+ "nr_vertices": 15684,
+ "surface_area": 0.16073596841812174,
+ "volume": 0.0011425366504369883
+ }
+ },
+ "Reebok_ULTIMATIC_2V": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_ULTIMATIC_2V",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.048804834634941105,
+ -0.12014416431661111,
+ -0.03450412935886238
+ ],
+ [
+ 0.0417761653650589,
+ 0.10252183568338889,
+ 0.06372087064113763
+ ]
+ ],
+ "mass": 0.0005949234546237295,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok ULTIMATIC 2V",
+ "nr_faces": 33366,
+ "nr_vertices": 18422,
+ "surface_area": 0.09874280776816856,
+ "volume": 0.0005949234546237295
+ }
+ },
+ "Reebok_VERSA_TRAIN": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_VERSA_TRAIN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.060159135027652966,
+ -0.16570636533391844,
+ -0.04135660330502877
+ ],
+ [
+ 0.05011586497234703,
+ 0.13345563466608157,
+ 0.07831639669497123
+ ]
+ ],
+ "mass": 0.001129265565444005,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok VERSA TRAIN",
+ "nr_faces": 39860,
+ "nr_vertices": 22394,
+ "surface_area": 0.16027980695151975,
+ "volume": 0.001129265565444005
+ }
+ },
+ "Reebok_ZIGCOOPERSTOWN_QUAG": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_ZIGCOOPERSTOWN_QUAG",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05855375926568958,
+ -0.17891442759471954,
+ -0.05030357816493064
+ ],
+ [
+ 0.05333624073431042,
+ 0.14052557240528046,
+ 0.09424342183506937
+ ]
+ ],
+ "mass": 0.0012639967184794694,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok ZIGCOOPERSTOWN QUAG",
+ "nr_faces": 40876,
+ "nr_vertices": 22884,
+ "surface_area": 0.19070309396888352,
+ "volume": 0.0012639967184794694
+ }
+ },
+ "Reebok_ZIGLITE_RUSH": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_ZIGLITE_RUSH",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.055230442502752886,
+ -0.13918554967190563,
+ -0.04319757483902889
+ ],
+ [
+ 0.05263455749724712,
+ 0.13384945032809437,
+ 0.0870294251609711
+ ]
+ ],
+ "mass": 0.0011516509411477818,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok ZIGLITE RUSH",
+ "nr_faces": 37146,
+ "nr_vertices": 19846,
+ "surface_area": 0.11051049580076083,
+ "volume": 0.0011516509411477818
+ }
+ },
+ "Reebok_ZIGLITE_RUSH_AC": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_ZIGLITE_RUSH_AC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0495983110873233,
+ -0.11252083783069196,
+ -0.033212021370580644
+ ],
+ [
+ 0.0465096889126767,
+ 0.11487916216930805,
+ 0.06738097862941936
+ ]
+ ],
+ "mass": 0.0006576397471730097,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok ZIGLITE RUSH AC",
+ "nr_faces": 22490,
+ "nr_vertices": 12334,
+ "surface_area": 0.08144846291733632,
+ "volume": 0.0006576397471730097
+ }
+ },
+ "Reebok_ZIGSTORM": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_ZIGSTORM",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11639417059736884,
+ -0.04887689722818329,
+ -0.034696529973990226
+ ],
+ [
+ 0.14454282940263116,
+ 0.054832102771816715,
+ 0.07890447002600978
+ ]
+ ],
+ "mass": 0.0007144472599694645,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok ZIGSTORM",
+ "nr_faces": 23022,
+ "nr_vertices": 13465,
+ "surface_area": 0.10419755368913194,
+ "volume": 0.0007144472599694645
+ }
+ },
+ "Reebok_ZIGTECH_SHARK_MAYHEM360": {
+ "asset_type": "FileBasedObject",
+ "id": "Reebok_ZIGTECH_SHARK_MAYHEM360",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05879426765550335,
+ -0.15239686003508618,
+ -0.046192326114307986
+ ],
+ [
+ 0.05300073234449665,
+ 0.14513413996491384,
+ 0.07439267388569201
+ ]
+ ],
+ "mass": 0.00135273372057228,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reebok ZIGTECH SHARK MAYHEM360",
+ "nr_faces": 29884,
+ "nr_vertices": 17131,
+ "surface_area": 0.13118436094020194,
+ "volume": 0.00135273372057228
+ }
+ },
+ "Reef_Star_Cushion_Flipflops_Size_8_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Reef_Star_Cushion_Flipflops_Size_8_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04927168019097909,
+ -0.12611719245749572,
+ -0.01364378050388667
+ ],
+ [
+ 0.055951319809020905,
+ 0.13232480754250428,
+ 0.04172321949611333
+ ]
+ ],
+ "mass": 0.0004329326716043245,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Reef Star Cushion Flipflops, Size 8, Black",
+ "nr_faces": 13916,
+ "nr_vertices": 7291,
+ "surface_area": 0.05957256171288827,
+ "volume": 0.0004329326716043245
+ }
+ },
+ "Remington_1_12_inch_Hair_Straightener": {
+ "asset_type": "FileBasedObject",
+ "id": "Remington_1_12_inch_Hair_Straightener",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05782085955052621,
+ -0.17974358806721372,
+ -0.019495023838567733
+ ],
+ [
+ 0.032739140449473784,
+ 0.1855764119327863,
+ 0.027189976161432268
+ ]
+ ],
+ "mass": 0.0002977939689764173,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Remington 1 1/2 inch Hair Straightener",
+ "nr_faces": 15806,
+ "nr_vertices": 8998,
+ "surface_area": 0.054731087561134,
+ "volume": 0.0002977939689764173
+ }
+ },
+ "Remington_TStudio_Hair_Dryer": {
+ "asset_type": "FileBasedObject",
+ "id": "Remington_TStudio_Hair_Dryer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1328898736575575,
+ -0.16218565854552164,
+ -0.039378975247753085
+ ],
+ [
+ 0.19711812634244252,
+ 0.08916034145447838,
+ 0.050271024752246915
+ ]
+ ],
+ "mass": 0.0011681706266030907,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Remington T/Studio Hair Dryer",
+ "nr_faces": 49084,
+ "nr_vertices": 38682,
+ "surface_area": 0.11598143913835021,
+ "volume": 0.0011681706266030907
+ }
+ },
+ "Remington_TStudio_Silk_Ceramic_Hair_Straightener_2_Inch_Floating_Plates": {
+ "asset_type": "FileBasedObject",
+ "id": "Remington_TStudio_Silk_Ceramic_Hair_Straightener_2_Inch_Floating_Plates",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03839131167495325,
+ -0.1895083149980775,
+ -0.0267616474166262
+ ],
+ [
+ 0.08589168832504676,
+ 0.1334876850019225,
+ 0.0393243525833738
+ ]
+ ],
+ "mass": 0.00037895438994435115,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Remington TStudio Silk Ceramic Hair Straightener 2 Inch Floating Plates\nCombining advanced technology, high-performance ceramic coating, and real crushed pearls, the remington t/studio silk ceramic 1-inch slim straightener delivers professional, salon-quality results with each use. It quickly reaches a top heat of 450 degrees fahrenheit and has precise digital controls with temperature lock so you can enjoy smooth, silky hair in just minutes.",
+ "nr_faces": 20762,
+ "nr_vertices": 11129,
+ "surface_area": 0.07829731981147137,
+ "volume": 0.00037895438994435115
+ }
+ },
+ "Retail_Leadership_Summit": {
+ "asset_type": "FileBasedObject",
+ "id": "Retail_Leadership_Summit",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1354633644127018,
+ -0.14289142861002407,
+ -0.07007224195670025
+ ],
+ [
+ 0.13200163558729822,
+ 0.14560357138997593,
+ 0.047947758043299746
+ ]
+ ],
+ "mass": 0.0013367092054979279,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Retail Leadership Summit\nRetail Leadership Summit",
+ "nr_faces": 16554,
+ "nr_vertices": 8946,
+ "surface_area": 0.20750841076198387,
+ "volume": 0.0013367092054979279
+ }
+ },
+ "Retail_Leadership_Summit_eCT3zqHYIkX": {
+ "asset_type": "FileBasedObject",
+ "id": "Retail_Leadership_Summit_eCT3zqHYIkX",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11819778887128225,
+ -0.14349874650416705,
+ -0.05794811858971811
+ ],
+ [
+ 0.12404121112871774,
+ 0.13040225349583295,
+ 0.06572188141028189
+ ]
+ ],
+ "mass": 0.00044004875169193375,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Retail Leadership Summit\nRetail Leadership Summit",
+ "nr_faces": 15774,
+ "nr_vertices": 8207,
+ "surface_area": 0.21968095184937614,
+ "volume": 0.00044004875169193375
+ }
+ },
+ "Retail_Leadership_Summit_tQFCizMt6g0": {
+ "asset_type": "FileBasedObject",
+ "id": "Retail_Leadership_Summit_tQFCizMt6g0",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12586315955210034,
+ -0.13822843535277504,
+ -0.06289525537036815
+ ],
+ [
+ 0.12129084044789964,
+ 0.13530656464722496,
+ 0.06239274462963186
+ ]
+ ],
+ "mass": 0.002071240988552453,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Retail Leadership Summit\nRetail Leadership Summit",
+ "nr_faces": 53672,
+ "nr_vertices": 27251,
+ "surface_area": 0.18422645147102573,
+ "volume": 0.002071240988552453
+ }
+ },
+ "Rexy_Glove_Heavy_Duty_Gloves_Medium": {
+ "asset_type": "FileBasedObject",
+ "id": "Rexy_Glove_Heavy_Duty_Gloves_Medium",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16246018389040062,
+ -0.1301418809746697,
+ -0.01408239307834344
+ ],
+ [
+ 0.1563258161095994,
+ 0.12613711902533029,
+ 0.022235606921656555
+ ]
+ ],
+ "mass": 0.0005776192580192036,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Rexy Glove Heavy Duty Gloves, Medium",
+ "nr_faces": 14716,
+ "nr_vertices": 8084,
+ "surface_area": 0.12184078624848035,
+ "volume": 0.0005776192580192036
+ }
+ },
+ "Rexy_Glove_Heavy_Duty_Large": {
+ "asset_type": "FileBasedObject",
+ "id": "Rexy_Glove_Heavy_Duty_Large",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13600953112885233,
+ -0.11988578274099934,
+ -0.012918506955601577
+ ],
+ [
+ 0.13807546887114766,
+ 0.12430121725900066,
+ 0.02096849304439842
+ ]
+ ],
+ "mass": 0.00044381049360854986,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Rexy Glove Heavy Duty, Large",
+ "nr_faces": 42558,
+ "nr_vertices": 22237,
+ "surface_area": 0.11178386932327843,
+ "volume": 0.00044381049360854986
+ }
+ },
+ "Romantic_Blush_Tieks_Metallic_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Romantic_Blush_Tieks_Metallic_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04599537461437227,
+ -0.11992696041677589,
+ -0.025794769719839118
+ ],
+ [
+ 0.03715162538562773,
+ 0.1266180395832241,
+ 0.05107223028016088
+ ]
+ ],
+ "mass": 0.0004683702445222895,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Romantic Blush Tieks - Metallic Italian Leather Ballet Flats\nRomantic Blush Tieks are sure to make any girl blush! The lovely combination of sparkling silver and pale pink fashions one of our most feminine and beautiful ballet flats. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 20168,
+ "nr_vertices": 10836,
+ "surface_area": 0.07362594783640786,
+ "volume": 0.0004683702445222895
+ }
+ },
+ "Room_Essentials_Bowl_Turquiose": {
+ "asset_type": "FileBasedObject",
+ "id": "Room_Essentials_Bowl_Turquiose",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07903202228177457,
+ -0.07917968294549325,
+ -0.03899573016636755
+ ],
+ [
+ 0.07785497771822544,
+ 0.07804131705450675,
+ 0.04357026983363245
+ ]
+ ],
+ "mass": 0.00023189011928879567,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Room Essentials Bowl, Turquiose",
+ "nr_faces": 5112,
+ "nr_vertices": 2653,
+ "surface_area": 0.07988020168224899,
+ "volume": 0.00023189011928879567
+ }
+ },
+ "Room_Essentials_Dish_Drainer_Collapsible_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Room_Essentials_Dish_Drainer_Collapsible_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15798664214355232,
+ -0.1849222803396999,
+ -0.036674669849662576
+ ],
+ [
+ 0.15753335785644768,
+ 0.1827217196603001,
+ 0.043363330150337415
+ ]
+ ],
+ "mass": 0.0024460430589388713,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Room Essentials Dish Drainer, Collapsible, White",
+ "nr_faces": 27562,
+ "nr_vertices": 17070,
+ "surface_area": 0.4390499479150288,
+ "volume": 0.0024460430589388713
+ }
+ },
+ "Room_Essentials_Fabric_Cube_Lavender": {
+ "asset_type": "FileBasedObject",
+ "id": "Room_Essentials_Fabric_Cube_Lavender",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1336448131289243,
+ -0.14689857146083088,
+ -0.1116364441332946
+ ],
+ [
+ 0.14668118687107567,
+ 0.13884742853916912,
+ 0.17319355586670537
+ ]
+ ],
+ "mass": 0.0019776478527165423,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Room Essentials Fabric Cube - Lavender",
+ "nr_faces": 11496,
+ "nr_vertices": 6383,
+ "surface_area": 0.7253288666258404,
+ "volume": 0.0019776478527165423
+ }
+ },
+ "Room_Essentials_Kitchen_Towels_16_x_26_2_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Room_Essentials_Kitchen_Towels_16_x_26_2_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07454086159135927,
+ -0.0879705748944693,
+ -0.0344665414673136
+ ],
+ [
+ 0.07733513840864074,
+ 0.0954544251055307,
+ 0.044025458532686405
+ ]
+ ],
+ "mass": 0.0014908670776052173,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Room Essentials Kitchen Towels, 16\" x 26\" - 2 count",
+ "nr_faces": 55644,
+ "nr_vertices": 29206,
+ "surface_area": 0.10926329172590477,
+ "volume": 0.0014908670776052173
+ }
+ },
+ "Room_Essentials_Mug_White_Yellow": {
+ "asset_type": "FileBasedObject",
+ "id": "Room_Essentials_Mug_White_Yellow",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05692388751175071,
+ -0.05260732489741204,
+ -0.054220136137226246
+ ],
+ [
+ 0.07991411248824928,
+ 0.04958367510258797,
+ 0.05057386386277375
+ ]
+ ],
+ "mass": 0.000172398945725301,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Room Essentials Mug, White/ Yellow",
+ "nr_faces": 8454,
+ "nr_vertices": 4441,
+ "surface_area": 0.06384872109715506,
+ "volume": 0.000172398945725301
+ }
+ },
+ "Room_Essentials_Salad_Plate_Turquoise": {
+ "asset_type": "FileBasedObject",
+ "id": "Room_Essentials_Salad_Plate_Turquoise",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11020123071537603,
+ -0.1098405909947474,
+ -0.01202884352504462
+ ],
+ [
+ 0.11170576928462397,
+ 0.1120534090052526,
+ 0.01634815647495538
+ ]
+ ],
+ "mass": 0.00021645592995767467,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Room Essentials Salad Plate, Turquoise",
+ "nr_faces": 2608,
+ "nr_vertices": 1371,
+ "surface_area": 0.08434483379700408,
+ "volume": 0.00021645592995767467
+ }
+ },
+ "Rose_Garden_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes": {
+ "asset_type": "FileBasedObject",
+ "id": "Rose_Garden_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05036733001158579,
+ -0.12141785868535115,
+ -0.02757740374611263
+ ],
+ [
+ 0.04299666998841421,
+ 0.12545214131464885,
+ 0.051325596253887364
+ ]
+ ],
+ "mass": 0.0005366047781628733,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Rose Garden Tieks - Leather Ballet Flats with Floral Rosettes\nFall in love all over again with these charming, hand-stitched ballet flats. The delicate blend of fuchsia, white, pink and green, twisted into tiny fabric roses, is a true work of art. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 43880,
+ "nr_vertices": 26863,
+ "surface_area": 0.08056842671775298,
+ "volume": 0.0005366047781628733
+ }
+ },
+ "Rubbermaid_Large_Drainer": {
+ "asset_type": "FileBasedObject",
+ "id": "Rubbermaid_Large_Drainer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17934063734270284,
+ -0.12002395080180245,
+ -0.04730068852290832
+ ],
+ [
+ 0.15995536265729718,
+ 0.32232304919819754,
+ 0.07336231147709169
+ ]
+ ],
+ "mass": 0.0009886401697797105,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Rubbermaid Large Drainer",
+ "nr_faces": 40146,
+ "nr_vertices": 25585,
+ "surface_area": 0.3556092004552197,
+ "volume": 0.0009886401697797105
+ }
+ },
+ "SAMBA_HEMP": {
+ "asset_type": "FileBasedObject",
+ "id": "SAMBA_HEMP",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056322458963286,
+ -0.14187540144485924,
+ -0.03689860078400196
+ ],
+ [
+ 0.045828541036714,
+ 0.14813459855514075,
+ 0.07264239921599805
+ ]
+ ],
+ "mass": 0.0011623055420531654,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "SAMBA HEMP",
+ "nr_faces": 28556,
+ "nr_vertices": 15793,
+ "surface_area": 0.10989019041705542,
+ "volume": 0.0011623055420531654
+ }
+ },
+ "SAMOA": {
+ "asset_type": "FileBasedObject",
+ "id": "SAMOA",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.054981737036693776,
+ -0.15062919062353716,
+ -0.037571676712620974
+ ],
+ [
+ 0.049849262963306225,
+ 0.14213180937646286,
+ 0.09397132328737903
+ ]
+ ],
+ "mass": 0.001229739255307693,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "SAMOA",
+ "nr_faces": 25698,
+ "nr_vertices": 15243,
+ "surface_area": 0.12657781335238,
+ "volume": 0.001229739255307693
+ }
+ },
+ "SAMe_200": {
+ "asset_type": "FileBasedObject",
+ "id": "SAMe_200",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.043110752909293164,
+ -0.02413627918768414,
+ -0.07919967346461901
+ ],
+ [
+ 0.04332924709070684,
+ 0.024221720812315863,
+ 0.079639326535381
+ ]
+ ],
+ "mass": 0.0006081614117115911,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "SAM-e 200\nJarrow Formulas SAM-e 200 provides a full 200 mg SAM-e (net yield) from 400 mg of SAM-e tosylate disulfate. SAM-e 200 is manufactured under low temperature and low humidity and is enteric-coated to ensure a biologically active product. Found in all living cells, SAM-e is a metabolite of methionine (an essential amino acid). SAM-e is a chiral molecule and consists of two forms: (S,S) SAM-e and (R,S) SAM-e. The biologically active form is the (S,S) structure, while the (R,S) structure is biologically inactive. Jarrow Formulas SAM-e is made naturally by microbiological fermentation and then specially processed without solvents to preserve 68-80% (S,S) SAM-e, the highest active level available. SAM-e supports the production of healthy connective tissue through transulfuration. In this process, critical components of connective tissue, including glucosamine and the chondroitin sulfates, are sulfated by SAM-e metabolites.* SAM-e methylation reactions are involved in the synthesis of neurotransmitters such as L-DOPA, dopamine and related hormones, serotonin, epinephrine and phosphatidylcholine (a component of lecithin).* SAM-e metabolism supports the synthesis of glutathione (GSH) and glutathione-dependent enzymes (glutathione peroxidase and glutathione-S-transferase), which are substances important for liver function, including phase II detoxification.* Jarrow Formulas SAM-e 200 is foil blister-packed to maximize stability and safety. DO NOT use if outer seal of blister pack is broken. Full Potency 200 mg SAM-e is derived from 400 mg of SAM-e tosylate disulfate. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 4602,
+ "nr_vertices": 2436,
+ "surface_area": 0.04689151547158282,
+ "volume": 0.0006081614117115911
+ }
+ },
+ "SAMe_200_KX7ZmOw47co": {
+ "asset_type": "FileBasedObject",
+ "id": "SAMe_200_KX7ZmOw47co",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.041274689833980575,
+ -0.024329083575178403,
+ -0.0656158205835177
+ ],
+ [
+ 0.04126731016601942,
+ 0.023826916424821598,
+ 0.06536517941648229
+ ]
+ ],
+ "mass": 0.00048313430146001746,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "SAM-e 200\nJarrow Formulas SAM-e 200 provides a full 200 mg SAM-e (net yield) from 400 mg of SAM-e tosylate disulfate. SAM-e 200 is manufactured under low temperature and low humidity and is enteric-coated to ensure a biologically active product. Found in all living cells, SAM-e is a metabolite of methionine (an essential amino acid). SAM-e is a chiral molecule and consists of two forms: (S,S) SAM-e and (R,S) SAM-e. The biologically active form is the (S,S) structure, while the (R,S) structure is biologically inactive. Jarrow Formulas SAM-e is made naturally by microbiological fermentation and then specially processed without solvents to preserve 68-80% (S,S) SAM-e, the highest active level available. SAM-e supports the production of healthy connective tissue through transulfuration. In this process, critical components of connective tissue, including glucosamine and the chondroitin sulfates, are sulfated by SAM-e metabolites.* SAM-e methylation reactions are involved in the synthesis of neurotransmitters such as L-DOPA, dopamine and related hormones, serotonin, epinephrine and phosphatidylcholine (a component of lecithin).* SAM-e metabolism supports the synthesis of glutathione (GSH) and glutathione-dependent enzymes (glutathione peroxidase and glutathione-S-transferase), which are substances important for liver function, including phase II detoxification.* Jarrow Formulas SAM-e 200 is foil blister-packed to maximize stability and safety. DO NOT use if outer seal of blister pack is broken. Full Potency 200 mg SAM-e is derived from 400 mg of SAM-e tosylate disulfate. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 6318,
+ "nr_vertices": 3332,
+ "surface_area": 0.03881545855467301,
+ "volume": 0.00048313430146001746
+ }
+ },
+ "SANDWICH_MEAL": {
+ "asset_type": "FileBasedObject",
+ "id": "SANDWICH_MEAL",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06152423313246031,
+ -0.07806517204821972,
+ -0.018102278801069824
+ ],
+ [
+ 0.06673276686753969,
+ 0.060353827951780285,
+ 0.030523721198930178
+ ]
+ ],
+ "mass": 0.00029493811760913284,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SANDWICH MEAL\nThe set includes 2 slices of bread and onion, 1 plate, 1 banana, and 1 slice of cheese, ham, cucumber, and tomato. Great for pretend and imaginative play.",
+ "nr_faces": 11956,
+ "nr_vertices": 6603,
+ "surface_area": 0.04887160012141994,
+ "volume": 0.00029493811760913284
+ }
+ },
+ "SAPPHIRE_R7_260X_OC": {
+ "asset_type": "FileBasedObject",
+ "id": "SAPPHIRE_R7_260X_OC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08556588933227219,
+ -0.0344360146829818,
+ -0.1371805357023942
+ ],
+ [
+ 0.08542811066772782,
+ 0.0348839853170182,
+ 0.13538346429760578
+ ]
+ ],
+ "mass": 0.0028674806978146936,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "SAPPHIRE R7 260X OC\nSAPPHIRE 260X is a near perfect entry level gaming card. Delivering great MOBA performance this card uses 2GB of GDDR5 to deliver solid gaming for a low price.",
+ "nr_faces": 17102,
+ "nr_vertices": 8909,
+ "surface_area": 0.13984642577140777,
+ "volume": 0.0028674806978146936
+ }
+ },
+ "SCHOOL_BUS": {
+ "asset_type": "FileBasedObject",
+ "id": "SCHOOL_BUS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.015652973779770367,
+ -0.052659796543234876,
+ -0.01970306485139281
+ ],
+ [
+ 0.01617802622022963,
+ 0.04513920345676513,
+ 0.01858293514860719
+ ]
+ ],
+ "mass": 8.886608650304216e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SCHOOL BUS",
+ "nr_faces": 9300,
+ "nr_vertices": 4813,
+ "surface_area": 0.013284441588048519,
+ "volume": 8.886608650304216e-05
+ }
+ },
+ "SHAPE_MATCHING": {
+ "asset_type": "FileBasedObject",
+ "id": "SHAPE_MATCHING",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09672212806544916,
+ -0.08966357701744132,
+ -0.012771325517616245
+ ],
+ [
+ 0.15737887193455083,
+ 0.09965042298255868,
+ 0.021245674482383757
+ ]
+ ],
+ "mass": 0.00040715049749643435,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SHAPE MATCHING\nSet included 8 different puzzles blocks with two-sided curved base. Matching the corresponding halves and places the complete shape on the board. Good for differentiating colors, shapes, and forms. Curved base for easy flip over.",
+ "nr_faces": 5048,
+ "nr_vertices": 2781,
+ "surface_area": 0.09055253618512538,
+ "volume": 0.00040715049749643435
+ }
+ },
+ "SHAPE_MATCHING_NxacpAY9jDt": {
+ "asset_type": "FileBasedObject",
+ "id": "SHAPE_MATCHING_NxacpAY9jDt",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08625828983858057,
+ -0.0936170942372655,
+ -0.014411472304038548
+ ],
+ [
+ 0.08893171016141943,
+ 0.0956489057627345,
+ 0.02010852769596145
+ ]
+ ],
+ "mass": 0.0004063033215216896,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SHAPE MATCHING\nSet included 8 different puzzles blocks with two-sided curved base. Matching the corresponding halves and places the complete shape on the board. Good for differentiating colors, shapes, and forms. Curved base for easy flip over.",
+ "nr_faces": 6078,
+ "nr_vertices": 3257,
+ "surface_area": 0.08434540162402816,
+ "volume": 0.0004063033215216896
+ }
+ },
+ "SHAPE_SORTER": {
+ "asset_type": "FileBasedObject",
+ "id": "SHAPE_SORTER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17310681533462685,
+ -0.09360937751104202,
+ -0.014141467378806512
+ ],
+ [
+ 0.16317118466537314,
+ 0.09573762248895798,
+ 0.03166553262119349
+ ]
+ ],
+ "mass": 0.0004674813108616887,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SHAPE SORTER\nLearn about geometry, fraction and shapes while matching and building the different shapes on the curved two-sided base.",
+ "nr_faces": 4902,
+ "nr_vertices": 2955,
+ "surface_area": 0.10896511502479674,
+ "volume": 0.0004674813108616887
+ }
+ },
+ "SIT_N_WALK_PUPPY": {
+ "asset_type": "FileBasedObject",
+ "id": "SIT_N_WALK_PUPPY",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06384929075169254,
+ -0.10618145752103691,
+ -0.026476321797009383
+ ],
+ [
+ 0.059230709248307464,
+ 0.08044654247896307,
+ 0.06340867820299062
+ ]
+ ],
+ "mass": 0.00030488883598756337,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SIT N WALK PUPPY\nPull the Sit N Walk Puppy along and it will walk and sit just like a real puppy!",
+ "nr_faces": 14588,
+ "nr_vertices": 8115,
+ "surface_area": 0.0484755261722366,
+ "volume": 0.00030488883598756337
+ }
+ },
+ "SLACK_CRUISER": {
+ "asset_type": "FileBasedObject",
+ "id": "SLACK_CRUISER",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.061368455367919225,
+ -0.14442036513274342,
+ -0.036447871700244806
+ ],
+ [
+ 0.049422544632080775,
+ 0.1645506348672566,
+ 0.0914951282997552
+ ]
+ ],
+ "mass": 0.001300755760537789,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "SLACK CRUISER\nFW-SHOES",
+ "nr_faces": 24796,
+ "nr_vertices": 14231,
+ "surface_area": 0.1346208103357425,
+ "volume": 0.001300755760537789
+ }
+ },
+ "SNAIL_MEASURING_TAPE": {
+ "asset_type": "FileBasedObject",
+ "id": "SNAIL_MEASURING_TAPE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.031994827840723564,
+ -0.06238090587020668,
+ -0.028074956161121135
+ ],
+ [
+ 0.031899172159276436,
+ 0.13207609412979332,
+ 0.037637043838878864
+ ]
+ ],
+ "mass": 0.00019150095510226734,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SNAIL MEASURING TAPE\nQuickly learn spatial recognition and exploration through measurement with this not so fast critter.",
+ "nr_faces": 8564,
+ "nr_vertices": 4651,
+ "surface_area": 0.0264195641500192,
+ "volume": 0.00019150095510226734
+ }
+ },
+ "SORTING_BUS": {
+ "asset_type": "FileBasedObject",
+ "id": "SORTING_BUS",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14002513551068385,
+ -0.16514317764040418,
+ -0.04821236688645246
+ ],
+ [
+ 0.14806486448931616,
+ 0.12511882235959582,
+ 0.08725063311354755
+ ]
+ ],
+ "mass": 0.0009402961060377782,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SORTING BUS\nThe shape sorting bus contains shapes that when sorted correctly will fit into the bus. Pull the sign on the bus and all the pieces will slide out.",
+ "nr_faces": 16932,
+ "nr_vertices": 10243,
+ "surface_area": 0.18725560281405845,
+ "volume": 0.0009402961060377782
+ }
+ },
+ "SORTING_TRAIN": {
+ "asset_type": "FileBasedObject",
+ "id": "SORTING_TRAIN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05034090731875969,
+ -0.16771398616118097,
+ -0.0525689264059083
+ ],
+ [
+ 0.05048509268124031,
+ 0.07048501383881903,
+ 0.08526007359409168
+ ]
+ ],
+ "mass": 0.0007021252117537773,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SORTING TRAIN\nShape and sort features enable this set to form a train which can be used as a pull toy.",
+ "nr_faces": 15666,
+ "nr_vertices": 8844,
+ "surface_area": 0.07787635261812337,
+ "volume": 0.0007021252117537773
+ }
+ },
+ "SPEED_BOAT": {
+ "asset_type": "FileBasedObject",
+ "id": "SPEED_BOAT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.049732446474195946,
+ -0.05793107288561692,
+ -0.024761079062404233
+ ],
+ [
+ 0.09277555352580405,
+ 0.06186492711438308,
+ 0.04146492093759576
+ ]
+ ],
+ "mass": 0.00031472238211377695,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "SPEED BOAT\nImagine racing across the sea at super speeds! This delightful set stimulates interactive and imaginative play.",
+ "nr_faces": 17886,
+ "nr_vertices": 11727,
+ "surface_area": 0.035584032903466706,
+ "volume": 0.00031472238211377695
+ }
+ },
+ "STACKING_BEAR": {
+ "asset_type": "FileBasedObject",
+ "id": "STACKING_BEAR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05418471799385864,
+ -0.052592027741481424,
+ -0.07523367708136401
+ ],
+ [
+ 0.05390228200614136,
+ 0.048623972258518576,
+ 0.10275932291863599
+ ]
+ ],
+ "mass": 0.0008430053665060113,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "STACKING BEAR\nBuild the colorful bear by stacking and matching ?the blocks with the corresponding grooves.",
+ "nr_faces": 14018,
+ "nr_vertices": 7521,
+ "surface_area": 0.06136104071735058,
+ "volume": 0.0008430053665060113
+ }
+ },
+ "STACKING_BEAR_V04KKgGBn2A": {
+ "asset_type": "FileBasedObject",
+ "id": "STACKING_BEAR_V04KKgGBn2A",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10595199482823828,
+ -0.12750039102634161,
+ -0.03206754391201336
+ ],
+ [
+ 0.11543700517176171,
+ 0.07290760897365839,
+ 0.06144145608798664
+ ]
+ ],
+ "mass": 0.0008346134116755524,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "STACKING BEAR\nBuild the colorful bear by stacking and matching ?the blocks with the corresponding grooves.",
+ "nr_faces": 11064,
+ "nr_vertices": 5921,
+ "surface_area": 0.095198077940398,
+ "volume": 0.0008346134116755524
+ }
+ },
+ "STACKING_RING": {
+ "asset_type": "FileBasedObject",
+ "id": "STACKING_RING",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04111190399846257,
+ -0.03915853194985005,
+ -0.07171991322248734
+ ],
+ [
+ 0.03801009600153744,
+ 0.04070046805014995,
+ 0.11567308677751266
+ ]
+ ],
+ "mass": 0.0004846371114930752,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "STACKING RING\nThe wooden ring set teaches children about sizes and colours. As a safety precaution the central rods is collapsible.",
+ "nr_faces": 14854,
+ "nr_vertices": 7830,
+ "surface_area": 0.04655372122334811,
+ "volume": 0.0004846371114930752
+ }
+ },
+ "STEAK_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "STEAK_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10841217044407535,
+ -0.07224212524149158,
+ -0.01349435649826065
+ ],
+ [
+ 0.09270082955592465,
+ 0.06660187475850841,
+ 0.026872643501739346
+ ]
+ ],
+ "mass": 0.00030510869669968797,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "STEAK SET\nIncludes 1 plate, 1 fork, 1 knife, 1 steak, 1 roll, 1 piece of corn, and 2 slices of onion and mushrooms.",
+ "nr_faces": 11304,
+ "nr_vertices": 6457,
+ "surface_area": 0.053871106418358086,
+ "volume": 0.00030510869669968797
+ }
+ },
+ "SUPERSTAR_CLR": {
+ "asset_type": "FileBasedObject",
+ "id": "SUPERSTAR_CLR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05524395846052487,
+ -0.14309844392709017,
+ -0.03818480118921101
+ ],
+ [
+ 0.049013041539475125,
+ 0.1490185560729098,
+ 0.07853619881078898
+ ]
+ ],
+ "mass": 0.0011571776715105274,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "SUPERSTAR CLR",
+ "nr_faces": 46090,
+ "nr_vertices": 25630,
+ "surface_area": 0.12871799453273639,
+ "volume": 0.0011571776715105274
+ }
+ },
+ "Saccharomyces_Boulardii_MOS_Value_Size": {
+ "asset_type": "FileBasedObject",
+ "id": "Saccharomyces_Boulardii_MOS_Value_Size",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0375333291849458,
+ -0.0370313080979083,
+ -0.061029833390701685
+ ],
+ [
+ 0.037298670815054204,
+ 0.0370156919020917,
+ 0.07404916660929832
+ ]
+ ],
+ "mass": 0.0004996789196877315,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Saccharomyces Boulardii + MOS Value Size",
+ "nr_faces": 6804,
+ "nr_vertices": 3515,
+ "surface_area": 0.03550477549009166,
+ "volume": 0.0004996789196877315
+ }
+ },
+ "Samoa_onepiece": {
+ "asset_type": "FileBasedObject",
+ "id": "Samoa_onepiece",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05371298369738448,
+ -0.14864228862850437,
+ -0.039669099146705473
+ ],
+ [
+ 0.04883801630261552,
+ 0.14379571137149563,
+ 0.07424790085329452
+ ]
+ ],
+ "mass": 0.00129332378218582,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Samoa (one-piece)",
+ "nr_faces": 24064,
+ "nr_vertices": 14195,
+ "surface_area": 0.11918366005553774,
+ "volume": 0.00129332378218582
+ }
+ },
+ "Samsung_CLTC406S_Toner_Cartridge_Cyan_1pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Samsung_CLTC406S_Toner_Cartridge_Cyan_1pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.19370571991314386,
+ -0.04205225697836125,
+ -0.0923439508939489
+ ],
+ [
+ 0.19485128008685612,
+ 0.04183074302163875,
+ 0.0922190491060511
+ ]
+ ],
+ "mass": 0.005471364468225608,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Samsung CLT-C406S Toner Cartridge, Cyan - 1-pack",
+ "nr_faces": 2066,
+ "nr_vertices": 1114,
+ "surface_area": 0.22571001913987326,
+ "volume": 0.005471364468225608
+ }
+ },
+ "Santa_Cruz_Mens": {
+ "asset_type": "FileBasedObject",
+ "id": "Santa_Cruz_Mens",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06058233100226189,
+ -0.14278466434294257,
+ -0.030219247737631884
+ ],
+ [
+ 0.05170166899773811,
+ 0.1558183356570574,
+ 0.07377875226236812
+ ]
+ ],
+ "mass": 0.0009873641376442763,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Santa Cruz Mens",
+ "nr_faces": 22024,
+ "nr_vertices": 11577,
+ "surface_area": 0.1319647596430403,
+ "volume": 0.0009873641376442763
+ }
+ },
+ "Santa_Cruz_Mens_G7kQXK7cIky": {
+ "asset_type": "FileBasedObject",
+ "id": "Santa_Cruz_Mens_G7kQXK7cIky",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06040403443789574,
+ -0.1400500197678319,
+ -0.03056543354931837
+ ],
+ [
+ 0.053936965562104255,
+ 0.1606859802321681,
+ 0.07084656645068163
+ ]
+ ],
+ "mass": 0.0010888532363355612,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Santa Cruz Mens",
+ "nr_faces": 21024,
+ "nr_vertices": 11185,
+ "surface_area": 0.1261395683829773,
+ "volume": 0.0010888532363355612
+ }
+ },
+ "Santa_Cruz_Mens_YmsMDkFf11Z": {
+ "asset_type": "FileBasedObject",
+ "id": "Santa_Cruz_Mens_YmsMDkFf11Z",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.060415982786933754,
+ -0.1393137740896748,
+ -0.030401329449126133
+ ],
+ [
+ 0.048569017213066244,
+ 0.1591352259103252,
+ 0.07554067055087386
+ ]
+ ],
+ "mass": 0.0010602847356760274,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Santa Cruz Mens",
+ "nr_faces": 22054,
+ "nr_vertices": 11520,
+ "surface_area": 0.12238788351180382,
+ "volume": 0.0010602847356760274
+ }
+ },
+ "Santa_Cruz_Mens_umxTczr1Ygg": {
+ "asset_type": "FileBasedObject",
+ "id": "Santa_Cruz_Mens_umxTczr1Ygg",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059968618595393056,
+ -0.1460273264671023,
+ -0.029770669847488416
+ ],
+ [
+ 0.05380738140460694,
+ 0.1546726735328977,
+ 0.07289633015251158
+ ]
+ ],
+ "mass": 0.0009670765526249445,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Santa Cruz Mens",
+ "nr_faces": 21310,
+ "nr_vertices": 11223,
+ "surface_area": 0.13787509393496256,
+ "volume": 0.0009670765526249445
+ }
+ },
+ "Santa_Cruz_Mens_vnbiTDDt5xH": {
+ "asset_type": "FileBasedObject",
+ "id": "Santa_Cruz_Mens_vnbiTDDt5xH",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05971285250075163,
+ -0.14559379173838427,
+ -0.02910783499228281
+ ],
+ [
+ 0.04933414749924837,
+ 0.15316820826161573,
+ 0.0774721650077172
+ ]
+ ],
+ "mass": 0.000942126602871925,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Santa Cruz Mens",
+ "nr_faces": 29050,
+ "nr_vertices": 15717,
+ "surface_area": 0.14937450387052537,
+ "volume": 0.000942126602871925
+ }
+ },
+ "Sapota_Threshold_4_Ceramic_Round_Planter_Red": {
+ "asset_type": "FileBasedObject",
+ "id": "Sapota_Threshold_4_Ceramic_Round_Planter_Red",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05278725692419076,
+ -0.05518961789572324,
+ -0.04705644229061197
+ ],
+ [
+ 0.05320374307580924,
+ 0.05436438210427676,
+ 0.05008055770938803
+ ]
+ ],
+ "mass": 0.00014438879757913348,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Sapota Threshold 4\" Ceramic Round Planter Red",
+ "nr_faces": 13368,
+ "nr_vertices": 6857,
+ "surface_area": 0.061822380300373694,
+ "volume": 0.00014438879757913348
+ }
+ },
+ "Schleich_African_Black_Rhino": {
+ "asset_type": "FileBasedObject",
+ "id": "Schleich_African_Black_Rhino",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02080674734279307,
+ -0.0809857040937839,
+ -0.034866099101971595
+ ],
+ [
+ 0.020303252657206932,
+ 0.056514295906216094,
+ 0.0252559008980284
+ ]
+ ],
+ "mass": 0.00010621541871245883,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Schleich African Black Rhino",
+ "nr_faces": 12254,
+ "nr_vertices": 6650,
+ "surface_area": 0.017831892573999034,
+ "volume": 0.00010621541871245883
+ }
+ },
+ "Schleich_Allosaurus": {
+ "asset_type": "FileBasedObject",
+ "id": "Schleich_Allosaurus",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03056369180735659,
+ -0.09127421802423225,
+ -0.06104820401957104
+ ],
+ [
+ 0.03677430819264341,
+ 0.13165478197576777,
+ 0.057356795980428955
+ ]
+ ],
+ "mass": 0.00011612700794461882,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Schleich Allosaurus",
+ "nr_faces": 12258,
+ "nr_vertices": 6762,
+ "surface_area": 0.026815994890088464,
+ "volume": 0.00011612700794461882
+ }
+ },
+ "Schleich_Bald_Eagle": {
+ "asset_type": "FileBasedObject",
+ "id": "Schleich_Bald_Eagle",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.039667651944637866,
+ -0.035558212494048176,
+ -0.04080392655960456
+ ],
+ [
+ 0.036564348055362135,
+ 0.03574978750595182,
+ 0.04909007344039543
+ ]
+ ],
+ "mass": 2.9776897961848502e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Schleich Bald Eagle",
+ "nr_faces": 18510,
+ "nr_vertices": 10223,
+ "surface_area": 0.015407221160824925,
+ "volume": 2.9776897961848502e-05
+ }
+ },
+ "Schleich_Hereford_Bull": {
+ "asset_type": "FileBasedObject",
+ "id": "Schleich_Hereford_Bull",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02175865557048802,
+ -0.07270765093033249,
+ -0.04959501996387583
+ ],
+ [
+ 0.02202134442951198,
+ 0.06172634906966751,
+ 0.03201998003612417
+ ]
+ ],
+ "mass": 0.00013633086304433185,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Schleich Hereford Bull",
+ "nr_faces": 13512,
+ "nr_vertices": 7355,
+ "surface_area": 0.021385379339405347,
+ "volume": 0.00013633086304433185
+ }
+ },
+ "Schleich_Lion_Action_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Schleich_Lion_Action_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04251775748205364,
+ -0.022349251256340946,
+ -0.0396485172884072
+ ],
+ [
+ 0.07250024251794636,
+ 0.019329748743659055,
+ 0.030793482711592803
+ ]
+ ],
+ "mass": 6.437387145239615e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Schleich Lion Action Figure",
+ "nr_faces": 15058,
+ "nr_vertices": 7940,
+ "surface_area": 0.013646313902877752,
+ "volume": 6.437387145239615e-05
+ }
+ },
+ "Schleich_S_Bayala_Unicorn_70432": {
+ "asset_type": "FileBasedObject",
+ "id": "Schleich_S_Bayala_Unicorn_70432",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.026816095454057526,
+ -0.08272454581363979,
+ -0.05683286199168841
+ ],
+ [
+ 0.02783390454594247,
+ 0.0652634541863602,
+ 0.04481213800831159
+ ]
+ ],
+ "mass": 8.903650572314483e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Schleich S Bayala Unicorn, 70432",
+ "nr_faces": 16624,
+ "nr_vertices": 9072,
+ "surface_area": 0.021193824684251263,
+ "volume": 8.903650572314483e-05
+ }
+ },
+ "Schleich_Spinosaurus_Action_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Schleich_Spinosaurus_Action_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.035737979737234526,
+ -0.11432680470730641,
+ -0.07344174383653296
+ ],
+ [
+ 0.04112302026276547,
+ 0.1497531952926936,
+ 0.060090256163467054
+ ]
+ ],
+ "mass": 0.00018921195871123014,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Schleich Spinosaurus Action Figure",
+ "nr_faces": 14430,
+ "nr_vertices": 7854,
+ "surface_area": 0.03925512699044113,
+ "volume": 0.00018921195871123014
+ }
+ },
+ "Schleich_Therizinosaurus_ln9cruulPqc": {
+ "asset_type": "FileBasedObject",
+ "id": "Schleich_Therizinosaurus_ln9cruulPqc",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.072053351515354,
+ -0.11083005701201458,
+ -0.08772209105162834
+ ],
+ [
+ 0.042164648484646,
+ 0.10670194298798542,
+ 0.10967790894837165
+ ]
+ ],
+ "mass": 0.0002561534678101787,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Schleich Therizinosaurus",
+ "nr_faces": 19690,
+ "nr_vertices": 11010,
+ "surface_area": 0.047802033024892686,
+ "volume": 0.0002561534678101787
+ }
+ },
+ "Sea_to_Summit_Xl_Bowl": {
+ "asset_type": "FileBasedObject",
+ "id": "Sea_to_Summit_Xl_Bowl",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08905345158728671,
+ -0.09175331925861964,
+ -0.009539329266886738
+ ],
+ [
+ 0.09116654841271328,
+ 0.08855768074138036,
+ 0.025962670733113265
+ ]
+ ],
+ "mass": 0.00010543250696100767,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Sea to Summit Xl Bowl",
+ "nr_faces": 10900,
+ "nr_vertices": 5568,
+ "surface_area": 0.08179419953130704,
+ "volume": 0.00010543250696100767
+ }
+ },
+ "Seagate_1TB_Backup_Plus_portable_drive_Blue": {
+ "asset_type": "FileBasedObject",
+ "id": "Seagate_1TB_Backup_Plus_portable_drive_Blue",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.007862968966836657,
+ -0.04098313754184643,
+ -0.06136064110326796
+ ],
+ [
+ 0.007864031033163344,
+ 0.040808862458153565,
+ 0.06261635889673205
+ ]
+ ],
+ "mass": 0.00015009321724771284,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Seagate 1TB Backup Plus portable drive - Blue\nThe Backup Plus portable drive from Seagate is the simple, one-click way to protect and share your entire digital life?without getting in the way of the rest of your life.",
+ "nr_faces": 3272,
+ "nr_vertices": 1758,
+ "surface_area": 0.025368650629980182,
+ "volume": 0.00015009321724771284
+ }
+ },
+ "Seagate_1TB_Backup_Plus_portable_drive_Silver": {
+ "asset_type": "FileBasedObject",
+ "id": "Seagate_1TB_Backup_Plus_portable_drive_Silver",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.00823302238909847,
+ -0.04085147481783156,
+ -0.061660057770330026
+ ],
+ [
+ 0.00834097761090153,
+ 0.041077525182168444,
+ 0.06254894222966997
+ ]
+ ],
+ "mass": 0.00015053386660286434,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Seagate 1TB Backup Plus portable drive - Silver\nThe Backup Plus portable drive from Seagate is the simple, one-click way to protect and share your entire digital life?without getting in the way of the rest of your life.",
+ "nr_faces": 3026,
+ "nr_vertices": 1639,
+ "surface_area": 0.025421639400016315,
+ "volume": 0.00015053386660286434
+ }
+ },
+ "Seagate_1TB_Backup_Plus_portable_drive_for_Mac": {
+ "asset_type": "FileBasedObject",
+ "id": "Seagate_1TB_Backup_Plus_portable_drive_for_Mac",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.007940272850236912,
+ -0.04091869015045458,
+ -0.061407319826698406
+ ],
+ [
+ 0.008385727149763088,
+ 0.04103330984954542,
+ 0.0628636801733016
+ ]
+ ],
+ "mass": 0.0001509069848483168,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Seagate 1TB Backup Plus portable drive for Mac\nThe Backup Plus portable drive for Mac from Seagate is the simple way to protect and share your entire digital life?without getting in the way of the rest of your life.",
+ "nr_faces": 2888,
+ "nr_vertices": 1585,
+ "surface_area": 0.025448788723169913,
+ "volume": 0.0001509069848483168
+ }
+ },
+ "Seagate_1TB_Wireless_Plus_mobile_device_storage": {
+ "asset_type": "FileBasedObject",
+ "id": "Seagate_1TB_Wireless_Plus_mobile_device_storage",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.010285371539479442,
+ -0.04480200130690944,
+ -0.06456801962755074
+ ],
+ [
+ 0.010808628460520558,
+ 0.04471799869309056,
+ 0.06371098037244925
+ ]
+ ],
+ "mass": 0.00021984105785448864,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Seagate 1TB Wireless Plus mobile device storage\nEnjoy your content anywhere?without wires or web.",
+ "nr_faces": 20664,
+ "nr_vertices": 10576,
+ "surface_area": 0.029859062025486854,
+ "volume": 0.00021984105785448864
+ }
+ },
+ "Seagate_3TB_Central_shared_storage": {
+ "asset_type": "FileBasedObject",
+ "id": "Seagate_3TB_Central_shared_storage",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07302851486764993,
+ -0.10876133029770862,
+ -0.023843678451494134
+ ],
+ [
+ 0.07345248513235007,
+ 0.10841566970229138,
+ 0.022122321548505866
+ ]
+ ],
+ "mass": 0.0010774290940245143,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Seagate 3TB Central shared storage\nConnect Seagate? Central to your Wi-Fi router to organize and back up all your content on one device that you can access from anywhere.",
+ "nr_faces": 17842,
+ "nr_vertices": 9211,
+ "surface_area": 0.08045398356868154,
+ "volume": 0.0010774290940245143
+ }
+ },
+ "Seagate_Archive_HDD_8_TB_Internal_hard_drive_SATA_6Gbs_35_ST8000AS0002": {
+ "asset_type": "FileBasedObject",
+ "id": "Seagate_Archive_HDD_8_TB_Internal_hard_drive_SATA_6Gbs_35_ST8000AS0002",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.051383914422385796,
+ -0.013829613278367498,
+ -0.07389031685515011
+ ],
+ [
+ 0.0522500855776142,
+ 0.014233386721632501,
+ 0.07444968314484988
+ ]
+ ],
+ "mass": 0.0003621656758100515,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Seagate Archive HDD 8 TB Internal hard drive SATA 6Gb/s 3.5\" ST8000AS0002",
+ "nr_faces": 35114,
+ "nr_vertices": 18359,
+ "surface_area": 0.04211820873620688,
+ "volume": 0.0003621656758100515
+ }
+ },
+ "Shark": {
+ "asset_type": "FileBasedObject",
+ "id": "Shark",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07739982859085703,
+ -0.14408928294968235,
+ -0.06270009414588915
+ ],
+ [
+ 0.09844217140914296,
+ 0.24297271705031767,
+ 0.09851290585411085
+ ]
+ ],
+ "mass": 0.002430102566992564,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Shark\nShark",
+ "nr_faces": 21654,
+ "nr_vertices": 11567,
+ "surface_area": 0.136742408735501,
+ "volume": 0.002430102566992564
+ }
+ },
+ "Shaxon_100_Molded_Category_6_RJ45RJ45_Shielded_Patch_Cord_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Shaxon_100_Molded_Category_6_RJ45RJ45_Shielded_Patch_Cord_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08773627183188776,
+ -0.08538299348356312,
+ -0.030576198821620576
+ ],
+ [
+ 0.08701772816811225,
+ 0.08940300651643687,
+ 0.029932801178379424
+ ]
+ ],
+ "mass": 0.000901827269692472,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Shaxon 100' Molded Category 6 RJ45/RJ45 Shielded Patch Cord, White",
+ "nr_faces": 29228,
+ "nr_vertices": 15482,
+ "surface_area": 0.0924364521805028,
+ "volume": 0.000901827269692472
+ }
+ },
+ "Shurtape_30_Day_Removal_UV_Delct_15": {
+ "asset_type": "FileBasedObject",
+ "id": "Shurtape_30_Day_Removal_UV_Delct_15",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05851755927464147,
+ -0.058358905902301056,
+ -0.01923967446486084
+ ],
+ [
+ 0.058411440725358525,
+ 0.05840709409769894,
+ 0.01913932553513916
+ ]
+ ],
+ "mass": 0.00022177545472549712,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Shurtape 30 Day Removal UV Delct, 1.5\"",
+ "nr_faces": 4122,
+ "nr_vertices": 2138,
+ "surface_area": 0.033783363734453745,
+ "volume": 0.00022177545472549712
+ }
+ },
+ "Shurtape_Gaffers_Tape_Silver_2_x_60_yd": {
+ "asset_type": "FileBasedObject",
+ "id": "Shurtape_Gaffers_Tape_Silver_2_x_60_yd",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07671547842731409,
+ -0.07628866643339674,
+ -0.025355498031051426
+ ],
+ [
+ 0.07684252157268591,
+ 0.07649533356660325,
+ 0.025444501968948575
+ ]
+ ],
+ "mass": 0.000665616671571191,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Shurtape Gaffers Tape, Silver, 2\" x 60 yd",
+ "nr_faces": 3298,
+ "nr_vertices": 1774,
+ "surface_area": 0.061501087831458495,
+ "volume": 0.000665616671571191
+ }
+ },
+ "Shurtape_Tape_Purple_CP28": {
+ "asset_type": "FileBasedObject",
+ "id": "Shurtape_Tape_Purple_CP28",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059157408766428256,
+ -0.05845803514468033,
+ -0.02510167928783718
+ ],
+ [
+ 0.058987591233571744,
+ 0.05858196485531967,
+ 0.025096320712162817
+ ]
+ ],
+ "mass": 0.00029846615164732366,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Shurtape Tape, Purple, CP28",
+ "nr_faces": 4724,
+ "nr_vertices": 2446,
+ "surface_area": 0.041331287140314886,
+ "volume": 0.00029846615164732366
+ }
+ },
+ "Sienna_Brown_Croc_Tieks_Patent_Leather_Crocodile_Print_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Sienna_Brown_Croc_Tieks_Patent_Leather_Crocodile_Print_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0413521273001713,
+ -0.11561536834858664,
+ -0.02977265088178789
+ ],
+ [
+ 0.0414648726998287,
+ 0.12859863165141336,
+ 0.058558349118212116
+ ]
+ ],
+ "mass": 0.0004935980254905017,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Sienna Brown Croc Tieks - Patent Leather Crocodile Print Ballet Flats\nFor some fancy footwork this season, add striking style to your favorite looks with these patent, crocodile print ballet flats. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 21468,
+ "nr_vertices": 11299,
+ "surface_area": 0.07765818145559947,
+ "volume": 0.0004935980254905017
+ }
+ },
+ "Simon_Swipe_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Simon_Swipe_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11441452948685993,
+ -0.11457530356524763,
+ -0.020236823412534553
+ ],
+ [
+ 0.11471947051314008,
+ 0.11433369643475237,
+ 0.027443176587465444
+ ]
+ ],
+ "mass": 0.0008252862621417874,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Simon Swipe Game",
+ "nr_faces": 20590,
+ "nr_vertices": 10952,
+ "surface_area": 0.09552701554014907,
+ "volume": 0.0008252862621417874
+ }
+ },
+ "Sleep_Optimizer": {
+ "asset_type": "FileBasedObject",
+ "id": "Sleep_Optimizer",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04426808665944701,
+ -0.011817431205500164,
+ -0.06172081887631542
+ ],
+ [
+ 0.04426991334055299,
+ 0.011866568794499837,
+ 0.0844461811236846
+ ]
+ ],
+ "mass": 0.0002237026922814855,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Sleep Optimizer\nJarrow Formulas Sleep Optimizer combines herbs and amino acids that work together to facilitate falling asleep and maintaining a regular sleep cycle.* Gamma-aminobutyric acid (GABA), lemon balm, and L-tryptophan promote relaxation.* The combination of valerian and hops flower has been studied for its effect on reducing latency (the delay before entry into sleep).* Melatonin is a hormone secreted by the pineal gland that controls the biological clock and signals the entry into sleep.* Our biological clock can be disturbed by stress, crossing time zones, and changing work shifts. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 3698,
+ "nr_vertices": 2031,
+ "surface_area": 0.0324903530923283,
+ "volume": 0.0002237026922814855
+ }
+ },
+ "Smith_Hawken_Woven_BasketTray_Organizer_with_3_Compartments_95_x_9_x_13": {
+ "asset_type": "FileBasedObject",
+ "id": "Smith_Hawken_Woven_BasketTray_Organizer_with_3_Compartments_95_x_9_x_13",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.18876002929504984,
+ -0.15400390732076114,
+ -0.09044590084932343
+ ],
+ [
+ 0.17196597070495015,
+ 0.10344909267923887,
+ 0.17828309915067656
+ ]
+ ],
+ "mass": 0.0046475014745127035,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Smith & Hawken Woven Basket,Tray Organizer with 3 Compartments, 9.5\" x 9' x 13\"",
+ "nr_faces": 89522,
+ "nr_vertices": 66549,
+ "surface_area": 0.9620753114409804,
+ "volume": 0.0046475014745127035
+ }
+ },
+ "Snack_Catcher_Snack_Dispenser": {
+ "asset_type": "FileBasedObject",
+ "id": "Snack_Catcher_Snack_Dispenser",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06765266863480464,
+ -0.04564568791816815,
+ -0.04805503520422475
+ ],
+ [
+ 0.06732733136519536,
+ 0.04545631208183185,
+ 0.039906964795775254
+ ]
+ ],
+ "mass": 0.00039349734778179764,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Snack Catcher Snack Dispenser",
+ "nr_faces": 16406,
+ "nr_vertices": 8463,
+ "surface_area": 0.035590520881747224,
+ "volume": 0.00039349734778179764
+ }
+ },
+ "Sonicare_2_Series_Toothbrush_Plaque_Control": {
+ "asset_type": "FileBasedObject",
+ "id": "Sonicare_2_Series_Toothbrush_Plaque_Control",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08832845504599013,
+ -0.05130046773327688,
+ -0.12026191001592507
+ ],
+ [
+ 0.08895554495400987,
+ 0.05197853226672312,
+ 0.12189908998407493
+ ]
+ ],
+ "mass": 0.004085198671166729,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Sonicare 2 Series Toothbrush, Plaque Control",
+ "nr_faces": 1792,
+ "nr_vertices": 973,
+ "surface_area": 0.15883206987239884,
+ "volume": 0.004085198671166729
+ }
+ },
+ "Sonny_School_Bus": {
+ "asset_type": "FileBasedObject",
+ "id": "Sonny_School_Bus",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08017728070147166,
+ -0.13524715598427883,
+ -0.09124759554315093
+ ],
+ [
+ 0.08265571929852833,
+ 0.10470584401572118,
+ 0.13911140445684905
+ ]
+ ],
+ "mass": 0.002834001589977866,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Sonny School Bus",
+ "nr_faces": 38052,
+ "nr_vertices": 22146,
+ "surface_area": 0.2587745683819975,
+ "volume": 0.002834001589977866
+ }
+ },
+ "Sony_Acid_Music_Studio": {
+ "asset_type": "FileBasedObject",
+ "id": "Sony_Acid_Music_Studio",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0710345807007844,
+ -0.018395427152877526,
+ -0.09816032790513594
+ ],
+ [
+ 0.0706224192992156,
+ 0.017270572847122474,
+ 0.09811667209486406
+ ]
+ ],
+ "mass": 0.0008438368954790595,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Sony Acid Music Studio",
+ "nr_faces": 2330,
+ "nr_vertices": 1250,
+ "surface_area": 0.0728837199319981,
+ "volume": 0.0008438368954790595
+ }
+ },
+ "Sony_Downloadable_Loops": {
+ "asset_type": "FileBasedObject",
+ "id": "Sony_Downloadable_Loops",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07004208598648586,
+ -0.017881613960967217,
+ -0.09690538043356457
+ ],
+ [
+ 0.06949191401351414,
+ 0.017349386039032785,
+ 0.09826961956643543
+ ]
+ ],
+ "mass": 0.0008172793627753757,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Sony Downloadable Loops",
+ "nr_faces": 7502,
+ "nr_vertices": 3896,
+ "surface_area": 0.07090151887365989,
+ "volume": 0.0008172793627753757
+ }
+ },
+ "Sootheze_Cold_Therapy_Elephant": {
+ "asset_type": "FileBasedObject",
+ "id": "Sootheze_Cold_Therapy_Elephant",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13239267688852302,
+ -0.11520813501581907,
+ -0.07365874933344549
+ ],
+ [
+ 0.13553932311147698,
+ 0.10546086498418093,
+ 0.1337872506665545
+ ]
+ ],
+ "mass": 0.0022998138416819146,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Stuffed Toys",
+ "description": "Sootheze Cold Therapy, Elephant",
+ "nr_faces": 53518,
+ "nr_vertices": 29344,
+ "surface_area": 0.18649414048206708,
+ "volume": 0.0022998138416819146
+ }
+ },
+ "Sootheze_Toasty_Orca": {
+ "asset_type": "FileBasedObject",
+ "id": "Sootheze_Toasty_Orca",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09751393856479515,
+ -0.1710032361206436,
+ -0.039467565046351995
+ ],
+ [
+ 0.11675506143520485,
+ 0.2362727638793564,
+ 0.105307434953648
+ ]
+ ],
+ "mass": 0.0029794904673324596,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Stuffed Toys",
+ "description": "Sootheze Toasty Orca",
+ "nr_faces": 36482,
+ "nr_vertices": 19056,
+ "surface_area": 0.15519375112108166,
+ "volume": 0.0029794904673324596
+ }
+ },
+ "Sorry_Sliders_Board_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Sorry_Sliders_Board_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20216523543596912,
+ -0.03621827112691107,
+ -0.1368401377239589
+ ],
+ [
+ 0.2023737645640309,
+ 0.03348972887308893,
+ 0.1369878622760411
+ ]
+ ],
+ "mass": 0.006909181907594984,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Sorry Sliders Board Game",
+ "nr_faces": 1610,
+ "nr_vertices": 913,
+ "surface_area": 0.29946126618578806,
+ "volume": 0.006909181907594984
+ }
+ },
+ "Spectrum_Wall_Mount": {
+ "asset_type": "FileBasedObject",
+ "id": "Spectrum_Wall_Mount",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08096154052001464,
+ -0.049691332953577944,
+ -0.010315312301549457
+ ],
+ [
+ 0.07956945947998535,
+ 0.08978666704642206,
+ 0.04953668769845054
+ ]
+ ],
+ "mass": 5.391998142199617e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Spectrum Wall Mount",
+ "nr_faces": 6602,
+ "nr_vertices": 3658,
+ "surface_area": 0.02107565140725611,
+ "volume": 5.391998142199617e-05
+ }
+ },
+ "Sperry_TopSider_pSUFPWQXPp3": {
+ "asset_type": "FileBasedObject",
+ "id": "Sperry_TopSider_pSUFPWQXPp3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1373932722523876,
+ -0.05243722323157152,
+ -0.05686401649122178
+ ],
+ [
+ 0.10561772774761241,
+ 0.04074977676842848,
+ 0.13180098350877822
+ ]
+ ],
+ "mass": 0.001004196089698645,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Sperry Top-Sider",
+ "nr_faces": 14890,
+ "nr_vertices": 8015,
+ "surface_area": 0.12620994814536296,
+ "volume": 0.001004196089698645
+ }
+ },
+ "Sperry_TopSider_tNB9t6YBUf3": {
+ "asset_type": "FileBasedObject",
+ "id": "Sperry_TopSider_tNB9t6YBUf3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.050686046480771,
+ -0.146668843362464,
+ -0.06959094532911057
+ ],
+ [
+ 0.039142953519229,
+ 0.09713215663753601,
+ 0.11902105467088943
+ ]
+ ],
+ "mass": 0.0013261491632182553,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Sperry Top-Sider",
+ "nr_faces": 12712,
+ "nr_vertices": 6927,
+ "surface_area": 0.10167057294336765,
+ "volume": 0.0013261491632182553
+ }
+ },
+ "SpiderMan_Titan_Hero_12Inch_Action_Figure_5Hnn4mtkFsP": {
+ "asset_type": "FileBasedObject",
+ "id": "SpiderMan_Titan_Hero_12Inch_Action_Figure_5Hnn4mtkFsP",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04639915643496935,
+ -0.10762467090994869,
+ -0.16651148973977134
+ ],
+ [
+ 0.04762784356503065,
+ 0.03499932909005131,
+ 0.12164851026022866
+ ]
+ ],
+ "mass": 0.0003266797473280932,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Spider-Man Titan Hero 12-Inch Action Figure\nSpider-Man Titan Hero 12-Inch Action Figure Hasbro Spider-Man Action Figures One bite from a radioactive spider changed Peter Parker's life forever, giving him super-human powers and amazing wall-crawling ability. Wearing the mask that has made him a legend, he battles evil wherever a hero is needed as the one-and-only Spider-Man! Super-size your super hero adventures with this incredible Titan Hero Series Ultimate Spider-Man figure! This 12-inch web-slinging dynamo is ready to open up a large-sized attack on the foes of justice everywhere. With him at your side, there's no telling where your adventures will take you! Ages 4 and up.",
+ "nr_faces": 16320,
+ "nr_vertices": 8868,
+ "surface_area": 0.05548297233930738,
+ "volume": 0.0003266797473280932
+ }
+ },
+ "SpiderMan_Titan_Hero_12Inch_Action_Figure_oo1qph4wwiW": {
+ "asset_type": "FileBasedObject",
+ "id": "SpiderMan_Titan_Hero_12Inch_Action_Figure_oo1qph4wwiW",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04599055362971377,
+ -0.04273599293715012,
+ -0.1635939371255809
+ ],
+ [
+ 0.04826844637028623,
+ 0.03173200706284988,
+ 0.12453206287441909
+ ]
+ ],
+ "mass": 0.0003269742493187786,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Spider-Man Titan Hero 12-Inch Action Figure\nSpider-Man Titan Hero 12-Inch Action Figure Hasbro Spider-Man Action Figures One bite from a radioactive spider changed Peter Parker's life forever, giving him super-human powers and amazing wall-crawling ability. Wearing the mask that has made him a legend, he battles evil wherever a hero is needed as the one-and-only Spider-Man! Super-size your super hero adventures with this incredible Titan Hero Series Ultimate Spider-Man figure! This 12-inch web-slinging dynamo is ready to open up a large-sized attack on the foes of justice everywhere. With him at your side, there's no telling where your adventures will take you! Ages 4 and up.",
+ "nr_faces": 17460,
+ "nr_vertices": 9325,
+ "surface_area": 0.05514389418605207,
+ "volume": 0.0003269742493187786
+ }
+ },
+ "Spritz_Easter_Basket_Plastic_Teal": {
+ "asset_type": "FileBasedObject",
+ "id": "Spritz_Easter_Basket_Plastic_Teal",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09461787257678934,
+ -0.09444186347803481,
+ -0.04479359204911801
+ ],
+ [
+ 0.09667212742321066,
+ 0.0881921365219652,
+ 0.08413040795088199
+ ]
+ ],
+ "mass": 0.00011435291326437072,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Spritz Easter Basket, Plastic, Teal",
+ "nr_faces": 12630,
+ "nr_vertices": 7111,
+ "surface_area": 0.1827559879407976,
+ "volume": 0.00011435291326437072
+ }
+ },
+ "Squirrel": {
+ "asset_type": "FileBasedObject",
+ "id": "Squirrel",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.050899615299337404,
+ -0.06737458746320381,
+ -0.04974193698690889
+ ],
+ [
+ 0.0489483847006626,
+ 0.07371641253679619,
+ 0.0819440630130911
+ ]
+ ],
+ "mass": 0.0005770903371964403,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Squirrel\nSquirrel",
+ "nr_faces": 67434,
+ "nr_vertices": 47697,
+ "surface_area": 0.059924540356856335,
+ "volume": 0.0005770903371964403
+ }
+ },
+ "Squirt_Strain_Fruit_Basket": {
+ "asset_type": "FileBasedObject",
+ "id": "Squirt_Strain_Fruit_Basket",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05648670460681747,
+ -0.0458334324575813,
+ -0.039458603166020595
+ ],
+ [
+ 0.05746829539318253,
+ 0.0427735675424187,
+ 0.07344339683397941
+ ]
+ ],
+ "mass": 0.00036980437590739196,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Squirt & Strain Fruit Basket",
+ "nr_faces": 15612,
+ "nr_vertices": 8070,
+ "surface_area": 0.04353295140515879,
+ "volume": 0.00036980437590739196
+ }
+ },
+ "Squirtin_Barnyard_Friends_4pk": {
+ "asset_type": "FileBasedObject",
+ "id": "Squirtin_Barnyard_Friends_4pk",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09080862572715455,
+ -0.04243112365089397,
+ -0.028055952239098923
+ ],
+ [
+ 0.09548937427284546,
+ 0.03858087634910603,
+ 0.04079604776090108
+ ]
+ ],
+ "mass": 0.0002985937987290097,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Squirtin' Barnyard Friends - 4pk",
+ "nr_faces": 13838,
+ "nr_vertices": 7388,
+ "surface_area": 0.04105839798224552,
+ "volume": 0.0002985937987290097
+ }
+ },
+ "Star_Wars_Rogue_Squadron_Nintendo_64": {
+ "asset_type": "FileBasedObject",
+ "id": "Star_Wars_Rogue_Squadron_Nintendo_64",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05842899619407847,
+ -0.012103271745242486,
+ -0.03817735932168368
+ ],
+ [
+ 0.05811600380592153,
+ 0.012099728254757514,
+ 0.03942864067831632
+ ]
+ ],
+ "mass": 0.0001510036956280865,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Star Wars Rogue Squadron, Nintendo 64",
+ "nr_faces": 6710,
+ "nr_vertices": 3510,
+ "surface_area": 0.02337292473558025,
+ "volume": 0.0001510036956280865
+ }
+ },
+ "Starstruck_Tieks_Glittery_Gold_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Starstruck_Tieks_Glittery_Gold_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04317124323734782,
+ -0.12350355832164199,
+ -0.028088885507957448
+ ],
+ [
+ 0.040833756762652176,
+ 0.12021644167835802,
+ 0.05138711449204256
+ ]
+ ],
+ "mass": 0.00052214871061997,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Starstruck Tieks - Glittery Gold Italian Leather Ballet Flats\nThese glittery, one-of-a-kind ballet flats are sure to steal the show. Flashy, fun and fabulous, any outfit will become the perfect accessory to Starstruck Tieks. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 29670,
+ "nr_vertices": 15846,
+ "surface_area": 0.0733421300435457,
+ "volume": 0.00052214871061997
+ }
+ },
+ "Sterilite_Caddy_Blue_Sky_17_58_x_12_58_x_9_14": {
+ "asset_type": "FileBasedObject",
+ "id": "Sterilite_Caddy_Blue_Sky_17_58_x_12_58_x_9_14",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1617292108335235,
+ -0.22887729119019887,
+ -0.11987075646386663
+ ],
+ [
+ 0.1539787891664765,
+ 0.21771170880980112,
+ 0.11454424353613335
+ ]
+ ],
+ "mass": 0.002016996551695083,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Sterilite Caddy, Blue Sky, 17 5/8\" x 12 5/8\" x 9 1/4\"",
+ "nr_faces": 15520,
+ "nr_vertices": 9018,
+ "surface_area": 0.7769571491673033,
+ "volume": 0.002016996551695083
+ }
+ },
+ "Super_Mario_3D_World_Deluxe_Set": {
+ "asset_type": "FileBasedObject",
+ "id": "Super_Mario_3D_World_Deluxe_Set",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12785282809251408,
+ -0.07118448679279207,
+ -0.024918037458113926
+ ],
+ [
+ 0.12797217190748592,
+ 0.06226751320720793,
+ 0.028953962541886077
+ ]
+ ],
+ "mass": 0.0008250704960432338,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Super Mario 3D World Deluxe Set\n? Black Wii U Console\n? Super Mario 3D World Game \n? Nintendo Land Game\n? Wii U AC Adapter\n? Wii U GamePad AC Adapter\n? High Speed HDMI Cable\n? Sensor Bar\n? Wii U GamePad Cradle\n? Wii U GamePad Stand Support\n? Wii U Console Stand",
+ "nr_faces": 8820,
+ "nr_vertices": 4687,
+ "surface_area": 0.08406881870264789,
+ "volume": 0.0008250704960432338
+ }
+ },
+ "Super_Mario_3D_World_Deluxe_Set_yThuvW9vZed": {
+ "asset_type": "FileBasedObject",
+ "id": "Super_Mario_3D_World_Deluxe_Set_yThuvW9vZed",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.2977686653422326,
+ -0.14282006181855392,
+ -0.025626687574053526
+ ],
+ [
+ 0.16274633465776733,
+ 0.1288089381814461,
+ 0.029882312425946474
+ ]
+ ],
+ "mass": 0.0027753783894197692,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Super Mario 3D World Deluxe Set\n? Black Wii U Console\n? Super Mario 3D World Game \n? Nintendo Land Game\n? Wii U AC Adapter\n? Wii U GamePad AC Adapter\n? High Speed HDMI Cable\n? Sensor Bar\n? Wii U GamePad Cradle\n? Wii U GamePad Stand Support\n? Wii U Console Stand",
+ "nr_faces": 7322,
+ "nr_vertices": 3926,
+ "surface_area": 0.20386469492687787,
+ "volume": 0.0027753783894197692
+ }
+ },
+ "Super_Mario_3D_World_Wii_U_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Super_Mario_3D_World_Wii_U_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06580629725103739,
+ -0.09562586298297046,
+ -0.008039460287570032
+ ],
+ [
+ 0.07084070274896262,
+ 0.09531513701702954,
+ 0.008956539712429969
+ ]
+ ],
+ "mass": 0.00036475358039875846,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Super Mario 3D World [Wii U Game]",
+ "nr_faces": 2610,
+ "nr_vertices": 1401,
+ "surface_area": 0.061633637745477164,
+ "volume": 0.00036475358039875846
+ }
+ },
+ "Super_Mario_Kart_Super_Nintendo_Entertainment_System": {
+ "asset_type": "FileBasedObject",
+ "id": "Super_Mario_Kart_Super_Nintendo_Entertainment_System",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06841174591400342,
+ -0.014104716782003198,
+ -0.04628249526318045
+ ],
+ [
+ 0.06816525408599658,
+ 0.012112283217996801,
+ 0.04225250473681955
+ ]
+ ],
+ "mass": 0.00020263595401313032,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Media Cases",
+ "description": "Super Mario Kart, Super Nintendo Entertainment System",
+ "nr_faces": 10666,
+ "nr_vertices": 5585,
+ "surface_area": 0.03260642760271615,
+ "volume": 0.00020263595401313032
+ }
+ },
+ "Superman_Battle_of_Smallville": {
+ "asset_type": "FileBasedObject",
+ "id": "Superman_Battle_of_Smallville",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.2188879971378964,
+ -0.1216753071250083,
+ -0.04661072042046126
+ ],
+ [
+ 0.16544300286210362,
+ 0.1381196928749917,
+ 0.06167227957953874
+ ]
+ ],
+ "mass": 0.0006693670017358253,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Legos",
+ "description": "Superman?: Battle of Smallville\nSuper Heroes DC",
+ "nr_faces": 52036,
+ "nr_vertices": 36253,
+ "surface_area": 0.14161105690309578,
+ "volume": 0.0006693670017358253
+ }
+ },
+ "Supernatural_Ouija_Board_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Supernatural_Ouija_Board_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20633594460311067,
+ -0.028944674175106853,
+ -0.13591440857712472
+ ],
+ [
+ 0.20017205539688931,
+ 0.028291325824893146,
+ 0.13903459142287525
+ ]
+ ],
+ "mass": 0.005494860940910815,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Supernatural Ouija Board Game",
+ "nr_faces": 9076,
+ "nr_vertices": 5018,
+ "surface_area": 0.2816529227284677,
+ "volume": 0.005494860940910815
+ }
+ },
+ "Sushi_Mat": {
+ "asset_type": "FileBasedObject",
+ "id": "Sushi_Mat",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05856143395712106,
+ -0.1289847587865427,
+ -0.006805099178615137
+ ],
+ [
+ 0.06050756604287894,
+ 0.11989624121345731,
+ 0.008258900821384862
+ ]
+ ],
+ "mass": 0.00017578585513849,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Sushi Mat",
+ "nr_faces": 18076,
+ "nr_vertices": 11004,
+ "surface_area": 0.06906381731496779,
+ "volume": 0.00017578585513849
+ }
+ },
+ "Swiss_Miss_Hot_Cocoa_KCups_Milk_Chocolate_12_count": {
+ "asset_type": "FileBasedObject",
+ "id": "Swiss_Miss_Hot_Cocoa_KCups_Milk_Chocolate_12_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07557341531647405,
+ -0.05032816943903512,
+ -0.048906294035560134
+ ],
+ [
+ 0.07526858468352596,
+ 0.05026683056096488,
+ 0.050073705964439864
+ ]
+ ],
+ "mass": 0.0014163904949439166,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Swiss Miss Hot Cocoa K-Cups, Milk Chocolate - 12 count",
+ "nr_faces": 4312,
+ "nr_vertices": 2291,
+ "surface_area": 0.07327011575110627,
+ "volume": 0.0014163904949439166
+ }
+ },
+ "TABLEWARE_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "TABLEWARE_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17215020586618826,
+ -0.14574839720296187,
+ -0.013976185626813542
+ ],
+ [
+ 0.17834279413381174,
+ 0.14703360279703814,
+ 0.026687814373186458
+ ]
+ ],
+ "mass": 0.00044325625962621544,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TABLEWARE SET\nThe set includes 2 plates, 2 bowls, 2 knives, 2 spoons, and 2 forks.",
+ "nr_faces": 7710,
+ "nr_vertices": 4291,
+ "surface_area": 0.14001764125617883,
+ "volume": 0.00044325625962621544
+ }
+ },
+ "TABLEWARE_SET_5CHkPjjxVpp": {
+ "asset_type": "FileBasedObject",
+ "id": "TABLEWARE_SET_5CHkPjjxVpp",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20827150927656476,
+ -0.12746418998611378,
+ -0.016391958317563828
+ ],
+ [
+ 0.20394149072343523,
+ 0.1502228100138862,
+ 0.046866041682436174
+ ]
+ ],
+ "mass": 0.0005181310589102328,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TABLEWARE SET\nSet the table with this colorful kid-sized tableware. Includes two place settings - 2 plates, 2 bowls, 2 cups, 2 forks, 2 knives, and 2 spoons.",
+ "nr_faces": 8338,
+ "nr_vertices": 4742,
+ "surface_area": 0.16886195109020594,
+ "volume": 0.0005181310589102328
+ }
+ },
+ "TABLEWARE_SET_5ww1UFLuCJG": {
+ "asset_type": "FileBasedObject",
+ "id": "TABLEWARE_SET_5ww1UFLuCJG",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14740994650909134,
+ -0.09683055074690894,
+ -0.013805705811433274
+ ],
+ [
+ 0.14980005349090866,
+ 0.09963244925309106,
+ 0.04575629418856673
+ ]
+ ],
+ "mass": 0.0004725907394401268,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TABLEWARE SET\nThe set includes 2 plates, 2 bowls, 2 knives, 2 spoons, and 2 forks.",
+ "nr_faces": 26154,
+ "nr_vertices": 22495,
+ "surface_area": 0.15074395204552338,
+ "volume": 0.0004725907394401268
+ }
+ },
+ "TEA_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "TEA_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10559693147643384,
+ -0.08707645047447277,
+ -0.030987121477032156
+ ],
+ [
+ 0.15529006852356614,
+ 0.06805654952552724,
+ 0.06556487852296786
+ ]
+ ],
+ "mass": 0.0005655114598443587,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TEA SET\nHave tea-time with friends. Includes two place settings - teapot, sugar bowl, milk pitcher, 2 tea cups, 2 saucers, 2 tea spoons, ?2 tea bags, and 2 cubes of sugar.",
+ "nr_faces": 14476,
+ "nr_vertices": 8305,
+ "surface_area": 0.08894378810543441,
+ "volume": 0.0005655114598443587
+ }
+ },
+ "TERREX_FAST_R": {
+ "asset_type": "FileBasedObject",
+ "id": "TERREX_FAST_R",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.062278363976372056,
+ -0.16679013498934842,
+ -0.041251887097080595
+ ],
+ [
+ 0.05047763602362794,
+ 0.1363138650106516,
+ 0.09015411290291941
+ ]
+ ],
+ "mass": 0.0010854330645202568,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "TERREX FAST R\nFW-SHOES",
+ "nr_faces": 39346,
+ "nr_vertices": 22792,
+ "surface_area": 0.17554706019809552,
+ "volume": 0.0010854330645202568
+ }
+ },
+ "TERREX_FAST_X_GTX": {
+ "asset_type": "FileBasedObject",
+ "id": "TERREX_FAST_X_GTX",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06314205782885429,
+ -0.1662952728991388,
+ -0.047193319849438024
+ ],
+ [
+ 0.053252942171145706,
+ 0.14106472710086118,
+ 0.10752968015056197
+ ]
+ ],
+ "mass": 0.0013383985304330826,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "TERREX FAST X GTX\nFW-SHOES",
+ "nr_faces": 36824,
+ "nr_vertices": 20501,
+ "surface_area": 0.17947395579307573,
+ "volume": 0.0013383985304330826
+ }
+ },
+ "TOOL_BELT": {
+ "asset_type": "FileBasedObject",
+ "id": "TOOL_BELT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15789090695856695,
+ -0.08256239849743517,
+ -0.055706494961239
+ ],
+ [
+ 0.10342209304143303,
+ 0.08060060150256483,
+ 0.104878505038761
+ ]
+ ],
+ "mass": 0.0020295607896225892,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TOOL BELT\nBuild a bridge or fix a door. This handy, children?s tool belt fits up to a 25? waist. Includes a hammer, wrench, screwdriver, level tool, and a measuring tape. The fabric tool belt is hand and machine washable.",
+ "nr_faces": 24358,
+ "nr_vertices": 13999,
+ "surface_area": 0.14009421860891194,
+ "volume": 0.0020295607896225892
+ }
+ },
+ "TOP_TEN_HI": {
+ "asset_type": "FileBasedObject",
+ "id": "TOP_TEN_HI",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05388386865596192,
+ -0.1758845969899066,
+ -0.05228090851807144
+ ],
+ [
+ 0.05340313134403808,
+ 0.1253074030100934,
+ 0.11711009148192858
+ ]
+ ],
+ "mass": 0.0013329927720448246,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "TOP TEN HI\nFW-HIGH TOP",
+ "nr_faces": 36802,
+ "nr_vertices": 20258,
+ "surface_area": 0.19846553814659665,
+ "volume": 0.0013329927720448246
+ }
+ },
+ "TOP_TEN_HI_60KlbRbdoJA": {
+ "asset_type": "FileBasedObject",
+ "id": "TOP_TEN_HI_60KlbRbdoJA",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.052810497207532815,
+ -0.17655590728299742,
+ -0.05009949696142545
+ ],
+ [
+ 0.05195250279246719,
+ 0.12235909271700257,
+ 0.11206350303857454
+ ]
+ ],
+ "mass": 0.0013630290273383555,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "TOP TEN HI\nFW-HIGH TOP",
+ "nr_faces": 36504,
+ "nr_vertices": 20243,
+ "surface_area": 0.1869353981668357,
+ "volume": 0.0013630290273383555
+ }
+ },
+ "TOWER_TUMBLING": {
+ "asset_type": "FileBasedObject",
+ "id": "TOWER_TUMBLING",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10442861012040489,
+ -0.041443432970216736,
+ -0.0801660035208756
+ ],
+ [
+ 0.08451238987959511,
+ 0.04087756702978326,
+ 0.1465319964791244
+ ]
+ ],
+ "mass": 0.000536081792873064,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TOWER TUMBLING\nStack the rods and discs according to color or make various patterns to create a tower without falling.",
+ "nr_faces": 12690,
+ "nr_vertices": 7314,
+ "surface_area": 0.10399589126892983,
+ "volume": 0.000536081792873064
+ }
+ },
+ "TROCHILUS_BOOST": {
+ "asset_type": "FileBasedObject",
+ "id": "TROCHILUS_BOOST",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05606028182831151,
+ -0.14779748710254653,
+ -0.0321091260722344
+ ],
+ [
+ 0.048267718171688484,
+ 0.12352351289745346,
+ 0.08810587392776559
+ ]
+ ],
+ "mass": 0.0007958809311356844,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "TROCHILUS BOOST",
+ "nr_faces": 36728,
+ "nr_vertices": 20092,
+ "surface_area": 0.12547451130122605,
+ "volume": 0.0007958809311356844
+ }
+ },
+ "TURBOPROP_AIRPLANE_WITH_PILOT": {
+ "asset_type": "FileBasedObject",
+ "id": "TURBOPROP_AIRPLANE_WITH_PILOT",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.039512547334499916,
+ -0.04003521738404411,
+ -0.028083360168898015
+ ],
+ [
+ 0.05159845266550008,
+ 0.0506807826159559,
+ 0.03621063983110198
+ ]
+ ],
+ "mass": 6.725133816848316e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TURBOPROP AIRPLANE WITH PILOT",
+ "nr_faces": 14232,
+ "nr_vertices": 8264,
+ "surface_area": 0.01947205787035801,
+ "volume": 6.725133816848316e-05
+ }
+ },
+ "TWISTED_PUZZLE": {
+ "asset_type": "FileBasedObject",
+ "id": "TWISTED_PUZZLE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0883619355108206,
+ -0.09284306647940213,
+ -0.016156825777147964
+ ],
+ [
+ 0.0861620644891794,
+ 0.09581093352059786,
+ 0.018971174222852036
+ ]
+ ],
+ "mass": 0.0004892337988910839,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TWISTED PUZZLE\nTwisted and turn the blocks to complete the patterns on the guide. Go wild and create your own designs.",
+ "nr_faces": 4314,
+ "nr_vertices": 2407,
+ "surface_area": 0.08042900287632786,
+ "volume": 0.0004892337988910839
+ }
+ },
+ "TWISTED_PUZZLE_twb4AyFtu8Q": {
+ "asset_type": "FileBasedObject",
+ "id": "TWISTED_PUZZLE_twb4AyFtu8Q",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15797838212145116,
+ -0.09597920840494203,
+ -0.014180748762219942
+ ],
+ [
+ 0.14447561787854885,
+ 0.10806379159505797,
+ 0.021188251237780058
+ ]
+ ],
+ "mass": 0.0004940785083905315,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TWISTED PUZZLE\nTwisted and turn the blocks to complete the patterns on the guide. Go wild and create your own designs.",
+ "nr_faces": 3470,
+ "nr_vertices": 2054,
+ "surface_area": 0.10268670500771193,
+ "volume": 0.0004940785083905315
+ }
+ },
+ "TWIST_SHAPE": {
+ "asset_type": "FileBasedObject",
+ "id": "TWIST_SHAPE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09716399103629493,
+ -0.09400282930990167,
+ -0.014226782615091638
+ ],
+ [
+ 0.15901600896370507,
+ 0.09535617069009833,
+ 0.023478217384908358
+ ]
+ ],
+ "mass": 0.0003933961837298372,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "TWIST & SHAPE\nFeature as two-sided curved base which easy to flip over! Set included 4 different blocks which can be twisted to new shapes and match the shapes on the base.",
+ "nr_faces": 6106,
+ "nr_vertices": 3612,
+ "surface_area": 0.09062173971647307,
+ "volume": 0.0003933961837298372
+ }
+ },
+ "TZX_Runner": {
+ "asset_type": "FileBasedObject",
+ "id": "TZX_Runner",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0564461179434159,
+ -0.14560492753404955,
+ -0.04491784974726308
+ ],
+ [
+ 0.0508128820565841,
+ 0.14694607246595046,
+ 0.10065915025273692
+ ]
+ ],
+ "mass": 0.001321527123069751,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "T-ZX Runner",
+ "nr_faces": 40238,
+ "nr_vertices": 21859,
+ "surface_area": 0.14331678091295452,
+ "volume": 0.001321527123069751
+ }
+ },
+ "Tag_Dishtowel_18_x_26": {
+ "asset_type": "FileBasedObject",
+ "id": "Tag_Dishtowel_18_x_26",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08697775380390785,
+ -0.12826611931086843,
+ -0.009102999880918556
+ ],
+ [
+ 0.09142924619609215,
+ 0.10562588068913156,
+ 0.018257000119081445
+ ]
+ ],
+ "mass": 0.0005071298065416885,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Tag Dishtowel, 18\" x 26\"",
+ "nr_faces": 13616,
+ "nr_vertices": 7127,
+ "surface_area": 0.09575770478969356,
+ "volume": 0.0005071298065416885
+ }
+ },
+ "Tag_Dishtowel_Basket_Weave_Red_18_x_26": {
+ "asset_type": "FileBasedObject",
+ "id": "Tag_Dishtowel_Basket_Weave_Red_18_x_26",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08499179623627176,
+ -0.11431828840447184,
+ -0.010015729695862962
+ ],
+ [
+ 0.08552020376372824,
+ 0.11869571159552816,
+ 0.024838270304137038
+ ]
+ ],
+ "mass": 0.0005485599049532868,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Tag Dishtowel, Basket Weave Red, 18\" x 26\"",
+ "nr_faces": 20288,
+ "nr_vertices": 10517,
+ "surface_area": 0.093981570721411,
+ "volume": 0.0005485599049532868
+ }
+ },
+ "Tag_Dishtowel_Dobby_Stripe_Blue_18_x_26": {
+ "asset_type": "FileBasedObject",
+ "id": "Tag_Dishtowel_Dobby_Stripe_Blue_18_x_26",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0833012631869823,
+ -0.1129138899210864,
+ -0.008392605090057598
+ ],
+ [
+ 0.0884097368130177,
+ 0.1242531100789136,
+ 0.019890394909942405
+ ]
+ ],
+ "mass": 0.00046552424123271516,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Tag Dishtowel, Dobby Stripe Blue, 18' x 26\"",
+ "nr_faces": 19262,
+ "nr_vertices": 9911,
+ "surface_area": 0.09240100521924269,
+ "volume": 0.00046552424123271516
+ }
+ },
+ "Tag_Dishtowel_Green": {
+ "asset_type": "FileBasedObject",
+ "id": "Tag_Dishtowel_Green",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0876749568131801,
+ -0.1107391745032839,
+ -0.011100976746439823
+ ],
+ [
+ 0.0840750431868199,
+ 0.11948082549671611,
+ 0.024232023253560178
+ ]
+ ],
+ "mass": 0.000624755255083009,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Tag Dishtowel, Green",
+ "nr_faces": 20896,
+ "nr_vertices": 10805,
+ "surface_area": 0.09526541794452262,
+ "volume": 0.000624755255083009
+ }
+ },
+ "Tag_Dishtowel_Waffle_Gray_Checks_18_x_26": {
+ "asset_type": "FileBasedObject",
+ "id": "Tag_Dishtowel_Waffle_Gray_Checks_18_x_26",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0871614949141731,
+ -0.09389833154069684,
+ -0.01151976551737482
+ ],
+ [
+ 0.0986595050858269,
+ 0.08501466845930317,
+ 0.020572234482625185
+ ]
+ ],
+ "mass": 0.000556933893914675,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Tag Dishtowel, Waffle Gray Checks, 18\" x 26\"",
+ "nr_faces": 20908,
+ "nr_vertices": 10936,
+ "surface_area": 0.07979475107043738,
+ "volume": 0.000556933893914675
+ }
+ },
+ "Target_Basket_Medium": {
+ "asset_type": "FileBasedObject",
+ "id": "Target_Basket_Medium",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13948049731065182,
+ -0.13451338080641254,
+ -0.08987781715415505
+ ],
+ [
+ 0.13097450268934818,
+ 0.13351261919358745,
+ 0.12762918284584496
+ ]
+ ],
+ "mass": 0.004666664811422198,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Target Basket, Medium",
+ "nr_faces": 85812,
+ "nr_vertices": 50032,
+ "surface_area": 0.5363801403708951,
+ "volume": 0.004666664811422198
+ }
+ },
+ "Teenage_Mutant_Ninja_Turtles_Rahzar_Action_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Teenage_Mutant_Ninja_Turtles_Rahzar_Action_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04636141856854766,
+ -0.04183807096538637,
+ -0.07566542988432294
+ ],
+ [
+ 0.02434058143145234,
+ 0.04051192903461363,
+ 0.06289157011567705
+ ]
+ ],
+ "mass": 5.696530295231783e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Action Figures",
+ "description": "Teenage Mutant Ninja Turtles Rahzar Action Figure",
+ "nr_faces": 28442,
+ "nr_vertices": 16708,
+ "surface_area": 0.02331075687284638,
+ "volume": 5.696530295231783e-05
+ }
+ },
+ "Tena_Pads_Heavy_Long_42_pads": {
+ "asset_type": "FileBasedObject",
+ "id": "Tena_Pads_Heavy_Long_42_pads",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1893847294941505,
+ -0.06608026527014442,
+ -0.14284178919140328
+ ],
+ [
+ 0.18874627050584952,
+ 0.06287273472985558,
+ 0.14928521080859672
+ ]
+ ],
+ "mass": 0.012241362831933639,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Tena Pads, Heavy, Long - 42 pads\ndescription 1,045",
+ "nr_faces": 7920,
+ "nr_vertices": 4255,
+ "surface_area": 0.33517550139615054,
+ "volume": 0.012241362831933639
+ }
+ },
+ "Tetris_Link_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Tetris_Link_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16187011695543446,
+ -0.04622083513978695,
+ -0.13365190335282112
+ ],
+ [
+ 0.16121388304456552,
+ 0.04539016486021305,
+ 0.13341609664717885
+ ]
+ ],
+ "mass": 0.00700370506381038,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Tetris Link Game",
+ "nr_faces": 3192,
+ "nr_vertices": 1744,
+ "surface_area": 0.25950525104752276,
+ "volume": 0.00700370506381038
+ }
+ },
+ "The_Coffee_Bean_Tea_Leaf_KCup_Packs_Jasmine_Green_Tea_16_count": {
+ "asset_type": "FileBasedObject",
+ "id": "The_Coffee_Bean_Tea_Leaf_KCup_Packs_Jasmine_Green_Tea_16_count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07542496312185838,
+ -0.05017638581824715,
+ -0.07396822390186286
+ ],
+ [
+ 0.07493403687814161,
+ 0.05028761418175285,
+ 0.07395277609813714
+ ]
+ ],
+ "mass": 0.0020943051543550837,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "The Coffee Bean & Tea Leaf K-Cup Packs, Jasmine Green Tea - 16 count",
+ "nr_faces": 5942,
+ "nr_vertices": 3102,
+ "surface_area": 0.09613665941192677,
+ "volume": 0.0020943051543550837
+ }
+ },
+ "The_Scooper_Hooper": {
+ "asset_type": "FileBasedObject",
+ "id": "The_Scooper_Hooper",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0752392586002746,
+ -0.13582157302174142,
+ -0.02250826317396055
+ ],
+ [
+ 0.0746227413997254,
+ 0.12445042697825859,
+ 0.038937736826039446
+ ]
+ ],
+ "mass": 0.0004491161670918945,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "The Scooper Hooper",
+ "nr_faces": 17934,
+ "nr_vertices": 10631,
+ "surface_area": 0.10409859334264052,
+ "volume": 0.0004491161670918945
+ }
+ },
+ "Theanine": {
+ "asset_type": "FileBasedObject",
+ "id": "Theanine",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.026953971318775465,
+ -0.02699882148763023,
+ -0.044497513367274824
+ ],
+ [
+ 0.027014028681224534,
+ 0.02671717851236977,
+ 0.05292748663272518
+ ]
+ ],
+ "mass": 0.00019127094464127466,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Theanine",
+ "nr_faces": 9372,
+ "nr_vertices": 4813,
+ "surface_area": 0.019082356062579398,
+ "volume": 0.00019127094464127466
+ }
+ },
+ "Thomas_Friends_Woodan_Railway_Henry": {
+ "asset_type": "FileBasedObject",
+ "id": "Thomas_Friends_Woodan_Railway_Henry",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08798561706142972,
+ -0.01828403570904647,
+ -0.025946358572758843
+ ],
+ [
+ 0.09099438293857028,
+ 0.01906096429095353,
+ 0.02452664142724116
+ ]
+ ],
+ "mass": 0.0001298158083127442,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Thomas & Friends Woodan Railway, Henry",
+ "nr_faces": 26776,
+ "nr_vertices": 15398,
+ "surface_area": 0.033377142092406144,
+ "volume": 0.0001298158083127442
+ }
+ },
+ "Thomas_Friends_Wooden_Railway_Ascending_Track_Riser_Pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Thomas_Friends_Wooden_Railway_Ascending_Track_Riser_Pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20864717795449458,
+ -0.028648219690907147,
+ -0.06653113508894183
+ ],
+ [
+ 0.21666982204550542,
+ 0.029236780309092856,
+ 0.07643386491105816
+ ]
+ ],
+ "mass": 0.0006314480908400804,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Thomas & Friends Wooden Railway, Ascending Track & Riser Pack",
+ "nr_faces": 6272,
+ "nr_vertices": 3612,
+ "surface_area": 0.09754146800232852,
+ "volume": 0.0006314480908400804
+ }
+ },
+ "Thomas_Friends_Wooden_Railway_Deluxe_Track_Accessory_Pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Thomas_Friends_Wooden_Railway_Deluxe_Track_Accessory_Pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.20185693415625452,
+ -0.10240649067995326,
+ -0.011202037704371923
+ ],
+ [
+ 0.1551180658437455,
+ 0.10233850932004673,
+ 0.04686796229562808
+ ]
+ ],
+ "mass": 0.00030002831001085567,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Thomas & Friends Wooden Railway, Deluxe Track Accessory Pack",
+ "nr_faces": 7074,
+ "nr_vertices": 4034,
+ "surface_area": 0.07205398095229212,
+ "volume": 0.00030002831001085567
+ }
+ },
+ "Thomas_Friends_Wooden_Railway_Porter_5JzRhMm3a9o": {
+ "asset_type": "FileBasedObject",
+ "id": "Thomas_Friends_Wooden_Railway_Porter_5JzRhMm3a9o",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.019057981686477952,
+ -0.04503106502662744,
+ -0.025485303606520775
+ ],
+ [
+ 0.01839301831352205,
+ 0.04285593497337256,
+ 0.024599696393479226
+ ]
+ ],
+ "mass": 7.515996984274166e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Thomas & Friends Wooden Railway, Porter",
+ "nr_faces": 23052,
+ "nr_vertices": 12257,
+ "surface_area": 0.014713539333239515,
+ "volume": 7.515996984274166e-05
+ }
+ },
+ "Thomas_Friends_Wooden_Railway_Talking_Thomas_z7yi7UFHJRj": {
+ "asset_type": "FileBasedObject",
+ "id": "Thomas_Friends_Wooden_Railway_Talking_Thomas_z7yi7UFHJRj",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.019123951616336208,
+ -0.046653674255685375,
+ -0.02665003671292644
+ ],
+ [
+ 0.019079048383663793,
+ 0.041477325744314626,
+ 0.02369996328707356
+ ]
+ ],
+ "mass": 7.365712892229149e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Thomas & Friends Wooden Railway, Talking Thomas",
+ "nr_faces": 32342,
+ "nr_vertices": 17760,
+ "surface_area": 0.017952735850278866,
+ "volume": 7.365712892229149e-05
+ }
+ },
+ "Threshold_Bamboo_Ceramic_Soap_Dish": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Bamboo_Ceramic_Soap_Dish",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06207973201468654,
+ -0.04889441065269224,
+ -0.02347008938149055
+ ],
+ [
+ 0.06257826798531345,
+ 0.049179589347307755,
+ 0.02716091061850945
+ ]
+ ],
+ "mass": 0.00027855373526054663,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Bamboo Ceramic Soap Dish",
+ "nr_faces": 11820,
+ "nr_vertices": 6239,
+ "surface_area": 0.04711407821746888,
+ "volume": 0.00027855373526054663
+ }
+ },
+ "Threshold_Basket_Natural_Finish_Fabric_Liner_Small": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Basket_Natural_Finish_Fabric_Liner_Small",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11940697697914165,
+ -0.07862177911476377,
+ -0.06280126048451685
+ ],
+ [
+ 0.11987802302085834,
+ 0.08357222088523622,
+ 0.08481173951548314
+ ]
+ ],
+ "mass": 0.0021158642208612788,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Basket, Natural Finish, Fabric Liner, Small",
+ "nr_faces": 66390,
+ "nr_vertices": 40151,
+ "surface_area": 0.270315732484558,
+ "volume": 0.0021158642208612788
+ }
+ },
+ "Threshold_Bead_Cereal_Bowl_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Bead_Cereal_Bowl_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0846163683585339,
+ -0.08328709141178871,
+ -0.03241744454341888
+ ],
+ [
+ 0.0851446316414661,
+ 0.08303790858821129,
+ 0.03830655545658112
+ ]
+ ],
+ "mass": 0.0002229079674028005,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Threshold Bead Cereal Bowl, White",
+ "nr_faces": 14030,
+ "nr_vertices": 7217,
+ "surface_area": 0.08248017697450288,
+ "volume": 0.0002229079674028005
+ }
+ },
+ "Threshold_Bistro_Ceramic_Dinner_Plate_Ruby_Ring": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Bistro_Ceramic_Dinner_Plate_Ruby_Ring",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14846900823433984,
+ -0.13322936772509392,
+ -0.01253733201749336
+ ],
+ [
+ 0.12602299176566018,
+ 0.1407446322749061,
+ 0.020760667982506642
+ ]
+ ],
+ "mass": 0.00030861903758933946,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Bistro Ceramic Dinner Plate, Ruby Ring",
+ "nr_faces": 3464,
+ "nr_vertices": 1890,
+ "surface_area": 0.12809415226753457,
+ "volume": 0.00030861903758933946
+ }
+ },
+ "Threshold_Dinner_Plate_Square_Rim_White_Porcelain": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Dinner_Plate_Square_Rim_White_Porcelain",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.14025780334194038,
+ -0.1294353886460615,
+ -0.012254054286564417
+ ],
+ [
+ 0.1307061966580596,
+ 0.14410461135393848,
+ 0.026653945713435583
+ ]
+ ],
+ "mass": 0.0005373601324510556,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Dinner Plate, Square Rim, White, Porcelain",
+ "nr_faces": 4088,
+ "nr_vertices": 2122,
+ "surface_area": 0.1697507915350114,
+ "volume": 0.0005373601324510556
+ }
+ },
+ "Threshold_Hand_Towel_Blue_Medallion_16_x_27": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Hand_Towel_Blue_Medallion_16_x_27",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0910590764113355,
+ -0.11020125811795896,
+ -0.022674849737519723
+ ],
+ [
+ 0.0908229235886645,
+ 0.10228774188204105,
+ 0.02849015026248028
+ ]
+ ],
+ "mass": 0.001384747356711132,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Hand Towel, Blue Medallion, 16\" x 27\"",
+ "nr_faces": 23016,
+ "nr_vertices": 12056,
+ "surface_area": 0.11086291500126555,
+ "volume": 0.001384747356711132
+ }
+ },
+ "Threshold_Performance_Bath_Sheet_Sandoval_Blue_33_x_63": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Performance_Bath_Sheet_Sandoval_Blue_33_x_63",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11770235196942964,
+ -0.21418390559614714,
+ -0.0477470663993575
+ ],
+ [
+ 0.11996764803057035,
+ 0.21152109440385286,
+ 0.0555679336006425
+ ]
+ ],
+ "mass": 0.0077780236074550336,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Performance Bath Sheet, Sandoval Blue, 33\" x 63\"",
+ "nr_faces": 66084,
+ "nr_vertices": 34117,
+ "surface_area": 0.3087228927140936,
+ "volume": 0.0077780236074550336
+ }
+ },
+ "Threshold_Porcelain_Coffee_Mug_All_Over_Bead_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Porcelain_Coffee_Mug_All_Over_Bead_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07832206835209822,
+ -0.048249450920942905,
+ -0.05634206479131002
+ ],
+ [
+ 0.05241793164790179,
+ 0.04827254907905709,
+ 0.058281935208689975
+ ]
+ ],
+ "mass": 0.00017982272175384666,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Porcelain Coffee Mug, All Over Bead, White",
+ "nr_faces": 16644,
+ "nr_vertices": 8559,
+ "surface_area": 0.06908671018185755,
+ "volume": 0.00017982272175384666
+ }
+ },
+ "Threshold_Porcelain_Pitcher_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Porcelain_Pitcher_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0888007035467065,
+ -0.08442920487554564,
+ -0.12980393378714164
+ ],
+ [
+ 0.1500812964532935,
+ 0.08436979512445436,
+ 0.14864206621285836
+ ]
+ ],
+ "mass": 0.002110606354240598,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Porcelain Pitcher, White",
+ "nr_faces": 9344,
+ "nr_vertices": 4973,
+ "surface_area": 0.24938549616567818,
+ "volume": 0.002110606354240598
+ }
+ },
+ "Threshold_Porcelain_Serving_Bowl_Coupe_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Porcelain_Serving_Bowl_Coupe_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10402170932157073,
+ -0.1040885537799009,
+ -0.029553262272527945
+ ],
+ [
+ 0.10421229067842927,
+ 0.1052524462200991,
+ 0.03932973772747206
+ ]
+ ],
+ "mass": 0.00032534837395442113,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Porcelain Serving Bowl, Coupe, White",
+ "nr_faces": 5946,
+ "nr_vertices": 3063,
+ "surface_area": 0.10941430909257428,
+ "volume": 0.00032534837395442113
+ }
+ },
+ "Threshold_Porcelain_Spoon_Rest_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Porcelain_Spoon_Rest_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10538873683599159,
+ -0.057623164692806414,
+ -0.028399984203056235
+ ],
+ [
+ 0.1312882631640084,
+ 0.059965835307193585,
+ 0.04333701579694377
+ ]
+ ],
+ "mass": 0.000189618604796832,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Threshold Porcelain Spoon Rest, White",
+ "nr_faces": 8810,
+ "nr_vertices": 4510,
+ "surface_area": 0.04940844869261764,
+ "volume": 0.000189618604796832
+ }
+ },
+ "Threshold_Porcelain_Teapot_White": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Porcelain_Teapot_White",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09042234309521524,
+ -0.09539730636483318,
+ -0.05281003614275439
+ ],
+ [
+ 0.09626365690478476,
+ 0.08886169363516683,
+ 0.08353496385724561
+ ]
+ ],
+ "mass": 0.0021056495101361844,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Porcelain Teapot, White",
+ "nr_faces": 8324,
+ "nr_vertices": 4380,
+ "surface_area": 0.09770792459949473,
+ "volume": 0.0021056495101361844
+ }
+ },
+ "Threshold_Ramekin_White_Porcelain": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Ramekin_White_Porcelain",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0565149042070108,
+ -0.056709616209192,
+ -0.028886820168750386
+ ],
+ [
+ 0.0554700957929892,
+ 0.055012383790808,
+ 0.023879179831249618
+ ]
+ ],
+ "mass": 0.000398823758364738,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Ramekin, White, Porcelain",
+ "nr_faces": 6894,
+ "nr_vertices": 3558,
+ "surface_area": 0.03344600319236672,
+ "volume": 0.000398823758364738
+ }
+ },
+ "Threshold_Salad_Plate_Square_Rim_Porcelain": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Salad_Plate_Square_Rim_Porcelain",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10661741285240912,
+ -0.10635973929793169,
+ -0.01178566114699067
+ ],
+ [
+ 0.10533358714759088,
+ 0.10604826070206831,
+ 0.02254433885300933
+ ]
+ ],
+ "mass": 0.0002925713310837448,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Salad Plate, Square Rim, Porcelain",
+ "nr_faces": 3794,
+ "nr_vertices": 1965,
+ "surface_area": 0.10454629339390932,
+ "volume": 0.0002925713310837448
+ }
+ },
+ "Threshold_Textured_Damask_Bath_Towel_Pink": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Textured_Damask_Bath_Towel_Pink",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.17513505528460543,
+ -0.1750819819099773,
+ -0.025182771476729728
+ ],
+ [
+ 0.18130794471539458,
+ 0.16535501809002268,
+ 0.03227122852327027
+ ]
+ ],
+ "mass": 0.004822417601901217,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Textured Damask Bath Towel - Pink",
+ "nr_faces": 43716,
+ "nr_vertices": 22442,
+ "surface_area": 0.3017088946768957,
+ "volume": 0.004822417601901217
+ }
+ },
+ "Threshold_Tray_Rectangle_Porcelain": {
+ "asset_type": "FileBasedObject",
+ "id": "Threshold_Tray_Rectangle_Porcelain",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08440648009724686,
+ -0.1572955544701931,
+ -0.013096097044439266
+ ],
+ [
+ 0.08444151990275314,
+ 0.1571724455298069,
+ 0.021776902955560735
+ ]
+ ],
+ "mass": 0.00044601965440041,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Threshold Tray, Rectangle, Porcelain",
+ "nr_faces": 2740,
+ "nr_vertices": 1418,
+ "surface_area": 0.12257617125197177,
+ "volume": 0.00044601965440041
+ }
+ },
+ "Tiek_Blue_Patent_Tieks_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Tiek_Blue_Patent_Tieks_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04443384302016062,
+ -0.1213026824213934,
+ -0.02918834932955316
+ ],
+ [
+ 0.04101815697983938,
+ 0.1206493175786066,
+ 0.055981650670446845
+ ]
+ ],
+ "mass": 0.0005182350396154449,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Tiek Blue Patent Tieks - Italian Leather Ballet Flats\nStatement making is made simple with our Tiek Blue Patent Tieks. Our signature color is unique, bold and bright. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 21096,
+ "nr_vertices": 11482,
+ "surface_area": 0.0744656841699984,
+ "volume": 0.0005182350396154449
+ }
+ },
+ "Tieks_Ballet_Flats_Diamond_White_Croc": {
+ "asset_type": "FileBasedObject",
+ "id": "Tieks_Ballet_Flats_Diamond_White_Croc",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04429742836163627,
+ -0.12359719507388205,
+ -0.02737338698178096
+ ],
+ [
+ 0.03961357163836373,
+ 0.12051680492611795,
+ 0.05152461301821904
+ ]
+ ],
+ "mass": 0.0004458667966727915,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Tieks Ballet Flats, Diamond White Croc\nAdd classic elegance to your wardrobe with these chic, patent crocodile print ballet flats. A favorite among brides. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 22612,
+ "nr_vertices": 12354,
+ "surface_area": 0.08188645540716542,
+ "volume": 0.0004458667966727915
+ }
+ },
+ "Tieks_Ballet_Flats_Electric_Snake": {
+ "asset_type": "FileBasedObject",
+ "id": "Tieks_Ballet_Flats_Electric_Snake",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04341002246982917,
+ -0.11447260115958642,
+ -0.0304049319332086
+ ],
+ [
+ 0.04039897753017083,
+ 0.1279833988404136,
+ 0.0558700680667914
+ ]
+ ],
+ "mass": 0.0004939023709781883,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Tieks Ballet Flats, Electric Snake\nChannel your inner wild side in enchanting Electric Snake Tieks. With a blend of metallic gold, pink, aqua and black, these lust-worthy ballet flats will capture the spotlight. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 20538,
+ "nr_vertices": 11038,
+ "surface_area": 0.07599243060417796,
+ "volume": 0.0004939023709781883
+ }
+ },
+ "Timberland_Mens_Classic_2Eye_Boat_Shoe": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Classic_2Eye_Boat_Shoe",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.054951691279568615,
+ -0.13280090136944075,
+ -0.03032391100105475
+ ],
+ [
+ 0.056858308720431384,
+ 0.15104009863055923,
+ 0.05922708899894524
+ ]
+ ],
+ "mass": 0.0007793737557350036,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Classic 2-Eye Boat Shoe\nRugged, durable and hard-wearing the OK. We've been building boat shoes for decades, and this season we're building upon that experience to bring you the Men's Classic 2-Eye Boat Shoe. the OK. We've been building boat shoes for decades, and this season we're building upon that experience to bring you the Men's Classic 2-Eye Boat Shoe.",
+ "nr_faces": 24314,
+ "nr_vertices": 13079,
+ "surface_area": 0.11150461183646132,
+ "volume": 0.0007793737557350036
+ }
+ },
+ "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_Oxford": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_Oxford",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05665216456387846,
+ -0.13480725355335016,
+ -0.029544922273834193
+ ],
+ [
+ 0.05336483543612154,
+ 0.15780174644664982,
+ 0.05495107772616581
+ ]
+ ],
+ "mass": 0.0008462893969912847,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Earthkeepers Casco Bay Canvas Oxford\nCheck out our Men's Earthkeepers Casco Bay Canvas Oxford. Nothing says summer like a lightweight canvas shoe. Ours features uppers made of ReCanvas™ material, which looks and feels just like cotton canvas but is made entirely from recycled plastic bottles - perfect for warm-weather style and kinder to the environment at the same time.",
+ "nr_faces": 27704,
+ "nr_vertices": 14601,
+ "surface_area": 0.10734400042296163,
+ "volume": 0.0008462893969912847
+ }
+ },
+ "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_SlipOn": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_SlipOn",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05451044610139028,
+ -0.13189849817698746,
+ -0.02694165296031444
+ ],
+ [
+ 0.05277855389860972,
+ 0.15775550182301257,
+ 0.06169034703968556
+ ]
+ ],
+ "mass": 0.0006215686971347324,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Earthkeepers Casco Bay Canvas Slip-On\nExploring new gear for this season? Check out our Men's Earthkeepers Casco Bay Canvas Slip-On. Built for simplicity and comfort, our Casco Bay Canvas Slip-On features canvas uppers made entirely of recycled plastic bottles and features a brushed synthetic suede footbed cover.",
+ "nr_faces": 29278,
+ "nr_vertices": 16187,
+ "surface_area": 0.11794681486981631,
+ "volume": 0.0006215686971347324
+ }
+ },
+ "Timberland_Mens_Earthkeepers_Casco_Bay_Suede_1Eye": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Earthkeepers_Casco_Bay_Suede_1Eye",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05537445223049971,
+ -0.13720777097775716,
+ -0.027001317738747775
+ ],
+ [
+ 0.05402054776950029,
+ 0.15602022902224286,
+ 0.06427168226125222
+ ]
+ ],
+ "mass": 0.0006471525431896001,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Earthkeepers Casco Bay Suede 1-Eye\nGet geared up this season. Take a look at our Men's Earthkeepers Casco Bay Suede 1-Eye . One eye is all this low-profile shoe needs - its minimalist good looks are perfect for pairing with your warm-weather ensembles.",
+ "nr_faces": 32620,
+ "nr_vertices": 18424,
+ "surface_area": 0.1291439371185836,
+ "volume": 0.0006471525431896001
+ }
+ },
+ "Timberland_Mens_Earthkeepers_Heritage_2Eye_Boat_Shoe": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Earthkeepers_Heritage_2Eye_Boat_Shoe",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05624971108991803,
+ -0.14101403121313727,
+ -0.03224360880778873
+ ],
+ [
+ 0.04885728891008197,
+ 0.1516729687868627,
+ 0.06671339119221126
+ ]
+ ],
+ "mass": 0.0008196457638224653,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Earthkeepers Heritage 2-Eye Boat Shoe\nExploring new gear for this season? Check out our Men's Earthkeepers Heritage 2-Eye Boat Shoe. It just keeps getting better, and never goes out of style. With its premium leather and classic good looks, our Earthkeepers Heritage 2-Eye is better than ever this season.",
+ "nr_faces": 19778,
+ "nr_vertices": 10795,
+ "surface_area": 0.12240919857846015,
+ "volume": 0.0008196457638224653
+ }
+ },
+ "Timberland_Mens_Earthkeepers_Newmarket_6Inch_Cupsole_Boot": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Earthkeepers_Newmarket_6Inch_Cupsole_Boot",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056380699998572,
+ -0.17439941432839726,
+ -0.063214113138096
+ ],
+ [
+ 0.050173300001427994,
+ 0.11987558567160272,
+ 0.149073886861904
+ ]
+ ],
+ "mass": 0.0021983361356330607,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Earthkeepers Newmarket 6-Inch Cupsole Boot\nRugged, durable and hard-wearing Men's Earthkeepers Newmarket 6-Inch Cupsole Boot. We've been using nubuck leather to craft our hard-wearing boots for decades - and our Earthkeepers Newmarket 6-Inch Cupsole is the latest version of a classic style. Men's Earthkeepers Newmarket 6-Inch Cupsole Boot. We've been using nubuck leather to craft our hard-wearing boots for decades - and our Earthkeepers Newmarket 6-Inch Cupsole is the latest version of a classic style.",
+ "nr_faces": 16976,
+ "nr_vertices": 9609,
+ "surface_area": 0.13473274165637525,
+ "volume": 0.0021983361356330607
+ }
+ },
+ "Timberland_Mens_Earthkeepers_Stormbuck_Chukka": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Earthkeepers_Stormbuck_Chukka",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06030913003085165,
+ -0.17155392957312032,
+ -0.03523749316239178
+ ],
+ [
+ 0.05262486996914835,
+ 0.13525607042687968,
+ 0.08052750683760822
+ ]
+ ],
+ "mass": 0.0008678706515943603,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Earthkeepers Stormbuck Chukka\nCheck out our Men's Earthkeepers Stormbuck Chukka. Complicated isn't always better. Simple lines and eco-conscious materials speak for themselves in our Earthkeepers Stormbuck Chukka, which features premium, water-resistant suede uppers and our exclusive anti-fatigue technology built right into the footbed for all-day style and comfort.",
+ "nr_faces": 18420,
+ "nr_vertices": 10071,
+ "surface_area": 0.1607596448938302,
+ "volume": 0.0008678706515943603
+ }
+ },
+ "Timberland_Mens_Earthkeepers_Stormbuck_Lite_Plain_Toe_Oxford": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Earthkeepers_Stormbuck_Lite_Plain_Toe_Oxford",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0592098048456769,
+ -0.16390211074655708,
+ -0.03256407917710144
+ ],
+ [
+ 0.052299195154323096,
+ 0.14874588925344293,
+ 0.07886692082289856
+ ]
+ ],
+ "mass": 0.0009023739570462928,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Earthkeepers Stormbuck Lite Plain Toe Oxford\nExploring new gear for this season? Check out our Men's Earthkeepers Stormbuck Lite Plain Toe Oxford. Ready for outdoor adventure, but happy to hang out around the house This simply styled oxford has siped, compression-molded outsoles for traction, water-resistant uppers and a footbed made with our exclusive anti-fatigue technology for all-day comfort. This simply styled oxford has siped, compression-molded outsoles for traction, water-resistant uppers and a footbed made with our exclusive anti-fatigue technology for all-day comfort.",
+ "nr_faces": 17872,
+ "nr_vertices": 9956,
+ "surface_area": 0.1549548245573423,
+ "volume": 0.0009023739570462928
+ }
+ },
+ "Timberland_Mens_Earthkeepers_Stormbuck_Plain_Toe_Oxford": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Mens_Earthkeepers_Stormbuck_Plain_Toe_Oxford",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06000787686191339,
+ -0.15996095458422316,
+ -0.038311363388105174
+ ],
+ [
+ 0.05090812313808661,
+ 0.14527004541577684,
+ 0.09052863661189481
+ ]
+ ],
+ "mass": 0.0009857810905758533,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Men's Earthkeepers Stormbuck Plain Toe Oxford\nExploring new gear for this season? Check out our Men's Earthkeepers Stormbuck Plain Toe Oxford. One of our most classic styles, our Earthkeepers™ Stormbuck Plain Toe Oxford is versatile, waterproof and updated for the new season with plenty of eco-conscious features.",
+ "nr_faces": 28750,
+ "nr_vertices": 16515,
+ "surface_area": 0.1700478024868758,
+ "volume": 0.0009857810905758533
+ }
+ },
+ "Timberland_Womens_Classic_Amherst_2Eye_Boat_Shoe": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Womens_Classic_Amherst_2Eye_Boat_Shoe",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04978536109398136,
+ -0.1267206311223455,
+ -0.02989632018456286
+ ],
+ [
+ 0.04410763890601864,
+ 0.1400213688776545,
+ 0.06390367981543714
+ ]
+ ],
+ "mass": 0.000734503623891463,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Women's Classic Amherst 2-Eye Boat Shoe\nGet geared up this season. Take a look at our Women's Classic Amherst 2-Eye Boat Shoe. We made our name with the first waterproof boots, then we extended our craftsmanship to the boat shoe.",
+ "nr_faces": 28578,
+ "nr_vertices": 15407,
+ "surface_area": 0.10487672609106644,
+ "volume": 0.000734503623891463
+ }
+ },
+ "Timberland_Womens_Earthkeepers_Classic_Unlined_Boat_Shoe": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Womens_Earthkeepers_Classic_Unlined_Boat_Shoe",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04758002299082752,
+ -0.13431555837497558,
+ -0.026075153439562244
+ ],
+ [
+ 0.049024977009172487,
+ 0.1371134416250244,
+ 0.058842846560437756
+ ]
+ ],
+ "mass": 0.0006179402842971086,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Women's Earthkeepers Classic Unlined Boat Shoe\nShop Timberland for the Women's Earthkeepers Classic Unlined Boat Shoe. Great colors for the new season and a compression-molded midsole make this classic boat shoe comfy and perfectly on-trend.",
+ "nr_faces": 15342,
+ "nr_vertices": 8277,
+ "surface_area": 0.10556800644896164,
+ "volume": 0.0006179402842971086
+ }
+ },
+ "Timberland_Womens_Waterproof_Nellie_Chukka_Double": {
+ "asset_type": "FileBasedObject",
+ "id": "Timberland_Womens_Waterproof_Nellie_Chukka_Double",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05599280972280486,
+ -0.1460325915554368,
+ -0.04894100141121231
+ ],
+ [
+ 0.04872919027719514,
+ 0.13307340844456322,
+ 0.1007129985887877
+ ]
+ ],
+ "mass": 0.001267520630814939,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Timberland Women's Waterproof Nellie Chukka Double\nUpdated for the new season Women's Waterproof Nellie Chukka Double. We've used our exclusive anti-fatigue technology in the midsoles to ensure that our rugged but feminine Nellie Chukka Double offers the ultimate in comfort. Women's Waterproof Nellie Chukka Double. We've used our exclusive anti-fatigue technology in the midsoles to ensure that our rugged but feminine Nellie Chukka Double offers the ultimate in comfort.",
+ "nr_faces": 24054,
+ "nr_vertices": 13852,
+ "surface_area": 0.14124349618353757,
+ "volume": 0.001267520630814939
+ }
+ },
+ "Top_Paw_Dog_Bow_Bone_Ceramic_13_fl_oz_total": {
+ "asset_type": "FileBasedObject",
+ "id": "Top_Paw_Dog_Bow_Bone_Ceramic_13_fl_oz_total",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09403128527858642,
+ -0.09345546943047219,
+ -0.032319372014304314
+ ],
+ [
+ 0.09032571472141358,
+ 0.09213853056952781,
+ 0.036153627985695685
+ ]
+ ],
+ "mass": 0.0003093867713631948,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Top Paw Dog Bow, Bone, Ceramic - 13 fl oz total",
+ "nr_faces": 10930,
+ "nr_vertices": 5651,
+ "surface_area": 0.1219372708192071,
+ "volume": 0.0003093867713631948
+ }
+ },
+ "Top_Paw_Dog_Bowl_Blue_Paw_Bone_Ceramic_25_fl_oz_total": {
+ "asset_type": "FileBasedObject",
+ "id": "Top_Paw_Dog_Bowl_Blue_Paw_Bone_Ceramic_25_fl_oz_total",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07618198094161964,
+ -0.07648618715956247,
+ -0.02116079231757927
+ ],
+ [
+ 0.07631201905838035,
+ 0.07658781284043753,
+ 0.03915520768242073
+ ]
+ ],
+ "mass": 0.0002683698064735938,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Top Paw Dog Bowl, Blue Paw Bone, Ceramic - 25 fl oz total",
+ "nr_faces": 4612,
+ "nr_vertices": 2398,
+ "surface_area": 0.08375569878501686,
+ "volume": 0.0002683698064735938
+ }
+ },
+ "Tory_Burch_Kaitlin_Ballet_Mestico_in_BlackGold": {
+ "asset_type": "FileBasedObject",
+ "id": "Tory_Burch_Kaitlin_Ballet_Mestico_in_BlackGold",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04600487192520006,
+ -0.1268936953422925,
+ -0.02193708891676333
+ ],
+ [
+ 0.04058012807479994,
+ 0.1336563046577075,
+ 0.05207591108323667
+ ]
+ ],
+ "mass": 0.00030839442859143115,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Tory Burch Kaitlin Ballet - Mestico in Black/Gold",
+ "nr_faces": 34534,
+ "nr_vertices": 17598,
+ "surface_area": 0.07243084693661438,
+ "volume": 0.00030839442859143115
+ }
+ },
+ "Tory_Burch_Kiernan_Riding_Boot": {
+ "asset_type": "FileBasedObject",
+ "id": "Tory_Burch_Kiernan_Riding_Boot",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05877651228414106,
+ -0.17718799382667338,
+ -0.11666546729518575
+ ],
+ [
+ 0.04341148771585894,
+ 0.09797400617332663,
+ 0.17930353270481425
+ ]
+ ],
+ "mass": 0.0022353693099841114,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Tory Burch Kiernan Riding Boot\nDirectly from Tory Burch - A wardrobe staple ? our must-have riding boot. A classic equestrian shape dressed up with fretwork-inspired gold metal. Our leather Kiernan Boot is inset with a signature ?T? logo done in an open-cut design based on the decorative elements used in our boutiques, giving the minimalistic and infinitely versatile silhouette a hint of graphic shine. Tory Burch Official Site.",
+ "nr_faces": 7112,
+ "nr_vertices": 3718,
+ "surface_area": 0.13027153549777307,
+ "volume": 0.0022353693099841114
+ }
+ },
+ "Tory_Burch_Reva_Metal_Logo_Litus_Snake_Print_in_dark_BranchGold": {
+ "asset_type": "FileBasedObject",
+ "id": "Tory_Burch_Reva_Metal_Logo_Litus_Snake_Print_in_dark_BranchGold",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04252457644800155,
+ -0.12797296101058606,
+ -0.015856202361931547
+ ],
+ [
+ 0.04432942355199845,
+ 0.12982703898941395,
+ 0.04390179763806845
+ ]
+ ],
+ "mass": 0.00022919348477484314,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Tory Burch Reva (Metal Logo)- Litus Snake Print in dark Branch/Gold",
+ "nr_faces": 23850,
+ "nr_vertices": 12488,
+ "surface_area": 0.07285628243313805,
+ "volume": 0.00022919348477484314
+ }
+ },
+ "Tory_Burch_Sabe_65mm_Bootie_Split_Suede_in_Caramel": {
+ "asset_type": "FileBasedObject",
+ "id": "Tory_Burch_Sabe_65mm_Bootie_Split_Suede_in_Caramel",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05075027316082095,
+ -0.1321995807436819,
+ -0.05048589237938298
+ ],
+ [
+ 0.04271172683917905,
+ 0.1177204192563181,
+ 0.12949110762061702
+ ]
+ ],
+ "mass": 0.0008469508871492104,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Tory Burch Sabe 65mm Bootie- Split Suede in Caramel",
+ "nr_faces": 9660,
+ "nr_vertices": 5139,
+ "surface_area": 0.11845846274030394,
+ "volume": 0.0008469508871492104
+ }
+ },
+ "Toys_R_Us_Treat_Dispenser_Smart_Puzzle_Foobler": {
+ "asset_type": "FileBasedObject",
+ "id": "Toys_R_Us_Treat_Dispenser_Smart_Puzzle_Foobler",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07736837876203595,
+ -0.07656977894398907,
+ -0.07642717014940996
+ ],
+ [
+ 0.07735362123796405,
+ 0.07733422105601093,
+ 0.07703082985059004
+ ]
+ ],
+ "mass": 0.001907259270415379,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Toys R Us Treat Dispenser, Smart Puzzle, Foobler",
+ "nr_faces": 8852,
+ "nr_vertices": 4686,
+ "surface_area": 0.0801625382199539,
+ "volume": 0.001907259270415379
+ }
+ },
+ "Toysmith_Windem_Up_Flippin_Animals_Dog": {
+ "asset_type": "FileBasedObject",
+ "id": "Toysmith_Windem_Up_Flippin_Animals_Dog",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.015616782133407284,
+ -0.02357530309881393,
+ -0.02271210905764616
+ ],
+ [
+ 0.019219217866592714,
+ 0.02483069690118607,
+ 0.027213890942353842
+ ]
+ ],
+ "mass": 2.4912026157467832e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Toysmith Wind'em Up Flippin' Animals, Dog",
+ "nr_faces": 15672,
+ "nr_vertices": 8347,
+ "surface_area": 0.006729157305467265,
+ "volume": 2.4912026157467832e-05
+ }
+ },
+ "Transformers_Age_of_Extinction_Mega_1Step_Bumblebee_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Transformers_Age_of_Extinction_Mega_1Step_Bumblebee_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09450935114521974,
+ -0.04427953260214963,
+ -0.11898711136261785
+ ],
+ [
+ 0.09969264885478026,
+ 0.033689467397850364,
+ 0.14887188863738215
+ ]
+ ],
+ "mass": 0.0008717675734783243,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Transformers Age of Extinction Mega 1-Step Bumblebee Figure\nJoin the epic battle between the Autobots and Decepticons with this giant Bumblebee figure that switches between robot and vehicle modes in 1 awesome step! You can experience the wow of the fluid conversion you see your favorite Transformers characters perform. Just flip to change from robot to vehicle and back. With a firing disc launcher included, you can create exciting Transformers battles, all in larger, mega-sized scale!",
+ "nr_faces": 66112,
+ "nr_vertices": 45765,
+ "surface_area": 0.18194749032081262,
+ "volume": 0.0008717675734783243
+ }
+ },
+ "Transformers_Age_of_Extinction_Stomp_and_Chomp_Grimlock_Figure": {
+ "asset_type": "FileBasedObject",
+ "id": "Transformers_Age_of_Extinction_Stomp_and_Chomp_Grimlock_Figure",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12440959495164186,
+ -0.19573963781899298,
+ -0.18207640870341868
+ ],
+ [
+ 0.11973540504835814,
+ 0.282225362181007,
+ 0.14232659129658135
+ ]
+ ],
+ "mass": 0.003024962136228088,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Transformers Age of Extinction Stomp and Chomp Grimlock Figure\nYour Transformers adventures just got a whole lot bigger! Your Chomp and Stomp Grimlock figure is a giant, 20-inch robot with a mighty sword who's ready to take on any enemy. He changes in 1 step to a dino with a terrible, chomping jaw and light-up eyes! Team him up with the included Optimus Prime mini-figure for maximum mayhem.",
+ "nr_faces": 73004,
+ "nr_vertices": 56622,
+ "surface_area": 0.5104158563427195,
+ "volume": 0.003024962136228088
+ }
+ },
+ "Travel_Mate_P_series_Notebook": {
+ "asset_type": "FileBasedObject",
+ "id": "Travel_Mate_P_series_Notebook",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.16561380102319428,
+ -0.17308761240595527,
+ -0.03683195000656126
+ ],
+ [
+ 0.1670611989768057,
+ 0.20228838759404472,
+ 0.15703404999343876
+ ]
+ ],
+ "mass": 0.0013998202199844028,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Travel Mate P series Notebook\n14\" commerical notebok",
+ "nr_faces": 9486,
+ "nr_vertices": 5103,
+ "surface_area": 0.31663598214929145,
+ "volume": 0.0013998202199844028
+ }
+ },
+ "Travel_Smart_Neck_Rest_Inflatable": {
+ "asset_type": "FileBasedObject",
+ "id": "Travel_Smart_Neck_Rest_Inflatable",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05233322295270699,
+ -0.019920694619216733,
+ -0.077361815197249
+ ],
+ [
+ 0.05308177704729301,
+ 0.021277305380783266,
+ 0.095523184802751
+ ]
+ ],
+ "mass": 0.0005908123389809985,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Travel Smart Neck Rest, Inflatable",
+ "nr_faces": 3214,
+ "nr_vertices": 1798,
+ "surface_area": 0.052044654316937396,
+ "volume": 0.0005908123389809985
+ }
+ },
+ "TriStar_Products_PPC_Power_Pressure_Cooker_XL_in_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "TriStar_Products_PPC_Power_Pressure_Cooker_XL_in_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.15716797727357207,
+ -0.15023503156399504,
+ -0.1414811110120076
+ ],
+ [
+ 0.15469802272642794,
+ 0.14355196843600496,
+ 0.1882458889879924
+ ]
+ ],
+ "mass": 0.016410091785135805,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Tri-Star Products PPC Power Pressure Cooker XL in Black",
+ "nr_faces": 25054,
+ "nr_vertices": 12981,
+ "surface_area": 0.3885968384307551,
+ "volume": 0.016410091785135805
+ }
+ },
+ "Tune_Belt_Sport_Armband_For_Samsung_Galaxy_S3": {
+ "asset_type": "FileBasedObject",
+ "id": "Tune_Belt_Sport_Armband_For_Samsung_Galaxy_S3",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0657090036818429,
+ -0.02296168943374524,
+ -0.0974130223880914
+ ],
+ [
+ 0.0655759963181571,
+ 0.02277631056625476,
+ 0.12312097761190861
+ ]
+ ],
+ "mass": 0.00098479247261784,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Tune Belt Sport Armband For Samsung Galaxy S3",
+ "nr_faces": 2850,
+ "nr_vertices": 1571,
+ "surface_area": 0.07858919433492345,
+ "volume": 0.00098479247261784
+ }
+ },
+ "Twinlab_100_Whey_Protein_Fuel_Chocolate": {
+ "asset_type": "FileBasedObject",
+ "id": "Twinlab_100_Whey_Protein_Fuel_Chocolate",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.079017097351642,
+ -0.07838444336285462,
+ -0.12368389239140187
+ ],
+ [
+ 0.079157902648358,
+ 0.07843455663714538,
+ 0.1349751076085981
+ ]
+ ],
+ "mass": 0.004555338880710082,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Twinlab 100% Whey Protein Fuel Chocolate\nOur 100% Whey Fuel ever is a superior blend of high quality, bioavailable whey proteins that's fully instantized, quick dissolving and easy to mix with a rich, creamy taste in both water and skim milk. 100% Whey Fuel stimulates muscle protein anabolism, which maximizes muscle growth that occurs after exercise by enhancing muscle building and lean tissue mass.* It also increases muscle performance and improves post-workout recovery.* Clinical studies show that whey protein is one of the most anabolic muscle building proteins available, providing a rapid drive of amino acids to skeletal muscle tissue, thereby increasing the effects of weight training.* Enhanced muscle protein anabolism increases muscle growth to maximize gains.* Additionally, research shows that whey protein is among the most easily digested and absorbed proteins, and has one of the highest Protein Efficiency Ratios, providing more branched chain amino acids than most other proteins. 100% Whey Fuel stimulates muscle protein anabolism, which maximizes muscle growth that occurs after exercise by enhancing muscle building and lean tissue mass.* It also increases muscle performance and improves post-workout recovery*. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure or prevent disease.",
+ "nr_faces": 12770,
+ "nr_vertices": 6510,
+ "surface_area": 0.1508783104101872,
+ "volume": 0.004555338880710082
+ }
+ },
+ "Twinlab_100_Whey_Protein_Fuel_Cookies_and_Cream": {
+ "asset_type": "FileBasedObject",
+ "id": "Twinlab_100_Whey_Protein_Fuel_Cookies_and_Cream",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07913078320454615,
+ -0.07885041276858205,
+ -0.12374554495921845
+ ],
+ [
+ 0.07921521679545383,
+ 0.07889258723141794,
+ 0.13518345504078152
+ ]
+ ],
+ "mass": 0.004556200589223276,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Twinlab 100% Whey Protein Fuel Cookies and Cream\nOur 100% Whey Fuel ever is a superior blend of high quality, bioavailable whey proteins that's fully instantized, quick dissolving and easy to mix with a rich, creamy taste in both water and skim milk. 100% Whey Fuel stimulates muscle protein anabolism, which maximizes muscle growth that occurs after exercise by enhancing muscle building and lean tissue mass.* It also increases muscle performance and improves post-workout recovery.* Clinical studies show that whey protein is one of the most anabolic muscle building proteins available, providing a rapid drive of amino acids to skeletal muscle tissue, thereby increasing the effects of weight training.* Enhanced muscle protein anabolism increases muscle growth to maximize gains.* Additionally, research shows that whey protein is among the most easily digested and absorbed proteins, and has one of the highest Protein Efficiency Ratios, providing more branched chain amino acids than most other proteins. 100% Whey Fuel stimulates muscle protein anabolism, which maximizes muscle growth that occurs after exercise by enhancing muscle building and lean tissue mass.* It also increases muscle performance and improves post-workout recovery*. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure or prevent disease.",
+ "nr_faces": 12000,
+ "nr_vertices": 6135,
+ "surface_area": 0.15080956685633562,
+ "volume": 0.004556200589223276
+ }
+ },
+ "Twinlab_100_Whey_Protein_Fuel_Vanilla": {
+ "asset_type": "FileBasedObject",
+ "id": "Twinlab_100_Whey_Protein_Fuel_Vanilla",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07943785898576189,
+ -0.07848040032321862,
+ -0.12339082508712153
+ ],
+ [
+ 0.07935014101423812,
+ 0.07845459967678138,
+ 0.13578317491287845
+ ]
+ ],
+ "mass": 0.004563156495156107,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Twinlab 100% Whey Protein Fuel Vanilla\nOur 100% Whey Fuel ever is a superior blend of high quality, bioavailable whey proteins that's fully instantized, quick dissolving and easy to mix with a rich, creamy taste in both water and skim milk. 100% Whey Fuel stimulates muscle protein anabolism, which maximizes muscle growth that occurs after exercise by enhancing muscle building and lean tissue mass.* It also increases muscle performance and improves post-workout recovery.* Clinical studies show that whey protein is one of the most anabolic muscle building proteins available, providing a rapid drive of amino acids to skeletal muscle tissue, thereby increasing the effects of weight training.* Enhanced muscle protein anabolism increases muscle growth to maximize gains.* Additionally, research shows that whey protein is among the most easily digested and absorbed proteins, and has one of the highest Protein Efficiency Ratios, providing more branched chain amino acids than most other proteins. 100% Whey Fuel stimulates muscle protein anabolism, which maximizes muscle growth that occurs after exercise by enhancing muscle building and lean tissue mass.* It also increases muscle performance and improves post-workout recovery*. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure or prevent disease.",
+ "nr_faces": 10072,
+ "nr_vertices": 5171,
+ "surface_area": 0.15138050733615543,
+ "volume": 0.004563156495156107
+ }
+ },
+ "Twinlab_Nitric_Fuel": {
+ "asset_type": "FileBasedObject",
+ "id": "Twinlab_Nitric_Fuel",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03002861243399852,
+ -0.029577788311753405,
+ -0.05135127831547152
+ ],
+ [
+ 0.029692387566001482,
+ 0.029781211688246597,
+ 0.06189572168452848
+ ]
+ ],
+ "mass": 0.0002675065151650348,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Twinlab Nitric Fuel\nFinally, a product that takes you beyond a simple pump.* Nitric Fuel? floods muscles with Nitric Oxide, Beta-Alanine and Creatine in an innovative bi-layer tablet designed for both quick and prolonged power and pump.* Nitric Fuel goes beyond simple \"pump\" products by combining the volumizing effects of Nitric Oxide (from Di-arginine Malate and Citrulline Malate) with stamina-boosting Beta-Alanine and performance-enhancing Creatine (Di-creatine Malate).* Nitric Oxide increases blood flow, which may deliver more nutrients to muscles and help get that pumped-up post workout look.* In addition to Di-arginine Malate and Di-creatine Malate, Nitric Fuel's Power Pump Complex contains Citrulline Malate, a precursor to Nitric Oxide that helps promote resistance to fatigue and better muscle recovery; Aspartic acid, which may increase stamina; and L-histidine, an amino acid that combines with Beta- Alanine to further increase muscular strength.* We also added Glyceryl Monostearate, which helps transport water into muscle cells and may further promote muscle hydration.* All of these nutrients are combined in a unique bi-layer tablet. The gray side of the tablet dissolves quickly to kick-start your workout, while the blue side dissipates more slowly to fuel sustained and intense 1-2 hour workouts.* *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure or prevent disease.",
+ "nr_faces": 13250,
+ "nr_vertices": 6775,
+ "surface_area": 0.023633639297002684,
+ "volume": 0.0002675065151650348
+ }
+ },
+ "Twinlab_Premium_Creatine_Fuel_Powder": {
+ "asset_type": "FileBasedObject",
+ "id": "Twinlab_Premium_Creatine_Fuel_Powder",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.030154880620980172,
+ -0.029796754053934733,
+ -0.05187027000747382
+ ],
+ [
+ 0.029649119379019827,
+ 0.029803245946065267,
+ 0.06137172999252618
+ ]
+ ],
+ "mass": 0.00026784904906167965,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Twinlab Premium Creatine Fuel Powder\nResearch shows that Creatine users had a significant increase in peak power output, lean body mass and muscular performance.* Depletion of phosphocreatine can result in muscular fatigue and fading muscle power.* Research shows that users of high quality creatine monohydrate exhibited: Increased peak power*, Amplified muscular performance*, Improved lean body mass*, Advanced performance enhancer with pure Creatine Monohydrate, an energy enhancing supplement*, Improves muscle strength, performance and lean mass*, Featuring precision, micronized, German-sourced brand creatine (micronization allows Creatine powder to stay suspended in liquid longer). *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure or prevent disease.",
+ "nr_faces": 16960,
+ "nr_vertices": 8644,
+ "surface_area": 0.02357565942603337,
+ "volume": 0.00026784904906167965
+ }
+ },
+ "UGG_Bailey_Bow_Womens_Clogs_Black_7": {
+ "asset_type": "FileBasedObject",
+ "id": "UGG_Bailey_Bow_Womens_Clogs_Black_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06625753380749207,
+ -0.17019000771146828,
+ -0.0974691083181996
+ ],
+ [
+ 0.05881446619250793,
+ 0.12582799228853173,
+ 0.1429948916818004
+ ]
+ ],
+ "mass": 0.0028091114489071614,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "UGG Bailey Bow Women's Clogs- Black 7\nUggs Clogs: UGG Australia- UGGs Women Bailey Bow Clogs. The Bailey Bow is embellished with fixed, double ribbon bows at the back, enhancing the defining features of an UGG Classic. A light, flexible outsole and foundational Twinface sheepskin keep feet cozy and dry indoors or out, while durable construction and added foam ensure all-day comfort.",
+ "nr_faces": 27362,
+ "nr_vertices": 15766,
+ "surface_area": 0.15784222061405104,
+ "volume": 0.0028091114489071614
+ }
+ },
+ "UGG_Bailey_Button_Triplet_Womens_Boots_Black_7": {
+ "asset_type": "FileBasedObject",
+ "id": "UGG_Bailey_Button_Triplet_Womens_Boots_Black_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1731873497145932,
+ -0.07211390701094451,
+ -0.13865777272620608
+ ],
+ [
+ 0.09466965028540678,
+ 0.06098509298905549,
+ 0.1971142272737939
+ ]
+ ],
+ "mass": 0.003634026279279813,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "UGG Bailey Button Triplet Women's Boots- Black 7\nUgg Boots: Ugg Bailey Button Triplet Boots for Women by UGG Australia. A fresh take on the timeless style of the Classic Tall, the Bailey Button Triplet features wooden logo buttons with elastic-band closures. Lending signature UGG softness, Twinface sheepskin can be unbuttoned and cuffed to expose its cozy interior.",
+ "nr_faces": 19986,
+ "nr_vertices": 11222,
+ "surface_area": 0.1972804112032026,
+ "volume": 0.003634026279279813
+ }
+ },
+ "UGG_Bailey_Button_Womens_Boots_Black_7": {
+ "asset_type": "FileBasedObject",
+ "id": "UGG_Bailey_Button_Womens_Boots_Black_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06237154131676457,
+ -0.16959477477646362,
+ -0.09359905394511678
+ ],
+ [
+ 0.05098745868323543,
+ 0.11281222522353636,
+ 0.14382094605488321
+ ]
+ ],
+ "mass": 0.002636667714940721,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "UGG Bailey Button Women's Boots- Black 7\nUgg Boots: Ugg Bailey Button Boots for Women by UGG Australia. Bringing versatility to the calf-height style of the Classic Short, the Bailey Button showcases the exclusivewooden logo button with elastic-band closure--in a spectrum of colors. Signature Twinface sheepskin silhouette can be cuffed to expose its cozy interior.",
+ "nr_faces": 22838,
+ "nr_vertices": 12540,
+ "surface_area": 0.14716427937935278,
+ "volume": 0.002636667714940721
+ }
+ },
+ "UGG_Cambridge_Womens_Black_7": {
+ "asset_type": "FileBasedObject",
+ "id": "UGG_Cambridge_Womens_Black_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09162023924171969,
+ -0.1590240380177168,
+ -0.07350241641962435
+ ],
+ [
+ 0.07275976075828032,
+ 0.11486796198228322,
+ 0.14264358358037565
+ ]
+ ],
+ "mass": 0.002281010226165592,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "UGG Cambridge Women's - Black 7\nUggs : UGG Australia- UGGs Women Cambridge . Cozy up in our Classic Knit collection. Lined in sumptuous sheepskin with a fold-over knit collar, Cambridge is essentially the perfect pulloverfor your feet, featuring an adjustable strap for versatile fit and a sheepskin lined cushy foam insole for extra comfort.",
+ "nr_faces": 42030,
+ "nr_vertices": 22440,
+ "surface_area": 0.1756357682854523,
+ "volume": 0.002281010226165592
+ }
+ },
+ "UGG_Classic_Tall_Womens_Boots_Chestnut_7": {
+ "asset_type": "FileBasedObject",
+ "id": "UGG_Classic_Tall_Womens_Boots_Chestnut_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06286561149718385,
+ -0.179942675577616,
+ -0.13958505271168228
+ ],
+ [
+ 0.04692438850281615,
+ 0.11079932442238401,
+ 0.19240094728831772
+ ]
+ ],
+ "mass": 0.003657245231636936,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "UGG Classic Tall Women's Boots- Chestnut 7\nUgg Boots: Ugg Classic Tall Boots for Women by UGG Australia. One of UGG® Australia's most beloved silhouettes, the Classic Tall features cuffable Twinface sheepskin in a palette of seasonal shades. An icon of casual style, the chic silhouette showcases all the characteristics of the Classic Collection, keeping feet dry and comfortable with a moisture-wicking interior and trademark molded-EVA outsole.",
+ "nr_faces": 17234,
+ "nr_vertices": 9658,
+ "surface_area": 0.1967639453665808,
+ "volume": 0.003657245231636936
+ }
+ },
+ "UGG_Classic_Tall_Womens_Boots_Grey_7": {
+ "asset_type": "FileBasedObject",
+ "id": "UGG_Classic_Tall_Womens_Boots_Grey_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10518634163441505,
+ -0.16323487414460475,
+ -0.11893783462633646
+ ],
+ [
+ 0.07977965836558495,
+ 0.11839912585539525,
+ 0.21096516537366355
+ ]
+ ],
+ "mass": 0.003040399959961091,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "UGG Classic Tall Women's Boots- Grey 7\nUgg Boots: Ugg Classic Tall Boots for Women by UGG Australia. One of UGG® Australia's most beloved silhouettes, the Classic Tall features cuffable Twinface sheepskin in a palette of seasonal shades. An icon of casual style, the chic silhouette showcases all the characteristics of the Classic Collection, keeping feet dry and comfortable with a moisture-wicking interior and trademark molded-EVA outsole.",
+ "nr_faces": 20432,
+ "nr_vertices": 11054,
+ "surface_area": 0.21806684802872323,
+ "volume": 0.003040399959961091
+ }
+ },
+ "UGG_Jena_Womens_Java_7": {
+ "asset_type": "FileBasedObject",
+ "id": "UGG_Jena_Womens_Java_7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.056335161093480406,
+ -0.16670628884772265,
+ -0.09106826636096944
+ ],
+ [
+ 0.04422383890651959,
+ 0.12375371115227736,
+ 0.1618067336390306
+ ]
+ ],
+ "mass": 0.001967000007995228,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "UGG Jena Women's - Java 7\nUggs : UGG Australia- UGGs Women Jena . Statement-making style mavens will love this New Orleans-inspired military boot, designed with a removable kiltie and rich brogue detailing. Convertible in nature, this lace-up boot can be worn cuffed up or down, transitioning seamlessly from polished to playful.",
+ "nr_faces": 25212,
+ "nr_vertices": 14627,
+ "surface_area": 0.1444353217465657,
+ "volume": 0.001967000007995228
+ }
+ },
+ "US_Army_Stash_Lunch_Bag": {
+ "asset_type": "FileBasedObject",
+ "id": "US_Army_Stash_Lunch_Bag",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11364211946578773,
+ -0.08430692896243164,
+ -0.11616274983820891
+ ],
+ [
+ 0.11091888053421227,
+ 0.07667707103756835,
+ 0.1576452501617911
+ ]
+ ],
+ "mass": 0.006255631368311293,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "U.S. Army Stash Lunch Bag",
+ "nr_faces": 16422,
+ "nr_vertices": 8567,
+ "surface_area": 0.24424847347427428,
+ "volume": 0.006255631368311293
+ }
+ },
+ "U_By_Kotex_Cleanwear_Heavy_Flow_Pads_32_Ct": {
+ "asset_type": "FileBasedObject",
+ "id": "U_By_Kotex_Cleanwear_Heavy_Flow_Pads_32_Ct",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06975096625795889,
+ -0.05798596564524499,
+ -0.09403035952642347
+ ],
+ [
+ 0.07002203374204112,
+ 0.05899103435475501,
+ 0.09416064047357654
+ ]
+ ],
+ "mass": 0.0028642290670127407,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "U By Kotex Cleanwear Heavy Flow Pads 32 Ct\n2x, We've got answers to the questions you are afraid to ask. Serious attitude. Serious protection. For when things get heavy. Unique shape conforms to fit your body. First 4 layer advanced absorbency system. Clean Wear cover for a clean and fresh feeling. MemoryFlex core is ultra-thin and ultra-flexible to move with you. No. 66 Myth or Fact?: PMS is a pain in the back. Fact - Low back pain is pretty common just before and during the first few days of your period. It's your excuse to go get a massage or do some gentle yoga. Made in the USA from domestic and imported materials.",
+ "nr_faces": 3642,
+ "nr_vertices": 1943,
+ "surface_area": 0.11861131074880049,
+ "volume": 0.0028642290670127407
+ }
+ },
+ "U_By_Kotex_Sleek_Regular_Unscented_Tampons_36_Ct_Box": {
+ "asset_type": "FileBasedObject",
+ "id": "U_By_Kotex_Sleek_Regular_Unscented_Tampons_36_Ct_Box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.054890688959164574,
+ -0.046445244869144704,
+ -0.07291428562419158
+ ],
+ [
+ 0.054866311040835426,
+ 0.0460087551308553,
+ 0.07353771437580842
+ ]
+ ],
+ "mass": 0.0014116412322513106,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "U By Kotex Sleek Regular Unscented Tampons 36 Ct Box\n2X. Full size applicator. PerfectTouch grip. Get a hold of confident period protection. Smooth tip for easy insertion. PerfectTouch grip for just right placement. Slim size for your comfort. ubykotex.com. Made in the USA from domestic and imported material.",
+ "nr_faces": 6972,
+ "nr_vertices": 3631,
+ "surface_area": 0.07420686705815627,
+ "volume": 0.0014116412322513106
+ }
+ },
+ "Ubisoft_RockSmith_Real_Tone_Cable_Xbox_360": {
+ "asset_type": "FileBasedObject",
+ "id": "Ubisoft_RockSmith_Real_Tone_Cable_Xbox_360",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.09387568988750174,
+ -0.06359231457665815,
+ -0.017587562664249948
+ ],
+ [
+ 0.07777131011249827,
+ 0.07645568542334186,
+ 0.02601343733575005
+ ]
+ ],
+ "mass": 0.00015505468534666517,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Ubisoft RockSmith Real Tone Cable, Xbox 360",
+ "nr_faces": 37794,
+ "nr_vertices": 20544,
+ "surface_area": 0.051013866598026245,
+ "volume": 0.00015505468534666517
+ }
+ },
+ "Ultra_JarroDophilus": {
+ "asset_type": "FileBasedObject",
+ "id": "Ultra_JarroDophilus",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.029868163610770916,
+ -0.030113766901598026,
+ -0.05481697989136886
+ ],
+ [
+ 0.02966983638922908,
+ 0.029793233098401973,
+ 0.05457902010863113
+ ]
+ ],
+ "mass": 0.00036912384523230435,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Ultra Jarro-Dophilus",
+ "nr_faces": 5914,
+ "nr_vertices": 3122,
+ "surface_area": 0.031151704973081673,
+ "volume": 0.00036912384523230435
+ }
+ },
+ "Unmellow_Yellow_Tieks_Neon_Patent_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Unmellow_Yellow_Tieks_Neon_Patent_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04239767176636849,
+ -0.12185621678168446,
+ -0.028560403817363127
+ ],
+ [
+ 0.038478328233631516,
+ 0.12021578321831554,
+ 0.05257659618263687
+ ]
+ ],
+ "mass": 0.0004378921980462189,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Unmellow Yellow Tieks - Neon Patent Leather Ballet Flats\nShock your outfit to life in Unmellow Yellow Tieks. These patent, neon croc print ballet flats will electrify any look. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 20742,
+ "nr_vertices": 11365,
+ "surface_area": 0.08112170305894269,
+ "volume": 0.0004378921980462189
+ }
+ },
+ "Utana_5_Porcelain_Ramekin_Large": {
+ "asset_type": "FileBasedObject",
+ "id": "Utana_5_Porcelain_Ramekin_Large",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06611806215773076,
+ -0.06638782865079362,
+ -0.028198214708503647
+ ],
+ [
+ 0.06637993784226924,
+ 0.06545117134920639,
+ 0.04139978529149635
+ ]
+ ],
+ "mass": 0.00019031120152391504,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Utana 5\" Porcelain Ramekin, Large",
+ "nr_faces": 18670,
+ "nr_vertices": 9489,
+ "surface_area": 0.06621381204309593,
+ "volume": 0.00019031120152391504
+ }
+ },
+ "VANS_FIRE_ROASTED_VEGGIE_CRACKERS_GLUTEN_FREE": {
+ "asset_type": "FileBasedObject",
+ "id": "VANS_FIRE_ROASTED_VEGGIE_CRACKERS_GLUTEN_FREE",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07028326705229837,
+ -0.030467015156855716,
+ -0.10446343659509462
+ ],
+ [
+ 0.06981973294770163,
+ 0.029868984843144285,
+ 0.10471056340490537
+ ]
+ ],
+ "mass": 0.0016327660145903811,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "VAN'S FIRE ROASTED VEGGIE CRACKERS GLUTEN FREE",
+ "nr_faces": 2016,
+ "nr_vertices": 1088,
+ "surface_area": 0.09301926703849578,
+ "volume": 0.0016327660145903811
+ }
+ },
+ "VEGETABLE_GARDEN": {
+ "asset_type": "FileBasedObject",
+ "id": "VEGETABLE_GARDEN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10725115070861685,
+ -0.07254096146073077,
+ -0.011415471605744602
+ ],
+ [
+ 0.12269484929138315,
+ 0.11914203853926923,
+ 0.0344685283942554
+ ]
+ ],
+ "mass": 0.00035733726697012396,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "VEGETABLE GARDEN\nThe set includes a wheelbarrow, watering can, spade, 4 vegetable beds and removable carrots, radishes, turnips, and cauliflowers.",
+ "nr_faces": 16694,
+ "nr_vertices": 10418,
+ "surface_area": 0.08177072897915172,
+ "volume": 0.00035733726697012396
+ }
+ },
+ "Vans_Cereal_Honey_Nut_Crunch_11_oz_box": {
+ "asset_type": "FileBasedObject",
+ "id": "Vans_Cereal_Honey_Nut_Crunch_11_oz_box",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10136573657859344,
+ -0.028126348529572055,
+ -0.1396710932860196
+ ],
+ [
+ 0.10117826342140657,
+ 0.027512651470427946,
+ 0.14185390671398043
+ ]
+ ],
+ "mass": 0.0028342155117890436,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Van's Cereal, Honey Nut Crunch - 11 oz box",
+ "nr_faces": 1446,
+ "nr_vertices": 790,
+ "surface_area": 0.15250631432526265,
+ "volume": 0.0028342155117890436
+ }
+ },
+ "Victor_Reversible_Bookend": {
+ "asset_type": "FileBasedObject",
+ "id": "Victor_Reversible_Bookend",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13912399339219977,
+ -0.06317027512172659,
+ -0.09703408557717204
+ ],
+ [
+ 0.09581700660780021,
+ 0.04573072487827341,
+ 0.13939691442282798
+ ]
+ ],
+ "mass": 0.0029010774087651473,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Victor Reversible Bookend",
+ "nr_faces": 16418,
+ "nr_vertices": 9941,
+ "surface_area": 0.18369892885186712,
+ "volume": 0.0029010774087651473
+ }
+ },
+ "Vtech_Cruise_Learn_Car_25_Years": {
+ "asset_type": "FileBasedObject",
+ "id": "Vtech_Cruise_Learn_Car_25_Years",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.26987495710876497,
+ -0.09264050435650915,
+ -0.04903706959579292
+ ],
+ [
+ 0.08466804289123508,
+ 0.08126549564349085,
+ 0.06894393040420707
+ ]
+ ],
+ "mass": 0.0009108515676157093,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Vtech Cruise & Learn Car, 2-5 Years",
+ "nr_faces": 18502,
+ "nr_vertices": 10972,
+ "surface_area": 0.09057015948178676,
+ "volume": 0.0009108515676157093
+ }
+ },
+ "Vtech_Roll_Learn_Turtle": {
+ "asset_type": "FileBasedObject",
+ "id": "Vtech_Roll_Learn_Turtle",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08431460466814387,
+ -0.1274084591090548,
+ -0.05345929178396158
+ ],
+ [
+ 0.08511739533185612,
+ 0.1050855408909452,
+ 0.06405370821603842
+ ]
+ ],
+ "mass": 0.0016814695384605402,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Vtech Roll & Learn Turtle",
+ "nr_faces": 30686,
+ "nr_vertices": 17857,
+ "surface_area": 0.11713727619805037,
+ "volume": 0.0016814695384605402
+ }
+ },
+ "Vtech_Stack_Sing_Rings_636_Months": {
+ "asset_type": "FileBasedObject",
+ "id": "Vtech_Stack_Sing_Rings_636_Months",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06726532787626412,
+ -0.06400858563277698,
+ -0.06824564875140918
+ ],
+ [
+ 0.06820467212373589,
+ 0.06409541436722302,
+ 0.16517535124859084
+ ]
+ ],
+ "mass": 0.0013033849943224845,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Vtech Stack & Sing Rings, 6-36 Months",
+ "nr_faces": 21056,
+ "nr_vertices": 11638,
+ "surface_area": 0.12016605797705882,
+ "volume": 0.0013033849943224845
+ }
+ },
+ "WATER_LANDING_NET": {
+ "asset_type": "FileBasedObject",
+ "id": "WATER_LANDING_NET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1508973425633205,
+ -0.12776487949884544,
+ -0.025945619421782407
+ ],
+ [
+ 0.23995565743667951,
+ 0.07727312050115456,
+ 0.0495393805782176
+ ]
+ ],
+ "mass": 0.0006399507575875064,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "WATER LANDING NET\nGone fishin' with your wooden toy Landing Net! The set includes a landing net, a fish, a turtle, a starfish and 2 different cups. Kids will enjoy experimenting different flows of water with these 3 cups. Some are pierced and kids can enjoy dumping, filling, reversing, the possibilities are endless.",
+ "nr_faces": 30798,
+ "nr_vertices": 19966,
+ "surface_area": 0.12798627593167738,
+ "volume": 0.0006399507575875064
+ }
+ },
+ "WHALE_WHISTLE_6PCS_SET": {
+ "asset_type": "FileBasedObject",
+ "id": "WHALE_WHISTLE_6PCS_SET",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.029296585195880694,
+ -0.02897032023194069,
+ -0.015888812758363444
+ ],
+ [
+ 0.02900841480411931,
+ 0.044320679768059305,
+ 0.022138187241636558
+ ]
+ ],
+ "mass": 6.0593426680809e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "WHALE WHISTLE (6PCS@ SET)\n6 Pieces Per Set",
+ "nr_faces": 6452,
+ "nr_vertices": 3422,
+ "surface_area": 0.008801999141069073,
+ "volume": 6.0593426680809e-05
+ }
+ },
+ "W_Lou_z0dkC78niiZ": {
+ "asset_type": "FileBasedObject",
+ "id": "W_Lou_z0dkC78niiZ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1524573058483892,
+ -0.0546183743359802,
+ -0.08283558752552603
+ ],
+ [
+ 0.10036869415161079,
+ 0.037337625664019804,
+ 0.18572341247447394
+ ]
+ ],
+ "mass": 0.0015827534669733694,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "W Lou",
+ "nr_faces": 10160,
+ "nr_vertices": 5388,
+ "surface_area": 0.12937114686665285,
+ "volume": 0.0015827534669733694
+ }
+ },
+ "Weisshai_Great_White_Shark": {
+ "asset_type": "FileBasedObject",
+ "id": "Weisshai_Great_White_Shark",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.08362636102633036,
+ -0.07645450063875603,
+ -0.023032258038891525
+ ],
+ [
+ 0.06006963897366963,
+ 0.09062249936124397,
+ 0.05173674196110847
+ ]
+ ],
+ "mass": 0.000122754619626923,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "None",
+ "description": "Weisshai Great White Shark\nTest",
+ "nr_faces": 5912,
+ "nr_vertices": 3324,
+ "surface_area": 0.022760209382989373,
+ "volume": 0.000122754619626923
+ }
+ },
+ "Weston_No_22_Cajun_Jerky_Tonic_12_fl_oz_nLj64ZnGwDh": {
+ "asset_type": "FileBasedObject",
+ "id": "Weston_No_22_Cajun_Jerky_Tonic_12_fl_oz_nLj64ZnGwDh",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03274528848240038,
+ -0.03124994572940301,
+ -0.0850363260466666
+ ],
+ [
+ 0.03143871151759962,
+ 0.03128905427059699,
+ 0.1140446739533334
+ ]
+ ],
+ "mass": 0.00046933422911017714,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Weston No. 22 Cajun Jerky Tonic - 12 fl oz\nWeston Premium Jerky Tonic - the cure for the tired tastebud! Our bottles let you use only what you need. Mix one tablespoon of seasoning with one tablespoon of water for every one pound of meat.",
+ "nr_faces": 17068,
+ "nr_vertices": 8680,
+ "surface_area": 0.03823758870802357,
+ "volume": 0.00046933422911017714
+ }
+ },
+ "Weston_No_33_Signature_Sausage_Tonic_12_fl_oz": {
+ "asset_type": "FileBasedObject",
+ "id": "Weston_No_33_Signature_Sausage_Tonic_12_fl_oz",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03355905547694444,
+ -0.03139971039026868,
+ -0.08457034172495824
+ ],
+ [
+ 0.03193294452305556,
+ 0.03109128960973132,
+ 0.11410165827504176
+ ]
+ ],
+ "mass": 0.0004656309430202861,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Weston No. 33 Signature Sausage Tonic - 12 fl oz\nWeston Premium Jerky Tonic - the cure for the tired tastebud! Our bottles let you use only what you need. Mix one tablespoon of seasoning with one tablespoon of water for every one pound of meat.",
+ "nr_faces": 13526,
+ "nr_vertices": 6893,
+ "surface_area": 0.03794849033846388,
+ "volume": 0.0004656309430202861
+ }
+ },
+ "Whey_Protein_3_Flavor_Variety_Pack_12_Packets": {
+ "asset_type": "FileBasedObject",
+ "id": "Whey_Protein_3_Flavor_Variety_Pack_12_Packets",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.052116791673334134,
+ -0.07691547348319529,
+ -0.07765781451503721
+ ],
+ [
+ 0.052622208326665865,
+ 0.0772055265168047,
+ 0.07759118548496279
+ ]
+ ],
+ "mass": 0.0024235413300086666,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Whey Protein, 3 Flavor Variety Pack - 12 Packets\nJarrow FORMULAS WHEY PROTEIN is a 100%natural protein concentrate of whey, from cows not treated with growth hormone (rBST), and is ultrafiltered to be low in fat, lactose and carbohydrates. WHEY PROTEIN is a rich natural source of BCAAs (Isoleucine, Leucine and Valine). Each packet (? 23 grams) of WHEY PROTEIN provides a total of 4 grams of BCAAs. No other source of protein provides as much of the BCAAs as whey. WHEY PROTEIN is rich in essential amino acids, ranking it with egg as one of the highest quality protein sources available. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 2562,
+ "nr_vertices": 1404,
+ "surface_area": 0.1071233200067687,
+ "volume": 0.0024235413300086666
+ }
+ },
+ "Whey_Protein_Chocolate_12_Packets": {
+ "asset_type": "FileBasedObject",
+ "id": "Whey_Protein_Chocolate_12_Packets",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05184304053440985,
+ -0.07719034060707866,
+ -0.07801981207175457
+ ],
+ [
+ 0.05178395946559015,
+ 0.07674565939292134,
+ 0.07805118792824545
+ ]
+ ],
+ "mass": 0.0023942376829879006,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Whey Protein, Chocolate - 12 Packets\nJarrow FORMULAS WHEY PROTEIN is a 100%natural protein concentrate of whey, from cows not treated with growth hormone (rBST), and is ultrafiltered to be low in fat, lactose and carbohydrates. WHEY PROTEIN is a rich natural source of BCAAs (Isoleucine, Leucine and Valine). Each packet (27 grams) of WHEY PROTEIN provides a total of 4 grams of BCAAs. No other source of protein provides as much of the BCAAs as whey. WHEY PROTEIN is rich in essential amino acids, ranking it with egg as one of the highest quality protein sources available. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 3594,
+ "nr_vertices": 1894,
+ "surface_area": 0.10733397366779052,
+ "volume": 0.0023942376829879006
+ }
+ },
+ "Whey_Protein_Vanilla": {
+ "asset_type": "FileBasedObject",
+ "id": "Whey_Protein_Vanilla",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0611705015974844,
+ -0.06096897640344577,
+ -0.08232225165018014
+ ],
+ [
+ 0.061124498402515604,
+ 0.06106002359655423,
+ 0.08670874834981987
+ ]
+ ],
+ "mass": 0.0017833943411836959,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Whey Protein, Vanilla",
+ "nr_faces": 10702,
+ "nr_vertices": 5908,
+ "surface_area": 0.08374453291791471,
+ "volume": 0.0017833943411836959
+ }
+ },
+ "Whey_Protein_Vanilla_12_Packets": {
+ "asset_type": "FileBasedObject",
+ "id": "Whey_Protein_Vanilla_12_Packets",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05218807356996196,
+ -0.07776083875410357,
+ -0.07776222382215273
+ ],
+ [
+ 0.052360926430038035,
+ 0.07797816124589642,
+ 0.07781677617784727
+ ]
+ ],
+ "mass": 0.0024290801366861027,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Whey Protein, Vanilla - 12 Packets\nJarrow FORMULAS WHEY PROTEIN is a 100% natural protein concentrate of whey, from cows not treated with growth hormone (rBST), and is ultrafiltered to be low in fat, lactose and carbohydrates. WHEY PROTEIN is a rich natural source of BCAAs (Isoleucine, Leucine and Valine). Each packet (26 grams) of WHEY PROTEIN provides a total of 4 grams of BCAAs. No other source of protein provides as much of the BCAAs as whey. WHEY PROTEIN is rich in essential amino acids, ranking it with egg as one of the highest quality protein sources available. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 2778,
+ "nr_vertices": 1502,
+ "surface_area": 0.10721852079700432,
+ "volume": 0.0024290801366861027
+ }
+ },
+ "White_Rose_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes": {
+ "asset_type": "FileBasedObject",
+ "id": "White_Rose_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.048298547747559595,
+ -0.11770092615937651,
+ -0.027706145648212922
+ ],
+ [
+ 0.038756452252440406,
+ 0.1260430738406235,
+ 0.05139885435178707
+ ]
+ ],
+ "mass": 0.00048260254743366963,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "White Rose Tieks - Leather Ballet Flats with Floral Rosettes\nHand-stitched, fabric flower petals form a beautiful rose mosaic that makes these ballet flats a spring-to-summer staple and a favorite among brides. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 43360,
+ "nr_vertices": 26854,
+ "surface_area": 0.07900310940763389,
+ "volume": 0.00048260254743366963
+ }
+ },
+ "Wild_Copper_Tieks_Metallic_Italian_Leather_Ballet_Flats": {
+ "asset_type": "FileBasedObject",
+ "id": "Wild_Copper_Tieks_Metallic_Italian_Leather_Ballet_Flats",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.045381158220805795,
+ -0.12256293616378515,
+ -0.027051073695900093
+ ],
+ [
+ 0.0404778417791942,
+ 0.12096006383621485,
+ 0.05244492630409991
+ ]
+ ],
+ "mass": 0.0005151663199380921,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Wild Copper Tieks - Metallic Italian Leather Ballet Flats\nThese luxurious, metallic ballet flats add sparkle to every ensemble. Made with premium, soft, top-grain Italian leather. Non-elasticized, cushioned back and padded instep. Foldable split-sole design for ultimate portability. Signature Tiek Blue stripes and durable, non-skid rubber soles.",
+ "nr_faces": 20854,
+ "nr_vertices": 11229,
+ "surface_area": 0.07216258526265379,
+ "volume": 0.0005151663199380921
+ }
+ },
+ "Wilton_Easy_Layers_Cake_Pan_Set": {
+ "asset_type": "FileBasedObject",
+ "id": "Wilton_Easy_Layers_Cake_Pan_Set",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.10447545602516584,
+ -0.025610687411425834,
+ -0.08821282291159241
+ ],
+ [
+ 0.08754554397483416,
+ 0.024614312588574168,
+ 0.08863317708840761
+ ]
+ ],
+ "mass": 0.0012411892574555996,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Wilton Easy Layers Cake Pan Set",
+ "nr_faces": 6328,
+ "nr_vertices": 3475,
+ "surface_area": 0.10458035388098488,
+ "volume": 0.0012411892574555996
+ }
+ },
+ "Wilton_Pearlized_Sugar_Sprinkles_525_oz_Gold": {
+ "asset_type": "FileBasedObject",
+ "id": "Wilton_Pearlized_Sugar_Sprinkles_525_oz_Gold",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.02265774955011346,
+ -0.022751250412745595,
+ -0.06819001851025915
+ ],
+ [
+ 0.02308325044988654,
+ 0.022851749587254402,
+ 0.06628898148974086
+ ]
+ ],
+ "mass": 0.00019222397186707964,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Wilton Pearlized Sugar Sprinkles 5.25 oz. - Gold\nMade in the USA.",
+ "nr_faces": 13322,
+ "nr_vertices": 6819,
+ "surface_area": 0.021248050035631315,
+ "volume": 0.00019222397186707964
+ }
+ },
+ "Wilton_PreCut_Parchment_Sheets_10_x_15_24_sheets": {
+ "asset_type": "FileBasedObject",
+ "id": "Wilton_PreCut_Parchment_Sheets_10_x_15_24_sheets",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.13602748950844032,
+ -0.026475960149621263,
+ -0.02855730864259973
+ ],
+ [
+ 0.1376605104915597,
+ 0.026475039850378735,
+ 0.02815469135740027
+ ]
+ ],
+ "mass": 0.0007351183536928199,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Wilton Pre-Cut Parchment Sheets, 10\" x 15\" - 24 sheets",
+ "nr_faces": 1554,
+ "nr_vertices": 866,
+ "surface_area": 0.059469457182928856,
+ "volume": 0.0007351183536928199
+ }
+ },
+ "Winning_Moves_1180_Aggravation_Board_Game": {
+ "asset_type": "FileBasedObject",
+ "id": "Winning_Moves_1180_Aggravation_Board_Game",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.24026667168150903,
+ -0.022909624880399396,
+ -0.12363138973375846
+ ],
+ [
+ 0.24072232831849097,
+ 0.023862375119600602,
+ 0.12396761026624152
+ ]
+ ],
+ "mass": 0.0047877134763389465,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Board Games",
+ "description": "Winning Moves 1180 Aggravation Board Game",
+ "nr_faces": 1022,
+ "nr_vertices": 562,
+ "surface_area": 0.2882808783393925,
+ "volume": 0.0047877134763389465
+ }
+ },
+ "Wishbone_Pencil_Case": {
+ "asset_type": "FileBasedObject",
+ "id": "Wishbone_Pencil_Case",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11194779482646101,
+ -0.04552102756148127,
+ -0.040896538864103174
+ ],
+ [
+ 0.109225205173539,
+ 0.047297972438518736,
+ 0.05365446113589682
+ ]
+ ],
+ "mass": 0.0010765173534771368,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bag",
+ "description": "Wishbone Pencil Case",
+ "nr_faces": 11502,
+ "nr_vertices": 6249,
+ "surface_area": 0.06707644085222073,
+ "volume": 0.0010765173534771368
+ }
+ },
+ "Womens_Angelfish_Boat_Shoe_in_Linen_Leopard_Sequin_NJDwosWNeZz": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Angelfish_Boat_Shoe_in_Linen_Leopard_Sequin_NJDwosWNeZz",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04753324102995465,
+ -0.11933203710600142,
+ -0.02129673069834861
+ ],
+ [
+ 0.041305758970045355,
+ 0.12306796289399857,
+ 0.054677269301651385
+ ]
+ ],
+ "mass": 0.000438536598045651,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Angelfish Boat Shoe in Linen / Leopard Sequin\nWomen's Angelfish Boat Shoe",
+ "nr_faces": 18204,
+ "nr_vertices": 9741,
+ "surface_area": 0.0856185510102574,
+ "volume": 0.000438536598045651
+ }
+ },
+ "Womens_Angelfish_Boat_Shoe_in_Linen_Oat": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Angelfish_Boat_Shoe_in_Linen_Oat",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05168090078319936,
+ -0.12086477278305106,
+ -0.021213315226943263
+ ],
+ [
+ 0.04625909921680064,
+ 0.12352722721694893,
+ 0.05592868477305674
+ ]
+ ],
+ "mass": 0.0004569811096855719,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Angelfish Boat Shoe in Linen Oat\nWomen's Angelfish Boat Shoe",
+ "nr_faces": 17926,
+ "nr_vertices": 9603,
+ "surface_area": 0.08562298516071717,
+ "volume": 0.0004569811096855719
+ }
+ },
+ "Womens_Audrey_Slip_On_Boat_Shoe_in_Graphite_Nubuck_xWVkCJ5vxZe": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Audrey_Slip_On_Boat_Shoe_in_Graphite_Nubuck_xWVkCJ5vxZe",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.043134751653564576,
+ -0.11821001108480025,
+ -0.0184269371963696
+ ],
+ [
+ 0.03997624834643542,
+ 0.13039398891519974,
+ 0.05241606280363041
+ ]
+ ],
+ "mass": 0.0003503992757907144,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Audrey Slip On Boat Shoe in Graphite Nubuck\nWomen's Audrey Slip On Boat Shoe",
+ "nr_faces": 16654,
+ "nr_vertices": 8947,
+ "surface_area": 0.08055976060365702,
+ "volume": 0.0003503992757907144
+ }
+ },
+ "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.115216758889307,
+ -0.049349121047798775,
+ -0.023470525796322608
+ ],
+ [
+ 0.129281241110693,
+ 0.04577587895220123,
+ 0.050234474203677396
+ ]
+ ],
+ "mass": 0.0004659656765440565,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Authentic Original Boat Shoe in Classic Brown Leather\nWomen's Authentic Original Boat Shoe",
+ "nr_faces": 19084,
+ "nr_vertices": 10345,
+ "surface_area": 0.08720060651797443,
+ "volume": 0.0004659656765440565
+ }
+ },
+ "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_48Nh7VuMwW6": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_48Nh7VuMwW6",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.050044132741174904,
+ -0.11896580931041673,
+ -0.023177348612320382
+ ],
+ [
+ 0.047297867258825094,
+ 0.12631119068958327,
+ 0.05111065138767962
+ ]
+ ],
+ "mass": 0.0004423107158199246,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Authentic Original Boat Shoe in Classic Brown Leather\nWomen's Authentic Original Boat Shoe",
+ "nr_faces": 18644,
+ "nr_vertices": 10287,
+ "surface_area": 0.0907253159588744,
+ "volume": 0.0004423107158199246
+ }
+ },
+ "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_cJSCWiH7QmB": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_cJSCWiH7QmB",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04348842814313559,
+ -0.11757487713695074,
+ -0.02297741834816472
+ ],
+ [
+ 0.04504857185686441,
+ 0.12888112286304926,
+ 0.05037258165183528
+ ]
+ ],
+ "mass": 0.0004566706484557203,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Authentic Original Boat Shoe in Classic Brown Leather\nWomen's Authentic Original Boat Shoe",
+ "nr_faces": 19216,
+ "nr_vertices": 10411,
+ "surface_area": 0.08844189735002425,
+ "volume": 0.0004566706484557203
+ }
+ },
+ "Womens_Authentic_Original_Boat_Shoe_in_Navy_Deerskin_50lWJaLWG8R": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Authentic_Original_Boat_Shoe_in_Navy_Deerskin_50lWJaLWG8R",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12244030389470945,
+ -0.05114421280304126,
+ -0.0241779885912285
+ ],
+ [
+ 0.13653769610529057,
+ 0.04581778719695874,
+ 0.0559000114087715
+ ]
+ ],
+ "mass": 0.0004891831917407598,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Authentic Original Boat Shoe in Navy Deerskin\nWomen's Authentic Original Boat Shoe",
+ "nr_faces": 18998,
+ "nr_vertices": 10473,
+ "surface_area": 0.09932757601704545,
+ "volume": 0.0004891831917407598
+ }
+ },
+ "Womens_Betty_Chukka_Boot_in_Grey_Jersey_Sequin": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Betty_Chukka_Boot_in_Grey_Jersey_Sequin",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.048980919810666816,
+ -0.12464241933621205,
+ -0.030759902026033924
+ ],
+ [
+ 0.042827080189333185,
+ 0.12497658066378796,
+ 0.08853309797396607
+ ]
+ ],
+ "mass": 0.0006915276342969397,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Betty Chukka Boot in Grey Jersey Sequin\nWomen's Betty Chukka Boot",
+ "nr_faces": 18206,
+ "nr_vertices": 9825,
+ "surface_area": 0.10490145521615825,
+ "volume": 0.0006915276342969397
+ }
+ },
+ "Womens_Betty_Chukka_Boot_in_Navy_Jersey_Sequin_y0SsHk7dKUX": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Betty_Chukka_Boot_in_Navy_Jersey_Sequin_y0SsHk7dKUX",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04891662261623802,
+ -0.12458216139957916,
+ -0.031757742190848814
+ ],
+ [
+ 0.04141837738376198,
+ 0.12374783860042084,
+ 0.08041925780915118
+ ]
+ ],
+ "mass": 0.000724011807594363,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Betty Chukka Boot in Navy Jersey Sequin\nWomen's Betty Chukka Boot",
+ "nr_faces": 20268,
+ "nr_vertices": 11216,
+ "surface_area": 0.10394972865933118,
+ "volume": 0.000724011807594363
+ }
+ },
+ "Womens_Betty_Chukka_Boot_in_Navy_aEE8OqvMII4": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Betty_Chukka_Boot_in_Navy_aEE8OqvMII4",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.050199771268644416,
+ -0.12910529214320868,
+ -0.031589329056601285
+ ],
+ [
+ 0.042019228731355586,
+ 0.11879270785679133,
+ 0.08107567094339871
+ ]
+ ],
+ "mass": 0.0006018043352046328,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Betty Chukka Boot in Navy\nWomen's Betty Chukka Boot",
+ "nr_faces": 22772,
+ "nr_vertices": 12452,
+ "surface_area": 0.12329376227617421,
+ "volume": 0.0006018043352046328
+ }
+ },
+ "Womens_Betty_Chukka_Boot_in_Salt_Washed_Red_AL2YrOt9CRy": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Betty_Chukka_Boot_in_Salt_Washed_Red_AL2YrOt9CRy",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.049127522484140596,
+ -0.12153218741793248,
+ -0.030099555282593365
+ ],
+ [
+ 0.045366477515859406,
+ 0.12581881258206754,
+ 0.08245244471740663
+ ]
+ ],
+ "mass": 0.0006666051325558778,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Betty Chukka Boot in Salt Washed Red\nWomen's Betty Chukka Boot",
+ "nr_faces": 17996,
+ "nr_vertices": 9624,
+ "surface_area": 0.10569037203706445,
+ "volume": 0.0006666051325558778
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_JJ2pfEHTZG7": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_JJ2pfEHTZG7",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.055414729655351345,
+ -0.14637330520302996,
+ -0.025188254951683985
+ ],
+ [
+ 0.049700270344648655,
+ 0.14232269479697005,
+ 0.06400274504831602
+ ]
+ ],
+ "mass": 0.0006455907194561599,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in Brown Deerskin\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 25088,
+ "nr_vertices": 14358,
+ "surface_area": 0.13195465327733802,
+ "volume": 0.0006455907194561599
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_i1TgjjO0AKY": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_i1TgjjO0AKY",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05150974179776025,
+ -0.11741415509251672,
+ -0.024671534724537186
+ ],
+ [
+ 0.046790258202239754,
+ 0.13169184490748329,
+ 0.05754046527546282
+ ]
+ ],
+ "mass": 0.0005158651669374468,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in Brown Deerskin\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 20328,
+ "nr_vertices": 11047,
+ "surface_area": 0.08882339053389336,
+ "volume": 0.0005158651669374468
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_kqi81aojcOR": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_kqi81aojcOR",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12112170087596438,
+ -0.04323129298760789,
+ -0.024885506864703307
+ ],
+ [
+ 0.1286452991240356,
+ 0.04884670701239211,
+ 0.061514493135296694
+ ]
+ ],
+ "mass": 0.0005215412125759693,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in Linen / Natural Sparkle Suede\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 19938,
+ "nr_vertices": 10626,
+ "surface_area": 0.09109174942342592,
+ "volume": 0.0005215412125759693
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_w34KNQ41csH": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_w34KNQ41csH",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04932776831767976,
+ -0.12076279451257574,
+ -0.02530875363000094
+ ],
+ [
+ 0.04304923168232024,
+ 0.12885620548742427,
+ 0.05755424636999906
+ ]
+ ],
+ "mass": 0.0005413939221768113,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in Linen / Natural Sparkle Suede\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 17972,
+ "nr_vertices": 9599,
+ "surface_area": 0.09081107376954174,
+ "volume": 0.0005413939221768113
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.047197041395609846,
+ -0.11409066335947979,
+ -0.023078430617944852
+ ],
+ [
+ 0.046628958604390154,
+ 0.12935433664052023,
+ 0.05979456938205514
+ ]
+ ],
+ "mass": 0.0004934973074076982,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in Linen Oat\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 19904,
+ "nr_vertices": 12786,
+ "surface_area": 0.0864283912688467,
+ "volume": 0.0004934973074076982
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_IbrSyJdpT3h": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_IbrSyJdpT3h",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04739997482341015,
+ -0.11911555854310903,
+ -0.024997766667844288
+ ],
+ [
+ 0.04069202517658985,
+ 0.12807044145689098,
+ 0.054749233332155714
+ ]
+ ],
+ "mass": 0.0005636548264926533,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in Linen Oat\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 16578,
+ "nr_vertices": 8836,
+ "surface_area": 0.0835890882363776,
+ "volume": 0.0005636548264926533
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_niKJKeWsmxY": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_niKJKeWsmxY",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.12000757097643351,
+ -0.0442887518027705,
+ -0.02478207839288499
+ ],
+ [
+ 0.12735742902356648,
+ 0.0449472481972295,
+ 0.055566921607115016
+ ]
+ ],
+ "mass": 0.0005520890561460726,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in Linen Oat\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 16458,
+ "nr_vertices": 8758,
+ "surface_area": 0.08414243351595564,
+ "volume": 0.0005520890561460726
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Tan": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_Tan",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11960194053157508,
+ -0.04382738637186821,
+ -0.025097023110772967
+ ],
+ [
+ 0.1296900594684249,
+ 0.04610261362813178,
+ 0.06462697688922703
+ ]
+ ],
+ "mass": 0.0005533272853530444,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in Tan\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 21022,
+ "nr_vertices": 11185,
+ "surface_area": 0.08646234175557539,
+ "volume": 0.0005533272853530444
+ }
+ },
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_White_Tumbled_YG44xIePRHw": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Bluefish_2Eye_Boat_Shoe_in_White_Tumbled_YG44xIePRHw",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11925620275840461,
+ -0.041360807165398694,
+ -0.024876361879692662
+ ],
+ [
+ 0.13144179724159538,
+ 0.047408192834601307,
+ 0.06201763812030734
+ ]
+ ],
+ "mass": 0.0005089909751456091,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Women's Bluefish 2-Eye Boat Shoe in White Tumbled\nWomen's Bluefish 2-Eye Boat Shoe",
+ "nr_faces": 27864,
+ "nr_vertices": 16953,
+ "surface_area": 0.09037260488898596,
+ "volume": 0.0005089909751456091
+ }
+ },
+ "Womens_Canvas_Bahama_in_Black": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Canvas_Bahama_in_Black",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1144203224077617,
+ -0.04462174270083772,
+ -0.022772729022457618
+ ],
+ [
+ 0.1288306775922383,
+ 0.04263325729916228,
+ 0.05967827097754238
+ ]
+ ],
+ "mass": 0.00047707808383197996,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Canvas Bahama in Black\nWomen's Canvas Bahama",
+ "nr_faces": 15574,
+ "nr_vertices": 8293,
+ "surface_area": 0.0827997373464707,
+ "volume": 0.00047707808383197996
+ }
+ },
+ "Womens_Canvas_Bahama_in_Black_vnJULsDVyq5": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Canvas_Bahama_in_Black_vnJULsDVyq5",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04646163968631067,
+ -0.11273107518646208,
+ -0.023297404655391766
+ ],
+ [
+ 0.03968836031368934,
+ 0.1309549248135379,
+ 0.05428559534460824
+ ]
+ ],
+ "mass": 0.0005115765178682337,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Canvas Bahama in Black\nWomen's Canvas Bahama",
+ "nr_faces": 16170,
+ "nr_vertices": 8680,
+ "surface_area": 0.08104682464884386,
+ "volume": 0.0005115765178682337
+ }
+ },
+ "Womens_Canvas_Bahama_in_White_4UyOhP6rYGO": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Canvas_Bahama_in_White_4UyOhP6rYGO",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04748964965132109,
+ -0.11200488161410427,
+ -0.022570204631740472
+ ],
+ [
+ 0.04256435034867891,
+ 0.13278011838589573,
+ 0.05742779536825953
+ ]
+ ],
+ "mass": 0.0004999778451116976,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Canvas Bahama in White\nWomen's Canvas Bahama",
+ "nr_faces": 12688,
+ "nr_vertices": 6862,
+ "surface_area": 0.08177423928527192,
+ "volume": 0.0004999778451116976
+ }
+ },
+ "Womens_Canvas_Bahama_in_White_UfZPHGQpvz0": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Canvas_Bahama_in_White_UfZPHGQpvz0",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1110284695502784,
+ -0.04599809733269794,
+ -0.023003891583148847
+ ],
+ [
+ 0.1330895304497216,
+ 0.04183890266730206,
+ 0.057210108416851146
+ ]
+ ],
+ "mass": 0.0005204252639121671,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Canvas Bahama in White\nWomen's Canvas Bahama",
+ "nr_faces": 13010,
+ "nr_vertices": 6920,
+ "surface_area": 0.08071105972043531,
+ "volume": 0.0005204252639121671
+ }
+ },
+ "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_8LigQYwf4gr": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_8LigQYwf4gr",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11722542167975243,
+ -0.04719309390827863,
+ -0.022427672460855096
+ ],
+ [
+ 0.12995857832024757,
+ 0.04412690609172137,
+ 0.052140327539144896
+ ]
+ ],
+ "mass": 0.00044275481099255817,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Cloud Logo Authentic Original Boat Shoe in Black Supersoft\nWomen's Cloud Logo Authentic Original Boat Shoe",
+ "nr_faces": 26776,
+ "nr_vertices": 14939,
+ "surface_area": 0.08750783059152696,
+ "volume": 0.00044275481099255817
+ }
+ },
+ "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_cZR022qFI4k": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_cZR022qFI4k",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0492808629114108,
+ -0.11938217795121886,
+ -0.02262309143847203
+ ],
+ [
+ 0.0445081370885892,
+ 0.12867982204878115,
+ 0.052207908561527974
+ ]
+ ],
+ "mass": 0.0004309669021207656,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Cloud Logo Authentic Original Boat Shoe in Black Supersoft\nWomen's Cloud Logo Authentic Original Boat Shoe",
+ "nr_faces": 23766,
+ "nr_vertices": 12949,
+ "surface_area": 0.0916785187827094,
+ "volume": 0.0004309669021207656
+ }
+ },
+ "Womens_Hikerfish_Boot_in_Black_Leopard_bVSNY1Le1sm": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Hikerfish_Boot_in_Black_Leopard_bVSNY1Le1sm",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1364660198832231,
+ -0.046277091441504895,
+ -0.0497626879148468
+ ],
+ [
+ 0.1115969801167769,
+ 0.044494908558495104,
+ 0.1370163120851532
+ ]
+ ],
+ "mass": 0.0010547704741944446,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Hikerfish Boot in Black / Leopard\nWomen's Hikerfish Boot",
+ "nr_faces": 27230,
+ "nr_vertices": 14795,
+ "surface_area": 0.1373845320810885,
+ "volume": 0.0010547704741944446
+ }
+ },
+ "Womens_Hikerfish_Boot_in_Black_Leopard_ridcCWsv8rW": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Hikerfish_Boot_in_Black_Leopard_ridcCWsv8rW",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0628296479434722,
+ -0.1412708626171102,
+ -0.05417818025720574
+ ],
+ [
+ 0.0524153520565278,
+ 0.10306613738288982,
+ 0.13365781974279425
+ ]
+ ],
+ "mass": 0.0012365836709977327,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Hikerfish Boot in Black / Leopard\nWomen's Hikerfish Boot",
+ "nr_faces": 24584,
+ "nr_vertices": 13347,
+ "surface_area": 0.1244541861501952,
+ "volume": 0.0012365836709977327
+ }
+ },
+ "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_QktIyAkonrU": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_QktIyAkonrU",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.1458643215172169,
+ -0.04572508100659876,
+ -0.05617758405102744
+ ],
+ [
+ 0.10306567848278311,
+ 0.04398591899340124,
+ 0.13633341594897255
+ ]
+ ],
+ "mass": 0.0012951368230805418,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Hikerfish Boot in Linen Leather / Sparkle Suede\nWomen's Hikerfish Boot",
+ "nr_faces": 20600,
+ "nr_vertices": 11284,
+ "surface_area": 0.13060205391681287,
+ "volume": 0.0012951368230805418
+ }
+ },
+ "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_imlP8VkwqIH": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_imlP8VkwqIH",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.044608779755532346,
+ -0.13826317707992639,
+ -0.04968677134934741
+ ],
+ [
+ 0.04584422024446766,
+ 0.1102438229200736,
+ 0.1434652286506526
+ ]
+ ],
+ "mass": 0.001074412065486256,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Hikerfish Boot in Linen Leather / Sparkle Suede\nWomen's Hikerfish Boot",
+ "nr_faces": 20658,
+ "nr_vertices": 11291,
+ "surface_area": 0.13791868145305347,
+ "volume": 0.001074412065486256
+ }
+ },
+ "Womens_Multi_13": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Multi_13",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.03080309296851035,
+ -0.03079008807897526,
+ -0.05301748134874599
+ ],
+ [
+ 0.03084590703148965,
+ 0.030796911921024742,
+ 0.06019551865125401
+ ]
+ ],
+ "mass": 0.0002971400228161976,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Women's Multi 1-3",
+ "nr_faces": 10530,
+ "nr_vertices": 5397,
+ "surface_area": 0.026324628494870467,
+ "volume": 0.0002971400228161976
+ }
+ },
+ "Womens_Sequin_Bahama_in_White_Sequin_V9K1hf24Oxe": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Sequin_Bahama_in_White_Sequin_V9K1hf24Oxe",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11445405225182059,
+ -0.04478517693638514,
+ -0.02384933349510852
+ ],
+ [
+ 0.1346029477481794,
+ 0.04351882306361486,
+ 0.06309966650489149
+ ]
+ ],
+ "mass": 0.000503349436944271,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Sequin Bahama in White Sequin\nWomen's Sequin Bahama",
+ "nr_faces": 13638,
+ "nr_vertices": 7420,
+ "surface_area": 0.08823692057372234,
+ "volume": 0.000503349436944271
+ }
+ },
+ "Womens_Sequin_Bahama_in_White_Sequin_XoR8xTlxj1g": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Sequin_Bahama_in_White_Sequin_XoR8xTlxj1g",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04823617657826293,
+ -0.12294099565269438,
+ -0.0326330727418658
+ ],
+ [
+ 0.04313082342173707,
+ 0.12176300434730562,
+ 0.08084292725813422
+ ]
+ ],
+ "mass": 0.0007516766367139925,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Sequin Bahama in White Sequin\nWomen's Sequin Bahama",
+ "nr_faces": 23926,
+ "nr_vertices": 13343,
+ "surface_area": 0.09920815554796558,
+ "volume": 0.0007516766367139925
+ }
+ },
+ "Womens_Sequin_Bahama_in_White_Sequin_yGVsSA4tOwJ": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Sequin_Bahama_in_White_Sequin_yGVsSA4tOwJ",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05191939036797749,
+ -0.11293577858713835,
+ -0.024296823212317135
+ ],
+ [
+ 0.04939360963202251,
+ 0.13372322141286164,
+ 0.08189017678768287
+ ]
+ ],
+ "mass": 0.000516248581270237,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Sequin Bahama in White Sequin\nWomen's Sequin Bahama",
+ "nr_faces": 16678,
+ "nr_vertices": 9241,
+ "surface_area": 0.09335018536175876,
+ "volume": 0.000516248581270237
+ }
+ },
+ "Womens_Sparkle_Suede_Angelfish_in_Grey_Sparkle_Suede_Silver": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Sparkle_Suede_Angelfish_in_Grey_Sparkle_Suede_Silver",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05321991824240005,
+ -0.1171096113025517,
+ -0.02220512240995468
+ ],
+ [
+ 0.05034208175759995,
+ 0.1219803886974483,
+ 0.055214877590045314
+ ]
+ ],
+ "mass": 0.00045730494683765647,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Sparkle Suede Angelfish in Grey Sparkle Suede / Silver\nWomen's Sparkle Suede Angelfish",
+ "nr_faces": 18986,
+ "nr_vertices": 10144,
+ "surface_area": 0.08370794627954456,
+ "volume": 0.00045730494683765647
+ }
+ },
+ "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_tYrIBLMhSTN": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_tYrIBLMhSTN",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04962771088286089,
+ -0.11392553696759011,
+ -0.024908999623983227
+ ],
+ [
+ 0.04458628911713911,
+ 0.13464646303240987,
+ 0.06397300037601678
+ ]
+ ],
+ "mass": 0.0005025852548336538,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Sparkle Suede Bahama in Silver Sparkle Suede / Grey Patent\nWomen's Sparkle Suede Bahama",
+ "nr_faces": 14916,
+ "nr_vertices": 8074,
+ "surface_area": 0.09121790078125093,
+ "volume": 0.0005025852548336538
+ }
+ },
+ "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_x9rclU7EJXx": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_x9rclU7EJXx",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11224117717833164,
+ -0.046913163563724755,
+ -0.02487082471864281
+ ],
+ [
+ 0.13616882282166837,
+ 0.042520836436275244,
+ 0.06023217528135719
+ ]
+ ],
+ "mass": 0.0005276394739378402,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Sparkle Suede Bahama in Silver Sparkle Suede / Grey Patent\nWomen's Sparkle Suede Bahama",
+ "nr_faces": 13136,
+ "nr_vertices": 7093,
+ "surface_area": 0.08767083424923552,
+ "volume": 0.0005276394739378402
+ }
+ },
+ "Womens_Suede_Bahama_in_Graphite_Suede_cUAjIMhWSO9": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Suede_Bahama_in_Graphite_Suede_cUAjIMhWSO9",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11667460366475862,
+ -0.046724338572115075,
+ -0.021502841270976725
+ ],
+ [
+ 0.13836839633524137,
+ 0.04244866142788493,
+ 0.06298615872902327
+ ]
+ ],
+ "mass": 0.0004824405814501702,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Suede Bahama in Graphite Suede\nWomen's Suede Bahama",
+ "nr_faces": 12208,
+ "nr_vertices": 6555,
+ "surface_area": 0.0873968018195703,
+ "volume": 0.0004824405814501702
+ }
+ },
+ "Womens_Suede_Bahama_in_Graphite_Suede_p1KUwoWbw7R": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Suede_Bahama_in_Graphite_Suede_p1KUwoWbw7R",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059711405993711615,
+ -0.14808482903901768,
+ -0.01879312015893707
+ ],
+ [
+ 0.05864459400628838,
+ 0.14659517096098232,
+ 0.060782879841062926
+ ]
+ ],
+ "mass": 0.0006317352446927721,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Suede Bahama in Graphite Suede\nWomen's Suede Bahama",
+ "nr_faces": 10528,
+ "nr_vertices": 5668,
+ "surface_area": 0.08588722118550808,
+ "volume": 0.0006317352446927721
+ }
+ },
+ "Womens_Suede_Bahama_in_Graphite_Suede_t22AJSRjBOX": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Suede_Bahama_in_Graphite_Suede_t22AJSRjBOX",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.046347991213336145,
+ -0.12194434419278233,
+ -0.02227890541667035
+ ],
+ [
+ 0.041400008786663854,
+ 0.13374365580721767,
+ 0.05010209458332965
+ ]
+ ],
+ "mass": 0.0004936618874386391,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Suede Bahama in Graphite Suede\nWomen's Suede Bahama",
+ "nr_faces": 18034,
+ "nr_vertices": 10502,
+ "surface_area": 0.09558193452365113,
+ "volume": 0.0004936618874386391
+ }
+ },
+ "Womens_Teva_Capistrano_Bootie": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Teva_Capistrano_Bootie",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05734186796365322,
+ -0.16270003685736406,
+ -0.05325692773423421
+ ],
+ [
+ 0.04402613203634678,
+ 0.12776996314263595,
+ 0.13795807226576579
+ ]
+ ],
+ "mass": 0.0015647267758958398,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Teva Capistrano Bootie",
+ "nr_faces": 19818,
+ "nr_vertices": 10484,
+ "surface_area": 0.13783185274562637,
+ "volume": 0.0015647267758958398
+ }
+ },
+ "Womens_Teva_Capistrano_Bootie_ldjRT9yZ5Ht": {
+ "asset_type": "FileBasedObject",
+ "id": "Womens_Teva_Capistrano_Bootie_ldjRT9yZ5Ht",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05444267947486159,
+ -0.16324717924138765,
+ -0.053817515305755785
+ ],
+ [
+ 0.04464732052513841,
+ 0.12940482075861237,
+ 0.1373514846942442
+ ]
+ ],
+ "mass": 0.0015925515294333249,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "Women's Teva Capistrano Bootie",
+ "nr_faces": 20664,
+ "nr_vertices": 10915,
+ "surface_area": 0.1364538806247858,
+ "volume": 0.0015925515294333249
+ }
+ },
+ "Wooden_ABC_123_Blocks_50_pack": {
+ "asset_type": "FileBasedObject",
+ "id": "Wooden_ABC_123_Blocks_50_pack",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.11439469268984687,
+ -0.03135370581066564,
+ -0.056150506409626426
+ ],
+ [
+ 0.09948630731015314,
+ 0.031289294189334356,
+ 0.06700549359037358
+ ]
+ ],
+ "mass": 0.0013717785756982893,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Toys",
+ "description": "Wooden ABC 123 Blocks - 50 pack",
+ "nr_faces": 16908,
+ "nr_vertices": 8708,
+ "surface_area": 0.08856663179830497,
+ "volume": 0.0013717785756982893
+ }
+ },
+ "Wrigley_Orbit_Mint_Variety_18_Count": {
+ "asset_type": "FileBasedObject",
+ "id": "Wrigley_Orbit_Mint_Variety_18_Count",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0971366200074548,
+ -0.025296157688809953,
+ -0.11438414102491057
+ ],
+ [
+ 0.0974373799925452,
+ 0.025720842311190047,
+ 0.11462885897508944
+ ]
+ ],
+ "mass": 0.0020922213556522932,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Wrigley Orbit Mint Variety 18 Count",
+ "nr_faces": 2634,
+ "nr_vertices": 1383,
+ "surface_area": 0.12415591364351818,
+ "volume": 0.0020922213556522932
+ }
+ },
+ "Xyli_Pure_Xylitol": {
+ "asset_type": "FileBasedObject",
+ "id": "Xyli_Pure_Xylitol",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.04856475607526808,
+ -0.04744242074605128,
+ -0.07414985449202456
+ ],
+ [
+ 0.04840924392473192,
+ 0.047541579253948724,
+ 0.07298214550797544
+ ]
+ ],
+ "mass": 0.0010096184328772838,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Bottles and Cans and Cups",
+ "description": "Xyli Pure Xylitol",
+ "nr_faces": 5536,
+ "nr_vertices": 2874,
+ "surface_area": 0.05575055593447816,
+ "volume": 0.0010096184328772838
+ }
+ },
+ "YumYum_D3_Liquid": {
+ "asset_type": "FileBasedObject",
+ "id": "YumYum_D3_Liquid",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.016796215277677724,
+ -0.017333338218932588,
+ -0.04940784039891261
+ ],
+ [
+ 0.016499784722322275,
+ 0.01709366178106741,
+ 0.05066615960108739
+ ]
+ ],
+ "mass": 9.674798237173416e-05,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Consumer Goods",
+ "description": "Yum-Yum D3 Liquid\nJarrow Formulas Yum-Yum D3 Liquid delivers 200 IU of vitamin D3 (cholecalciferol) per drop. Vitamin D3 is essential for children (and adults) in promoting healthy bones, teeth, brain and immune system.* WARNING: Breast-fed and partially breast-fed infants should not consume more than 400 IU (international units) of vitamin D per day. Limit intake of this product to 2 drops per day in infants. *These statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.",
+ "nr_faces": 3790,
+ "nr_vertices": 2041,
+ "surface_area": 0.013702381434139998,
+ "volume": 9.674798237173416e-05
+ }
+ },
+ "ZX700_lYiwcTIekXk": {
+ "asset_type": "FileBasedObject",
+ "id": "ZX700_lYiwcTIekXk",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.059010689542227754,
+ -0.15149723956065228,
+ -0.041685521164611945
+ ],
+ [
+ 0.05154831045777225,
+ 0.1422617604393477,
+ 0.09550347883538805
+ ]
+ ],
+ "mass": 0.0012850594776253042,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ZX700",
+ "nr_faces": 29206,
+ "nr_vertices": 15704,
+ "surface_area": 0.13584862689275887,
+ "volume": 0.0012850594776253042
+ }
+ },
+ "ZX700_mf9Pc06uL06": {
+ "asset_type": "FileBasedObject",
+ "id": "ZX700_mf9Pc06uL06",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.058542437991901,
+ -0.1634929470981264,
+ -0.04227410384474295
+ ],
+ [
+ 0.051194562008099,
+ 0.1293330529018736,
+ 0.08965589615525704
+ ]
+ ],
+ "mass": 0.0010977728108701856,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ZX700",
+ "nr_faces": 34414,
+ "nr_vertices": 18801,
+ "surface_area": 0.16907304227960998,
+ "volume": 0.0010977728108701856
+ }
+ },
+ "ZX700_mzGbdP3u6JB": {
+ "asset_type": "FileBasedObject",
+ "id": "ZX700_mzGbdP3u6JB",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.057398411995069946,
+ -0.15109960130367409,
+ -0.04047953111073217
+ ],
+ [
+ 0.050984588004930054,
+ 0.14066939869632591,
+ 0.09085246888926782
+ ]
+ ],
+ "mass": 0.001302407986510583,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ZX700",
+ "nr_faces": 32970,
+ "nr_vertices": 17815,
+ "surface_area": 0.1302158127471413,
+ "volume": 0.001302407986510583
+ }
+ },
+ "ZigKick_Hoops": {
+ "asset_type": "FileBasedObject",
+ "id": "ZigKick_Hoops",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06292946521819419,
+ -0.13433862566495589,
+ -0.04859671479919998
+ ],
+ [
+ 0.05467253478180581,
+ 0.1448193743350441,
+ 0.11214528520080003
+ ]
+ ],
+ "mass": 0.00150815543593658,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "ZigKick Hoops\nFootwear",
+ "nr_faces": 26360,
+ "nr_vertices": 15055,
+ "surface_area": 0.14444700930844626,
+ "volume": 0.00150815543593658
+ }
+ },
+ "adiZero_Slide_2_SC": {
+ "asset_type": "FileBasedObject",
+ "id": "adiZero_Slide_2_SC",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.07066631525524646,
+ -0.1356208082782409,
+ -0.0193914580800591
+ ],
+ [
+ 0.08238168474475355,
+ 0.15552919172175908,
+ 0.06682354191994092
+ ]
+ ],
+ "mass": 0.0006016209703960026,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "adiZero Slide 2 SC\nFW-SLIDES",
+ "nr_faces": 13138,
+ "nr_vertices": 6951,
+ "surface_area": 0.09894142520971269,
+ "volume": 0.0006016209703960026
+ }
+ },
+ "adistar_boost_m": {
+ "asset_type": "FileBasedObject",
+ "id": "adistar_boost_m",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.06058142101538301,
+ -0.16543064195966567,
+ -0.03919081498710658
+ ],
+ [
+ 0.05198757898461699,
+ 0.13926135804033432,
+ 0.0841321850128934
+ ]
+ ],
+ "mass": 0.0011355451619344107,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "adistar boost m\nFW-SHOES",
+ "nr_faces": 32918,
+ "nr_vertices": 18299,
+ "surface_area": 0.16240083007924963,
+ "volume": 0.0011355451619344107
+ }
+ },
+ "adizero_5Tool_25": {
+ "asset_type": "FileBasedObject",
+ "id": "adizero_5Tool_25",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.05589463503674004,
+ -0.15376306547037527,
+ -0.055071268654697046
+ ],
+ [
+ 0.04522336496325997,
+ 0.13621593452962474,
+ 0.09926473134530295
+ ]
+ ],
+ "mass": 0.0009252020180352738,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "adizero 5-Tool 2.5",
+ "nr_faces": 27160,
+ "nr_vertices": 15833,
+ "surface_area": 0.15396160217170865,
+ "volume": 0.0009252020180352738
+ }
+ },
+ "adizero_F50_TRX_FG_LEA": {
+ "asset_type": "FileBasedObject",
+ "id": "adizero_F50_TRX_FG_LEA",
+ "kwargs": {
+ "bounds": [
+ [
+ -0.0511443727825661,
+ -0.14749930593386468,
+ -0.040754874056736834
+ ],
+ [
+ 0.046398627217433895,
+ 0.13400769406613533,
+ 0.06843512594326318
+ ]
+ ],
+ "mass": 0.0007204372347894012,
+ "render_filename": "{asset_dir}/visual_geometry.obj",
+ "simulation_filename": "{asset_dir}/object.urdf"
+ },
+ "license": "CC BY-SA 4.0",
+ "metadata": {
+ "category": "Shoe",
+ "description": "adizero F50 TRX FG LEA",
+ "nr_faces": 23144,
+ "nr_vertices": 13170,
+ "surface_area": 0.13075197408403355,
+ "volume": 0.0007204372347894012
+ }
+ }
+ },
+ "data_dir": "gs://kubric-public/assets/GSO",
+ "name": "GSO",
+ "version": "1.0"
+}
\ No newline at end of file
diff --git a/eq-kubric/3d_data/GSO_dict_all.json b/eq-kubric/3d_data/GSO_dict_all.json
new file mode 100644
index 0000000000000000000000000000000000000000..5ad2dffaead9e91edde7a8915c9360e633628889
--- /dev/null
+++ b/eq-kubric/3d_data/GSO_dict_all.json
@@ -0,0 +1,1035 @@
+{
+ "11pro_SL_TRX_FG": "11pro_SL_TRX_FG",
+ "2_of_Jenga_Classic_Game": "2_of_Jenga_Classic_Game",
+ "30_CONSTRUCTION_SET": "30_CONSTRUCTION_SET",
+ "3D_Dollhouse_Happy_Brother": "3D_Dollhouse_Happy_Brother",
+ "3D_Dollhouse_Lamp": "3D_Dollhouse_Lamp",
+ "3D_Dollhouse_Refrigerator": "green doll house wooden refrigerator",
+ "3D_Dollhouse_Sink": "3D_Dollhouse_Sink",
+ "3D_Dollhouse_Sofa": "purple doll house wooden sofa",
+ "3D_Dollhouse_Swing": "3D_Dollhouse_Swing",
+ "3D_Dollhouse_TablePurple": "3D_Dollhouse_TablePurple",
+ "3M_Antislip_Surfacing_Light_Duty_White": "3M_Antislip_Surfacing_Light_Duty_White",
+ "3M_Vinyl_Tape_Green_1_x_36_yd": "3M_Vinyl_Tape_Green_1_x_36_yd",
+ "45oz_RAMEKIN_ASST_DEEP_COLORS": "45oz_RAMEKIN_ASST_DEEP_COLORS",
+ "50_BLOCKS": "50_BLOCKS",
+ "5_HTP": "5_HTP",
+ "60_CONSTRUCTION_SET": "60_CONSTRUCTION_SET",
+ "ACE_Coffee_Mug_Kristen_16_oz_cup": "red coffee mug",
+ "ALPHABET_AZ_GRADIENT": "ALPHABET_AZ_GRADIENT",
+ "ALPHABET_AZ_GRADIENT_WQb1ufEycSj": "ALPHABET_AZ_GRADIENT_WQb1ufEycSj",
+ "AMBERLIGHT_UP_W": "AMBERLIGHT_UP_W",
+ "ASICS_GEL1140V_WhiteBlackSilver": "ASICS_GEL1140V_WhiteBlackSilver",
+ "ASICS_GEL1140V_WhiteRoyalSilver": "ASICS_GEL1140V_WhiteRoyalSilver",
+ "ASICS_GELAce_Pro_Pearl_WhitePink": "ASICS_GELAce_Pro_Pearl_WhitePink",
+ "ASICS_GELBlur33_20_GS_BlackWhiteSafety_Orange": "ASICS_GELBlur33_20_GS_BlackWhiteSafety_Orange",
+ "ASICS_GELBlur33_20_GS_Flash_YellowHot_PunchSilver": "ASICS_GELBlur33_20_GS_Flash_YellowHot_PunchSilver",
+ "ASICS_GELChallenger_9_Royal_BlueWhiteBlack": "ASICS_GELChallenger_9_Royal_BlueWhiteBlack",
+ "ASICS_GELDirt_Dog_4_SunFlameBlack": "ASICS_GELDirt_Dog_4_SunFlameBlack",
+ "ASICS_GELLinksmaster_WhiteCoffeeSand": "ASICS_GELLinksmaster_WhiteCoffeeSand",
+ "ASICS_GELLinksmaster_WhiteRasberryGunmetal": "ASICS_GELLinksmaster_WhiteRasberryGunmetal",
+ "ASICS_GELLinksmaster_WhiteSilverCarolina_Blue": "ASICS_GELLinksmaster_WhiteSilverCarolina_Blue",
+ "ASICS_GELResolution_5_Flash_YellowBlackSilver": "ASICS_GELResolution_5_Flash_YellowBlackSilver",
+ "ASICS_GELTour_Lyte_WhiteOrchidSilver": "ASICS_GELTour_Lyte_WhiteOrchidSilver",
+ "ASICS_HyperRocketgirl_SP_5_WhiteMalibu_BlueBlack": "ASICS_HyperRocketgirl_SP_5_WhiteMalibu_BlueBlack",
+ "ASSORTED_VEGETABLE_SET": "ASSORTED_VEGETABLE_SET",
+ "Adrenaline_GTS_13_Color_DrkDenimWhtBachlorBttnSlvr_Size_50_yfK40TNjq0V": "Adrenaline_GTS_13_Color_DrkDenimWhtBachlorBttnSlvr_Size_50_yfK40TNjq0V",
+ "Adrenaline_GTS_13_Color_WhtObsdianBlckOlmpcSlvr_Size_70": "Adrenaline_GTS_13_Color_WhtObsdianBlckOlmpcSlvr_Size_70",
+ "Air_Hogs_Wind_Flyers_Set_Airplane_Red": "Air_Hogs_Wind_Flyers_Set_Airplane_Red",
+ "AllergenFree_JarroDophilus": "AllergenFree_JarroDophilus",
+ "Android_Figure_Chrome": "Android_Figure_Chrome",
+ "Android_Figure_Orange": "Android_Figure_Orange",
+ "Android_Figure_Panda": "Android_Figure_Panda",
+ "Android_Lego": "Android_Lego",
+ "Animal_Crossing_New_Leaf_Nintendo_3DS_Game": "Animal_Crossing_New_Leaf_Nintendo_3DS_Game",
+ "Animal_Planet_Foam_2Headed_Dragon": "Animal_Planet_Foam_2Headed_Dragon",
+ "Apples_to_Apples_Kids_Edition": "Apples_to_Apples_Kids_Edition",
+ "Arm_Hammer_Diaper_Pail_Refills_12_Pack_MFWkmoweejt": "Arm_Hammer_Diaper_Pail_Refills_12_Pack_MFWkmoweejt",
+ "Aroma_Stainless_Steel_Milk_Frother_2_Cup": "stainless steel milk frother",
+ "Asus_80211ac_DualBand_Gigabit_Wireless_Router_RTAC68R": "Asus_80211ac_DualBand_Gigabit_Wireless_Router_RTAC68R",
+ "Asus_M5A78LMUSB3_Motherboard_Micro_ATX_Socket_AM3": "Asus_M5A78LMUSB3_Motherboard_Micro_ATX_Socket_AM3",
+ "Asus_M5A99FX_PRO_R20_Motherboard_ATX_Socket_AM3": "Asus_M5A99FX_PRO_R20_Motherboard_ATX_Socket_AM3",
+ "Asus_Sabertooth_990FX_20_Motherboard_ATX_Socket_AM3": "Asus_Sabertooth_990FX_20_Motherboard_ATX_Socket_AM3",
+ "Asus_Sabertooth_Z97_MARK_1_Motherboard_ATX_LGA1150_Socket": "Asus_Sabertooth_Z97_MARK_1_Motherboard_ATX_LGA1150_Socket",
+ "Asus_X99Deluxe_Motherboard_ATX_LGA2011v3_Socket": "Asus_X99Deluxe_Motherboard_ATX_LGA2011v3_Socket",
+ "Asus_Z87PRO_Motherboard_ATX_LGA1150_Socket": "Asus_Z87PRO_Motherboard_ATX_LGA1150_Socket",
+ "Asus_Z97AR_LGA_1150_Intel_ATX_Motherboard": "Asus_Z97AR_LGA_1150_Intel_ATX_Motherboard",
+ "Asus_Z97IPLUS_Motherboard_Mini_ITX_LGA1150_Socket": "Asus_Z97IPLUS_Motherboard_Mini_ITX_LGA1150_Socket",
+ "Avengers_Gamma_Green_Smash_Fists": "Avengers_Gamma_Green_Smash_Fists",
+ "Avengers_Thor_PLlrpYniaeB": "Avengers_Thor_PLlrpYniaeB",
+ "Azure_Snake_Tieks_Leather_Snake_Print_Ballet_Flats": "Azure_Snake_Tieks_Leather_Snake_Print_Ballet_Flats",
+ "BABY_CAR": "BABY_CAR",
+ "BAGEL_WITH_CHEESE": "BAGEL_WITH_CHEESE",
+ "BAKING_UTENSILS": "BAKING_UTENSILS",
+ "BALANCING_CACTUS": "BALANCING_CACTUS",
+ "BATHROOM_CLASSIC": "BATHROOM_CLASSIC",
+ "BATHROOM_FURNITURE_SET_1": "BATHROOM_FURNITURE_SET_1",
+ "BEDROOM_CLASSIC": "BEDROOM_CLASSIC",
+ "BEDROOM_CLASSIC_Gi22DjScTVS": "BEDROOM_CLASSIC_Gi22DjScTVS",
+ "BEDROOM_NEO": "BEDROOM_NEO",
+ "BIA_Cordon_Bleu_White_Porcelain_Utensil_Holder_900028": "BIA_Cordon_Bleu_White_Porcelain_Utensil_Holder_900028",
+ "BIA_Porcelain_Ramekin_With_Glazed_Rim_35_45_oz_cup": "BIA_Porcelain_Ramekin_With_Glazed_Rim_35_45_oz_cup",
+ "BIRD_RATTLE": "BIRD_RATTLE",
+ "BRAILLE_ALPHABET_AZ": "BRAILLE_ALPHABET_AZ",
+ "BREAKFAST_MENU": "BREAKFAST_MENU",
+ "BUILD_A_ROBOT": "BUILD_A_ROBOT",
+ "BUILD_A_ZOO": "BUILD_A_ZOO",
+ "BUNNY_RACER": "BUNNY_RACER",
+ "BUNNY_RATTLE": "BUNNY_RATTLE",
+ "Baby_Elements_Stacking_Cups": "Baby_Elements_Stacking_Cups",
+ "Balderdash_Game": "Balderdash_Game",
+ "Beetle_Adventure_Racing_Nintendo_64": "Beetle_Adventure_Racing_Nintendo_64",
+ "Beta_Glucan": "Beta_Glucan",
+ "Beyonc_Life_is_But_a_Dream_DVD": "Beyonc_Life_is_But_a_Dream_DVD",
+ "Bifidus_Balance_FOS": "Bifidus_Balance_FOS",
+ "Big_Dot_Aqua_Pencil_Case": "Big_Dot_Aqua_Pencil_Case",
+ "Big_Dot_Pink_Pencil_Case": "Big_Dot_Pink_Pencil_Case",
+ "Big_O_Sponges_Assorted_Cellulose_12_pack": "Big_O_Sponges_Assorted_Cellulose_12_pack",
+ "BlackBlack_Nintendo_3DSXL": "BlackBlack_Nintendo_3DSXL",
+ "Black_Decker_CM2035B_12Cup_Thermal_Coffeemaker": "Black_Decker_CM2035B_12Cup_Thermal_Coffeemaker",
+ "Black_Decker_Stainless_Steel_Toaster_4_Slice": "stainless steel toaster",
+ "Black_Elderberry_Syrup_54_oz_Gaia_Herbs": "Black_Elderberry_Syrup_54_oz_Gaia_Herbs",
+ "Black_Forest_Fruit_Snacks_28_Pack_Grape": "Black_Forest_Fruit_Snacks_28_Pack_Grape",
+ "Black_Forest_Fruit_Snacks_Juicy_Filled_Centers_10_pouches_9_oz_total": "Black_Forest_Fruit_Snacks_Juicy_Filled_Centers_10_pouches_9_oz_total",
+ "Black_and_Decker_PBJ2000_FusionBlade_Blender_Jars": "Black_and_Decker_PBJ2000_FusionBlade_Blender_Jars",
+ "Black_and_Decker_TR3500SD_2Slice_Toaster": "Black_and_Decker_TR3500SD_2Slice_Toaster",
+ "Blackcurrant_Lutein": "Blackcurrant_Lutein",
+ "BlueBlack_Nintendo_3DSXL": "BlueBlack_Nintendo_3DSXL",
+ "Blue_Jasmine_Includes_Digital_Copy_UltraViolet_DVD": "Blue_Jasmine_Includes_Digital_Copy_UltraViolet_DVD",
+ "Borage_GLA240Gamma_Tocopherol": "Borage_GLA240Gamma_Tocopherol",
+ "Bradshaw_International_11642_7_Qt_MP_Plastic_Bowl": "Bradshaw_International_11642_7_Qt_MP_Plastic_Bowl",
+ "Breyer_Horse_Of_The_Year_2015": "Breyer_Horse_Of_The_Year_2015",
+ "Brisk_Iced_Tea_Lemon_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": "Brisk_Iced_Tea_Lemon_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+ "Brother_Ink_Cartridge_Magenta_LC75M": "Brother_Ink_Cartridge_Magenta_LC75M",
+ "Brother_LC_1053PKS_Ink_Cartridge_CyanMagentaYellow_1pack": "Brother_LC_1053PKS_Ink_Cartridge_CyanMagentaYellow_1pack",
+ "Brother_Printing_Cartridge_PC501": "Brother_Printing_Cartridge_PC501",
+ "CARSII": "CARSII",
+ "CAR_CARRIER_TRAIN": "CAR_CARRIER_TRAIN",
+ "CASTLE_BLOCKS": "CASTLE_BLOCKS",
+ "CHICKEN_NESTING": "CHICKEN_NESTING",
+ "CHICKEN_RACER": "CHICKEN_RACER",
+ "CHILDRENS_ROOM_NEO": "CHILDRENS_ROOM_NEO",
+ "CHILDREN_BEDROOM_CLASSIC": "CHILDREN_BEDROOM_CLASSIC",
+ "CITY_TAXI_POLICE_CAR": "CITY_TAXI_POLICE_CAR",
+ "CLIMACOOL_BOAT_BREEZE_IE6CyqSaDwN": "CLIMACOOL_BOAT_BREEZE_IE6CyqSaDwN",
+ "COAST_GUARD_BOAT": "COAST_GUARD_BOAT",
+ "CONE_SORTING": "CONE_SORTING",
+ "CONE_SORTING_kg5fbARBwts": "CONE_SORTING_kg5fbARBwts",
+ "CREATIVE_BLOCKS_35_MM": "CREATIVE_BLOCKS_35_MM",
+ "California_Navy_Tieks_Italian_Leather_Ballet_Flats": "California_Navy_Tieks_Italian_Leather_Ballet_Flats",
+ "Calphalon_Kitchen_Essentials_12_Cast_Iron_Fry_Pan_Black": "Calphalon_Kitchen_Essentials_12_Cast_Iron_Fry_Pan_Black",
+ "Canon_225226_Ink_Cartridges_BlackColor_Cyan_Magenta_Yellow_6_count": "Canon_225226_Ink_Cartridges_BlackColor_Cyan_Magenta_Yellow_6_count",
+ "Canon_Ink_Cartridge_Green_6": "Canon_Ink_Cartridge_Green_6",
+ "Canon_Pixma_Chromalife_100_Magenta_8": "Canon_Pixma_Chromalife_100_Magenta_8",
+ "Canon_Pixma_Ink_Cartridge_251_M": "Canon_Pixma_Ink_Cartridge_251_M",
+ "Canon_Pixma_Ink_Cartridge_8": "Canon_Pixma_Ink_Cartridge_8",
+ "Canon_Pixma_Ink_Cartridge_8_Green": "Canon_Pixma_Ink_Cartridge_8_Green",
+ "Canon_Pixma_Ink_Cartridge_8_Red": "Canon_Pixma_Ink_Cartridge_8_Red",
+ "Canon_Pixma_Ink_Cartridge_Cyan_251": "Canon_Pixma_Ink_Cartridge_Cyan_251",
+ "Cascadia_8_Color_AquariusHibscsBearingSeaBlk_Size_50": "Cascadia_8_Color_AquariusHibscsBearingSeaBlk_Size_50",
+ "Central_Garden_Flower_Pot_Goo_425": "Central_Garden_Flower_Pot_Goo_425",
+ "Chef_Style_Round_Cake_Pan_9_inch_pan": "Chef_Style_Round_Cake_Pan_9_inch_pan",
+ "Chefmate_8_Frypan": "black frypan",
+ "Chelsea_BlkHeelPMP_DwxLtZNxLZZ": "Chelsea_BlkHeelPMP_DwxLtZNxLZZ",
+ "Chelsea_lo_fl_rdheel_nQ0LPNF1oMw": "red high heel",
+ "Chelsea_lo_fl_rdheel_zAQrnhlEfw8": "Chelsea_lo_fl_rdheel_zAQrnhlEfw8",
+ "Circo_Fish_Toothbrush_Holder_14995988": "Circo_Fish_Toothbrush_Holder_14995988",
+ "ClimaCool_Aerate_2_W_Wide": "ClimaCool_Aerate_2_W_Wide",
+ "Clorox_Premium_Choice_Gloves_SM_1_pair": "Clorox_Premium_Choice_Gloves_SM_1_pair",
+ "Closetmaid_Premium_Fabric_Cube_Red": "Closetmaid_Premium_Fabric_Cube_Red",
+ "Clue_Board_Game_Classic_Edition": "Clue_Board_Game_Classic_Edition",
+ "CoQ10": "white drug bottle",
+ "CoQ10_BjTLbuRVt1t": "CoQ10_BjTLbuRVt1t",
+ "CoQ10_wSSVoxVppVD": "CoQ10_wSSVoxVppVD",
+ "Cole_Hardware_Antislip_Surfacing_Material_White": "Cole_Hardware_Antislip_Surfacing_Material_White",
+ "Cole_Hardware_Antislip_Surfacing_White_2_x_60": "Cole_Hardware_Antislip_Surfacing_White_2_x_60",
+ "Cole_Hardware_Bowl_Scirocco_YellowBlue": "Cole_Hardware_Bowl_Scirocco_YellowBlue",
+ "Cole_Hardware_Butter_Dish_Square_Red": "Cole_Hardware_Butter_Dish_Square_Red",
+ "Cole_Hardware_Deep_Bowl_Good_Earth_1075": "Cole_Hardware_Deep_Bowl_Good_Earth_1075",
+ "Cole_Hardware_Dishtowel_Blue": "Cole_Hardware_Dishtowel_Blue",
+ "Cole_Hardware_Dishtowel_BlueWhite": "Cole_Hardware_Dishtowel_BlueWhite",
+ "Cole_Hardware_Dishtowel_Multicolors": "Cole_Hardware_Dishtowel_Multicolors",
+ "Cole_Hardware_Dishtowel_Red": "Cole_Hardware_Dishtowel_Red",
+ "Cole_Hardware_Dishtowel_Stripe": "Cole_Hardware_Dishtowel_Stripe",
+ "Cole_Hardware_Electric_Pot_Assortment_55": "Cole_Hardware_Electric_Pot_Assortment_55",
+ "Cole_Hardware_Electric_Pot_Cabana_55": "Cole_Hardware_Electric_Pot_Cabana_55",
+ "Cole_Hardware_Flower_Pot_1025": "Cole_Hardware_Flower_Pot_1025",
+ "Cole_Hardware_Hammer_Black": "black and yellow hammer",
+ "Cole_Hardware_Mini_Honey_Dipper": "Cole_Hardware_Mini_Honey_Dipper",
+ "Cole_Hardware_Mug_Classic_Blue": "Cole_Hardware_Mug_Classic_Blue",
+ "Cole_Hardware_Orchid_Pot_85": "Cole_Hardware_Orchid_Pot_85",
+ "Cole_Hardware_Plant_Saucer_Brown_125": "Cole_Hardware_Plant_Saucer_Brown_125",
+ "Cole_Hardware_Plant_Saucer_Glazed_9": "Cole_Hardware_Plant_Saucer_Glazed_9",
+ "Cole_Hardware_Saucer_Electric": "Cole_Hardware_Saucer_Electric",
+ "Cole_Hardware_Saucer_Glazed_6": "Cole_Hardware_Saucer_Glazed_6",
+ "Cole_Hardware_School_Bell_Solid_Brass_38": "Cole_Hardware_School_Bell_Solid_Brass_38",
+ "Colton_Wntr_Chukka_y4jO0I8JQFW": "Colton_Wntr_Chukka_y4jO0I8JQFW",
+ "Connect_4_Launchers": "Connect_4_Launchers",
+ "Cootie_Game": "Cootie_Game",
+ "Cootie_Game_tDhURNbfU5J": "Cootie_Game_tDhURNbfU5J",
+ "Copperhead_Snake_Tieks_Brown_Snake_Print_Ballet_Flats": "Copperhead_Snake_Tieks_Brown_Snake_Print_Ballet_Flats",
+ "Corningware_CW_by_Corningware_3qt_Oblong_Casserole_Dish_Blue": "Corningware_CW_by_Corningware_3qt_Oblong_Casserole_Dish_Blue",
+ "Court_Attitude": "Court_Attitude",
+ "Craftsman_Grip_Screwdriver_Phillips_Cushion": "Craftsman_Grip_Screwdriver_Phillips_Cushion",
+ "Crayola_Bonus_64_Crayons": "Crayola_Bonus_64_Crayons",
+ "Crayola_Crayons_120_crayons": "Crayola_Crayons_120_crayons",
+ "Crayola_Crayons_24_count": "Crayola_Crayons_24_count",
+ "Crayola_Crayons_Washable_24_crayons": "Crayola_Crayons_Washable_24_crayons",
+ "Crayola_Model_Magic_Modeling_Material_Single_Packs_6_pack_05_oz_packs": "Crayola_Model_Magic_Modeling_Material_Single_Packs_6_pack_05_oz_packs",
+ "Crayola_Model_Magic_Modeling_Material_White_3_oz": "Crayola_Model_Magic_Modeling_Material_White_3_oz",
+ "Crayola_Washable_Fingerpaint_Red_Blue_Yellow_3_count_8_fl_oz_bottes_each": "Crayola_Washable_Fingerpaint_Red_Blue_Yellow_3_count_8_fl_oz_bottes_each",
+ "Crayola_Washable_Sidewalk_Chalk_16_pack": "Crayola_Washable_Sidewalk_Chalk_16_pack",
+ "Crayola_Washable_Sidewalk_Chalk_16_pack_wDZECiw7J6s": "Crayola_Washable_Sidewalk_Chalk_16_pack_wDZECiw7J6s",
+ "Crazy_8": "Crazy_8",
+ "Crazy_Shadow_2": "Crazy_Shadow_2",
+ "Crazy_Shadow_2_oW4Jd10HFFr": "Crazy_Shadow_2_oW4Jd10HFFr",
+ "Cream_Tieks_Italian_Leather_Ballet_Flats": "Cream_Tieks_Italian_Leather_Ballet_Flats",
+ "Creatine_Monohydrate": "Creatine_Monohydrate",
+ "Crosley_Alarm_Clock_Vintage_Metal": "vintage metal alarm clock",
+ "Crunch_Girl_Scouts_Candy_Bars_Peanut_Butter_Creme_78_oz_box": "Crunch_Girl_Scouts_Candy_Bars_Peanut_Butter_Creme_78_oz_box",
+ "Curver_Storage_Bin_Black_Small": "Curver_Storage_Bin_Black_Small",
+ "DANCING_ALLIGATOR": "DANCING_ALLIGATOR",
+ "DANCING_ALLIGATOR_zoWBjc0jbTs": "DANCING_ALLIGATOR_zoWBjc0jbTs",
+ "DIM_CDG": "DIM_CDG",
+ "DINING_ROOM_CLASSIC": "DINING_ROOM_CLASSIC",
+ "DINING_ROOM_CLASSIC_UJuxQ0hv5XU": "DINING_ROOM_CLASSIC_UJuxQ0hv5XU",
+ "DINNING_ROOM_FURNITURE_SET_1": "DINNING_ROOM_FURNITURE_SET_1",
+ "DOLL_FAMILY": "DOLL_FAMILY",
+ "DPC_Handmade_Hat_Brown": "DPC_Handmade_Hat_Brown",
+ "DPC_Thinsulate_Isolate_Gloves_Brown": "DPC_Thinsulate_Isolate_Gloves_Brown",
+ "DPC_tropical_Trends_Hat": "DPC_tropical_Trends_Hat",
+ "DRAGON_W": "DRAGON_W",
+ "D_ROSE_45": "D_ROSE_45",
+ "D_ROSE_773_II_Kqclsph05pE": "D_ROSE_773_II_Kqclsph05pE",
+ "D_ROSE_773_II_hvInJwJ5HUD": "D_ROSE_773_II_hvInJwJ5HUD",
+ "D_ROSE_ENGLEWOOD_II": "D_ROSE_ENGLEWOOD_II",
+ "Dell_Ink_Cartridge": "Dell_Ink_Cartridge",
+ "Dell_Ink_Cartridge_Yellow_31": "Dell_Ink_Cartridge_Yellow_31",
+ "Dell_Series_9_Color_Ink_Cartridge_MK993_High_Yield": "Dell_Series_9_Color_Ink_Cartridge_MK993_High_Yield",
+ "Design_Ideas_Drawer_Store_Organizer": "Design_Ideas_Drawer_Store_Organizer",
+ "Deskstar_Desk_Top_Hard_Drive_1_TB": "Deskstar_Desk_Top_Hard_Drive_1_TB",
+ "Diamond_Visions_Scissors_Red": "red scissors",
+ "Diet_Pepsi_Soda_Cola12_Pack_12_oz_Cans": "Diet_Pepsi_Soda_Cola12_Pack_12_oz_Cans",
+ "Digital_Camo_Double_Decker_Lunch_Bag": "Digital_Camo_Double_Decker_Lunch_Bag",
+ "Dino_3": "Dino_3",
+ "Dino_4": "Dino_4",
+ "Dino_5": "Dino_5",
+ "Dixie_10_ounce_Bowls_35_ct": "Dixie_10_ounce_Bowls_35_ct",
+ "Dog": "Dog",
+ "Don_Franciscos_Gourmet_Coffee_Medium_Decaf_100_Colombian_12_oz_340_g": "Don_Franciscos_Gourmet_Coffee_Medium_Decaf_100_Colombian_12_oz_340_g",
+ "Down_To_Earth_Ceramic_Orchid_Pot_Asst_Blue": "Down_To_Earth_Ceramic_Orchid_Pot_Asst_Blue",
+ "Down_To_Earth_Orchid_Pot_Ceramic_Lime": "Down_To_Earth_Orchid_Pot_Ceramic_Lime",
+ "Down_To_Earth_Orchid_Pot_Ceramic_Red": "Down_To_Earth_Orchid_Pot_Ceramic_Red",
+ "ENFR_MID_ENFORCER": "ENFR_MID_ENFORCER",
+ "Eat_to_Live_The_Amazing_NutrientRich_Program_for_Fast_and_Sustained_Weight_Loss_Revised_Edition_Book": "Eat_to_Live_The_Amazing_NutrientRich_Program_for_Fast_and_Sustained_Weight_Loss_Revised_Edition_Book",
+ "Ecoforms_Cup_B4_SAN": "Ecoforms_Cup_B4_SAN",
+ "Ecoforms_Garden_Pot_GP16ATurquois": "Ecoforms_Garden_Pot_GP16ATurquois",
+ "Ecoforms_Plant_Bowl_Atlas_Low": "Ecoforms_Plant_Bowl_Atlas_Low",
+ "Ecoforms_Plant_Bowl_Turquoise_7": "Ecoforms_Plant_Bowl_Turquoise_7",
+ "Ecoforms_Plant_Container_12_Pot_Nova": "Ecoforms_Plant_Container_12_Pot_Nova",
+ "Ecoforms_Plant_Container_B4_Har": "Ecoforms_Plant_Container_B4_Har",
+ "Ecoforms_Plant_Container_FB6_Tur": "Ecoforms_Plant_Container_FB6_Tur",
+ "Ecoforms_Plant_Container_GP16AMOCHA": "Ecoforms_Plant_Container_GP16AMOCHA",
+ "Ecoforms_Plant_Container_GP16A_Coral": "Ecoforms_Plant_Container_GP16A_Coral",
+ "Ecoforms_Plant_Container_QP6CORAL": "Ecoforms_Plant_Container_QP6CORAL",
+ "Ecoforms_Plant_Container_QP6HARVEST": "Ecoforms_Plant_Container_QP6HARVEST",
+ "Ecoforms_Plant_Container_QP_Harvest": "Ecoforms_Plant_Container_QP_Harvest",
+ "Ecoforms_Plant_Container_QP_Turquoise": "Ecoforms_Plant_Container_QP_Turquoise",
+ "Ecoforms_Plant_Container_Quadra_Sand_QP6": "Ecoforms_Plant_Container_Quadra_Sand_QP6",
+ "Ecoforms_Plant_Container_Quadra_Turquoise_QP12": "Ecoforms_Plant_Container_Quadra_Turquoise_QP12",
+ "Ecoforms_Plant_Container_S14Turquoise": "Ecoforms_Plant_Container_S14Turquoise",
+ "Ecoforms_Plant_Container_S24NATURAL": "Ecoforms_Plant_Container_S24NATURAL",
+ "Ecoforms_Plant_Container_S24Turquoise": "Ecoforms_Plant_Container_S24Turquoise",
+ "Ecoforms_Plant_Container_SB9Turquoise": "Ecoforms_Plant_Container_SB9Turquoise",
+ "Ecoforms_Plant_Container_URN_NAT": "Ecoforms_Plant_Container_URN_NAT",
+ "Ecoforms_Plant_Container_URN_SAN": "Ecoforms_Plant_Container_URN_SAN",
+ "Ecoforms_Plant_Container_Urn_55_Avocado": "Ecoforms_Plant_Container_Urn_55_Avocado",
+ "Ecoforms_Plant_Container_Urn_55_Mocha": "Ecoforms_Plant_Container_Urn_55_Mocha",
+ "Ecoforms_Plant_Plate_S11Turquoise": "Ecoforms_Plant_Plate_S11Turquoise",
+ "Ecoforms_Plant_Pot_GP9AAvocado": "Ecoforms_Plant_Pot_GP9AAvocado",
+ "Ecoforms_Plant_Pot_GP9_SAND": "Ecoforms_Plant_Pot_GP9_SAND",
+ "Ecoforms_Plant_Saucer_S14MOCHA": "Ecoforms_Plant_Saucer_S14MOCHA",
+ "Ecoforms_Plant_Saucer_S14NATURAL": "Ecoforms_Plant_Saucer_S14NATURAL",
+ "Ecoforms_Plant_Saucer_S17MOCHA": "Ecoforms_Plant_Saucer_S17MOCHA",
+ "Ecoforms_Plant_Saucer_S20MOCHA": "Ecoforms_Plant_Saucer_S20MOCHA",
+ "Ecoforms_Plant_Saucer_SQ1HARVEST": "Ecoforms_Plant_Saucer_SQ1HARVEST",
+ "Ecoforms_Plant_Saucer_SQ8COR": "Ecoforms_Plant_Saucer_SQ8COR",
+ "Ecoforms_Planter_Bowl_Cole_Hardware": "Ecoforms_Planter_Bowl_Cole_Hardware",
+ "Ecoforms_Planter_Pot_GP12AAvocado": "Ecoforms_Planter_Pot_GP12AAvocado",
+ "Ecoforms_Planter_Pot_QP6Ebony": "Ecoforms_Planter_Pot_QP6Ebony",
+ "Ecoforms_Plate_S20Avocado": "Ecoforms_Plate_S20Avocado",
+ "Ecoforms_Pot_Nova_6_Turquoise": "Ecoforms_Pot_Nova_6_Turquoise",
+ "Ecoforms_Quadra_Saucer_SQ1_Avocado": "Ecoforms_Quadra_Saucer_SQ1_Avocado",
+ "Ecoforms_Saucer_SQ3_Turquoise": "Ecoforms_Saucer_SQ3_Turquoise",
+ "Elephant": "Elephant",
+ "Embark_Lunch_Cooler_Blue": "Embark_Lunch_Cooler_Blue",
+ "Envision_Home_Dish_Drying_Mat_Red_6_x_18": "Envision_Home_Dish_Drying_Mat_Red_6_x_18",
+ "Epson_273XL_Ink_Cartridge_Magenta": "Epson_273XL_Ink_Cartridge_Magenta",
+ "Epson_DURABrite_Ultra_786_Black_Ink_Cartridge_T786120S": "Epson_DURABrite_Ultra_786_Black_Ink_Cartridge_T786120S",
+ "Epson_Ink_Cartridge_126_Yellow": "Epson_Ink_Cartridge_126_Yellow",
+ "Epson_Ink_Cartridge_Black_200": "Epson_Ink_Cartridge_Black_200",
+ "Epson_LabelWorks_LC4WBN9_Tape_reel_labels_047_x_295_Roll_Black_on_White": "Epson_LabelWorks_LC4WBN9_Tape_reel_labels_047_x_295_Roll_Black_on_White",
+ "Epson_LabelWorks_LC5WBN9_Tape_reel_labels_071_x_295_Roll_Black_on_White": "Epson_LabelWorks_LC5WBN9_Tape_reel_labels_071_x_295_Roll_Black_on_White",
+ "Epson_T5803_Ink_Cartridge_Magenta_1pack": "Epson_T5803_Ink_Cartridge_Magenta_1pack",
+ "Epson_UltraChrome_T0543_Ink_Cartridge_Magenta_1pack": "Epson_UltraChrome_T0543_Ink_Cartridge_Magenta_1pack",
+ "Epson_UltraChrome_T0548_Ink_Cartridge_Matte_Black_1pack": "Epson_UltraChrome_T0548_Ink_Cartridge_Matte_Black_1pack",
+ "F10_TRX_FG_ssscuo9tGxb": "F10_TRX_FG_ssscuo9tGxb",
+ "F10_TRX_TF_rH7tmKCdUJq": "F10_TRX_TF_rH7tmKCdUJq",
+ "F5_TRX_FG": "F5_TRX_FG",
+ "FAIRY_TALE_BLOCKS": "FAIRY_TALE_BLOCKS",
+ "FARM_ANIMAL": "FARM_ANIMAL",
+ "FARM_ANIMAL_9GyfdcPyESK": "FARM_ANIMAL_9GyfdcPyESK",
+ "FIRE_ENGINE": "FIRE_ENGINE",
+ "FIRE_TRUCK": "FIRE_TRUCK",
+ "FISHING_GAME": "FISHING_GAME",
+ "FOOD_BEVERAGE_SET": "FOOD_BEVERAGE_SET",
+ "FRACTION_FUN_n4h4qte23QR": "FRACTION_FUN_n4h4qte23QR",
+ "FRUIT_VEGGIE_DOMINO_GRADIENT": "FRUIT_VEGGIE_DOMINO_GRADIENT",
+ "FRUIT_VEGGIE_MEMO_GRADIENT": "FRUIT_VEGGIE_MEMO_GRADIENT",
+ "FYW_ALTERNATION": "FYW_ALTERNATION",
+ "FYW_DIVISION": "FYW_DIVISION",
+ "FemDophilus": "FemDophilus",
+ "Final_Fantasy_XIV_A_Realm_Reborn_60Day_Subscription": "Final_Fantasy_XIV_A_Realm_Reborn_60Day_Subscription",
+ "Firefly_Clue_Board_Game": "Firefly_Clue_Board_Game",
+ "FisherPrice_Make_A_Match_Game_Thomas_Friends": "FisherPrice_Make_A_Match_Game_Thomas_Friends",
+ "Fisher_price_Classic_Toys_Buzzy_Bee": "Fisher_price_Classic_Toys_Buzzy_Bee",
+ "Focus_8643_Lime_Squeezer_10x35x188_Enamelled_Aluminum_Light": "Focus_8643_Lime_Squeezer_10x35x188_Enamelled_Aluminum_Light",
+ "Folic_Acid": "Folic_Acid",
+ "Footed_Bowl_Sand": "Footed_Bowl_Sand",
+ "Fresca_Peach_Citrus_Sparkling_Flavored_Soda_12_PK": "Fresca_Peach_Citrus_Sparkling_Flavored_Soda_12_PK",
+ "Frozen_Olafs_In_Trouble_PopOMatic_Game": "Frozen_Olafs_In_Trouble_PopOMatic_Game",
+ "Frozen_Olafs_In_Trouble_PopOMatic_Game_OEu83W9T8pD": "Frozen_Olafs_In_Trouble_PopOMatic_Game_OEu83W9T8pD",
+ "Frozen_Scrabble_Jr": "Frozen_Scrabble_Jr",
+ "Fruity_Friends": "Fruity_Friends",
+ "Fujifilm_instax_SHARE_SP1_10_photos": "Fujifilm_instax_SHARE_SP1_10_photos",
+ "Full_Circle_Happy_Scraps_Out_Collector_Gray": "Full_Circle_Happy_Scraps_Out_Collector_Gray",
+ "GARDEN_SWING": "GARDEN_SWING",
+ "GEARS_PUZZLES_STANDARD_gcYxhNHhKlI": "GEARS_PUZZLES_STANDARD_gcYxhNHhKlI",
+ "GEOMETRIC_PEG_BOARD": "GEOMETRIC_PEG_BOARD",
+ "GEOMETRIC_SORTING_BOARD": "GEOMETRIC_SORTING_BOARD",
+ "GEOMETRIC_SORTING_BOARD_MNi4Rbuz9vj": "GEOMETRIC_SORTING_BOARD_MNi4Rbuz9vj",
+ "GIRLS_DECKHAND": "GIRLS_DECKHAND",
+ "GRANDFATHER_DOLL": "GRANDFATHER_DOLL",
+ "GRANDMOTHER": "GRANDMOTHER",
+ "Germanium_GE132": "Germanium_GE132",
+ "Ghost_6_Color_BlckWhtLavaSlvrCitrus_Size_80": "Ghost_6_Color_BlckWhtLavaSlvrCitrus_Size_80",
+ "Ghost_6_Color_MdngtDenmPomBrtePnkSlvBlk_Size_50": "Ghost_6_Color_MdngtDenmPomBrtePnkSlvBlk_Size_50",
+ "Ghost_6_GTX_Color_AnthBlckSlvrFernSulphSprng_Size_80": "Ghost_6_GTX_Color_AnthBlckSlvrFernSulphSprng_Size_80",
+ "Gigabyte_GA78LMTUSB3_50_Motherboard_Micro_ATX_Socket_AM3": "Gigabyte_GA78LMTUSB3_50_Motherboard_Micro_ATX_Socket_AM3",
+ "Gigabyte_GA970AUD3P_10_Motherboard_ATX_Socket_AM3": "Gigabyte_GA970AUD3P_10_Motherboard_ATX_Socket_AM3",
+ "Gigabyte_GAZ97XSLI_10_motherboard_ATX_LGA1150_Socket_Z97": "Gigabyte_GAZ97XSLI_10_motherboard_ATX_LGA1150_Socket_Z97",
+ "Glycerin_11_Color_AqrsDrsdnBluBlkSlvShckOrng_Size_50": "Glycerin_11_Color_AqrsDrsdnBluBlkSlvShckOrng_Size_50",
+ "Glycerin_11_Color_BrllntBluSkydvrSlvrBlckWht_Size_80": "Glycerin_11_Color_BrllntBluSkydvrSlvrBlckWht_Size_80",
+ "GoPro_HERO3_Composite_Cable": "GoPro_HERO3_Composite_Cable",
+ "Google_Cardboard_Original_package": "Google_Cardboard_Original_package",
+ "Grand_Prix": "Grand_Prix",
+ "Granimals_20_Wooden_ABC_Blocks_Wagon": "Granimals_20_Wooden_ABC_Blocks_Wagon",
+ "Granimals_20_Wooden_ABC_Blocks_Wagon_85VdSftGsLi": "Granimals_20_Wooden_ABC_Blocks_Wagon_85VdSftGsLi",
+ "Granimals_20_Wooden_ABC_Blocks_Wagon_g2TinmUGGHI": "Granimals_20_Wooden_ABC_Blocks_Wagon_g2TinmUGGHI",
+ "Great_Dinos_Triceratops_Toy": "Great_Dinos_Triceratops_Toy",
+ "Great_Jones_Wingtip": "Great_Jones_Wingtip",
+ "Great_Jones_Wingtip_j5NV8GRnitM": "Great_Jones_Wingtip_j5NV8GRnitM",
+ "Great_Jones_Wingtip_kAqSg6EgG0I": "Great_Jones_Wingtip_kAqSg6EgG0I",
+ "Great_Jones_Wingtip_wxH3dbtlvBC": "Great_Jones_Wingtip_wxH3dbtlvBC",
+ "Grreat_Choice_Dog_Double_Dish_Plastic_Blue": "Grreat_Choice_Dog_Double_Dish_Plastic_Blue",
+ "Grreatv_Choice_Dog_Bowl_Gray_Bones_Plastic_20_fl_oz_total": "Grreatv_Choice_Dog_Bowl_Gray_Bones_Plastic_20_fl_oz_total",
+ "Guardians_of_the_Galaxy_Galactic_Battlers_Rocket_Raccoon_Figure": "Guardians_of_the_Galaxy_Galactic_Battlers_Rocket_Raccoon_Figure",
+ "HAMMER_BALL": "HAMMER_BALL",
+ "HAMMER_PEG": "HAMMER_PEG",
+ "HAPPY_ENGINE": "HAPPY_ENGINE",
+ "HELICOPTER": "HELICOPTER",
+ "HP_1800_Tablet_8GB_7": "HP_1800_Tablet_8GB_7",
+ "HP_Card_Invitation_Kit": "HP_Card_Invitation_Kit",
+ "Hasbro_Cranium_Performance_and_Acting_Game": "Hasbro_Cranium_Performance_and_Acting_Game",
+ "Hasbro_Dont_Wake_Daddy_Board_Game": "Hasbro_Dont_Wake_Daddy_Board_Game",
+ "Hasbro_Dont_Wake_Daddy_Board_Game_NJnjGna4u1a": "Hasbro_Dont_Wake_Daddy_Board_Game_NJnjGna4u1a",
+ "Hasbro_Life_Board_Game": "Hasbro_Life_Board_Game",
+ "Hasbro_Monopoly_Hotels_Game": "Hasbro_Monopoly_Hotels_Game",
+ "Hasbro_Trivial_Pursuit_Family_Edition_Game": "Hasbro_Trivial_Pursuit_Family_Edition_Game",
+ "HeavyDuty_Flashlight": "HeavyDuty_Flashlight",
+ "Hefty_Waste_Basket_Decorative_Bronze_85_liter": "Hefty_Waste_Basket_Decorative_Bronze_85_liter",
+ "Hey_You_Pikachu_Nintendo_64": "Hey_You_Pikachu_Nintendo_64",
+ "Hilary": "Hilary",
+ "Home_Fashions_Washcloth_Linen": "Home_Fashions_Washcloth_Linen",
+ "Home_Fashions_Washcloth_Olive_Green": "Home_Fashions_Washcloth_Olive_Green",
+ "Horse_Dreams_Pencil_Case": "Horse_Dreams_Pencil_Case",
+ "Horses_in_Pink_Pencil_Case": "Horses_in_Pink_Pencil_Case",
+ "House_of_Cards_The_Complete_First_Season_4_Discs_DVD": "House_of_Cards_The_Complete_First_Season_4_Discs_DVD",
+ "Hyaluronic_Acid": "Hyaluronic_Acid",
+ "HyperX_Cloud_II_Headset_Gun_Metal": "HyperX_Cloud_II_Headset_Gun_Metal",
+ "HyperX_Cloud_II_Headset_Red": "HyperX_Cloud_II_Headset_Red",
+ "INTERNATIONAL_PAPER_Willamette_4_Brown_Bag_500Count": "INTERNATIONAL_PAPER_Willamette_4_Brown_Bag_500Count",
+ "Imaginext_Castle_Ogre": "Imaginext_Castle_Ogre",
+ "In_Green_Company_Surface_Saver_Ring_10_Terra_Cotta": "In_Green_Company_Surface_Saver_Ring_10_Terra_Cotta",
+ "Inositol": "Inositol",
+ "InterDesign_Over_Door": "InterDesign_Over_Door",
+ "IsoRich_Soy": "IsoRich_Soy",
+ "JA_Henckels_International_Premio_Cutlery_Block_Set_14Piece": "JA_Henckels_International_Premio_Cutlery_Block_Set_14Piece",
+ "JBL_Charge_Speaker_portable_wireless_wired_Green": "JBL_Charge_Speaker_portable_wireless_wired_Green",
+ "JS_WINGS_20_BLACK_FLAG": "JS_WINGS_20_BLACK_FLAG",
+ "JUICER_SET": "JUICER_SET",
+ "JUNGLE_HEIGHT": "JUNGLE_HEIGHT",
+ "Jansport_School_Backpack_Blue_Streak": "blue and black backpack",
+ "JarroDophilusFOS_Value_Size": "JarroDophilusFOS_Value_Size",
+ "JarroSil_Activated_Silicon": "JarroSil_Activated_Silicon",
+ "JarroSil_Activated_Silicon_5exdZHIeLAp": "JarroSil_Activated_Silicon_5exdZHIeLAp",
+ "Jarrow_Formulas_Glucosamine_Hci_Mega_1000_100_ct": "Jarrow_Formulas_Glucosamine_Hci_Mega_1000_100_ct",
+ "Jarrow_Glucosamine_Chondroitin_Combination_120_Caps": "Jarrow_Glucosamine_Chondroitin_Combination_120_Caps",
+ "Jawbone_UP24_Wireless_Activity_Tracker_Pink_Coral_L": "Jawbone_UP24_Wireless_Activity_Tracker_Pink_Coral_L",
+ "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_Kit_Jet_Black_M60": "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_Kit_Jet_Black_M60",
+ "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_MediumDark_Brown_M40": "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_MediumDark_Brown_M40",
+ "Just_For_Men_ShampooIn_Haircolor_Jet_Black_60": "Just_For_Men_ShampooIn_Haircolor_Jet_Black_60",
+ "Just_For_Men_ShampooIn_Haircolor_Light_Brown_25": "Just_For_Men_ShampooIn_Haircolor_Light_Brown_25",
+ "Just_For_Men_Shampoo_In_Haircolor_Darkest_Brown_50": "Just_For_Men_Shampoo_In_Haircolor_Darkest_Brown_50",
+ "Justified_The_Complete_Fourth_Season_3_Discs_DVD": "Justified_The_Complete_Fourth_Season_3_Discs_DVD",
+ "KID_ROOM_FURNITURE_SET_1": "KID_ROOM_FURNITURE_SET_1",
+ "KITCHEN_FURNITURE_SET_1": "KITCHEN_FURNITURE_SET_1",
+ "KITCHEN_SET_CLASSIC_40HwCHfeG0H": "KITCHEN_SET_CLASSIC_40HwCHfeG0H",
+ "KS_Chocolate_Cube_Box_Assortment_By_Neuhaus_2010_Ounces": "white gift box with red straps",
+ "Kanex_MultiSync_Wireless_Keyboard": "Kanex_MultiSync_Wireless_Keyboard",
+ "Kid_Icarus_Uprising_Nintendo_3DS_Game": "Kid_Icarus_Uprising_Nintendo_3DS_Game",
+ "Kingston_DT4000MR_G2_Management_Ready_USB_64GB": "Kingston_DT4000MR_G2_Management_Ready_USB_64GB",
+ "Kong_Puppy_Teething_Rubber_Small_Pink": "Kong_Puppy_Teething_Rubber_Small_Pink",
+ "Kotex_U_Barely_There_Liners_Thin_60_count": "Kotex_U_Barely_There_Liners_Thin_60_count",
+ "Kotex_U_Tween_Pads_16_pads": "Kotex_U_Tween_Pads_16_pads",
+ "Kotobuki_Saucer_Dragon_Fly": "Kotobuki_Saucer_Dragon_Fly",
+ "Krill_Oil": "Krill_Oil",
+ "LACING_SHEEP": "LACING_SHEEP",
+ "LADYBUG_BEAD": "LADYBUG_BEAD",
+ "LEGO_5887_Dino_Defense_HQ": "LEGO_5887_Dino_Defense_HQ",
+ "LEGO_Bricks_More_Creative_Suitcase": "LEGO_Bricks_More_Creative_Suitcase",
+ "LEGO_City_Advent_Calendar": "LEGO_City_Advent_Calendar",
+ "LEGO_Creationary_Game": "LEGO_Creationary_Game",
+ "LEGO_Creationary_Game_ZJa163wlWp2": "LEGO_Creationary_Game_ZJa163wlWp2",
+ "LEGO_Duplo_Build_and_Play_Box_4629": "LEGO_Duplo_Build_and_Play_Box_4629",
+ "LEGO_Duplo_Creative_Animals_10573": "LEGO_Duplo_Creative_Animals_10573",
+ "LEGO_Fusion_Set_Town_Master": "LEGO_Fusion_Set_Town_Master",
+ "LEGO_Star_Wars_Advent_Calendar": "LEGO_Star_Wars_Advent_Calendar",
+ "LEUCIPPUS_ADIPURE": "LEUCIPPUS_ADIPURE",
+ "LTyrosine": "LTyrosine",
+ "Lactoferrin": "Lactoferrin",
+ "Lalaloopsy_Peanut_Big_Top_Tricycle": "Lalaloopsy_Peanut_Big_Top_Tricycle",
+ "Lavender_Snake_Tieks_Snake_Print_Ballet_Flats": "Lavender_Snake_Tieks_Snake_Print_Ballet_Flats",
+ "Leap_Frog_Paint_Dabber_Dot_Art_5_paint_bottles": "Leap_Frog_Paint_Dabber_Dot_Art_5_paint_bottles",
+ "Lego_Friends_Advent_Calendar": "Lego_Friends_Advent_Calendar",
+ "Lego_Friends_Mia": "Lego_Friends_Mia",
+ "Lenovo_Yoga_2_11": "Lenovo_Yoga_2_11",
+ "Little_Big_Planet_3_Plush_Edition": "Little_Big_Planet_3_Plush_Edition",
+ "Little_Debbie_Chocolate_Cupcakes_8_ct": "Little_Debbie_Chocolate_Cupcakes_8_ct",
+ "Little_Debbie_Cloud_Cakes_10_ct": "Little_Debbie_Cloud_Cakes_10_ct",
+ "Little_Debbie_Donut_Sticks_6_cake_donuts_10_oz_total": "Little_Debbie_Donut_Sticks_6_cake_donuts_10_oz_total",
+ "Little_House_on_the_Prairie_Season_Two_5_Discs_Includes_Digital": "Little_House_on_the_Prairie_Season_Two_5_Discs_Includes_Digital",
+ "Logitech_Ultimate_Ears_Boom_Wireless_Speaker_Night_Black": "Logitech_Ultimate_Ears_Boom_Wireless_Speaker_Night_Black",
+ "Lovable_Huggable_Cuddly_Boutique_Teddy_Bear_Beige": "Lovable_Huggable_Cuddly_Boutique_Teddy_Bear_Beige",
+ "Lovestruck_Tieks_Glittery_Rose_Gold_Italian_Leather_Ballet_Flats": "Lovestruck_Tieks_Glittery_Rose_Gold_Italian_Leather_Ballet_Flats",
+ "Luigis_Mansion_Dark_Moon_Nintendo_3DS_Game": "Luigis_Mansion_Dark_Moon_Nintendo_3DS_Game",
+ "Lutein": "Lutein",
+ "MARTIN_WEDGE_LACE_BOOT": "MARTIN_WEDGE_LACE_BOOT",
+ "MEAT_SET": "MEAT_SET",
+ "MINI_EXCAVATOR": "MINI_EXCAVATOR",
+ "MINI_FIRE_ENGINE": "MINI_FIRE_ENGINE",
+ "MINI_ROLLER": "MINI_ROLLER",
+ "MIRACLE_POUNDING": "MIRACLE_POUNDING",
+ "MK7": "MK7",
+ "MODERN_DOLL_FAMILY": "MODERN_DOLL_FAMILY",
+ "MONKEY_BOWLING": "MONKEY_BOWLING",
+ "MOSAIC": "MOSAIC",
+ "MOVING_MOUSE_PW_6PCSSET": "MOVING_MOUSE_PW_6PCSSET",
+ "MY_MOOD_MEMO": "MY_MOOD_MEMO",
+ "Mad_Gab_Refresh_Card_Game": "Mad_Gab_Refresh_Card_Game",
+ "Magnifying_Glassassrt": "Magnifying_Glassassrt",
+ "Marc_Anthony_Skip_Professional_Oil_of_Morocco_Conditioner_with_Argan_Oil": "Marc_Anthony_Skip_Professional_Oil_of_Morocco_Conditioner_with_Argan_Oil",
+ "Marc_Anthony_Strictly_Curls_Curl_Envy_Perfect_Curl_Cream_6_fl_oz_bottle": "Marc_Anthony_Strictly_Curls_Curl_Envy_Perfect_Curl_Cream_6_fl_oz_bottle",
+ "Marc_Anthony_True_Professional_Oil_of_Morocco_Argan_Oil_Treatment": "Marc_Anthony_True_Professional_Oil_of_Morocco_Argan_Oil_Treatment",
+ "Marc_Anthony_True_Professional_Strictly_Curls_Curl_Defining_Lotion": "Marc_Anthony_True_Professional_Strictly_Curls_Curl_Defining_Lotion",
+ "Mario_Luigi_Dream_Team_Nintendo_3DS_Game": "Mario_Luigi_Dream_Team_Nintendo_3DS_Game",
+ "Mario_Party_9_Wii_Game": "Mario_Party_9_Wii_Game",
+ "Markings_Desk_Caddy": "Markings_Desk_Caddy",
+ "Markings_Letter_Holder": "Markings_Letter_Holder",
+ "Marvel_Avengers_Titan_Hero_Series_Doctor_Doom": "Marvel_Avengers_Titan_Hero_Series_Doctor_Doom",
+ "Mastic_Gum": "Mastic_Gum",
+ "Matte_Black_Tieks_Italian_Leather_Ballet_Flats": "Matte_Black_Tieks_Italian_Leather_Ballet_Flats",
+ "Mattel_SKIP_BO_Card_Game": "Mattel_SKIP_BO_Card_Game",
+ "Melissa_Doug_Cart_Turtle_Block": "Melissa_Doug_Cart_Turtle_Block",
+ "Melissa_Doug_Chunky_Puzzle_Vehicles": "Melissa_Doug_Chunky_Puzzle_Vehicles",
+ "Melissa_Doug_Felt_Food_Pizza_Set": "Melissa_Doug_Felt_Food_Pizza_Set",
+ "Melissa_Doug_Jumbo_Knob_Puzzles_Barnyard_Animals": "Melissa_Doug_Jumbo_Knob_Puzzles_Barnyard_Animals",
+ "Melissa_Doug_Pattern_Blocks_and_Boards": "Melissa_Doug_Pattern_Blocks_and_Boards",
+ "Melissa_Doug_Pound_and_Roll": "Melissa_Doug_Pound_and_Roll",
+ "Melissa_Doug_See_Spell": "Melissa_Doug_See_Spell",
+ "Melissa_Doug_Shape_Sorting_Clock": "Melissa_Doug_Shape_Sorting_Clock",
+ "Melissa_Doug_Traffic_Signs_and_Vehicles": "Melissa_Doug_Traffic_Signs_and_Vehicles",
+ "Mens_ASV_Billfish_Boat_Shoe_in_Dark_Brown_Leather_zdHVHXueI3w": "Mens_ASV_Billfish_Boat_Shoe_in_Dark_Brown_Leather_zdHVHXueI3w",
+ "Mens_ASV_Billfish_Boat_Shoe_in_Tan_Leather_wmUJ5PbwANc": "Mens_ASV_Billfish_Boat_Shoe_in_Tan_Leather_wmUJ5PbwANc",
+ "Mens_ASV_Shock_Light_Bungee_in_Light_Grey_xGCOvtLDnQJ": "Mens_ASV_Shock_Light_Bungee_in_Light_Grey_xGCOvtLDnQJ",
+ "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_NHHQddDLQys": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_NHHQddDLQys",
+ "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_RpT4GvUXRRP": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_RpT4GvUXRRP",
+ "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_xgoEcZtRNmH": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_xgoEcZtRNmH",
+ "Mens_Bahama_in_Black_b4ADzYywRHl": "Mens_Bahama_in_Black_b4ADzYywRHl",
+ "Mens_Bahama_in_Khaki_Oyster_xU2jeqYwhQJ": "Mens_Bahama_in_Khaki_Oyster_xU2jeqYwhQJ",
+ "Mens_Bahama_in_White_vSwvGMCo32f": "Mens_Bahama_in_White_vSwvGMCo32f",
+ "Mens_Billfish_3Eye_Boat_Shoe_in_Dark_Tan_wyns9HRcEuH": "Mens_Billfish_3Eye_Boat_Shoe_in_Dark_Tan_wyns9HRcEuH",
+ "Mens_Billfish_Slip_On_in_Coffee_e8bPKE9Lfgo": "Mens_Billfish_Slip_On_in_Coffee_e8bPKE9Lfgo",
+ "Mens_Billfish_Slip_On_in_Coffee_nK6AJJAHOae": "Mens_Billfish_Slip_On_in_Coffee_nK6AJJAHOae",
+ "Mens_Billfish_Slip_On_in_Tan_Beige_aaVUk0tNTv8": "Mens_Billfish_Slip_On_in_Tan_Beige_aaVUk0tNTv8",
+ "Mens_Billfish_Ultra_Lite_Boat_Shoe_in_Dark_Brown_Blue_c6zDZTtRJr6": "Mens_Billfish_Ultra_Lite_Boat_Shoe_in_Dark_Brown_Blue_c6zDZTtRJr6",
+ "Mens_Gold_Cup_ASV_2Eye_Boat_Shoe_in_Cognac_Leather": "Mens_Gold_Cup_ASV_2Eye_Boat_Shoe_in_Cognac_Leather",
+ "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_EjPnk3E8fCs": "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_EjPnk3E8fCs",
+ "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_GkQBKqABeQN": "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_GkQBKqABeQN",
+ "Mens_Gold_Cup_ASV_Dress_Casual_Venetian_in_Dark_Brown_Leather": "Mens_Gold_Cup_ASV_Dress_Casual_Venetian_in_Dark_Brown_Leather",
+ "Mens_Largo_Slip_On_in_Taupe_gooyS417q4R": "Mens_Largo_Slip_On_in_Taupe_gooyS417q4R",
+ "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_9d05GG33QQQ": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_9d05GG33QQQ",
+ "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_K9e8FoV73uZ": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_K9e8FoV73uZ",
+ "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_OysterTaupe_otyRrfvPMiA": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_OysterTaupe_otyRrfvPMiA",
+ "Mens_RR_Moc_in_Navy_Suede_vmFfijhBzL3": "Mens_RR_Moc_in_Navy_Suede_vmFfijhBzL3",
+ "Mens_Santa_Cruz_Thong_in_Chocolate_La1fo2mAovE": "Mens_Santa_Cruz_Thong_in_Chocolate_La1fo2mAovE",
+ "Mens_Santa_Cruz_Thong_in_Chocolate_lvxYW7lek6B": "Mens_Santa_Cruz_Thong_in_Chocolate_lvxYW7lek6B",
+ "Mens_Santa_Cruz_Thong_in_Tan_r59C69daRPh": "Mens_Santa_Cruz_Thong_in_Tan_r59C69daRPh",
+ "Mens_Striper_Sneaker_in_White_rnp8HUli59Y": "Mens_Striper_Sneaker_in_White_rnp8HUli59Y",
+ "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto",
+ "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_FT0I9OjSA6O": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_FT0I9OjSA6O",
+ "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_rCdzRZqgCnI": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_rCdzRZqgCnI",
+ "Mens_Wave_Driver_Kiltie_Moc_in_Tan_Leather": "Mens_Wave_Driver_Kiltie_Moc_in_Tan_Leather",
+ "Metallic_Gold_Tieks_Italian_Leather_Ballet_Flats": "Metallic_Gold_Tieks_Italian_Leather_Ballet_Flats",
+ "Metallic_Pewter_Tieks_Italian_Leather_Ballet_Flats": "Metallic_Pewter_Tieks_Italian_Leather_Ballet_Flats",
+ "Mist_Wipe_Warmer": "Mist_Wipe_Warmer",
+ "My_First_Animal_Tower": "My_First_Animal_Tower",
+ "My_First_Rolling_Lion": "My_First_Rolling_Lion",
+ "My_First_Wiggle_Crocodile": "My_First_Wiggle_Crocodile",
+ "My_Little_Pony_Princess_Celestia": "My_Little_Pony_Princess_Celestia",
+ "My_Monopoly_Board_Game": "My_Monopoly_Board_Game",
+ "NAPA_VALLEY_NAVAJO_SANDAL": "NAPA_VALLEY_NAVAJO_SANDAL",
+ "NESCAFE_NESCAFE_TC_STKS_DECAF_6_CT": "NESCAFE_NESCAFE_TC_STKS_DECAF_6_CT",
+ "NUTS_BOLTS": "NUTS_BOLTS",
+ "NattoMax": "NattoMax",
+ "Neat_Solutions_Character_Bib_2_pack": "Neat_Solutions_Character_Bib_2_pack",
+ "Nescafe_16Count_Dolce_Gusto_Cappuccino_Capsules": "Nescafe_16Count_Dolce_Gusto_Cappuccino_Capsules",
+ "Nescafe_Memento_Latte_Caramel_8_08_oz_23_g_packets_64_oz_184_g": "Nescafe_Memento_Latte_Caramel_8_08_oz_23_g_packets_64_oz_184_g",
+ "Nescafe_Momento_Mocha_Specialty_Coffee_Mix_8_ct": "Nescafe_Momento_Mocha_Specialty_Coffee_Mix_8_ct",
+ "Nescafe_Tasters_Choice_Instant_Coffee_Decaf_House_Blend_Light_7_oz": "Nescafe_Tasters_Choice_Instant_Coffee_Decaf_House_Blend_Light_7_oz",
+ "Nestl_Crunch_Girl_Scouts_Cookie_Flavors_Caramel_Coconut_78_oz_box": "Nestl_Crunch_Girl_Scouts_Cookie_Flavors_Caramel_Coconut_78_oz_box",
+ "Nestl_Skinny_Cow_Heavenly_Crisp_Candy_Bar_Chocolate_Raspberry_6_pack_462_oz_total": "Nestl_Skinny_Cow_Heavenly_Crisp_Candy_Bar_Chocolate_Raspberry_6_pack_462_oz_total",
+ "Nestle_Candy_19_oz_Butterfinger_Singles_116567": "Nestle_Candy_19_oz_Butterfinger_Singles_116567",
+ "Nestle_Carnation_Cinnamon_Coffeecake_Kit_1913OZ": "Nestle_Carnation_Cinnamon_Coffeecake_Kit_1913OZ",
+ "Nestle_Nesquik_Chocolate_Powder_Flavored_Milk_Additive_109_Oz_Canister": "Nestle_Nesquik_Chocolate_Powder_Flavored_Milk_Additive_109_Oz_Canister",
+ "Nestle_Nips_Hard_Candy_Peanut_Butter": "Nestle_Nips_Hard_Candy_Peanut_Butter",
+ "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can": "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can",
+ "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can_aX0ygjh3bxi": "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can_aX0ygjh3bxi",
+ "Nestle_Raisinets_Milk_Chocolate_35_oz_992_g": "Nestle_Raisinets_Milk_Chocolate_35_oz_992_g",
+ "Nestle_Skinny_Cow_Dreamy_Clusters_Candy_Dark_Chocolate_6_pack_1_oz_pouches": "Nestle_Skinny_Cow_Dreamy_Clusters_Candy_Dark_Chocolate_6_pack_1_oz_pouches",
+ "Netgear_Ac1750_Router_Wireless_Dual_Band_Gigabit_Router": "Netgear_Ac1750_Router_Wireless_Dual_Band_Gigabit_Router",
+ "Netgear_N750_Wireless_Dual_Band_Gigabit_Router": "Netgear_N750_Wireless_Dual_Band_Gigabit_Router",
+ "Netgear_Nighthawk_X6_AC3200_TriBand_Gigabit_Wireless_Router": "Netgear_Nighthawk_X6_AC3200_TriBand_Gigabit_Wireless_Router",
+ "New_Super_Mario_BrosWii_Wii_Game": "New_Super_Mario_BrosWii_Wii_Game",
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Leonardo": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Leonardo",
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Michelangelo": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Michelangelo",
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Raphael": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Raphael",
+ "Nickelodeon_The_Spongebob_Movie_PopAPart_Spongebob": "Nickelodeon_The_Spongebob_Movie_PopAPart_Spongebob",
+ "Nightmare_Before_Christmas_Collectors_Edition_Operation": "Nightmare_Before_Christmas_Collectors_Edition_Operation",
+ "Nikon_1_AW1_w11275mm_Lens_Silver": "Nikon_1_AW1_w11275mm_Lens_Silver",
+ "Nintendo_2DS_Crimson_Red": "Nintendo_2DS_Crimson_Red",
+ "Nintendo_Mario_Action_Figure": "Nintendo_Mario_Action_Figure",
+ "Nintendo_Wii_Party_U_with_Controller_Wii_U_Game": "Nintendo_Wii_Party_U_with_Controller_Wii_U_Game",
+ "Nintendo_Yoshi_Action_Figure": "Nintendo_Yoshi_Action_Figure",
+ "Nips_Hard_Candy_Rich_Creamy_Butter_Rum_4_oz_1133_g": "Nips_Hard_Candy_Rich_Creamy_Butter_Rum_4_oz_1133_g",
+ "Nordic_Ware_Original_Bundt_Pan": "Nordic_Ware_Original_Bundt_Pan",
+ "Now_Designs_Bowl_Akita_Black": "Now_Designs_Bowl_Akita_Black",
+ "Now_Designs_Dish_Towel_Mojave_18_x_28": "Now_Designs_Dish_Towel_Mojave_18_x_28",
+ "Now_Designs_Snack_Bags_Bicycle_2_count": "Now_Designs_Snack_Bags_Bicycle_2_count",
+ "OVAL_XYLOPHONE": "OVAL_XYLOPHONE",
+ "OWL_SORTER": "OWL_SORTER",
+ "OXO_Cookie_Spatula": "OXO_Cookie_Spatula",
+ "OXO_Soft_Works_Can_Opener_SnapLock": "OXO_Soft_Works_Can_Opener_SnapLock",
+ "Object": "Object",
+ "Object_REmvBDJStub": "Object_REmvBDJStub",
+ "Ocedar_Snap_On_Dust_Pan_And_Brush_1_ct": "Ocedar_Snap_On_Dust_Pan_And_Brush_1_ct",
+ "Office_Depot_Canon_CL211XL_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Canon_CL211XL_Remanufactured_Ink_Cartridge_TriColor",
+ "Office_Depot_Canon_CLI36_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Canon_CLI36_Remanufactured_Ink_Cartridge_TriColor",
+ "Office_Depot_Canon_CLI_221BK_Ink_Cartridge_Black_2946B001": "Office_Depot_Canon_CLI_221BK_Ink_Cartridge_Black_2946B001",
+ "Office_Depot_Canon_CLI_8CMY_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": "Office_Depot_Canon_CLI_8CMY_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+ "Office_Depot_Canon_CLI_8Y_Ink_Cartridge_Yellow_0623B002": "Office_Depot_Canon_CLI_8Y_Ink_Cartridge_Yellow_0623B002",
+ "Office_Depot_Canon_CL_41_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Canon_CL_41_Remanufactured_Ink_Cartridge_TriColor",
+ "Office_Depot_Canon_PG21XL_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Canon_PG21XL_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_Canon_PGI22_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Canon_PGI22_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_Canon_PGI35_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Canon_PGI35_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_Canon_PGI5BK_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Canon_PGI5BK_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_Canon_PG_240XL_Ink_Cartridge_Black_5206B001": "Office_Depot_Canon_PG_240XL_Ink_Cartridge_Black_5206B001",
+ "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_TriColor",
+ "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_TriColor",
+ "Office_Depot_Dell_Series_5_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Dell_Series_5_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_Dell_Series_9_Color_Ink_Ink_Cartridge_MK991_MK993": "Office_Depot_Dell_Series_9_Color_Ink_Ink_Cartridge_MK991_MK993",
+ "Office_Depot_Dell_Series_9_Ink_Cartridge_Black_MK992": "Office_Depot_Dell_Series_9_Ink_Cartridge_Black_MK992",
+ "Office_Depot_HP_2_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": "Office_Depot_HP_2_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+ "Office_Depot_HP_564XL_Ink_Cartridge_Black_CN684WN": "Office_Depot_HP_564XL_Ink_Cartridge_Black_CN684WN",
+ "Office_Depot_HP_564XL_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": "Office_Depot_HP_564XL_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+ "Office_Depot_HP_61Tricolor_Ink_Cartridge": "Office_Depot_HP_61Tricolor_Ink_Cartridge",
+ "Office_Depot_HP_71_Remanufactured_Ink_Cartridge_Black": "Office_Depot_HP_71_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_HP_74XL75_Remanufactured_Ink_Cartridges_BlackTriColor_2_count": "Office_Depot_HP_74XL75_Remanufactured_Ink_Cartridges_BlackTriColor_2_count",
+ "Office_Depot_HP_75_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_HP_75_Remanufactured_Ink_Cartridge_TriColor",
+ "Office_Depot_HP_920XL_920_High_Yield_Black_and_Standard_CMY_Color_Ink_Cartridges": "Office_Depot_HP_920XL_920_High_Yield_Black_and_Standard_CMY_Color_Ink_Cartridges",
+ "Office_Depot_HP_932XL_Ink_Cartridge_Black_CN053A": "Office_Depot_HP_932XL_Ink_Cartridge_Black_CN053A",
+ "Office_Depot_HP_950XL_Ink_Cartridge_Black_CN045AN": "Office_Depot_HP_950XL_Ink_Cartridge_Black_CN045AN",
+ "Office_Depot_HP_96_Remanufactured_Ink_Cartridge_Black": "Office_Depot_HP_96_Remanufactured_Ink_Cartridge_Black",
+ "Office_Depot_HP_98_Remanufactured_Ink_Cartridge_Black": "Office_Depot_HP_98_Remanufactured_Ink_Cartridge_Black",
+ "Olive_Kids_Birdie_Lunch_Box": "Olive_Kids_Birdie_Lunch_Box",
+ "Olive_Kids_Birdie_Munch_n_Lunch": "Olive_Kids_Birdie_Munch_n_Lunch",
+ "Olive_Kids_Birdie_Pack_n_Snack": "Olive_Kids_Birdie_Pack_n_Snack",
+ "Olive_Kids_Birdie_Sidekick_Backpack": "Olive_Kids_Birdie_Sidekick_Backpack",
+ "Olive_Kids_Butterfly_Garden_Munch_n_Lunch_Bag": "Olive_Kids_Butterfly_Garden_Munch_n_Lunch_Bag",
+ "Olive_Kids_Butterfly_Garden_Pencil_Case": "Olive_Kids_Butterfly_Garden_Pencil_Case",
+ "Olive_Kids_Dinosaur_Land_Lunch_Box": "Olive_Kids_Dinosaur_Land_Lunch_Box",
+ "Olive_Kids_Dinosaur_Land_Munch_n_Lunch": "Olive_Kids_Dinosaur_Land_Munch_n_Lunch",
+ "Olive_Kids_Dinosaur_Land_Pack_n_Snack": "Olive_Kids_Dinosaur_Land_Pack_n_Snack",
+ "Olive_Kids_Dinosaur_Land_Sidekick_Backpack": "Olive_Kids_Dinosaur_Land_Sidekick_Backpack",
+ "Olive_Kids_Game_On_Lunch_Box": "Olive_Kids_Game_On_Lunch_Box",
+ "Olive_Kids_Game_On_Munch_n_Lunch": "Olive_Kids_Game_On_Munch_n_Lunch",
+ "Olive_Kids_Game_On_Pack_n_Snack": "Olive_Kids_Game_On_Pack_n_Snack",
+ "Olive_Kids_Mermaids_Pack_n_Snack_Backpack": "Olive_Kids_Mermaids_Pack_n_Snack_Backpack",
+ "Olive_Kids_Paisley_Pencil_Case": "Olive_Kids_Paisley_Pencil_Case",
+ "Olive_Kids_Robots_Pencil_Case": "Olive_Kids_Robots_Pencil_Case",
+ "Olive_Kids_Trains_Planes_Trucks_Bogo_Backpack": "Olive_Kids_Trains_Planes_Trucks_Bogo_Backpack",
+ "Olive_Kids_Trains_Planes_Trucks_Munch_n_Lunch_Bag": "Olive_Kids_Trains_Planes_Trucks_Munch_n_Lunch_Bag",
+ "Orbit_Bubblemint_Mini_Bottle_6_ct": "Orbit_Bubblemint_Mini_Bottle_6_ct",
+ "Organic_Whey_Protein_Unflavored": "Organic_Whey_Protein_Unflavored",
+ "Organic_Whey_Protein_Vanilla": "Organic_Whey_Protein_Vanilla",
+ "Ortho_Forward_Facing": "Ortho_Forward_Facing",
+ "Ortho_Forward_Facing_3Q6J2oKJD92": "Ortho_Forward_Facing_3Q6J2oKJD92",
+ "Ortho_Forward_Facing_CkAW6rL25xH": "Ortho_Forward_Facing_CkAW6rL25xH",
+ "Ortho_Forward_Facing_QCaor9ImJ2G": "Ortho_Forward_Facing_QCaor9ImJ2G",
+ "PARENT_ROOM_FURNITURE_SET_1": "PARENT_ROOM_FURNITURE_SET_1",
+ "PARENT_ROOM_FURNITURE_SET_1_DLKEy8H4mwK": "PARENT_ROOM_FURNITURE_SET_1_DLKEy8H4mwK",
+ "PEEKABOO_ROLLER": "PEEKABOO_ROLLER",
+ "PEPSI_NEXT_CACRV": "PEPSI_NEXT_CACRV",
+ "PETS_ACCESSORIES": "PETS_ACCESSORIES",
+ "PHEEHAN_RUN": "PHEEHAN_RUN",
+ "PINEAPPLE_MARACA_6_PCSSET": "PINEAPPLE_MARACA_6_PCSSET",
+ "POUNDING_MUSHROOMS": "POUNDING_MUSHROOMS",
+ "PUNCH_DROP": "PUNCH_DROP",
+ "PUNCH_DROP_TjicLPMqLvz": "PUNCH_DROP_TjicLPMqLvz",
+ "Paint_Maker": "Paint_Maker",
+ "Paper_Mario_Sticker_Star_Nintendo_3DS_Game": "Paper_Mario_Sticker_Star_Nintendo_3DS_Game",
+ "Pass_The_Popcorn_Movie_Guessing_Game": "Pass_The_Popcorn_Movie_Guessing_Game",
+ "Paul_Frank_Dot_Lunch_Box": "Paul_Frank_Dot_Lunch_Box",
+ "Pennington_Electric_Pot_Cabana_4": "Pennington_Electric_Pot_Cabana_4",
+ "Pepsi_Caffeine_Free_Diet_12_CT": "Pepsi_Caffeine_Free_Diet_12_CT",
+ "Pepsi_Cola_Caffeine_Free_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": "Pepsi_Cola_Caffeine_Free_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+ "Pepsi_Cola_Wild_Cherry_Diet_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": "Pepsi_Cola_Wild_Cherry_Diet_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+ "Pepsi_Max_Cola_Zero_Calorie_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": "Pepsi_Max_Cola_Zero_Calorie_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+ "Perricoen_MD_No_Concealer_Concealer": "Perricoen_MD_No_Concealer_Concealer",
+ "Perricone_MD_AcylGlutathione_Deep_Crease_Serum": "Perricone_MD_AcylGlutathione_Deep_Crease_Serum",
+ "Perricone_MD_AcylGlutathione_Eye_Lid_Serum": "Perricone_MD_AcylGlutathione_Eye_Lid_Serum",
+ "Perricone_MD_Best_of_Perricone_7Piece_Collection_MEGsO6GIsyL": "Perricone_MD_Best_of_Perricone_7Piece_Collection_MEGsO6GIsyL",
+ "Perricone_MD_Blue_Plasma_Orbital": "Perricone_MD_Blue_Plasma_Orbital",
+ "Perricone_MD_Chia_Serum": "Perricone_MD_Chia_Serum",
+ "Perricone_MD_Cold_Plasma": "Perricone_MD_Cold_Plasma",
+ "Perricone_MD_Cold_Plasma_Body": "Perricone_MD_Cold_Plasma_Body",
+ "Perricone_MD_Face_Finishing_Moisturizer": "Perricone_MD_Face_Finishing_Moisturizer",
+ "Perricone_MD_Face_Finishing_Moisturizer_4_oz": "Perricone_MD_Face_Finishing_Moisturizer_4_oz",
+ "Perricone_MD_Firming_Neck_Therapy_Treatment": "Perricone_MD_Firming_Neck_Therapy_Treatment",
+ "Perricone_MD_Health_Weight_Management_Supplements": "Perricone_MD_Health_Weight_Management_Supplements",
+ "Perricone_MD_High_Potency_Evening_Repair": "Perricone_MD_High_Potency_Evening_Repair",
+ "Perricone_MD_Hypoallergenic_Firming_Eye_Cream_05_oz": "Perricone_MD_Hypoallergenic_Firming_Eye_Cream_05_oz",
+ "Perricone_MD_Hypoallergenic_Gentle_Cleanser": "Perricone_MD_Hypoallergenic_Gentle_Cleanser",
+ "Perricone_MD_Neuropeptide_Facial_Conformer": "Perricone_MD_Neuropeptide_Facial_Conformer",
+ "Perricone_MD_Neuropeptide_Firming_Moisturizer": "Perricone_MD_Neuropeptide_Firming_Moisturizer",
+ "Perricone_MD_No_Bronzer_Bronzer": "Perricone_MD_No_Bronzer_Bronzer",
+ "Perricone_MD_No_Foundation_Foundation_No_1": "Perricone_MD_No_Foundation_Foundation_No_1",
+ "Perricone_MD_No_Foundation_Serum": "Perricone_MD_No_Foundation_Serum",
+ "Perricone_MD_No_Lipstick_Lipstick": "Perricone_MD_No_Lipstick_Lipstick",
+ "Perricone_MD_No_Mascara_Mascara": "Perricone_MD_No_Mascara_Mascara",
+ "Perricone_MD_Nutritive_Cleanser": "Perricone_MD_Nutritive_Cleanser",
+ "Perricone_MD_OVM": "Perricone_MD_OVM",
+ "Perricone_MD_Omega_3_Supplements": "Perricone_MD_Omega_3_Supplements",
+ "Perricone_MD_Photo_Plasma": "Perricone_MD_Photo_Plasma",
+ "Perricone_MD_Skin_Clear_Supplements": "Perricone_MD_Skin_Clear_Supplements",
+ "Perricone_MD_Skin_Total_Body_Supplements": "Perricone_MD_Skin_Total_Body_Supplements",
+ "Perricone_MD_Super_Berry_Powder_with_Acai_Supplements": "Perricone_MD_Super_Berry_Powder_with_Acai_Supplements",
+ "Perricone_MD_The_Cold_Plasma_Face_Eyes_Duo": "Perricone_MD_The_Cold_Plasma_Face_Eyes_Duo",
+ "Perricone_MD_The_Crease_Cure_Duo": "Perricone_MD_The_Crease_Cure_Duo",
+ "Perricone_MD_The_Metabolic_Formula_Supplements": "Perricone_MD_The_Metabolic_Formula_Supplements",
+ "Perricone_MD_The_Power_Treatments": "Perricone_MD_The_Power_Treatments",
+ "Perricone_MD_Vitamin_C_Ester_15": "Perricone_MD_Vitamin_C_Ester_15",
+ "Perricone_MD_Vitamin_C_Ester_Serum": "Perricone_MD_Vitamin_C_Ester_Serum",
+ "Persona_Q_Shadow_of_the_Labyrinth_Nintendo_3DS": "Persona_Q_Shadow_of_the_Labyrinth_Nintendo_3DS",
+ "Pet_Dophilus_powder": "Pet_Dophilus_powder",
+ "Philips_60ct_Warm_White_LED_Smooth_Mini_String_Lights": "Philips_60ct_Warm_White_LED_Smooth_Mini_String_Lights",
+ "Philips_EcoVantage_43_W_Light_Bulbs_Natural_Light_2_pack": "Philips_EcoVantage_43_W_Light_Bulbs_Natural_Light_2_pack",
+ "Philips_Sonicare_Tooth_Brush_2_count": "Philips_Sonicare_Tooth_Brush_2_count",
+ "Phillips_Caplets_Size_24": "Phillips_Caplets_Size_24",
+ "Phillips_Colon_Health_Probiotic_Capsule": "Phillips_Colon_Health_Probiotic_Capsule",
+ "Phillips_Milk_of_Magnesia_Saline_Laxative_Liquid_Original": "Phillips_Milk_of_Magnesia_Saline_Laxative_Liquid_Original",
+ "Phillips_Stool_Softener_Liquid_Gels_30_liquid_gels": "Phillips_Stool_Softener_Liquid_Gels_30_liquid_gels",
+ "PhosphOmega": "PhosphOmega",
+ "Pinwheel_Pencil_Case": "Pinwheel_Pencil_Case",
+ "Playmates_Industrial_CoSplinter_Teenage_Mutant_Ninja_Turtle_Action_Figure": "Playmates_Industrial_CoSplinter_Teenage_Mutant_Ninja_Turtle_Action_Figure",
+ "Playmates_nickelodeon_teenage_mutant_ninja_turtles_shredder": "Playmates_nickelodeon_teenage_mutant_ninja_turtles_shredder",
+ "Poise_Ultimate_Pads_Long": "Poise_Ultimate_Pads_Long",
+ "Pokmon_Conquest_Nintendo_DS_Game": "Pokmon_Conquest_Nintendo_DS_Game",
+ "Pokmon_X_Nintendo_3DS_Game": "Pokmon_X_Nintendo_3DS_Game",
+ "Pokmon_Y_Nintendo_3DS_Game": "Pokmon_Y_Nintendo_3DS_Game",
+ "Pok\u00e9mon_Omega_Ruby_Alpha_Sapphire_Dual_Pack_Nintendo_3DS": "Pok\u00e9mon_Omega_Ruby_Alpha_Sapphire_Dual_Pack_Nintendo_3DS",
+ "Pok\u00e9mon_Yellow_Special_Pikachu_Edition_Nintendo_Game_Boy_Color": "Pok\u00e9mon_Yellow_Special_Pikachu_Edition_Nintendo_Game_Boy_Color",
+ "Polar_Herring_Fillets_Smoked_Peppered_705_oz_total": "Polar_Herring_Fillets_Smoked_Peppered_705_oz_total",
+ "Pony_C_Clamp_1440": "Pony_C_Clamp_1440",
+ "Poppin_File_Sorter_Blue": "Poppin_File_Sorter_Blue",
+ "Poppin_File_Sorter_Pink": "Poppin_File_Sorter_Pink",
+ "Poppin_File_Sorter_White": "Poppin_File_Sorter_White",
+ "Predator_LZ_TRX_FG": "Predator_LZ_TRX_FG",
+ "Predito_LZ_TRX_FG_W": "Predito_LZ_TRX_FG_W",
+ "ProSport_Harness_to_Booster_Seat": "ProSport_Harness_to_Booster_Seat",
+ "Progressive_Rubber_Spatulas_3_count": "Progressive_Rubber_Spatulas_3_count",
+ "Prostate_Optimizer": "Prostate_Optimizer",
+ "Provence_Bath_Towel_Royal_Blue": "Provence_Bath_Towel_Royal_Blue",
+ "PureCadence_2_Color_HiRskRedNghtlfeSlvrBlckWht_Size_70": "PureCadence_2_Color_HiRskRedNghtlfeSlvrBlckWht_Size_70",
+ "PureCadence_2_Color_TleBluLmePnchSlvMoodIndgWh_Size_50_EEzAfcBfHHO": "PureCadence_2_Color_TleBluLmePnchSlvMoodIndgWh_Size_50_EEzAfcBfHHO",
+ "PureConnect_2_Color_AnthrcteKnckoutPnkGrnGecko_Size_50": "PureConnect_2_Color_AnthrcteKnckoutPnkGrnGecko_Size_50",
+ "PureConnect_2_Color_BlckBrllntBluNghtlfeAnthrct_Size_70": "PureConnect_2_Color_BlckBrllntBluNghtlfeAnthrct_Size_70",
+ "PureConnect_2_Color_FernNightlifeSilverBlack_Size_70_5w0BYsiogeV": "PureConnect_2_Color_FernNightlifeSilverBlack_Size_70_5w0BYsiogeV",
+ "PureFlow_2_Color_RylPurHibiscusBlkSlvrWht_Size_50": "PureFlow_2_Color_RylPurHibiscusBlkSlvrWht_Size_50",
+ "QAbsorb_CoQ10": "QAbsorb_CoQ10",
+ "QAbsorb_CoQ10_53iUqjWjW3O": "QAbsorb_CoQ10_53iUqjWjW3O",
+ "QHPomegranate": "QHPomegranate",
+ "Quercetin_500": "Quercetin_500",
+ "REEF_BANTU": "black boot",
+ "REEF_BRAIDED_CUSHION": "REEF_BRAIDED_CUSHION",
+ "REEF_ZENFUN": "REEF_ZENFUN",
+ "RESCUE_CREW": "RESCUE_CREW",
+ "RJ_Rabbit_Easter_Basket_Blue": "RJ_Rabbit_Easter_Basket_Blue",
+ "ROAD_CONSTRUCTION_SET": "ROAD_CONSTRUCTION_SET",
+ "Racoon": "Racoon",
+ "Ravenna_4_Color_WhtOlyBluBlkShkOrngSlvRdO_Size_70": "Ravenna_4_Color_WhtOlyBluBlkShkOrngSlvRdO_Size_70",
+ "Rayna_BootieWP": "Rayna_BootieWP",
+ "Razer_Abyssus_Ambidextrous_Gaming_Mouse": "Razer_Abyssus_Ambidextrous_Gaming_Mouse",
+ "Razer_BlackWidow_Stealth_2014_Keyboard_07VFzIVabgh": "black keyboard",
+ "Razer_BlackWidow_Ultimate_2014_Mechanical_Gaming_Keyboard": "Razer_BlackWidow_Ultimate_2014_Mechanical_Gaming_Keyboard",
+ "Razer_Blackwidow_Tournament_Edition_Keyboard": "Razer_Blackwidow_Tournament_Edition_Keyboard",
+ "Razer_Goliathus_Control_Edition_Small_Soft_Gaming_Mouse_Mat": "Razer_Goliathus_Control_Edition_Small_Soft_Gaming_Mouse_Mat",
+ "Razer_Kraken_71_Chroma_headset_Full_size_Black": "Razer_Kraken_71_Chroma_headset_Full_size_Black",
+ "Razer_Kraken_Pro_headset_Full_size_Black": "Razer_Kraken_Pro_headset_Full_size_Black",
+ "Razer_Naga_MMO_Gaming_Mouse": "Razer_Naga_MMO_Gaming_Mouse",
+ "Razer_Taipan_Black_Ambidextrous_Gaming_Mouse": "black gaming mouse",
+ "Razer_Taipan_White_Ambidextrous_Gaming_Mouse": "white gaming mouse",
+ "ReadytoUse_Rolled_Fondant_Pure_White_24_oz_box": "ReadytoUse_Rolled_Fondant_Pure_White_24_oz_box",
+ "Real_Deal_1nIwCHX1MTh": "Real_Deal_1nIwCHX1MTh",
+ "RedBlack_Nintendo_3DSXL": "black and red gameboy",
+ "Reebok_ALLYLYNN": "Reebok_ALLYLYNN",
+ "Reebok_BREAKPOINT_LO_2V": "Reebok_BREAKPOINT_LO_2V",
+ "Reebok_BREAKPOINT_MID": "Reebok_BREAKPOINT_MID",
+ "Reebok_CLASSIC_JOGGER": "Reebok_CLASSIC_JOGGER",
+ "Reebok_CLASSIC_LEGACY_II": "Reebok_CLASSIC_LEGACY_II",
+ "Reebok_CL_DIBELLO_II": "Reebok_CL_DIBELLO_II",
+ "Reebok_CL_LTHR_R12": "Reebok_CL_LTHR_R12",
+ "Reebok_CL_RAYEN": "Reebok_CL_RAYEN",
+ "Reebok_COMFORT_REEFRESH_FLIP": "Reebok_COMFORT_REEFRESH_FLIP",
+ "Reebok_DMX_MAX_MANIA_WD_D": "Reebok_DMX_MAX_MANIA_WD_D",
+ "Reebok_DMX_MAX_PLUS_ATHLETIC": "Reebok_DMX_MAX_PLUS_ATHLETIC",
+ "Reebok_DMX_MAX_PLUS_RAINWALKER": "Reebok_DMX_MAX_PLUS_RAINWALKER",
+ "Reebok_EASYTONE_CL_LEATHER": "Reebok_EASYTONE_CL_LEATHER",
+ "Reebok_FS_HI_INT_R12": "Reebok_FS_HI_INT_R12",
+ "Reebok_FS_HI_MINI": "Reebok_FS_HI_MINI",
+ "Reebok_FUELTRAIN": "Reebok_FUELTRAIN",
+ "Reebok_GL_6000": "Reebok_GL_6000",
+ "Reebok_HIMARA_LTR": "Reebok_HIMARA_LTR",
+ "Reebok_JR_ZIG_COOPERSTOWN_MR": "Reebok_JR_ZIG_COOPERSTOWN_MR",
+ "Reebok_KAMIKAZE_II_MID": "Reebok_KAMIKAZE_II_MID",
+ "Reebok_PUMP_OMNI_LITE_HLS": "Reebok_PUMP_OMNI_LITE_HLS",
+ "Reebok_REALFLEX_SELECT": "Reebok_REALFLEX_SELECT",
+ "Reebok_REESCULPT_TRAINER_II": "Reebok_REESCULPT_TRAINER_II",
+ "Reebok_RETRO_RUSH_2V": "Reebok_RETRO_RUSH_2V",
+ "Reebok_R_CROSSFIT_OLY_UFORM": "Reebok_R_CROSSFIT_OLY_UFORM",
+ "Reebok_R_DANCE_FLASH": "Reebok_R_DANCE_FLASH",
+ "Reebok_SH_COURT_MID_II": "Reebok_SH_COURT_MID_II",
+ "Reebok_SH_NEWPORT_LOW": "Reebok_SH_NEWPORT_LOW",
+ "Reebok_SH_PRIME_COURT_LOW": "Reebok_SH_PRIME_COURT_LOW",
+ "Reebok_SH_PRIME_COURT_MID": "Reebok_SH_PRIME_COURT_MID",
+ "Reebok_SL_FLIP_UPDATE": "Reebok_SL_FLIP_UPDATE",
+ "Reebok_SMOOTHFLEX_CUSHRUN_20": "Reebok_SMOOTHFLEX_CUSHRUN_20",
+ "Reebok_SOMERSET_RUN": "Reebok_SOMERSET_RUN",
+ "Reebok_STUDIO_BEAT_LOW_V": "Reebok_STUDIO_BEAT_LOW_V",
+ "Reebok_TRIPLE_BREAK_LITE": "Reebok_TRIPLE_BREAK_LITE",
+ "Reebok_TURBO_RC": "Reebok_TURBO_RC",
+ "Reebok_ULTIMATIC_2V": "Reebok_ULTIMATIC_2V",
+ "Reebok_VERSA_TRAIN": "Reebok_VERSA_TRAIN",
+ "Reebok_ZIGCOOPERSTOWN_QUAG": "Reebok_ZIGCOOPERSTOWN_QUAG",
+ "Reebok_ZIGLITE_RUSH": "Reebok_ZIGLITE_RUSH",
+ "Reebok_ZIGLITE_RUSH_AC": "Reebok_ZIGLITE_RUSH_AC",
+ "Reebok_ZIGSTORM": "Reebok_ZIGSTORM",
+ "Reebok_ZIGTECH_SHARK_MAYHEM360": "Reebok_ZIGTECH_SHARK_MAYHEM360",
+ "Reef_Star_Cushion_Flipflops_Size_8_Black": "Reef_Star_Cushion_Flipflops_Size_8_Black",
+ "Remington_1_12_inch_Hair_Straightener": "Remington_1_12_inch_Hair_Straightener",
+ "Remington_TStudio_Hair_Dryer": "Remington_TStudio_Hair_Dryer",
+ "Remington_TStudio_Silk_Ceramic_Hair_Straightener_2_Inch_Floating_Plates": "Remington_TStudio_Silk_Ceramic_Hair_Straightener_2_Inch_Floating_Plates",
+ "Retail_Leadership_Summit": "brown hat",
+ "Retail_Leadership_Summit_eCT3zqHYIkX": "Retail_Leadership_Summit_eCT3zqHYIkX",
+ "Retail_Leadership_Summit_tQFCizMt6g0": "Retail_Leadership_Summit_tQFCizMt6g0",
+ "Rexy_Glove_Heavy_Duty_Gloves_Medium": "blue gloves",
+ "Rexy_Glove_Heavy_Duty_Large": "Rexy_Glove_Heavy_Duty_Large",
+ "Romantic_Blush_Tieks_Metallic_Italian_Leather_Ballet_Flats": "Romantic_Blush_Tieks_Metallic_Italian_Leather_Ballet_Flats",
+ "Room_Essentials_Bowl_Turquiose": "Room_Essentials_Bowl_Turquiose",
+ "Room_Essentials_Dish_Drainer_Collapsible_White": "Room_Essentials_Dish_Drainer_Collapsible_White",
+ "Room_Essentials_Fabric_Cube_Lavender": "Room_Essentials_Fabric_Cube_Lavender",
+ "Room_Essentials_Kitchen_Towels_16_x_26_2_count": "Room_Essentials_Kitchen_Towels_16_x_26_2_count",
+ "Room_Essentials_Mug_White_Yellow": "Room_Essentials_Mug_White_Yellow",
+ "Room_Essentials_Salad_Plate_Turquoise": "Room_Essentials_Salad_Plate_Turquoise",
+ "Rose_Garden_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes": "Rose_Garden_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes",
+ "Rubbermaid_Large_Drainer": "Rubbermaid_Large_Drainer",
+ "SAMBA_HEMP": "SAMBA_HEMP",
+ "SAMOA": "SAMOA",
+ "SAMe_200": "SAMe_200",
+ "SAMe_200_KX7ZmOw47co": "SAMe_200_KX7ZmOw47co",
+ "SANDWICH_MEAL": "SANDWICH_MEAL",
+ "SAPPHIRE_R7_260X_OC": "SAPPHIRE_R7_260X_OC",
+ "SCHOOL_BUS": "SCHOOL_BUS",
+ "SHAPE_MATCHING": "SHAPE_MATCHING",
+ "SHAPE_MATCHING_NxacpAY9jDt": "SHAPE_MATCHING_NxacpAY9jDt",
+ "SHAPE_SORTER": "SHAPE_SORTER",
+ "SIT_N_WALK_PUPPY": "SIT_N_WALK_PUPPY",
+ "SLACK_CRUISER": "SLACK_CRUISER",
+ "SNAIL_MEASURING_TAPE": "SNAIL_MEASURING_TAPE",
+ "SORTING_BUS": "SORTING_BUS",
+ "SORTING_TRAIN": "SORTING_TRAIN",
+ "SPEED_BOAT": "SPEED_BOAT",
+ "STACKING_BEAR": "STACKING_BEAR",
+ "STACKING_BEAR_V04KKgGBn2A": "STACKING_BEAR_V04KKgGBn2A",
+ "STACKING_RING": "STACKING_RING",
+ "STEAK_SET": "STEAK_SET",
+ "SUPERSTAR_CLR": "SUPERSTAR_CLR",
+ "Saccharomyces_Boulardii_MOS_Value_Size": "Saccharomyces_Boulardii_MOS_Value_Size",
+ "Samoa_onepiece": "Samoa_onepiece",
+ "Samsung_CLTC406S_Toner_Cartridge_Cyan_1pack": "Samsung_CLTC406S_Toner_Cartridge_Cyan_1pack",
+ "Santa_Cruz_Mens": "Santa_Cruz_Mens",
+ "Santa_Cruz_Mens_G7kQXK7cIky": "Santa_Cruz_Mens_G7kQXK7cIky",
+ "Santa_Cruz_Mens_YmsMDkFf11Z": "Santa_Cruz_Mens_YmsMDkFf11Z",
+ "Santa_Cruz_Mens_umxTczr1Ygg": "Santa_Cruz_Mens_umxTczr1Ygg",
+ "Santa_Cruz_Mens_vnbiTDDt5xH": "Santa_Cruz_Mens_vnbiTDDt5xH",
+ "Sapota_Threshold_4_Ceramic_Round_Planter_Red": "Sapota_Threshold_4_Ceramic_Round_Planter_Red",
+ "Schleich_African_Black_Rhino": "Schleich_African_Black_Rhino",
+ "Schleich_Allosaurus": "Schleich_Allosaurus",
+ "Schleich_Bald_Eagle": "bald eagle toy",
+ "Schleich_Hereford_Bull": "brown bull",
+ "Schleich_Lion_Action_Figure": "Schleich_Lion_Action_Figure",
+ "Schleich_S_Bayala_Unicorn_70432": "Schleich_S_Bayala_Unicorn_70432",
+ "Schleich_Spinosaurus_Action_Figure": "Schleich_Spinosaurus_Action_Figure",
+ "Schleich_Therizinosaurus_ln9cruulPqc": "Schleich_Therizinosaurus_ln9cruulPqc",
+ "Sea_to_Summit_Xl_Bowl": "Sea_to_Summit_Xl_Bowl",
+ "Seagate_1TB_Backup_Plus_portable_drive_Blue": "Seagate_1TB_Backup_Plus_portable_drive_Blue",
+ "Seagate_1TB_Backup_Plus_portable_drive_Silver": "Seagate_1TB_Backup_Plus_portable_drive_Silver",
+ "Seagate_1TB_Backup_Plus_portable_drive_for_Mac": "Seagate_1TB_Backup_Plus_portable_drive_for_Mac",
+ "Seagate_1TB_Wireless_Plus_mobile_device_storage": "Seagate_1TB_Wireless_Plus_mobile_device_storage",
+ "Seagate_3TB_Central_shared_storage": "Seagate_3TB_Central_shared_storage",
+ "Seagate_Archive_HDD_8_TB_Internal_hard_drive_SATA_6Gbs_35_ST8000AS0002": "Seagate_Archive_HDD_8_TB_Internal_hard_drive_SATA_6Gbs_35_ST8000AS0002",
+ "Shark": "Shark",
+ "Shaxon_100_Molded_Category_6_RJ45RJ45_Shielded_Patch_Cord_White": "Shaxon_100_Molded_Category_6_RJ45RJ45_Shielded_Patch_Cord_White",
+ "Shurtape_30_Day_Removal_UV_Delct_15": "Shurtape_30_Day_Removal_UV_Delct_15",
+ "Shurtape_Gaffers_Tape_Silver_2_x_60_yd": "Shurtape_Gaffers_Tape_Silver_2_x_60_yd",
+ "Shurtape_Tape_Purple_CP28": "Shurtape_Tape_Purple_CP28",
+ "Sienna_Brown_Croc_Tieks_Patent_Leather_Crocodile_Print_Ballet_Flats": "Sienna_Brown_Croc_Tieks_Patent_Leather_Crocodile_Print_Ballet_Flats",
+ "Simon_Swipe_Game": "Simon_Swipe_Game",
+ "Sleep_Optimizer": "Sleep_Optimizer",
+ "Smith_Hawken_Woven_BasketTray_Organizer_with_3_Compartments_95_x_9_x_13": "Smith_Hawken_Woven_BasketTray_Organizer_with_3_Compartments_95_x_9_x_13",
+ "Snack_Catcher_Snack_Dispenser": "Snack_Catcher_Snack_Dispenser",
+ "Sonicare_2_Series_Toothbrush_Plaque_Control": "Sonicare_2_Series_Toothbrush_Plaque_Control",
+ "Sonny_School_Bus": "school bus toy",
+ "Sony_Acid_Music_Studio": "Sony_Acid_Music_Studio",
+ "Sony_Downloadable_Loops": "Sony_Downloadable_Loops",
+ "Sootheze_Cold_Therapy_Elephant": "grey elephant toy",
+ "Sootheze_Toasty_Orca": "Sootheze_Toasty_Orca",
+ "Sorry_Sliders_Board_Game": "Sorry_Sliders_Board_Game",
+ "Spectrum_Wall_Mount": "Spectrum_Wall_Mount",
+ "Sperry_TopSider_pSUFPWQXPp3": "Sperry_TopSider_pSUFPWQXPp3",
+ "Sperry_TopSider_tNB9t6YBUf3": "Sperry_TopSider_tNB9t6YBUf3",
+ "SpiderMan_Titan_Hero_12Inch_Action_Figure_5Hnn4mtkFsP": "SpiderMan_Titan_Hero_12Inch_Action_Figure_5Hnn4mtkFsP",
+ "SpiderMan_Titan_Hero_12Inch_Action_Figure_oo1qph4wwiW": "SpiderMan_Titan_Hero_12Inch_Action_Figure_oo1qph4wwiW",
+ "Spritz_Easter_Basket_Plastic_Teal": "Spritz_Easter_Basket_Plastic_Teal",
+ "Squirrel": "Squirrel",
+ "Squirt_Strain_Fruit_Basket": "Squirt_Strain_Fruit_Basket",
+ "Squirtin_Barnyard_Friends_4pk": "Squirtin_Barnyard_Friends_4pk",
+ "Star_Wars_Rogue_Squadron_Nintendo_64": "Star_Wars_Rogue_Squadron_Nintendo_64",
+ "Starstruck_Tieks_Glittery_Gold_Italian_Leather_Ballet_Flats": "Starstruck_Tieks_Glittery_Gold_Italian_Leather_Ballet_Flats",
+ "Sterilite_Caddy_Blue_Sky_17_58_x_12_58_x_9_14": "Sterilite_Caddy_Blue_Sky_17_58_x_12_58_x_9_14",
+ "Super_Mario_3D_World_Deluxe_Set": "Super_Mario_3D_World_Deluxe_Set",
+ "Super_Mario_3D_World_Deluxe_Set_yThuvW9vZed": "Super_Mario_3D_World_Deluxe_Set_yThuvW9vZed",
+ "Super_Mario_3D_World_Wii_U_Game": "Super_Mario_3D_World_Wii_U_Game",
+ "Super_Mario_Kart_Super_Nintendo_Entertainment_System": "Super_Mario_Kart_Super_Nintendo_Entertainment_System",
+ "Superman_Battle_of_Smallville": "Superman_Battle_of_Smallville",
+ "Supernatural_Ouija_Board_Game": "Supernatural_Ouija_Board_Game",
+ "Sushi_Mat": "Sushi_Mat",
+ "Swiss_Miss_Hot_Cocoa_KCups_Milk_Chocolate_12_count": "Swiss_Miss_Hot_Cocoa_KCups_Milk_Chocolate_12_count",
+ "TABLEWARE_SET": "TABLEWARE_SET",
+ "TABLEWARE_SET_5CHkPjjxVpp": "TABLEWARE_SET_5CHkPjjxVpp",
+ "TABLEWARE_SET_5ww1UFLuCJG": "TABLEWARE_SET_5ww1UFLuCJG",
+ "TEA_SET": "TEA_SET",
+ "TERREX_FAST_R": "TERREX_FAST_R",
+ "TERREX_FAST_X_GTX": "TERREX_FAST_X_GTX",
+ "TOOL_BELT": "TOOL_BELT",
+ "TOP_TEN_HI": "TOP_TEN_HI",
+ "TOP_TEN_HI_60KlbRbdoJA": "TOP_TEN_HI_60KlbRbdoJA",
+ "TOWER_TUMBLING": "TOWER_TUMBLING",
+ "TROCHILUS_BOOST": "TROCHILUS_BOOST",
+ "TURBOPROP_AIRPLANE_WITH_PILOT": "TURBOPROP_AIRPLANE_WITH_PILOT",
+ "TWISTED_PUZZLE": "TWISTED_PUZZLE",
+ "TWISTED_PUZZLE_twb4AyFtu8Q": "TWISTED_PUZZLE_twb4AyFtu8Q",
+ "TWIST_SHAPE": "TWIST_SHAPE",
+ "TZX_Runner": "TZX_Runner",
+ "Tag_Dishtowel_18_x_26": "Tag_Dishtowel_18_x_26",
+ "Tag_Dishtowel_Basket_Weave_Red_18_x_26": "Tag_Dishtowel_Basket_Weave_Red_18_x_26",
+ "Tag_Dishtowel_Dobby_Stripe_Blue_18_x_26": "Tag_Dishtowel_Dobby_Stripe_Blue_18_x_26",
+ "Tag_Dishtowel_Green": "Tag_Dishtowel_Green",
+ "Tag_Dishtowel_Waffle_Gray_Checks_18_x_26": "Tag_Dishtowel_Waffle_Gray_Checks_18_x_26",
+ "Target_Basket_Medium": "Target_Basket_Medium",
+ "Teenage_Mutant_Ninja_Turtles_Rahzar_Action_Figure": "Teenage_Mutant_Ninja_Turtles_Rahzar_Action_Figure",
+ "Tena_Pads_Heavy_Long_42_pads": "Tena_Pads_Heavy_Long_42_pads",
+ "Tetris_Link_Game": "Tetris_Link_Game",
+ "The_Coffee_Bean_Tea_Leaf_KCup_Packs_Jasmine_Green_Tea_16_count": "The_Coffee_Bean_Tea_Leaf_KCup_Packs_Jasmine_Green_Tea_16_count",
+ "The_Scooper_Hooper": "The_Scooper_Hooper",
+ "Theanine": "Theanine",
+ "Thomas_Friends_Woodan_Railway_Henry": "Thomas_Friends_Woodan_Railway_Henry",
+ "Thomas_Friends_Wooden_Railway_Ascending_Track_Riser_Pack": "Thomas_Friends_Wooden_Railway_Ascending_Track_Riser_Pack",
+ "Thomas_Friends_Wooden_Railway_Deluxe_Track_Accessory_Pack": "Thomas_Friends_Wooden_Railway_Deluxe_Track_Accessory_Pack",
+ "Thomas_Friends_Wooden_Railway_Porter_5JzRhMm3a9o": "Thomas_Friends_Wooden_Railway_Porter_5JzRhMm3a9o",
+ "Thomas_Friends_Wooden_Railway_Talking_Thomas_z7yi7UFHJRj": "Thomas_Friends_Wooden_Railway_Talking_Thomas_z7yi7UFHJRj",
+ "Threshold_Bamboo_Ceramic_Soap_Dish": "Threshold_Bamboo_Ceramic_Soap_Dish",
+ "Threshold_Basket_Natural_Finish_Fabric_Liner_Small": "fabric basket",
+ "Threshold_Bead_Cereal_Bowl_White": "Threshold_Bead_Cereal_Bowl_White",
+ "Threshold_Bistro_Ceramic_Dinner_Plate_Ruby_Ring": "Threshold_Bistro_Ceramic_Dinner_Plate_Ruby_Ring",
+ "Threshold_Dinner_Plate_Square_Rim_White_Porcelain": "Threshold_Dinner_Plate_Square_Rim_White_Porcelain",
+ "Threshold_Hand_Towel_Blue_Medallion_16_x_27": "Threshold_Hand_Towel_Blue_Medallion_16_x_27",
+ "Threshold_Performance_Bath_Sheet_Sandoval_Blue_33_x_63": "Threshold_Performance_Bath_Sheet_Sandoval_Blue_33_x_63",
+ "Threshold_Porcelain_Coffee_Mug_All_Over_Bead_White": "Threshold_Porcelain_Coffee_Mug_All_Over_Bead_White",
+ "Threshold_Porcelain_Pitcher_White": "Threshold_Porcelain_Pitcher_White",
+ "Threshold_Porcelain_Serving_Bowl_Coupe_White": "Threshold_Porcelain_Serving_Bowl_Coupe_White",
+ "Threshold_Porcelain_Spoon_Rest_White": "Threshold_Porcelain_Spoon_Rest_White",
+ "Threshold_Porcelain_Teapot_White": "white porcelain teapot",
+ "Threshold_Ramekin_White_Porcelain": "Threshold_Ramekin_White_Porcelain",
+ "Threshold_Salad_Plate_Square_Rim_Porcelain": "Threshold_Salad_Plate_Square_Rim_Porcelain",
+ "Threshold_Textured_Damask_Bath_Towel_Pink": "pink damask bath towel",
+ "Threshold_Tray_Rectangle_Porcelain": "Threshold_Tray_Rectangle_Porcelain",
+ "Tiek_Blue_Patent_Tieks_Italian_Leather_Ballet_Flats": "Tiek_Blue_Patent_Tieks_Italian_Leather_Ballet_Flats",
+ "Tieks_Ballet_Flats_Diamond_White_Croc": "Tieks_Ballet_Flats_Diamond_White_Croc",
+ "Tieks_Ballet_Flats_Electric_Snake": "Tieks_Ballet_Flats_Electric_Snake",
+ "Timberland_Mens_Classic_2Eye_Boat_Shoe": "Timberland_Mens_Classic_2Eye_Boat_Shoe",
+ "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_Oxford": "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_Oxford",
+ "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_SlipOn": "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_SlipOn",
+ "Timberland_Mens_Earthkeepers_Casco_Bay_Suede_1Eye": "Timberland_Mens_Earthkeepers_Casco_Bay_Suede_1Eye",
+ "Timberland_Mens_Earthkeepers_Heritage_2Eye_Boat_Shoe": "Timberland_Mens_Earthkeepers_Heritage_2Eye_Boat_Shoe",
+ "Timberland_Mens_Earthkeepers_Newmarket_6Inch_Cupsole_Boot": "Timberland_Mens_Earthkeepers_Newmarket_6Inch_Cupsole_Boot",
+ "Timberland_Mens_Earthkeepers_Stormbuck_Chukka": "Timberland_Mens_Earthkeepers_Stormbuck_Chukka",
+ "Timberland_Mens_Earthkeepers_Stormbuck_Lite_Plain_Toe_Oxford": "Timberland_Mens_Earthkeepers_Stormbuck_Lite_Plain_Toe_Oxford",
+ "Timberland_Mens_Earthkeepers_Stormbuck_Plain_Toe_Oxford": "Timberland_Mens_Earthkeepers_Stormbuck_Plain_Toe_Oxford",
+ "Timberland_Womens_Classic_Amherst_2Eye_Boat_Shoe": "Timberland_Womens_Classic_Amherst_2Eye_Boat_Shoe",
+ "Timberland_Womens_Earthkeepers_Classic_Unlined_Boat_Shoe": "Timberland_Womens_Earthkeepers_Classic_Unlined_Boat_Shoe",
+ "Timberland_Womens_Waterproof_Nellie_Chukka_Double": "Timberland_Womens_Waterproof_Nellie_Chukka_Double",
+ "Top_Paw_Dog_Bow_Bone_Ceramic_13_fl_oz_total": "Top_Paw_Dog_Bow_Bone_Ceramic_13_fl_oz_total",
+ "Top_Paw_Dog_Bowl_Blue_Paw_Bone_Ceramic_25_fl_oz_total": "Top_Paw_Dog_Bowl_Blue_Paw_Bone_Ceramic_25_fl_oz_total",
+ "Tory_Burch_Kaitlin_Ballet_Mestico_in_BlackGold": "Tory_Burch_Kaitlin_Ballet_Mestico_in_BlackGold",
+ "Tory_Burch_Kiernan_Riding_Boot": "Tory_Burch_Kiernan_Riding_Boot",
+ "Tory_Burch_Reva_Metal_Logo_Litus_Snake_Print_in_dark_BranchGold": "Tory_Burch_Reva_Metal_Logo_Litus_Snake_Print_in_dark_BranchGold",
+ "Tory_Burch_Sabe_65mm_Bootie_Split_Suede_in_Caramel": "Tory_Burch_Sabe_65mm_Bootie_Split_Suede_in_Caramel",
+ "Toys_R_Us_Treat_Dispenser_Smart_Puzzle_Foobler": "Toys_R_Us_Treat_Dispenser_Smart_Puzzle_Foobler",
+ "Toysmith_Windem_Up_Flippin_Animals_Dog": "white animal dog toy",
+ "Transformers_Age_of_Extinction_Mega_1Step_Bumblebee_Figure": "Transformers_Age_of_Extinction_Mega_1Step_Bumblebee_Figure",
+ "Transformers_Age_of_Extinction_Stomp_and_Chomp_Grimlock_Figure": "Transformers_Age_of_Extinction_Stomp_and_Chomp_Grimlock_Figure",
+ "Travel_Mate_P_series_Notebook": "black laptop",
+ "Travel_Smart_Neck_Rest_Inflatable": "Travel_Smart_Neck_Rest_Inflatable",
+ "TriStar_Products_PPC_Power_Pressure_Cooker_XL_in_Black": "black power pressure cooker",
+ "Tune_Belt_Sport_Armband_For_Samsung_Galaxy_S3": "Tune_Belt_Sport_Armband_For_Samsung_Galaxy_S3",
+ "Twinlab_100_Whey_Protein_Fuel_Chocolate": "Twinlab_100_Whey_Protein_Fuel_Chocolate",
+ "Twinlab_100_Whey_Protein_Fuel_Cookies_and_Cream": "Twinlab_100_Whey_Protein_Fuel_Cookies_and_Cream",
+ "Twinlab_100_Whey_Protein_Fuel_Vanilla": "Twinlab_100_Whey_Protein_Fuel_Vanilla",
+ "Twinlab_Nitric_Fuel": "Twinlab_Nitric_Fuel",
+ "Twinlab_Premium_Creatine_Fuel_Powder": "Twinlab_Premium_Creatine_Fuel_Powder",
+ "UGG_Bailey_Bow_Womens_Clogs_Black_7": "UGG_Bailey_Bow_Womens_Clogs_Black_7",
+ "UGG_Bailey_Button_Triplet_Womens_Boots_Black_7": "UGG_Bailey_Button_Triplet_Womens_Boots_Black_7",
+ "UGG_Bailey_Button_Womens_Boots_Black_7": "UGG_Bailey_Button_Womens_Boots_Black_7",
+ "UGG_Cambridge_Womens_Black_7": "UGG_Cambridge_Womens_Black_7",
+ "UGG_Classic_Tall_Womens_Boots_Chestnut_7": "UGG_Classic_Tall_Womens_Boots_Chestnut_7",
+ "UGG_Classic_Tall_Womens_Boots_Grey_7": "UGG_Classic_Tall_Womens_Boots_Grey_7",
+ "UGG_Jena_Womens_Java_7": "UGG_Jena_Womens_Java_7",
+ "US_Army_Stash_Lunch_Bag": "US_Army_Stash_Lunch_Bag",
+ "U_By_Kotex_Cleanwear_Heavy_Flow_Pads_32_Ct": "U_By_Kotex_Cleanwear_Heavy_Flow_Pads_32_Ct",
+ "U_By_Kotex_Sleek_Regular_Unscented_Tampons_36_Ct_Box": "U_By_Kotex_Sleek_Regular_Unscented_Tampons_36_Ct_Box",
+ "Ubisoft_RockSmith_Real_Tone_Cable_Xbox_360": "Ubisoft_RockSmith_Real_Tone_Cable_Xbox_360",
+ "Ultra_JarroDophilus": "Ultra_JarroDophilus",
+ "Unmellow_Yellow_Tieks_Neon_Patent_Leather_Ballet_Flats": "Unmellow_Yellow_Tieks_Neon_Patent_Leather_Ballet_Flats",
+ "Utana_5_Porcelain_Ramekin_Large": "white ramekin porcelain",
+ "VANS_FIRE_ROASTED_VEGGIE_CRACKERS_GLUTEN_FREE": "VANS_FIRE_ROASTED_VEGGIE_CRACKERS_GLUTEN_FREE",
+ "VEGETABLE_GARDEN": "VEGETABLE_GARDEN",
+ "Vans_Cereal_Honey_Nut_Crunch_11_oz_box": "Vans_Cereal_Honey_Nut_Crunch_11_oz_box",
+ "Victor_Reversible_Bookend": "Victor_Reversible_Bookend",
+ "Vtech_Cruise_Learn_Car_25_Years": "Vtech_Cruise_Learn_Car_25_Years",
+ "Vtech_Roll_Learn_Turtle": "green turtle toy",
+ "Vtech_Stack_Sing_Rings_636_Months": "Vtech_Stack_Sing_Rings_636_Months",
+ "WATER_LANDING_NET": "WATER_LANDING_NET",
+ "WHALE_WHISTLE_6PCS_SET": "WHALE_WHISTLE_6PCS_SET",
+ "W_Lou_z0dkC78niiZ": "W_Lou_z0dkC78niiZ",
+ "Weisshai_Great_White_Shark": "great white shark model",
+ "Weston_No_22_Cajun_Jerky_Tonic_12_fl_oz_nLj64ZnGwDh": "Weston_No_22_Cajun_Jerky_Tonic_12_fl_oz_nLj64ZnGwDh",
+ "Weston_No_33_Signature_Sausage_Tonic_12_fl_oz": "Weston_No_33_Signature_Sausage_Tonic_12_fl_oz",
+ "Whey_Protein_3_Flavor_Variety_Pack_12_Packets": "Whey_Protein_3_Flavor_Variety_Pack_12_Packets",
+ "Whey_Protein_Chocolate_12_Packets": "Whey_Protein_Chocolate_12_Packets",
+ "Whey_Protein_Vanilla": "Whey_Protein_Vanilla",
+ "Whey_Protein_Vanilla_12_Packets": "Whey_Protein_Vanilla_12_Packets",
+ "White_Rose_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes": "White_Rose_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes",
+ "Wild_Copper_Tieks_Metallic_Italian_Leather_Ballet_Flats": "Wild_Copper_Tieks_Metallic_Italian_Leather_Ballet_Flats",
+ "Wilton_Easy_Layers_Cake_Pan_Set": "Wilton_Easy_Layers_Cake_Pan_Set",
+ "Wilton_Pearlized_Sugar_Sprinkles_525_oz_Gold": "Wilton_Pearlized_Sugar_Sprinkles_525_oz_Gold",
+ "Wilton_PreCut_Parchment_Sheets_10_x_15_24_sheets": "Wilton_PreCut_Parchment_Sheets_10_x_15_24_sheets",
+ "Winning_Moves_1180_Aggravation_Board_Game": "Winning_Moves_1180_Aggravation_Board_Game",
+ "Wishbone_Pencil_Case": "Wishbone_Pencil_Case",
+ "Womens_Angelfish_Boat_Shoe_in_Linen_Leopard_Sequin_NJDwosWNeZz": "Womens_Angelfish_Boat_Shoe_in_Linen_Leopard_Sequin_NJDwosWNeZz",
+ "Womens_Angelfish_Boat_Shoe_in_Linen_Oat": "Womens_Angelfish_Boat_Shoe_in_Linen_Oat",
+ "Womens_Audrey_Slip_On_Boat_Shoe_in_Graphite_Nubuck_xWVkCJ5vxZe": "Womens_Audrey_Slip_On_Boat_Shoe_in_Graphite_Nubuck_xWVkCJ5vxZe",
+ "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather",
+ "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_48Nh7VuMwW6": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_48Nh7VuMwW6",
+ "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_cJSCWiH7QmB": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_cJSCWiH7QmB",
+ "Womens_Authentic_Original_Boat_Shoe_in_Navy_Deerskin_50lWJaLWG8R": "Womens_Authentic_Original_Boat_Shoe_in_Navy_Deerskin_50lWJaLWG8R",
+ "Womens_Betty_Chukka_Boot_in_Grey_Jersey_Sequin": "Womens_Betty_Chukka_Boot_in_Grey_Jersey_Sequin",
+ "Womens_Betty_Chukka_Boot_in_Navy_Jersey_Sequin_y0SsHk7dKUX": "Womens_Betty_Chukka_Boot_in_Navy_Jersey_Sequin_y0SsHk7dKUX",
+ "Womens_Betty_Chukka_Boot_in_Navy_aEE8OqvMII4": "Womens_Betty_Chukka_Boot_in_Navy_aEE8OqvMII4",
+ "Womens_Betty_Chukka_Boot_in_Salt_Washed_Red_AL2YrOt9CRy": "Womens_Betty_Chukka_Boot_in_Salt_Washed_Red_AL2YrOt9CRy",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_JJ2pfEHTZG7": "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_JJ2pfEHTZG7",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_i1TgjjO0AKY": "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_i1TgjjO0AKY",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_kqi81aojcOR": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_kqi81aojcOR",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_w34KNQ41csH": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_w34KNQ41csH",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_IbrSyJdpT3h": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_IbrSyJdpT3h",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_niKJKeWsmxY": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_niKJKeWsmxY",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_Tan": "Womens_Bluefish_2Eye_Boat_Shoe_in_Tan",
+ "Womens_Bluefish_2Eye_Boat_Shoe_in_White_Tumbled_YG44xIePRHw": "Womens_Bluefish_2Eye_Boat_Shoe_in_White_Tumbled_YG44xIePRHw",
+ "Womens_Canvas_Bahama_in_Black": "Womens_Canvas_Bahama_in_Black",
+ "Womens_Canvas_Bahama_in_Black_vnJULsDVyq5": "Womens_Canvas_Bahama_in_Black_vnJULsDVyq5",
+ "Womens_Canvas_Bahama_in_White_4UyOhP6rYGO": "white canvas shoe",
+ "Womens_Canvas_Bahama_in_White_UfZPHGQpvz0": "Womens_Canvas_Bahama_in_White_UfZPHGQpvz0",
+ "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_8LigQYwf4gr": "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_8LigQYwf4gr",
+ "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_cZR022qFI4k": "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_cZR022qFI4k",
+ "Womens_Hikerfish_Boot_in_Black_Leopard_bVSNY1Le1sm": "Womens_Hikerfish_Boot_in_Black_Leopard_bVSNY1Le1sm",
+ "Womens_Hikerfish_Boot_in_Black_Leopard_ridcCWsv8rW": "Womens_Hikerfish_Boot_in_Black_Leopard_ridcCWsv8rW",
+ "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_QktIyAkonrU": "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_QktIyAkonrU",
+ "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_imlP8VkwqIH": "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_imlP8VkwqIH",
+ "Womens_Multi_13": "Womens_Multi_13",
+ "Womens_Sequin_Bahama_in_White_Sequin_V9K1hf24Oxe": "Womens_Sequin_Bahama_in_White_Sequin_V9K1hf24Oxe",
+ "Womens_Sequin_Bahama_in_White_Sequin_XoR8xTlxj1g": "Womens_Sequin_Bahama_in_White_Sequin_XoR8xTlxj1g",
+ "Womens_Sequin_Bahama_in_White_Sequin_yGVsSA4tOwJ": "Womens_Sequin_Bahama_in_White_Sequin_yGVsSA4tOwJ",
+ "Womens_Sparkle_Suede_Angelfish_in_Grey_Sparkle_Suede_Silver": "Womens_Sparkle_Suede_Angelfish_in_Grey_Sparkle_Suede_Silver",
+ "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_tYrIBLMhSTN": "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_tYrIBLMhSTN",
+ "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_x9rclU7EJXx": "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_x9rclU7EJXx",
+ "Womens_Suede_Bahama_in_Graphite_Suede_cUAjIMhWSO9": "Womens_Suede_Bahama_in_Graphite_Suede_cUAjIMhWSO9",
+ "Womens_Suede_Bahama_in_Graphite_Suede_p1KUwoWbw7R": "Womens_Suede_Bahama_in_Graphite_Suede_p1KUwoWbw7R",
+ "Womens_Suede_Bahama_in_Graphite_Suede_t22AJSRjBOX": "Womens_Suede_Bahama_in_Graphite_Suede_t22AJSRjBOX",
+ "Womens_Teva_Capistrano_Bootie": "Womens_Teva_Capistrano_Bootie",
+ "Womens_Teva_Capistrano_Bootie_ldjRT9yZ5Ht": "Womens_Teva_Capistrano_Bootie_ldjRT9yZ5Ht",
+ "Wooden_ABC_123_Blocks_50_pack": "Wooden_ABC_123_Blocks_50_pack",
+ "Wrigley_Orbit_Mint_Variety_18_Count": "Wrigley_Orbit_Mint_Variety_18_Count",
+ "Xyli_Pure_Xylitol": "Xyli_Pure_Xylitol",
+ "YumYum_D3_Liquid": "YumYum_D3_Liquid",
+ "ZX700_lYiwcTIekXk": "ZX700_lYiwcTIekXk",
+ "ZX700_mf9Pc06uL06": "ZX700_mf9Pc06uL06",
+ "ZX700_mzGbdP3u6JB": "ZX700_mzGbdP3u6JB",
+ "ZigKick_Hoops": "ZigKick_Hoops",
+ "adiZero_Slide_2_SC": "adiZero_Slide_2_SC",
+ "adistar_boost_m": "black sneaker",
+ "adizero_5Tool_25": "adizero_5Tool_25",
+ "adizero_F50_TRX_FG_LEA": "adizero_F50_TRX_FG_LEA"
+}
\ No newline at end of file
diff --git a/eq-kubric/3d_data/GSO_dict_filtered.json b/eq-kubric/3d_data/GSO_dict_filtered.json
new file mode 100644
index 0000000000000000000000000000000000000000..3a1f393c16e2b8519752143bdf5482183eb039aa
--- /dev/null
+++ b/eq-kubric/3d_data/GSO_dict_filtered.json
@@ -0,0 +1,583 @@
+{
+ "purple-white lamp": [
+ "3D_Dollhouse_Lamp"
+ ],
+ "green wooden refrigerator": [
+ "3D_Dollhouse_Refrigerator"
+ ],
+ "purple wooden sofa": [
+ "3D_Dollhouse_Sofa"
+ ],
+ "purple wooden table": [
+ "3D_Dollhouse_TablePurple"
+ ],
+ "light-gray tape": [
+ "3M_Antislip_Surfacing_Light_Duty_White"
+ ],
+ "green tape": [
+ "3M_Vinyl_Tape_Green_1_x_36_yd"
+ ],
+ "green shiny bowl": [
+ "45oz_RAMEKIN_ASST_DEEP_COLORS"
+ ],
+ "blue medicine bottle": [
+ "5_HTP"
+ ],
+ "red coffee mug": [
+ "ACE_Coffee_Mug_Kristen_16_oz_cup"
+ ],
+ "blue sneakers": [
+ "AMBERLIGHT_UP_W"
+ ],
+ "white-black shoes": [
+ "ASICS_GEL1140V_WhiteBlackSilver",
+ "ASICS_GEL1140V_WhiteRoyalSilver"
+ ],
+ "white-pink shoes": [
+ "ASICS_GELAce_Pro_Pearl_WhitePink"
+ ],
+ "black-orange shoes": [
+ "ASICS_GELBlur33_20_GS_BlackWhiteSafety_Orange"
+ ],
+ "yellow-orange shoes": [
+ "ASICS_GELBlur33_20_GS_Flash_YellowHot_PunchSilver"
+ ],
+ "blue-white shoes": [
+ "ASICS_GELChallenger_9_Royal_BlueWhiteBlack"
+ ],
+ "red toy airplane": [
+ "Air_Hogs_Wind_Flyers_Set_Airplane_Red"
+ ],
+ "yellow medicine bottle": [
+ "AllergenFree_JarroDophilus"
+ ],
+ "silver android figure": [
+ "Android_Figure_Chrome"
+ ],
+ "orange android figure": [
+ "Android_Figure_Orange"
+ ],
+ "green-yellow boardgame": [
+ "Apples_to_Apples_Kids_Edition"
+ ],
+ "steel milk frother": [
+ "Aroma_Stainless_Steel_Milk_Frother_2_Cup"
+ ],
+ "green hulk toy fists": [
+ "Avengers_Gamma_Green_Smash_Fists"
+ ],
+ "white porcelain utensil holder": [
+ "BIA_Cordon_Bleu_White_Porcelain_Utensil_Holder_900028"
+ ],
+ "white porcelain ramekin": [
+ "BIA_Porcelain_Ramekin_With_Glazed_Rim_35_45_oz_cup",
+ "Threshold_Ramekin_White_Porcelain",
+ "Utana_5_Porcelain_Ramekin_Large"
+ ],
+ "stack of colorful cups": [
+ "Baby_Elements_Stacking_Cups"
+ ],
+ "black DVD": [
+ "Beyonc_Life_is_But_a_Dream_DVD"
+ ],
+ "purple medicine bottle": [
+ "Bifidus_Balance_FOS"
+ ],
+ "green-purple pencil case": [
+ "Big_Dot_Aqua_Pencil_Case"
+ ],
+ "pink-black pencil case": [
+ "Big_Dot_Pink_Pencil_Case"
+ ],
+ "purple sponge": [
+ "Big_O_Sponges_Assorted_Cellulose_12_pack"
+ ],
+ "black metal coffee maker": [
+ "Black_Decker_CM2035B_12Cup_Thermal_Coffeemaker"
+ ],
+ "stainless steel toaster": [
+ "Black_Decker_Stainless_Steel_Toaster_4_Slice"
+ ],
+ "Nintendo gaming console": [
+ "BlueBlack_Nintendo_3DSXL"
+ ],
+ "white DVD": [
+ "Blue_Jasmine_Includes_Digital_Copy_UltraViolet_DVD"
+ ],
+ "red bowl": [
+ "Bradshaw_International_11642_7_Qt_MP_Plastic_Bowl"
+ ],
+ "toy horse": [
+ "Breyer_Horse_Of_The_Year_2015"
+ ],
+ "CARSII": [
+ "CARSII"
+ ],
+ "black toy train loaded with cars": [
+ "CAR_CARRIER_TRAIN"
+ ],
+ "black ballet shoe": [
+ "California_Navy_Tieks_Italian_Leather_Ballet_Flats"
+ ],
+ "white bowl": [
+ "Calphalon_Kitchen_Essentials_12_Cast_Iron_Fry_Pan_Black",
+ "Threshold_Bead_Cereal_Bowl_White",
+ "Threshold_Porcelain_Serving_Bowl_Coupe_White"
+ ],
+ "round cake pan": [
+ "Chef_Style_Round_Cake_Pan_9_inch_pan"
+ ],
+ "black frypan": [
+ "Chefmate_8_Frypan"
+ ],
+ "golden-black high heel": [
+ "Chelsea_BlkHeelPMP_DwxLtZNxLZZ"
+ ],
+ "red high heel": [
+ "Chelsea_lo_fl_rdheel_nQ0LPNF1oMw"
+ ],
+ "pink high heel": [
+ "Chelsea_lo_fl_rdheel_zAQrnhlEfw8"
+ ],
+ "white drug bottle": [
+ "CoQ10"
+ ],
+ "toilet paper": [
+ "Cole_Hardware_Antislip_Surfacing_Material_White"
+ ],
+ "yellow round bowl": [
+ "Cole_Hardware_Bowl_Scirocco_YellowBlue"
+ ],
+ "brown bowl": [
+ "Cole_Hardware_Deep_Bowl_Good_Earth_1075"
+ ],
+ "blue-white dish towel": [
+ "Cole_Hardware_Dishtowel_BlueWhite"
+ ],
+ "red towel": [
+ "Cole_Hardware_Dishtowel_Red"
+ ],
+ "red-white striped towel": [
+ "Cole_Hardware_Dishtowel_Stripe",
+ "Tag_Dishtowel_Basket_Weave_Red_18_x_26"
+ ],
+ "red flower pot": [
+ "Cole_Hardware_Electric_Pot_Assortment_55",
+ "Sapota_Threshold_4_Ceramic_Round_Planter_Red"
+ ],
+ "orange flower pot": [
+ "Cole_Hardware_Electric_Pot_Cabana_55",
+ "Cole_Hardware_Orchid_Pot_85"
+ ],
+ "gray flower pot": [
+ "Cole_Hardware_Flower_Pot_1025"
+ ],
+ "black and yellow hammer": [
+ "Cole_Hardware_Hammer_Black"
+ ],
+ "brown round plate": [
+ "Cole_Hardware_Plant_Saucer_Brown_125",
+ "Cole_Hardware_Plant_Saucer_Glazed_9"
+ ],
+ "pink saucer": [
+ "Cole_Hardware_Saucer_Electric"
+ ],
+ "school bell": [
+ "Cole_Hardware_School_Bell_Solid_Brass_38"
+ ],
+ "leather boot": [
+ "Colton_Wntr_Chukka_y4jO0I8JQFW"
+ ],
+ "rectangular blue casserol dish": [
+ "Corningware_CW_by_Corningware_3qt_Oblong_Casserole_Dish_Blue"
+ ],
+ "screwdriver": [
+ "Craftsman_Grip_Screwdriver_Phillips_Cushion"
+ ],
+ "vintage metal alarm clock": [
+ "Crosley_Alarm_Clock_Vintage_Metal"
+ ],
+ "black net basket": [
+ "Curver_Storage_Bin_Black_Small"
+ ],
+ "black hat": [
+ "DPC_Handmade_Hat_Brown",
+ "Retail_Leadership_Summit_tQFCizMt6g0"
+ ],
+ "brown straw hat": [
+ "DPC_tropical_Trends_Hat"
+ ],
+ "red scissors": [
+ "Diamond_Visions_Scissors_Red"
+ ],
+ "toy T-Rex": [
+ "Dino_3"
+ ],
+ "toy triceratops": [
+ "Dino_4"
+ ],
+ "toy dicynodont dinosaur": [
+ "Dino_5"
+ ],
+ "white bowl with purple pattern": [
+ "Dixie_10_ounce_Bowls_35_ct"
+ ],
+ "Dog": [
+ "Dog"
+ ],
+ "white book": [
+ "Eat_to_Live_The_Amazing_NutrientRich_Program_for_Fast_and_Sustained_Weight_Loss_Revised_Edition_Book"
+ ],
+ "turquoise flower pot": [
+ "Ecoforms_Garden_Pot_GP16ATurquois"
+ ],
+ "green flower pot": [
+ "Ecoforms_Plant_Container_12_Pot_Nova"
+ ],
+ "red plant container": [
+ "Ecoforms_Plant_Container_QP6CORAL"
+ ],
+ "brown flower pot": [
+ "Ecoforms_Plant_Container_URN_NAT"
+ ],
+ "dark brown saucer": [
+ "Ecoforms_Plant_Saucer_S20MOCHA"
+ ],
+ "gray elephant toy": [
+ "Elephant"
+ ],
+ "blue cooler bag": [
+ "Embark_Lunch_Cooler_Blue"
+ ],
+ "blue-red soccer cleats": [
+ "F10_TRX_FG_ssscuo9tGxb"
+ ],
+ "yellow soccer cleats": [
+ "F5_TRX_FG"
+ ],
+ "FemDophilus": [
+ "FemDophilus"
+ ],
+ "garden swing": [
+ "GARDEN_SWING"
+ ],
+ "wooden doll": [
+ "GRANDFATHER_DOLL",
+ "GRANDMOTHER"
+ ],
+ "composite cable": [
+ "GoPro_HERO3_Composite_Cable"
+ ],
+ "green android mascot": [
+ "Great_Dinos_Triceratops_Toy"
+ ],
+ "blue dog dish": [
+ "Grreat_Choice_Dog_Double_Dish_Plastic_Blue"
+ ],
+ "red flashlight": [
+ "HeavyDuty_Flashlight"
+ ],
+ "black basket": [
+ "Hefty_Waste_Basket_Decorative_Bronze_85_liter"
+ ],
+ "brown leather boot": [
+ "Hilary",
+ "MARTIN_WEDGE_LACE_BOOT",
+ "Rayna_BootieWP",
+ "Sperry_TopSider_pSUFPWQXPp3",
+ "Sperry_TopSider_tNB9t6YBUf3",
+ "Tory_Burch_Sabe_65mm_Bootie_Split_Suede_in_Caramel",
+ "W_Lou_z0dkC78niiZ"
+ ],
+ "linen cloth": [
+ "Home_Fashions_Washcloth_Linen"
+ ],
+ "olive green cloth": [
+ "Home_Fashions_Washcloth_Olive_Green"
+ ],
+ "pink pencil case": [
+ "Horses_in_Pink_Pencil_Case"
+ ],
+ "green toy ogre": [
+ "Imaginext_Castle_Ogre"
+ ],
+ "Inositol": [
+ "Inositol"
+ ],
+ "green JBL portable speaker": [
+ "JBL_Charge_Speaker_portable_wireless_wired_Green"
+ ],
+ "blue and black backpack": [
+ "Jansport_School_Backpack_Blue_Streak"
+ ],
+ "white gift box with red straps": [
+ "KS_Chocolate_Cube_Box_Assortment_By_Neuhaus_2010_Ounces"
+ ],
+ "white keyboard": [
+ "Kanex_MultiSync_Wireless_Keyboard"
+ ],
+ "pale green saucer": [
+ "Kotobuki_Saucer_Dragon_Fly"
+ ],
+ "toy sheep": [
+ "LACING_SHEEP"
+ ],
+ "gray laptop": [
+ "Lenovo_Yoga_2_11"
+ ],
+ "brown teddy bear": [
+ "Lovable_Huggable_Cuddly_Boutique_Teddy_Bear_Beige"
+ ],
+ "green-orange magnifying glass": [
+ "Magnifying_Glassassrt"
+ ],
+ "blue conditioner bottle": [
+ "Marc_Anthony_Skip_Professional_Oil_of_Morocco_Conditioner_with_Argan_Oil"
+ ],
+ "brown leather shoe": [
+ "Mens_ASV_Billfish_Boat_Shoe_in_Dark_Brown_Leather_zdHVHXueI3w",
+ "Mens_Billfish_3Eye_Boat_Shoe_in_Dark_Tan_wyns9HRcEuH",
+ "Mens_Billfish_Slip_On_in_Tan_Beige_aaVUk0tNTv8"
+ ],
+ "sandal": [
+ "NAPA_VALLEY_NAVAJO_SANDAL"
+ ],
+ "white square bowl": [
+ "Neat_Solutions_Character_Bib_2_pack"
+ ],
+ "yellow nesquik chocolate powder canister": [
+ "Nestle_Nesquik_Chocolate_Powder_Flavored_Milk_Additive_109_Oz_Canister"
+ ],
+ "teenage mutant ninja turtle figure": [
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Leonardo",
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Michelangelo",
+ "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Raphael"
+ ],
+ "nikon camera lens": [
+ "Nikon_1_AW1_w11275mm_Lens_Silver"
+ ],
+ "black-red nintendo 2ds console": [
+ "Nintendo_2DS_Crimson_Red"
+ ],
+ "mario action figure": [
+ "Nintendo_Mario_Action_Figure"
+ ],
+ "green yoshi action figure": [
+ "Nintendo_Yoshi_Action_Figure"
+ ],
+ "black-white bowl": [
+ "Now_Designs_Bowl_Akita_Black"
+ ],
+ "green towel": [
+ "Now_Designs_Dish_Towel_Mojave_18_x_28"
+ ],
+ "colorful xylophone": [
+ "OVAL_XYLOPHONE"
+ ],
+ "black-purple spatula": [
+ "OXO_Cookie_Spatula"
+ ],
+ "black can opener": [
+ "OXO_Soft_Works_Can_Opener_SnapLock"
+ ],
+ "green hat with feather": [
+ "Object_REmvBDJStub"
+ ],
+ "white dust pan with brush": [
+ "Ocedar_Snap_On_Dust_Pan_And_Brush_1_ct"
+ ],
+ "turquoise backpack": [
+ "Olive_Kids_Birdie_Sidekick_Backpack"
+ ],
+ "yellow tow giraffe": [
+ "Ortho_Forward_Facing"
+ ],
+ "black helmet": [
+ "Ortho_Forward_Facing_CkAW6rL25xH"
+ ],
+ "toy koala": [
+ "Ortho_Forward_Facing_QCaor9ImJ2G"
+ ],
+ "yellow flower pot": [
+ "Pennington_Electric_Pot_Cabana_4"
+ ],
+ "colorful pencil case": [
+ "Pinwheel_Pencil_Case"
+ ],
+ "white soccer cleats": [
+ "Predator_LZ_TRX_FG",
+ "Predito_LZ_TRX_FG_W"
+ ],
+ "white plate with salad": [
+ "ProSport_Harness_to_Booster_Seat"
+ ],
+ "dark blue towel": [
+ "Provence_Bath_Towel_Royal_Blue"
+ ],
+ "black boot": [
+ "REEF_BANTU"
+ ],
+ "black flip-flop sandal": [
+ "REEF_BRAIDED_CUSHION",
+ "Reef_Star_Cushion_Flipflops_Size_8_Black"
+ ],
+ "white-blue basket": [
+ "RJ_Rabbit_Easter_Basket_Blue"
+ ],
+ "plush racoon": [
+ "Racoon"
+ ],
+ "black gaming mouse": [
+ "Razer_Abyssus_Ambidextrous_Gaming_Mouse",
+ "Razer_Naga_MMO_Gaming_Mouse",
+ "Razer_Taipan_Black_Ambidextrous_Gaming_Mouse"
+ ],
+ "black keyboard": [
+ "Razer_BlackWidow_Stealth_2014_Keyboard_07VFzIVabgh",
+ "Razer_BlackWidow_Ultimate_2014_Mechanical_Gaming_Keyboard",
+ "Razer_Blackwidow_Tournament_Edition_Keyboard"
+ ],
+ "white gaming mouse": [
+ "Razer_Taipan_White_Ambidextrous_Gaming_Mouse"
+ ],
+ "black and red gameboy": [
+ "RedBlack_Nintendo_3DSXL"
+ ],
+ "red hair dryer": [
+ "Remington_TStudio_Hair_Dryer"
+ ],
+ "brown hat": [
+ "Retail_Leadership_Summit"
+ ],
+ "gray hat": [
+ "Retail_Leadership_Summit_eCT3zqHYIkX"
+ ],
+ "blue gloves": [
+ "Rexy_Glove_Heavy_Duty_Gloves_Medium"
+ ],
+ "turquoise bowl": [
+ "Room_Essentials_Bowl_Turquiose"
+ ],
+ "white-yellow mug": [
+ "Room_Essentials_Mug_White_Yellow"
+ ],
+ "turquoise plate": [
+ "Room_Essentials_Salad_Plate_Turquoise"
+ ],
+ "dish drainer": [
+ "Rubbermaid_Large_Drainer"
+ ],
+ "brown shoe": [
+ "SAMBA_HEMP"
+ ],
+ "sandwich on plate": [
+ "SANDWICH_MEAL"
+ ],
+ "yellow school bus": [
+ "SCHOOL_BUS"
+ ],
+ "wooden ring stacker toy": [
+ "STACKING_RING"
+ ],
+ "rhino": [
+ "Schleich_African_Black_Rhino"
+ ],
+ "bald eagle": [
+ "Schleich_Bald_Eagle"
+ ],
+ "brown bull": [
+ "Schleich_Hereford_Bull"
+ ],
+ "lion": [
+ "Schleich_Lion_Action_Figure"
+ ],
+ "unicorn": [
+ "Schleich_S_Bayala_Unicorn_70432"
+ ],
+ "metal hard drive storage": [
+ "Seagate_Archive_HDD_8_TB_Internal_hard_drive_SATA_6Gbs_35_ST8000AS0002"
+ ],
+ "shark": [
+ "Shark",
+ "Weisshai_Great_White_Shark"
+ ],
+ "purple tape": [
+ "Shurtape_30_Day_Removal_UV_Delct_15"
+ ],
+ "gray tape": [
+ "Shurtape_Gaffers_Tape_Silver_2_x_60_yd"
+ ],
+ "grey elephant toy": [
+ "Sootheze_Cold_Therapy_Elephant"
+ ],
+ "orca toy": [
+ "Sootheze_Toasty_Orca"
+ ],
+ "spider man action figure": [
+ "SpiderMan_Titan_Hero_12Inch_Action_Figure_5Hnn4mtkFsP",
+ "SpiderMan_Titan_Hero_12Inch_Action_Figure_oo1qph4wwiW"
+ ],
+ "toy squirrel": [
+ "Squirrel"
+ ],
+ "bamboo sushi mat": [
+ "Sushi_Mat"
+ ],
+ "blue-white striped towel": [
+ "Tag_Dishtowel_Dobby_Stripe_Blue_18_x_26"
+ ],
+ "green-white striped towel": [
+ "Tag_Dishtowel_Green"
+ ],
+ "green toy train": [
+ "Thomas_Friends_Woodan_Railway_Henry"
+ ],
+ "woven storage basket": [
+ "Threshold_Basket_Natural_Finish_Fabric_Liner_Small"
+ ],
+ "white-red plate": [
+ "Threshold_Bistro_Ceramic_Dinner_Plate_Ruby_Ring"
+ ],
+ "white mug": [
+ "Threshold_Porcelain_Coffee_Mug_All_Over_Bead_White"
+ ],
+ "white porcelain teapot": [
+ "Threshold_Porcelain_Teapot_White"
+ ],
+ "white square saucer": [
+ "Threshold_Salad_Plate_Square_Rim_Porcelain"
+ ],
+ "pink bath towel": [
+ "Threshold_Textured_Damask_Bath_Towel_Pink"
+ ],
+ "rectangular porcelain tray": [
+ "Threshold_Tray_Rectangle_Porcelain"
+ ],
+ "white-pink dog bowl": [
+ "Top_Paw_Dog_Bow_Bone_Ceramic_13_fl_oz_total"
+ ],
+ "blue dog bowl": [
+ "Top_Paw_Dog_Bowl_Blue_Paw_Bone_Ceramic_25_fl_oz_total"
+ ],
+ "white animal dog toy": [
+ "Toysmith_Windem_Up_Flippin_Animals_Dog"
+ ],
+ "black laptop": [
+ "Travel_Mate_P_series_Notebook"
+ ],
+ "black power pressure cooker": [
+ "TriStar_Products_PPC_Power_Pressure_Cooker_XL_in_Black"
+ ],
+ "yellow ballet shoe": [
+ "Unmellow_Yellow_Tieks_Neon_Patent_Leather_Ballet_Flats"
+ ],
+ "green turtle toy": [
+ "Vtech_Roll_Learn_Turtle"
+ ],
+ "white shoe": [
+ "Womens_Canvas_Bahama_in_White_4UyOhP6rYGO"
+ ],
+ "black sneaker": [
+ "adistar_boost_m"
+ ]
+}
\ No newline at end of file
diff --git a/eq-kubric/create_scene.py b/eq-kubric/create_scene.py
new file mode 100644
index 0000000000000000000000000000000000000000..cec5c9760e949de6b1d96c4a2506c3394a193589
--- /dev/null
+++ b/eq-kubric/create_scene.py
@@ -0,0 +1,49 @@
+import subprocess
+
+def create_scene(index: int, dataset_type="location", max_num_objects=1, retries=10, log_file="logs/error_log.txt", verbose=False) -> int:
+ """
+ Attempts to create a data entry point in a dataset by running a Docker container that executes a Python script.
+
+ This function tries to execute a command to create a scene up to a specified number of retries. It logs the attempts and errors to a specified file. If successful, it returns 1; if it fails after all retries, it returns 0.
+
+ Args:
+ index (int): The index of the scene to generate, which affects the generate_idx parameter in the command.
+ dataset_type (str): The type of the dataset, which customizes the Python script to be executed.
+ max_num_objects (int): The maximum number of objects to include in the scene.
+ retries (int): The number of attempts to make in case of failure.
+ log_file (str): Path to the file where error logs are appended.
+
+ Returns:
+ int: 0 if the scene was successfully created, 1 otherwise.
+
+ Raises:
+ None directly by the function, but subprocess.run may raise an exception if the command execution fails critically.
+
+ Side Effects:
+ Writes to a log file at `log_file` path if any errors occur during the execution.
+ Tries to execute a Docker command which can affect system resources and Docker state.
+ """
+ command = f"""
+ sudo docker run --rm --interactive \
+ --user $(id -u):$(id -g) \
+ --volume "$(pwd):/kubric" kubricdockerhub/kubruntu \
+ /usr/bin/python3 eq-kubric/my_kubric_twoframe_{dataset_type}.py \
+ --sub_outputdir {dataset_type} \
+ --generate_idx {index+1} \
+ --max_num_objects {max_num_objects}
+ """
+
+ attempt = 0
+ while attempt < retries:
+ result = subprocess.run(command, shell=True, capture_output=True, text=True)
+ if result.returncode == 0 and ("INFO:root:Done!" in result.stderr or "INFO:root:Done!" in result.stdout):
+ return 0
+ attempt += 1
+ if verbose:
+ print(f"Attempt {attempt} failed with return code {result.returncode}.")
+ print(result.stderr)
+
+ error_message = f"Failed to create a scene after {attempt} attempts: Index: {index+1}, Dataset Type: '{dataset_type}'."
+ with open(log_file, "a") as file:
+ file.write(f"{error_message}\n")
+ return 1
diff --git a/eq-kubric/main.py b/eq-kubric/main.py
new file mode 100644
index 0000000000000000000000000000000000000000..b35aeb56547aa31c24b01083ec9fbd69f6fe5182
--- /dev/null
+++ b/eq-kubric/main.py
@@ -0,0 +1,16 @@
+import argparse
+from create_dataset import create_dataset
+
+def main():
+ parser = argparse.ArgumentParser(description='Create a dataset.')
+ parser.add_argument('dataset_length', type=int, help='The length of the dataset')
+ parser.add_argument('--dataset_type', type=str, default='location', help='Type of dataset to create (default: location)')
+ parser.add_argument('--max_num_objects', type=int, default=4, help='Maximum number of objects in the scene (default: 4)')
+ parser.add_argument('--n_jobs', type=int, default=1, help='Number of parallel jobs to run (default: 1)')
+ parser.add_argument('--verbose', action='store_true', help='Print verbose output')
+
+ args = parser.parse_args()
+ create_dataset(args.dataset_length, args.dataset_type, args.max_num_objects, args.n_jobs, args.verbose)
+
+if __name__ == '__main__':
+ main()
diff --git a/eq-kubric/my_kubric_twoframe_attribute.py b/eq-kubric/my_kubric_twoframe_attribute.py
new file mode 100644
index 0000000000000000000000000000000000000000..c56b54b7e862d108483357838b006b43a8339153
--- /dev/null
+++ b/eq-kubric/my_kubric_twoframe_attribute.py
@@ -0,0 +1,587 @@
+# Copyright 2022 The Kubric Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Worker file for the Multi-Object Video (MOVi) C (and CC) datasets.
+ * The number of objects is randomly chosen between
+ --min_num_objects (3) and --max_num_objects (10)
+ * The objects are randomly chosen from the Google Scanned Objects dataset
+
+ * Background is an random HDRI from the HDRI Haven dataset,
+ projected onto a Dome (half-sphere).
+ The HDRI is also used for lighting the scene.
+"""
+
+import logging
+
+import bpy
+import copy
+import os
+import kubric as kb
+from kubric.simulator import PyBullet
+from kubric.renderer import Blender
+import numpy as np
+import random
+import shutil
+
+from GSO_transfer import GSO_dict, GSO_dict_attr
+from utils import save_scene_instruction, dataset_dir
+
+# --- Some configuration values
+DATASET_TYPE = "attribute"
+# the region in which to place objects [(min), (max)]
+SPAWN_REGION = [(-8, -8, 0), (8, 8, 5)]
+SPAWN_REGION_OBJ = [[-6, -6, 0.5], [6, 6, 0.5]]
+VELOCITY_RANGE = [(-4., -4., 0.), (4., 4., 0.)]
+
+# --- CLI arguments
+parser = kb.ArgumentParser()
+parser.add_argument("--objects_split", choices=["train", "test"],
+ default="train")
+# Configuration for the objects of the scene
+parser.add_argument("--min_num_objects", type=int, default=1,
+ help="minimum number of objects")
+parser.add_argument("--max_num_objects", type=int, default=4,
+ help="maximum number of objects")
+# Configuration for the floor and background
+parser.add_argument("--floor_friction", type=float, default=0.3)
+parser.add_argument("--floor_restitution", type=float, default=0.5)
+parser.add_argument("--backgrounds_split", choices=["train", "test"],
+ default="train")
+
+parser.add_argument("--camera", choices=["fixed_random", "linear_movement"],
+ default="fixed_random")
+parser.add_argument("--max_camera_movement", type=float, default=4.0)
+parser.add_argument("--smallest_scale", type=float, default=1.5)
+parser.add_argument("--largest_scale", type=float, default=4.)
+
+# Configuration for the source of the assets
+parser.add_argument("--kubasic_assets", type=str,
+ default="gs://kubric-public/assets/KuBasic/KuBasic.json")
+parser.add_argument("--hdri_assets", type=str,
+ default="gs://kubric-public/assets/HDRI_haven/HDRI_haven.json")
+parser.add_argument("--gso_assets", type=str,
+ default="gs://kubric-public/assets/GSO/GSO.json")
+parser.add_argument("--save_state", dest="save_state", action="store_true")
+parser.set_defaults(save_state=False, frame_end=24, frame_rate=12,
+ resolution=512)
+parser.add_argument("--sub_outputdir", type=str, default="test sub output dir")
+parser.add_argument("--generate_idx", type=int, default=-1, help="generation idx")
+FLAGS = parser.parse_args()
+
+
+import pyquaternion as pyquat
+def default_rng():
+ return np.random.RandomState()
+
+
+# def random_rotation(axis=None, rng=default_rng()):
+# """ Compute a random rotation as a quaternion.
+# If axis is None the rotation is sampled uniformly over all possible orientations.
+# Otherwise it corresponds to a random rotation around the given axis."""
+
+# if axis is None:
+# # uniform across rotation space
+# # copied from pyquat.Quaternion.random to be able to use a custom rng
+# r1, r2, r3 = rng.random(3)
+
+# q1 = np.sqrt(1.0 - r1) * (np.sin(2 * np.pi * r2))
+# q2 = np.sqrt(1.0 - r1) * (np.cos(2 * np.pi * r2))
+# q3 = np.sqrt(r1) * (np.sin(2 * np.pi * r3))
+# q4 = np.sqrt(r1) * (np.cos(2 * np.pi * r3))
+
+# return q1, q2, q3, q4
+
+# else:
+# if isinstance(axis, str) and axis.upper() in ["X", "Y", "Z"]:
+# axis = {"X": (1., 0., 0.),
+# "Y": (0., 1., 0.),
+# "Z": (0., 0., 1.)}[axis.upper()]
+
+# # quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(0, 2*np.pi))
+# quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(-0.5*np.pi, 0.5*np.pi)) # -0.5pi -- 0.5pi
+# return tuple(quat)
+
+
+# from kubric.core import objects
+# def rotation_sampler(axis=None):
+# def _sampler(obj: objects.PhysicalObject, rng):
+# obj.quaternion = random_rotation(axis=axis, rng=rng)
+# return _sampler
+
+
+def move_until_no_overlap(asset, simulator, spawn_region=((-1, -1, -1), (1, 1, 1)), max_trials=100,
+ rng=default_rng()):
+ return kb.randomness.resample_while(asset,
+ samplers=[kb.randomness.position_sampler(spawn_region)],
+ condition=simulator.check_overlap,
+ max_trials=max_trials,
+ rng=rng)
+
+
+def check_ok(obj, pos, region):
+ # import pdb; pdb.set_trace()
+ x, y, z = pos
+ if pos[0]region[1][0] or pos[1]region[1][1]: #or pos[2]region[1][2]:
+ return False
+
+ if simulator.check_overlap(obj):
+ return False
+
+ return True
+
+
+def get_obj_x_left(bound, scale):
+ return -bound[0][0] * scale[0]
+
+def get_obj_x_right(bound, scale):
+ return bound[1][0] * scale[0]
+
+def get_obj_y_front(bound, scale):
+ return -bound[0][1] * scale[1]
+
+def get_obj_y_behind(bound, scale):
+ return bound[1][1] * scale[1]
+
+def get_obj_z(bound, scale):
+ return bound[0][2] * scale[2]
+
+def get_obj_z_up(bound, scale):
+ return bound[1][2] * scale[2]
+
+
+def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+
+ obj_z = - get_obj_z(bounds, scale)
+ # import pdb; pdb.set_trace()
+ ref_x_left, ref_x_right, ref_y_front, ref_y_behind = get_obj_x_left(ref_object.bounds, ref_object.scale), get_obj_x_right(ref_object.bounds, ref_object.scale), get_obj_y_front(ref_object.bounds, ref_object.scale), get_obj_y_behind(ref_object.bounds, ref_object.scale)
+ ref_x, ref_y, ref_z = ref_pos
+ if ref_location == 'front':
+ return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y-ref_y_front-6, ref_y-ref_y_front-2), obj_z+0.02]
+ elif ref_location == 'behind':
+ return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y+ref_y_behind+3, ref_y+ref_y_behind+7), obj_z+0.02]
+ elif ref_location == 'left':
+ return [rng.uniform(ref_x-ref_x_left-6, ref_x-ref_x_left-2), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+ elif ref_location == 'right':
+ return [rng.uniform(ref_x+ref_x_right+2, ref_x+ref_x_right+6), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+ elif ref_location == 'on':
+ return [ref_x, ref_y, ref_z+ref_z_up+obj_z+1]
+
+def get_second_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+ obj_z = -get_obj_z(bounds, scale)
+ ref_x, ref_y, ref_z = ref_pos
+
+ if ref_location == 'on':
+ return [ref_x, ref_y, ref_z]
+ else:
+ return [ref_x, ref_y, obj_z + 0.02]
+
+
+def add_new_obj(scene, new_obj, ref_location, ref_object, rng, max_trails=50, second_obj=False):
+
+ ref_obj_pos = ref_object.position
+ # import pdb; pdb.set_trace()
+ ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+ if not second_obj:
+ new_obj_pos = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ else:
+ new_obj_pos = get_second_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ new_obj.position = new_obj_pos
+ scene += new_obj
+
+ # import pdb; pdb.set_trace()
+ trails = 0
+ while not check_ok(new_obj, new_obj.position, SPAWN_REGION_OBJ):
+ trails += 1
+ # import pdb; pdb.set_trace()
+ # new_obj.position = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ if not second_obj:
+ new_obj_pos = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ else:
+ new_obj_pos = get_second_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ new_obj.position = new_obj_pos
+ # new_obj.quaternion = random_rotation(axis="Z", rng=rng)
+ if trails > max_trails:
+ print('cannot put the object, break')
+ # import pdb; pdb.set_trace()
+ return None
+ print('try {} times'.format(trails))
+ return scene
+
+def gen_caption(obj_name, obj_scale, ref_obj_name, ref_obj_scale, use_attr):
+ def get_change_size_exp(obj_scale, ref_obj_scale):
+ if obj_scale < ref_obj_scale:
+ return random.choice(["smaller", "small"])
+ elif obj_scale > ref_obj_scale:
+ return random.choice(["larger", "bigger", "large", "big"])
+ else:
+ return "same size"
+
+ ref_obj_size_exp = get_change_size_exp(obj_scale, ref_obj_scale)
+
+ if use_attr != "scale":
+ edit_instruction = random.choice(["transform", "convert", "turn"])
+ caption = f'{edit_instruction} the {ref_obj_name} into a {obj_name}'
+ else:
+ edit_instruction = random.choice(["make", "turn"])
+ caption = f'{edit_instruction} the {ref_obj_name} {ref_obj_size_exp}'
+ return caption
+
+def sample_unique_items(GSO_dict, num_samples):
+ unique_items = {}
+ sampled_values = set()
+ active_keys = list(GSO_dict.keys())
+
+ while len(unique_items) < num_samples:
+ key = random.choice(active_keys)
+ value = GSO_dict[key]
+
+ if value not in sampled_values:
+ sampled_values.add(value)
+ unique_items[key] = value
+
+ active_keys.remove(key)
+ if not active_keys:
+ break
+
+ return list(unique_items.keys())
+
+# --- Common setups & resources
+print('Generate {} Sample'.format(FLAGS.generate_idx))
+scene, rng, output_dir, scratch_dir = kb.setup(FLAGS)
+output_dir = output_dir / FLAGS.sub_outputdir
+
+simulator = PyBullet(scene, scratch_dir)
+renderer = Blender(scene, scratch_dir, samples_per_pixel=64)
+kubasic = kb.AssetSource.from_manifest(FLAGS.kubasic_assets)
+gso = kb.AssetSource.from_manifest(FLAGS.gso_assets)
+hdri_source = kb.AssetSource.from_manifest(FLAGS.hdri_assets)
+
+# --- Populate the scene
+# background HDRI
+train_backgrounds, test_backgrounds = hdri_source.get_test_split(fraction=0.)
+logging.info("Choosing one of the %d training backgrounds...", len(train_backgrounds))
+hdri_id = rng.choice(train_backgrounds)
+
+background_hdri = hdri_source.create(asset_id=hdri_id)
+#assert isinstance(background_hdri, kb.Texture)
+logging.info("Using background %s", hdri_id)
+scene.metadata["background"] = hdri_id
+renderer._set_ambient_light_hdri(background_hdri.filename)
+
+
+# Dome
+dome = kubasic.create(asset_id="dome", name="dome",
+ friction=FLAGS.floor_friction,
+ restitution=FLAGS.floor_restitution,
+ static=True, background=True)
+assert isinstance(dome, kb.FileBasedObject)
+scene += dome
+dome_blender = dome.linked_objects[renderer]
+texture_node = dome_blender.data.materials[0].node_tree.nodes["Image Texture"]
+texture_node.image = bpy.data.images.load(background_hdri.filename)
+
+def get_linear_camera_motion_start_end(
+ movement_speed: float,
+ inner_radius: float = 8.,
+ outer_radius: float = 12.,
+ z_offset: float = 0.1,
+):
+ """Sample a linear path which starts and ends within a half-sphere shell."""
+ while True:
+ camera_start = np.array(kb.sample_point_in_half_sphere_shell(inner_radius,
+ outer_radius,
+ z_offset))
+ direction = rng.rand(3) - 0.5
+ movement = direction / np.linalg.norm(direction) * movement_speed
+ camera_end = camera_start + movement
+ if (inner_radius <= np.linalg.norm(camera_end) <= outer_radius and
+ camera_end[2] > z_offset):
+ return camera_start, camera_end
+
+
+# Camera
+logging.info("Setting up the Camera...")
+scene.camera = kb.PerspectiveCamera(focal_length=35., sensor_width=36)
+if FLAGS.camera == "fixed_random":
+ # scene.camera.position = kb.sample_point_in_half_sphere_shell(
+ # inner_radius=7., outer_radius=9., offset=4)
+ scene.camera.position = (0, -10, 12)
+ scene.camera.look_at((0, 0, 0))
+elif FLAGS.camera == "linear_movement":
+ camera_start, camera_end = get_linear_camera_motion_start_end(
+ movement_speed=rng.uniform(low=0., high=FLAGS.max_camera_movement)
+ )
+ # linearly interpolate the camera position between these two points
+ # while keeping it focused on the center of the scene
+ # we start one frame early and end one frame late to ensure that
+ # forward and backward flow are still consistent for the last and first frames
+ for frame in range(FLAGS.frame_start - 1, FLAGS.frame_end + 2):
+ interp = ((frame - FLAGS.frame_start + 1) /
+ (FLAGS.frame_end - FLAGS.frame_start + 3))
+ scene.camera.position = (interp * np.array(camera_start) +
+ (1 - interp) * np.array(camera_end))
+ scene.camera.look_at((0, 0, 0))
+ scene.camera.keyframe_insert("position", frame)
+ scene.camera.keyframe_insert("quaternion", frame)
+
+
+# Add random objects
+active_split = list(GSO_dict_attr['base_set'].keys())
+num_objects = rng.randint(FLAGS.min_num_objects,
+ FLAGS.max_num_objects+1)
+
+logging.info("Step 1: Randomly placing %d objects:", num_objects)
+object_state_save_dict = {}
+object_state_ref_dict = {}
+
+
+# not resample objects
+# object_id_list = random.sample(active_split, num_objects)
+object_id_list = sample_unique_items(GSO_dict, num_objects+1)
+
+for i in range(num_objects):
+ # object_id = rng.choice(active_split)
+ object_id = object_id_list[i]
+ obj = gso.create(asset_id=object_id)
+
+
+ assert isinstance(obj, kb.FileBasedObject)
+ scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+ obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+
+
+ obj_pos_z = - get_obj_z(obj.bounds, obj.scale)
+ SPAWN_REGION_OBJ[0][2], SPAWN_REGION_OBJ[1][2] = obj_pos_z, obj_pos_z
+ obj.position = rng.uniform(*SPAWN_REGION_OBJ)
+
+ obj.metadata["scale"] = scale
+ scene += obj
+ move_until_no_overlap(obj, simulator, spawn_region=SPAWN_REGION_OBJ, rng=rng)
+ # initialize velocity randomly but biased towards center
+ # obj.velocity = (rng.uniform(*VELOCITY_RANGE) -
+ # [obj.position[0], obj.position[1], 0])
+ # print(obj.position)
+ obj.velocity = [0, 0, 0]
+ logging.info(" Added %s at %s", obj.asset_id, obj.position)
+ object_state_save_dict[i] = {'object_id': object_id,
+ 'object_scale': obj.scale,
+ 'object_quaternion': obj.quaternion,
+ 'object_bounds': obj.bounds}
+ object_state_ref_dict[i] = {'object': obj}
+
+
+
+# # choose the object to change the attribute
+# active_split_choose = random.choice(list(GSO_dict_attr['choose_set'].keys()))
+# object_choose1, object_choose2 = random.sample(list(GSO_dict_attr['choose_set'][active_split_choose].keys()), 2)
+# # choose the ref object and the location
+# ref_object = object_state_ref_dict[rng.choice(list(object_state_ref_dict.keys()))]['object'] # random choose an reference object
+# ref_object_name = GSO_dict[ref_object.asset_id]
+# ref_location = ref_object.position
+
+# random choose two location
+LOC_SET = ['front', 'behind', 'left', 'right', 'on']
+use_location = random.sample(LOC_SET, 1)[0]
+ATTR_SET = [use_location, 'scale']
+use_attr = random.sample(ATTR_SET, 1)[0]
+
+if use_attr != 'scale':
+ # choose the object to change the attribute
+ active_split_choose = random.choice(list(GSO_dict_attr['choose_set'].keys()))
+ object_choose1, object_choose2 = random.sample(list(GSO_dict_attr['choose_set'][active_split_choose].keys()), 2)
+ # choose the ref object and the location
+ ref_object = object_state_ref_dict[rng.choice(list(object_state_ref_dict.keys()))]['object'] # random choose an reference object
+ ref_object_name = GSO_dict[ref_object.asset_id]
+ ref_location = ref_object.position
+
+ # 1st
+ print('Generate the first scene.')
+ # object_id = rng.choice(active_split)
+ object_id = object_choose1
+ obj = gso.create(asset_id=object_id)
+ scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+ obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+ obj.metadata["scale"] = scale
+
+ new_object_name = GSO_dict_attr['choose_set'][active_split_choose][object_id]
+ print('Add new object {}'.format(new_object_name))
+
+
+ # obj 2
+ object2_id = object_choose2
+ obj2 = gso.create(asset_id=object2_id)
+ # scale2 = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+ # obj2.scale = scale2 / np.max(obj2.bounds[1] - obj2.bounds[0])
+ # obj2.metadata["scale"] = scale2
+ obj2.scale = scale / np.max(obj2.bounds[1] - obj2.bounds[0])
+ obj2.metadata["scale"] = scale
+
+ new_object2_name = GSO_dict_attr['choose_set'][active_split_choose][object2_id] # Updated to use object2_id
+ print('Add second object {}'.format(new_object2_name)) # Refers to new_object2_name
+ #obj 2
+
+ scene = add_new_obj(scene, obj, use_attr, ref_object, rng, max_trails=500)
+ if scene is None:
+ exit()
+ frame = renderer.render_still()
+
+ os.makedirs(output_dir/'{}'.format(FLAGS.generate_idx), exist_ok=True)
+ kb.write_png(frame["rgba"], output_dir/"{}/image0.png".format(FLAGS.generate_idx))
+ caption_1 = gen_caption(new_object_name, obj.metadata["scale"], new_object2_name, obj2.metadata["scale"], use_attr)
+ print(caption_1)
+
+ # 2nd
+ print('Generate the second scene.')
+ scene.remove(obj)
+ scene = add_new_obj(scene, obj2, use_attr, obj, rng, max_trails=500, second_obj=True)
+
+ if scene is None:
+ print('cannot put the object, break')
+ shutil.rmtree(output_dir / '{}'.format(FLAGS.generate_idx))
+ exit()
+
+ frame = renderer.render_still()
+ kb.write_png(frame["rgba"], output_dir/"{}/image1.png".format(FLAGS.generate_idx))
+ caption_2 = gen_caption(new_object2_name, obj2.metadata["scale"], new_object_name, obj.metadata["scale"], use_attr)
+ print(caption_2)
+else:
+ # choose the object to change the attribute
+ # active_split_choose = random.choice(list(GSO_dict_attr['choose_set'].keys()))
+ # object_choose1, object_choose2 = random.sample(list(GSO_dict_attr['choose_set'][active_split_choose].keys()), 2)
+ object_choose1 = random.choice(list(GSO_dict.keys()))
+
+ # choose the ref object and the location
+ ref_object = object_state_ref_dict[rng.choice(list(object_state_ref_dict.keys()))]['object'] # random choose an reference object
+ ref_object_name = GSO_dict[ref_object.asset_id]
+ ref_location = ref_object.position
+
+ # 1st
+ print('Generate the first scene.')
+ # object_id = rng.choice(active_split)
+ object_id = object_choose1
+ obj = gso.create(asset_id=object_id)
+ scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+ obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+ obj.metadata["scale"] = scale
+
+ new_object_name = GSO_dict[object_id]
+ print('Add new object {}'.format(new_object_name))
+
+
+ # obj 2
+ object2_id = object_choose1
+ obj2 = gso.create(asset_id=object2_id)
+ scale2 = rng.uniform(FLAGS.smallest_scale-1, FLAGS.largest_scale+2)
+ obj2.scale = scale2 / np.max(obj2.bounds[1] - obj2.bounds[0])
+ obj2.metadata["scale"] = scale2
+
+ new_object2_name = GSO_dict[object2_id] # Updated to use object2_id
+ print('Add second object {}'.format(new_object2_name)) # Refers to new_object2_name
+ #obj 2
+
+ scene = add_new_obj(scene, obj, use_location, ref_object, rng, max_trails=500)
+ if scene is None:
+ exit()
+ frame = renderer.render_still()
+
+ os.makedirs(output_dir/'{}'.format(FLAGS.generate_idx), exist_ok=True)
+ kb.write_png(frame["rgba"], output_dir/"{}/image0.png".format(FLAGS.generate_idx))
+ caption_1 = gen_caption(new_object_name, obj.metadata["scale"], new_object2_name, obj2.metadata["scale"], use_attr)
+ print(caption_1)
+
+ # 2nd
+ print('Generate the second scene.')
+ scene.remove(obj)
+ scene = add_new_obj(scene, obj2, use_location, obj, rng, max_trails=500, second_obj=True)
+
+ if scene is None:
+ print('cannot put the object, break')
+ shutil.rmtree(output_dir / '{}'.format(FLAGS.generate_idx))
+ exit()
+
+ frame = renderer.render_still()
+ kb.write_png(frame["rgba"], output_dir/"{}/image1.png".format(FLAGS.generate_idx))
+ caption_2 = gen_caption(new_object2_name, obj2.metadata["scale"], new_object_name, obj.metadata["scale"], use_attr)
+ print(caption_2)
+
+local_ann = [
+ {
+ 'input': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx),
+ 'output': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx),
+ 'instruction': caption_2,
+ },
+ {
+ 'input': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx),
+ 'output': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx),
+ 'instruction': caption_1,
+ }
+]
+save_scene_instruction(f"{output_dir}/eq_kubric_{DATASET_TYPE}.json", local_ann, DATASET_TYPE, FLAGS.generate_idx)
+
+kb.done()
+
+# if FLAGS.save_state:
+# logging.info("Saving the simulator state to '%s' prior to the simulation.",
+# output_dir / "scene.bullet")
+# simulator.save_state(output_dir / "scene.bullet")
+#
+# # Run dynamic objects simulation
+# logging.info("Running the simulation ...")
+# animation, collisions = simulator.run(frame_start=0,
+# frame_end=scene.frame_end+1)
+#
+# # --- Rendering
+# if FLAGS.save_state:
+# logging.info("Saving the renderer state to '%s' ",
+# output_dir / "scene.blend")
+# renderer.save_state(output_dir / "scene.blend")
+#
+#
+# logging.info("Rendering the scene ...")
+# data_stack = renderer.render()
+#
+# # --- Postprocessing
+# kb.compute_visibility(data_stack["segmentation"], scene.assets)
+# visible_foreground_assets = [asset for asset in scene.foreground_assets
+# if np.max(asset.metadata["visibility"]) > 0]
+# visible_foreground_assets = sorted( # sort assets by their visibility
+# visible_foreground_assets,
+# key=lambda asset: np.sum(asset.metadata["visibility"]),
+# reverse=True)
+#
+# data_stack["segmentation"] = kb.adjust_segmentation_idxs(
+# data_stack["segmentation"],
+# scene.assets,
+# visible_foreground_assets)
+# scene.metadata["num_instances"] = len(visible_foreground_assets)
+#
+# # Save to image files
+# kb.write_image_dict(data_stack, output_dir)
+# kb.post_processing.compute_bboxes(data_stack["segmentation"],
+# visible_foreground_assets)
+#
+# # --- Metadata
+# logging.info("Collecting and storing metadata for each object.")
+# kb.write_json(filename=output_dir / "metadata.json", data={
+# "flags": vars(FLAGS),
+# "metadata": kb.get_scene_metadata(scene),
+# "camera": kb.get_camera_info(scene.camera),
+# "instances": kb.get_instance_info(scene, visible_foreground_assets),
+# })
+# kb.write_json(filename=output_dir / "events.json", data={
+# "collisions": kb.process_collisions(
+# collisions, scene, assets_subset=visible_foreground_assets),
+# })
+#
+# kb.done()
diff --git a/eq-kubric/my_kubric_twoframe_closer.py b/eq-kubric/my_kubric_twoframe_closer.py
new file mode 100644
index 0000000000000000000000000000000000000000..78becb932e1b8c97cecea0dc5566cce5975eebe4
--- /dev/null
+++ b/eq-kubric/my_kubric_twoframe_closer.py
@@ -0,0 +1,479 @@
+# Copyright 2022 The Kubric Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Worker file for the Multi-Object Video (MOVi) C (and CC) datasets.
+ * The number of objects is randomly chosen between
+ --min_num_objects (3) and --max_num_objects (10)
+ * The objects are randomly chosen from the Google Scanned Objects dataset
+
+ * Background is an random HDRI from the HDRI Haven dataset,
+ projected onto a Dome (half-sphere).
+ The HDRI is also used for lighting the scene.
+"""
+
+import logging
+
+import bpy
+import copy
+import os
+import kubric as kb
+from kubric.simulator import PyBullet
+from kubric.renderer import Blender
+import numpy as np
+import random
+import shutil
+
+from GSO_transfer import GSO_dict
+from utils import save_scene_instruction, dataset_dir
+
+# --- Some configuration values
+DATASET_TYPE = "closer"
+# the region in which to place objects [(min), (max)]
+SPAWN_REGION = [(-8, -8, 0), (8, 8, 5)]
+SPAWN_REGION_OBJ = [[-6, -6, 0.5], [6, 6, 0.5]]
+VELOCITY_RANGE = [(-4., -4., 0.), (4., 4., 0.)]
+
+# --- CLI arguments
+parser = kb.ArgumentParser()
+parser.add_argument("--objects_split", choices=["train", "test"],
+ default="train")
+# Configuration for the objects of the scene
+parser.add_argument("--min_num_objects", type=int, default=1,
+ help="minimum number of objects")
+parser.add_argument("--max_num_objects", type=int, default=5,
+ help="maximum number of objects")
+# Configuration for the floor and background
+parser.add_argument("--floor_friction", type=float, default=0.3)
+parser.add_argument("--floor_restitution", type=float, default=0.5)
+parser.add_argument("--backgrounds_split", choices=["train", "test"],
+ default="train")
+
+parser.add_argument("--camera", choices=["fixed_random", "linear_movement"],
+ default="fixed_random")
+parser.add_argument("--max_camera_movement", type=float, default=4.0)
+parser.add_argument("--smallest_scale", type=float, default=2.)
+parser.add_argument("--largest_scale", type=float, default=4.)
+
+# Configuration for the source of the assets
+parser.add_argument("--kubasic_assets", type=str,
+ default="gs://kubric-public/assets/KuBasic/KuBasic.json")
+parser.add_argument("--hdri_assets", type=str,
+ default="gs://kubric-public/assets/HDRI_haven/HDRI_haven.json")
+parser.add_argument("--gso_assets", type=str,
+ default="gs://kubric-public/assets/GSO/GSO.json")
+parser.add_argument("--save_state", dest="save_state", action="store_true")
+parser.set_defaults(save_state=False, frame_end=24, frame_rate=12,
+ resolution=512)
+parser.add_argument("--sub_outputdir", type=str, default="test sub output dir")
+parser.add_argument("--generate_idx", type=int, default=-1, help="generation idx")
+FLAGS = parser.parse_args()
+
+
+import pyquaternion as pyquat
+def default_rng():
+ return np.random.RandomState()
+
+def random_rotation(axis=None, rng=default_rng()):
+ """ Compute a random rotation as a quaternion.
+ If axis is None the rotation is sampled uniformly over all possible orientations.
+ Otherwise it corresponds to a random rotation around the given axis."""
+
+ if axis is None:
+ # uniform across rotation space
+ # copied from pyquat.Quaternion.random to be able to use a custom rng
+ r1, r2, r3 = rng.random(3)
+
+ q1 = np.sqrt(1.0 - r1) * (np.sin(2 * np.pi * r2))
+ q2 = np.sqrt(1.0 - r1) * (np.cos(2 * np.pi * r2))
+ q3 = np.sqrt(r1) * (np.sin(2 * np.pi * r3))
+ q4 = np.sqrt(r1) * (np.cos(2 * np.pi * r3))
+
+ return q1, q2, q3, q4
+
+ else:
+ if isinstance(axis, str) and axis.upper() in ["X", "Y", "Z"]:
+ axis = {"X": (1., 0., 0.),
+ "Y": (0., 1., 0.),
+ "Z": (0., 0., 1.)}[axis.upper()]
+
+ # quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(0, 2*np.pi))
+ quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(-0.5*np.pi, 0.5*np.pi)) # -0.5pi -- 0.5pi
+ return tuple(quat)
+
+
+from kubric.core import objects
+def rotation_sampler(axis=None):
+ def _sampler(obj: objects.PhysicalObject, rng):
+ obj.quaternion = random_rotation(axis=axis, rng=rng)
+ return _sampler
+
+
+def move_until_no_overlap(asset, simulator, spawn_region=((-1, -1, -1), (1, 1, 1)), max_trials=100,
+ rng=default_rng()):
+ return kb.randomness.resample_while(asset,
+ # samplers=[rotation_sampler(axis='Z'), kb.randomness.position_sampler(spawn_region)],
+ samplers=[kb.randomness.position_sampler(spawn_region)],
+ condition=simulator.check_overlap,
+ max_trials=max_trials,
+ rng=rng)
+
+
+def check_ok(obj, pos, region):
+ # import pdb; pdb.set_trace()
+ x, y, z = pos
+ if pos[0]region[1][0] or pos[1]region[1][1]: #or pos[2]region[1][2]:
+ return False
+
+ if simulator.check_overlap(obj):
+ return False
+
+ return True
+
+
+def get_obj_x_left(bound, scale):
+ return -bound[0][0] * scale[0]
+
+def get_obj_x_right(bound, scale):
+ return bound[1][0] * scale[0]
+
+def get_obj_y_front(bound, scale):
+ return -bound[0][1] * scale[1]
+
+def get_obj_y_behind(bound, scale):
+ return bound[1][1] * scale[1]
+
+def get_obj_z(bound, scale):
+ return bound[0][2] * scale[2]
+
+def get_obj_z_up(bound, scale):
+ return bound[1][2] * scale[2]
+
+
+# def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+# obj_z = - get_obj_z(bounds, scale)
+# # import pdb; pdb.set_trace()
+# ref_x_left, ref_x_right, ref_y_front, ref_y_behind = get_obj_x_left(ref_object.bounds, ref_object.scale), get_obj_x_right(ref_object.bounds, ref_object.scale), get_obj_y_front(ref_object.bounds, ref_object.scale), get_obj_y_behind(ref_object.bounds, ref_object.scale)
+# ref_x, ref_y, ref_z = ref_pos
+# if ref_location == 'front':
+# return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y-ref_y_front-6, ref_y-ref_y_front-2), obj_z+0.02]
+# elif ref_location == 'behind':
+# return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y+ref_y_behind+2, ref_y+ref_y_behind+6), obj_z+0.02]
+# elif ref_location == 'left':
+# return [rng.uniform(ref_x-ref_x_left-6, ref_x-ref_x_left-2), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+# elif ref_location == 'right':
+# return [rng.uniform(ref_x+ref_x_right+2, ref_x+ref_x_right+6), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+# elif ref_location == 'on':
+# return [ref_x, ref_y, ref_z+ref_z_up+obj_z+1]
+
+def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+ # Calculate the z-position based on the object's bounds and scale
+ obj_z = -get_obj_z(bounds, scale) + 0.2 # Ensuring the object is slightly above the ground
+
+ # Extract the bounds from the SPAWN_REGION_OBJ variable
+ spawn_x_min, spawn_y_min, _ = SPAWN_REGION_OBJ[0]
+ spawn_x_max, spawn_y_max, _ = SPAWN_REGION_OBJ[1]
+
+ # Calculate the maximum offsets within the given spawn bounds
+ max_offset_x = spawn_x_max - spawn_x_min + 1
+ max_offset_y = spawn_y_max - spawn_y_min + 1
+
+ # Define absolute positions for each location using straightforward calculations
+ import random
+
+ # Return the position for the specified location
+ return locations.get(ref_location, [ref_pos[0], ref_pos[1], obj_z]) # Default position if location is not specified
+
+def add_new_obj(scene, new_obj, ref_location, ref_object, rng, max_trails=50):
+
+ ref_obj_pos = ref_object.position
+ # import pdb; pdb.set_trace()
+ ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+ new_obj_pos = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ new_obj.position = new_obj_pos
+ scene += new_obj
+
+ # import pdb; pdb.set_trace()
+ trails = 0
+ while not check_ok(new_obj, new_obj.position, SPAWN_REGION_OBJ):
+ trails += 1
+ # import pdb; pdb.set_trace()
+ new_obj.position = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ # new_obj.quaternion = random_rotation(axis="Z", rng=rng)
+ if trails > max_trails:
+ print('cannot put the object, break')
+ # import pdb; pdb.set_trace()
+ return None
+ print('try {} times'.format(trails))
+ return scene
+
+def gen_caption(obj_name, obj_scale, ref_obj_name, ref_obj_scale, type='closer'):
+ if type == 'closer':
+ captions = [f'Move the {obj_name} and the {ref_obj_name} closer together.', f'Move the {obj_name} and the {ref_obj_name} closer.', f'Move the {obj_name} and the {ref_obj_name} closer to each other.', f'Move both objects closer', f'Move the two objects closer together.', f'Move the two objects closer to each other.']
+ elif type == 'further':
+ captions = [f'Move the {obj_name} further away from the {ref_obj_name}.', f'Move the {obj_name} and the {ref_obj_name} further apart.', f'Move the {obj_name} and the {ref_obj_name} further away from each other.', f'Move both objects further apart', f'Move the two objects further away from each other.', f'Move the two objects further apart.']
+ elif type == 'swap':
+ captions = [f'Swap the positions of the {obj_name} and the {ref_obj_name}.', f'Swap the positions of the {ref_obj_name} and the {obj_name}.', f'Swap the positions of the two objects.', f'Swap positions of both items.']
+ return random.choice(captions)
+
+
+# --- Common setups & resources
+print('Generate {} Sample'.format(FLAGS.generate_idx))
+scene, rng, output_dir, scratch_dir = kb.setup(FLAGS)
+output_dir = output_dir / FLAGS.sub_outputdir
+
+
+
+simulator = PyBullet(scene, scratch_dir)
+renderer = Blender(scene, scratch_dir, samples_per_pixel=64)
+kubasic = kb.AssetSource.from_manifest(FLAGS.kubasic_assets)
+gso = kb.AssetSource.from_manifest(FLAGS.gso_assets)
+hdri_source = kb.AssetSource.from_manifest(FLAGS.hdri_assets)
+
+
+# --- Populate the scene
+# background HDRI
+train_backgrounds, test_backgrounds = hdri_source.get_test_split(fraction=0.)
+logging.info("Choosing one of the %d training backgrounds...", len(train_backgrounds))
+hdri_id = rng.choice(train_backgrounds)
+
+background_hdri = hdri_source.create(asset_id=hdri_id)
+#assert isinstance(background_hdri, kb.Texture)
+logging.info("Using background %s", hdri_id)
+scene.metadata["background"] = hdri_id
+renderer._set_ambient_light_hdri(background_hdri.filename)
+
+
+# Dome
+dome = kubasic.create(asset_id="dome", name="dome",
+ friction=FLAGS.floor_friction,
+ restitution=FLAGS.floor_restitution,
+ static=True, background=True)
+assert isinstance(dome, kb.FileBasedObject)
+scene += dome
+dome_blender = dome.linked_objects[renderer]
+texture_node = dome_blender.data.materials[0].node_tree.nodes["Image Texture"]
+texture_node.image = bpy.data.images.load(background_hdri.filename)
+
+
+
+def get_linear_camera_motion_start_end(
+ movement_speed: float,
+ inner_radius: float = 8.,
+ outer_radius: float = 12.,
+ z_offset: float = 0.1,
+):
+ """Sample a linear path which starts and ends within a half-sphere shell."""
+ while True:
+ camera_start = np.array(kb.sample_point_in_half_sphere_shell(inner_radius,
+ outer_radius,
+ z_offset))
+ direction = rng.rand(3) - 0.5
+ movement = direction / np.linalg.norm(direction) * movement_speed
+ camera_end = camera_start + movement
+ if (inner_radius <= np.linalg.norm(camera_end) <= outer_radius and
+ camera_end[2] > z_offset):
+ return camera_start, camera_end
+
+
+# Camera
+logging.info("Setting up the Camera...")
+scene.camera = kb.PerspectiveCamera(focal_length=35., sensor_width=36)
+if FLAGS.camera == "fixed_random":
+ # scene.camera.position = kb.sample_point_in_half_sphere_shell(
+ # inner_radius=7., outer_radius=9., offset=4)
+ scene.camera.position = (0, -10, 15)
+ scene.camera.look_at((0, 0, 0))
+elif FLAGS.camera == "linear_movement":
+ camera_start, camera_end = get_linear_camera_motion_start_end(
+ movement_speed=rng.uniform(low=0., high=FLAGS.max_camera_movement)
+ )
+ # linearly interpolate the camera position between these two points
+ # while keeping it focused on the center of the scene
+ # we start one frame early and end one frame late to ensure that
+ # forward and backward flow are still consistent for the last and first frames
+ for frame in range(FLAGS.frame_start - 1, FLAGS.frame_end + 2):
+ interp = ((frame - FLAGS.frame_start + 1) /
+ (FLAGS.frame_end - FLAGS.frame_start + 3))
+ scene.camera.position = (interp * np.array(camera_start) +
+ (1 - interp) * np.array(camera_end))
+ scene.camera.look_at((0, 0, 0))
+ scene.camera.keyframe_insert("position", frame)
+ scene.camera.keyframe_insert("quaternion", frame)
+
+
+# Add random objects
+train_split, test_split = gso.get_test_split(fraction=0.)
+# if FLAGS.objects_split == "train":
+logging.info("Choosing one of the %d training objects...", len(train_split))
+# active_split = train_split
+active_split = list(GSO_dict.keys())
+
+# num_objects = rng.randint(FLAGS.min_num_objects,
+ # FLAGS.max_num_objects+1)
+num_objects = 2
+
+logging.info("Step 1: Randomly placing %d objects:", num_objects)
+object_state_save_dict = {}
+object_state_ref_dict = {}
+
+
+# not resample objects
+object_id_list = random.sample(active_split, num_objects+1)
+
+for i in range(num_objects):
+ # object_id = rng.choice(active_split)
+ object_id = object_id_list[i]
+ obj = gso.create(asset_id=object_id)
+
+
+ assert isinstance(obj, kb.FileBasedObject)
+ scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+ obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+
+
+ obj_pos_z = - get_obj_z(obj.bounds, obj.scale)
+ SPAWN_REGION_OBJ[0][2], SPAWN_REGION_OBJ[1][2] = obj_pos_z, obj_pos_z
+ obj.position = rng.uniform(*SPAWN_REGION_OBJ)
+
+ obj.metadata["scale"] = scale
+ scene += obj
+ move_until_no_overlap(obj, simulator, spawn_region=SPAWN_REGION_OBJ, rng=rng)
+ # initialize velocity randomly but biased towards center
+ # obj.velocity = (rng.uniform(*VELOCITY_RANGE) -
+ # [obj.position[0], obj.position[1], 0])
+ # print(obj.position)
+ obj.velocity = [0, 0, 0]
+ logging.info(" Added %s at %s", obj.asset_id, obj.position)
+ object_state_save_dict[i] = {'object_id': object_id,
+ 'object_scale': obj.scale,
+ 'object_quaternion': obj.quaternion,
+ 'object_bounds': obj.bounds}
+ object_state_ref_dict[i] = {'object': obj}
+
+
+ref_object = object_state_ref_dict[list(object_state_ref_dict.keys())[0]]['object']
+ref_object_name = GSO_dict[ref_object.asset_id]
+ref_location = ref_object.position
+
+obj = object_state_ref_dict[list(object_state_ref_dict.keys())[1]]['object']
+new_object_name = GSO_dict[obj.asset_id]
+
+# 1st
+print('Generate the first scene.')
+# object_id = rng.choice(active_split)
+# object_id = object_id_list[-1]
+# obj = gso.create(asset_id=object_id)
+# scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+# obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+# obj.metadata["scale"] = scale
+
+# new_object_name = GSO_dict[obj.asset_id]
+# print('Add new object {}'.format(new_object_name))
+
+
+# scene = add_new_obj(scene, obj, ref_location1, ref_object, rng, max_trails=500)
+if scene is None:
+ exit()
+frame = renderer.render_still()
+
+edits = ['close', 'swap']
+edit = random.choice(edits)
+
+os.makedirs(output_dir/'{}'.format(FLAGS.generate_idx), exist_ok=True)
+kb.write_png(frame["rgba"], output_dir/"{}/image0.png".format(FLAGS.generate_idx))
+caption_1 = gen_caption(new_object_name, obj.metadata["scale"], ref_object_name, ref_object.metadata["scale"], type="further" if edit == 'close' else 'swap')
+print(caption_1)
+
+
+# save meta ann
+object_state_save_dict[i+1] = {'object_id': object_id,
+ 'object_scale': obj.scale,
+ 'object_pos': obj.position,
+ 'object_quaternion': obj.quaternion,
+ 'object_bounds': obj.bounds}
+# import json
+# json.dump(object_state_save_dict, open(output_dir/'{}/meta_ann1.json'.format(FLAGS.generate_idx), 'w'))
+# np.save(output_dir/'{}/meta_ann1.npy'.format(FLAGS.generate_idx), object_state_save_dict)
+# renderer.save_state(output_dir/'{}/image1.blend'.format(FLAGS.generate_idx))
+
+
+
+# 2nd
+print('Generate the second scene.')
+# delete the last object to generate the second frame
+# import pdb; pdb.set_trace()
+# scene.remove(obj)
+# scene= add_new_obj(scene, obj, ref_location2, ref_object, rng, max_trails=100)
+ref_obj_pos = ref_object.position
+ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+logging.info(f'Object position: {obj.position}')
+
+obj1_pos = obj.position
+obj2_pos = ref_location
+if edit == 'close':
+ direction = obj2_pos - obj1_pos
+ factor1, factor2 = random.uniform(0.1, 0.3), random.uniform(0.1, 0.3)
+ obj.position = obj1_pos + direction * factor1
+ ref_object.position = obj2_pos - direction * factor2
+else:
+ obj.position = obj2_pos
+ ref_object.position = obj1_pos
+
+frame = renderer.render_still()
+kb.write_png(frame["rgba"], output_dir/"{}/image1.png".format(FLAGS.generate_idx))
+caption_2 = gen_caption(new_object_name, obj.metadata["scale"], ref_object_name, ref_object.metadata["scale"], type="closer" if edit == 'close' else 'swap')
+print(caption_2)
+
+# save meta ann
+object_state_save_dict[i+1] = {'object_id': object_id,
+ 'object_scale': obj.scale,
+ 'object_pos': obj.position,
+ 'object_quaternion': obj.quaternion,
+ 'object_bounds': obj.bounds}
+# import json
+# json.dump(object_state_save_dict, open(output_dir/'{}/meta_ann2.json'.format(FLAGS.generate_idx), 'w'))
+# np.save(output_dir/'{}/meta_ann2.npy'.format(FLAGS.generate_idx), object_state_save_dict)
+# renderer.save_state(output_dir/'{}/image2.blend'.format(FLAGS.generate_idx))
+
+
+# save json
+# local_ann = {'image0':"{}/image0.png".format(FLAGS.generate_idx), 'caption0':caption_1,
+# 'image1':"{}/image1.png".format(FLAGS.generate_idx), 'caption1':caption_2,
+# 'ann_path':"{}/ann.json".format(FLAGS.generate_idx),
+# 'obj_num':num_objects+1}
+# json.dump(local_ann, open("{}/{}/ann.json".format(str(output_dir), FLAGS.generate_idx), 'w'))
+
+# import pdb; pdb.set_trace()
+# if not os.path.exists("{}/global_ann.json".format(str(output_dir))):
+# json.dump([], open("{}/global_ann.json".format(str(output_dir)), 'w'))
+# with open("{}/global_ann.json".format(str(output_dir)), 'r') as f:
+# old_data = json.load(f)
+# old_data.append(local_ann)
+# with open("{}/global_ann.json".format(str(output_dir)), "w") as f:
+# json.dump(old_data, f)
+
+local_ann = [{
+ 'input': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx),
+ 'output': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx),
+ 'instruction': caption_2,
+ },
+ {
+ 'input': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx),
+ 'output': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx),
+ 'instruction': caption_1,
+ }
+]
+save_scene_instruction(f"{output_dir}/eq_kubric_{DATASET_TYPE}.json", local_ann, DATASET_TYPE, FLAGS.generate_idx)
+
+kb.done()
diff --git a/eq-kubric/my_kubric_twoframe_rotate.py b/eq-kubric/my_kubric_twoframe_rotate.py
new file mode 100644
index 0000000000000000000000000000000000000000..86396d7e601c8215a5b92a1bfcf7183f306e1ae1
--- /dev/null
+++ b/eq-kubric/my_kubric_twoframe_rotate.py
@@ -0,0 +1,590 @@
+# Copyright 2022 The Kubric Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Worker file for the Multi-Object Video (MOVi) C (and CC) datasets.
+ * The number of objects is randomly chosen between
+ --min_num_objects (3) and --max_num_objects (10)
+ * The objects are randomly chosen from the Google Scanned Objects dataset
+
+ * Background is an random HDRI from the HDRI Haven dataset,
+ projected onto a Dome (half-sphere).
+ The HDRI is also used for lighting the scene.
+"""
+
+import logging
+
+import bpy
+import copy
+import os
+import kubric as kb
+from kubric.simulator import PyBullet
+from kubric.renderer import Blender
+import numpy as np
+import random
+import shutil
+
+from GSO_transfer import GSO_dict
+from utils import save_scene_instruction, dataset_dir
+
+# --- Some configuration values
+DATASET_TYPE = "rotate"
+# the region in which to place objects [(min), (max)]
+SPAWN_REGION = [(-8, -8, 0), (8, 8, 5)]
+SPAWN_REGION_OBJ = [[-6, -6, 0.5], [6, 6, 0.5]]
+VELOCITY_RANGE = [(-4., -4., 0.), (4., 4., 0.)]
+
+# --- CLI arguments
+parser = kb.ArgumentParser()
+parser.add_argument("--objects_split", choices=["train", "test"],
+ default="train")
+# Configuration for the objects of the scene
+parser.add_argument("--min_num_objects", type=int, default=1,
+ help="minimum number of objects")
+parser.add_argument("--max_num_objects", type=int, default=5,
+ help="maximum number of objects")
+# Configuration for the floor and background
+parser.add_argument("--floor_friction", type=float, default=0.3)
+parser.add_argument("--floor_restitution", type=float, default=0.5)
+parser.add_argument("--backgrounds_split", choices=["train", "test"],
+ default="train")
+
+parser.add_argument("--camera", choices=["fixed_random", "linear_movement"],
+ default="fixed_random")
+parser.add_argument("--max_camera_movement", type=float, default=4.0)
+parser.add_argument("--smallest_scale", type=float, default=2.)
+parser.add_argument("--largest_scale", type=float, default=4.)
+
+# Configuration for the source of the assets
+parser.add_argument("--kubasic_assets", type=str,
+ default="gs://kubric-public/assets/KuBasic/KuBasic.json")
+parser.add_argument("--hdri_assets", type=str,
+ default="gs://kubric-public/assets/HDRI_haven/HDRI_haven.json")
+parser.add_argument("--gso_assets", type=str,
+ default="gs://kubric-public/assets/GSO/GSO.json")
+parser.add_argument("--save_state", dest="save_state", action="store_true")
+parser.set_defaults(save_state=False, frame_end=24, frame_rate=12,
+ resolution=512)
+parser.add_argument("--sub_outputdir", type=str, default="test sub output dir")
+parser.add_argument("--generate_idx", type=int, default=-1, help="generation idx")
+FLAGS = parser.parse_args()
+
+
+import pyquaternion as pyquat
+def default_rng():
+ return np.random.RandomState()
+
+import numpy as np
+
+def rotation(axis='Z', degrees=0):
+ """ Compute a specific rotation as a quaternion along a given axis by a specified degree.
+
+ Args:
+ axis (str): Axis to rotate around ('X', 'Y', 'Z').
+ degrees (float): Angle in degrees to rotate around the specified axis.
+
+ Returns:
+ tuple: Quaternion representing the rotation.
+ """
+ # Convert degrees to radians
+ degrees = degrees + random.uniform(-10, 10)
+ radians = np.radians(degrees)
+
+ # Define axes
+ axis_vectors = {
+ 'X': (1., 0., 0.),
+ 'Y': (0., 1., 0.),
+ 'Z': (0., 0., 1.)
+ }
+
+ # Get the axis vector
+ axis_vector = axis_vectors.get(axis.upper(), (0., 0., 1.)) # Default to Z-axis if unspecified
+
+ # Create the quaternion for the rotation
+ quat = pyquat.Quaternion(axis=axis_vector, angle=radians)
+ return tuple(quat)
+
+def random_rotation(axis=None, rng=default_rng()):
+ """ Compute a random rotation as a quaternion.
+ If axis is None the rotation is sampled uniformly over all possible orientations.
+ Otherwise it corresponds to a random rotation around the given axis."""
+
+ if axis is None:
+ # uniform across rotation space
+ # copied from pyquat.Quaternion.random to be able to use a custom rng
+ r1, r2, r3 = rng.random(3)
+
+ q1 = np.sqrt(1.0 - r1) * (np.sin(2 * np.pi * r2))
+ q2 = np.sqrt(1.0 - r1) * (np.cos(2 * np.pi * r2))
+ q3 = np.sqrt(r1) * (np.sin(2 * np.pi * r3))
+ q4 = np.sqrt(r1) * (np.cos(2 * np.pi * r3))
+
+ return q1, q2, q3, q4
+
+ else:
+ if isinstance(axis, str) and axis.upper() in ["X", "Y", "Z"]:
+ axis = {"X": (1., 0., 0.),
+ "Y": (0., 1., 0.),
+ "Z": (0., 0., 1.)}[axis.upper()]
+
+ # quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(0, 2*np.pi))
+ quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(-0.5*np.pi, 0.5*np.pi)) # -0.5pi -- 0.5pi
+ return tuple(quat)
+
+
+from kubric.core import objects
+def rotation_sampler(axis=None):
+ def _sampler(obj: objects.PhysicalObject, rng):
+ obj.quaternion = random_rotation(axis=axis, rng=rng)
+ return _sampler
+
+
+def move_until_no_overlap(asset, simulator, spawn_region=((-1, -1, -1), (1, 1, 1)), max_trials=100,
+ rng=default_rng()):
+ return kb.randomness.resample_while(asset,
+ # samplers=[rotation_sampler(axis='Z'), kb.randomness.position_sampler(spawn_region)],
+ samplers=[kb.randomness.position_sampler(spawn_region)],
+ condition=simulator.check_overlap,
+ max_trials=max_trials,
+ rng=rng)
+
+
+def check_ok(obj, pos, region):
+ # import pdb; pdb.set_trace()
+ x, y, z = pos
+ if pos[0]region[1][0] or pos[1]region[1][1]: #or pos[2]region[1][2]:
+ return False
+
+ if simulator.check_overlap(obj):
+ return False
+
+ return True
+
+
+def get_obj_x_left(bound, scale):
+ return -bound[0][0] * scale[0]
+
+def get_obj_x_right(bound, scale):
+ return bound[1][0] * scale[0]
+
+def get_obj_y_front(bound, scale):
+ return -bound[0][1] * scale[1]
+
+def get_obj_y_behind(bound, scale):
+ return bound[1][1] * scale[1]
+
+def get_obj_z(bound, scale):
+ return bound[0][2] * scale[2]
+
+def get_obj_z_up(bound, scale):
+ return bound[1][2] * scale[2]
+
+
+# def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+# obj_z = - get_obj_z(bounds, scale)
+# # import pdb; pdb.set_trace()
+# ref_x_left, ref_x_right, ref_y_front, ref_y_behind = get_obj_x_left(ref_object.bounds, ref_object.scale), get_obj_x_right(ref_object.bounds, ref_object.scale), get_obj_y_front(ref_object.bounds, ref_object.scale), get_obj_y_behind(ref_object.bounds, ref_object.scale)
+# ref_x, ref_y, ref_z = ref_pos
+# if ref_location == 'front':
+# return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y-ref_y_front-6, ref_y-ref_y_front-2), obj_z+0.02]
+# elif ref_location == 'behind':
+# return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y+ref_y_behind+2, ref_y+ref_y_behind+6), obj_z+0.02]
+# elif ref_location == 'left':
+# return [rng.uniform(ref_x-ref_x_left-6, ref_x-ref_x_left-2), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+# elif ref_location == 'right':
+# return [rng.uniform(ref_x+ref_x_right+2, ref_x+ref_x_right+6), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+# elif ref_location == 'on':
+# return [ref_x, ref_y, ref_z+ref_z_up+obj_z+1]
+
+def sample_unique_items(GSO_dict, num_samples):
+ unique_items = {}
+ sampled_values = set()
+ active_keys = list(GSO_dict.keys())
+
+ while len(unique_items) < num_samples:
+ key = random.choice(active_keys)
+ value = GSO_dict[key]
+
+ if value not in sampled_values:
+ sampled_values.add(value)
+ unique_items[key] = value
+
+ active_keys.remove(key)
+ if not active_keys:
+ break
+
+ return list(unique_items.keys())
+
+
+def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+ # Calculate the z-position based on the object's bounds and scale
+ obj_z = -get_obj_z(bounds, scale) + 0.2 # Ensuring the object is slightly above the ground
+
+ # Extract the bounds from the SPAWN_REGION_OBJ variable
+ spawn_x_min, spawn_y_min, _ = SPAWN_REGION_OBJ[0]
+ spawn_x_max, spawn_y_max, _ = SPAWN_REGION_OBJ[1]
+
+ # Calculate the maximum offsets within the given spawn bounds
+ max_offset_x = spawn_x_max - spawn_x_min + 1
+ max_offset_y = spawn_y_max - spawn_y_min + 1
+
+ # Define absolute positions for each location using straightforward calculations
+ import random
+
+ locations = {
+ 'closer': [ref_pos[0], max(spawn_y_min, ref_pos[1] - max_offset_y) * random.uniform(0.5, 1.2), obj_z],
+ 'further away': [ref_pos[0], min(spawn_y_max, ref_pos[1] + max_offset_y) * random.uniform(0.5, 1.2), obj_z],
+ 'further left': [max(spawn_x_min, ref_pos[0] - max_offset_x) * random.uniform(0.5, 1.2), ref_pos[1], obj_z],
+ 'further right': [min(spawn_x_max, ref_pos[0] + max_offset_x) * random.uniform(0.5, 1.2), ref_pos[1], obj_z],
+ }
+
+ # Return the position for the specified location
+ return locations.get(ref_location, [ref_pos[0], ref_pos[1], obj_z]) # Default position if location is not specified
+
+def add_new_obj(scene, new_obj, ref_location, ref_object, rng, max_trails=50):
+
+ ref_obj_pos = ref_object.position
+ # import pdb; pdb.set_trace()
+ ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+ new_obj_pos = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ new_obj.position = new_obj_pos
+ scene += new_obj
+
+ # import pdb; pdb.set_trace()
+ trails = 0
+ while not check_ok(new_obj, new_obj.position, SPAWN_REGION_OBJ):
+ trails += 1
+ # import pdb; pdb.set_trace()
+ new_obj.position = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+ # new_obj.quaternion = random_rotation(axis="Z", rng=rng)
+ if trails > max_trails:
+ print('cannot put the object, break')
+ # import pdb; pdb.set_trace()
+ return None
+ print('try {} times'.format(trails))
+ return scene
+
+def gen_caption(obj_name, obj_scale, ref_obj_name, ref_obj_scale, rotation):
+
+ if rotation == "flipped upside down":
+ captions = [f'the {obj_name} is flipped upside down', f'flip the {obj_name} upside down', f'Turn the {obj_name} upside down']
+ elif rotation == "turn around":
+ captions = [f'turn the {obj_name} around']
+ elif rotation == "turn left":
+ captions = [f'turn the {obj_name} 90 degrees', f'rotate the {obj_name} 90 degrees']
+ elif rotation == "turn right":
+ captions = [f'turn the {obj_name} 90 degrees', f'rotate the {obj_name} 90 degrees']
+ elif rotation == "fall down":
+ captions = [f'let the {obj_name} fall down', f'push the {obj_name} down', f'let the {obj_name} drop']
+ else:
+ captions = ['Fail']
+
+ # edit_verb = random.choice(['put', 'shift', 'move'])
+ # # caption = f'the{obj_size_exp} {obj_name} {verb_exp} {location_exp} the{ref_obj_size_exp} {ref_obj_name}'
+ # caption = f'{edit_verb} the {obj_name} {location_exp}'
+
+ return captions[random.randint(0, len(captions)-1)]
+
+
+
+# --- Common setups & resources
+print('Generate {} Sample'.format(FLAGS.generate_idx))
+scene, rng, output_dir, scratch_dir = kb.setup(FLAGS)
+output_dir = output_dir / FLAGS.sub_outputdir
+
+
+
+simulator = PyBullet(scene, scratch_dir)
+renderer = Blender(scene, scratch_dir, samples_per_pixel=64)
+kubasic = kb.AssetSource.from_manifest(FLAGS.kubasic_assets)
+gso = kb.AssetSource.from_manifest(FLAGS.gso_assets)
+hdri_source = kb.AssetSource.from_manifest(FLAGS.hdri_assets)
+
+
+# --- Populate the scene
+# background HDRI
+train_backgrounds, test_backgrounds = hdri_source.get_test_split(fraction=0.)
+logging.info("Choosing one of the %d training backgrounds...", len(train_backgrounds))
+hdri_id = rng.choice(train_backgrounds)
+
+background_hdri = hdri_source.create(asset_id=hdri_id)
+#assert isinstance(background_hdri, kb.Texture)
+logging.info("Using background %s", hdri_id)
+scene.metadata["background"] = hdri_id
+renderer._set_ambient_light_hdri(background_hdri.filename)
+
+
+# Dome
+dome = kubasic.create(asset_id="dome", name="dome",
+ friction=FLAGS.floor_friction,
+ restitution=FLAGS.floor_restitution,
+ static=True, background=True)
+assert isinstance(dome, kb.FileBasedObject)
+scene += dome
+dome_blender = dome.linked_objects[renderer]
+texture_node = dome_blender.data.materials[0].node_tree.nodes["Image Texture"]
+texture_node.image = bpy.data.images.load(background_hdri.filename)
+
+
+
+def get_linear_camera_motion_start_end(
+ movement_speed: float,
+ inner_radius: float = 8.,
+ outer_radius: float = 12.,
+ z_offset: float = 0.1,
+):
+ """Sample a linear path which starts and ends within a half-sphere shell."""
+ while True:
+ camera_start = np.array(kb.sample_point_in_half_sphere_shell(inner_radius,
+ outer_radius,
+ z_offset))
+ direction = rng.rand(3) - 0.5
+ movement = direction / np.linalg.norm(direction) * movement_speed
+ camera_end = camera_start + movement
+ if (inner_radius <= np.linalg.norm(camera_end) <= outer_radius and
+ camera_end[2] > z_offset):
+ return camera_start, camera_end
+
+
+# Camera
+logging.info("Setting up the Camera...")
+scene.camera = kb.PerspectiveCamera(focal_length=35., sensor_width=36)
+if FLAGS.camera == "fixed_random":
+ # scene.camera.position = kb.sample_point_in_half_sphere_shell(
+ # inner_radius=7., outer_radius=9., offset=4)
+ y = 10 + rng.uniform(-1, 1)
+ z = 12 + rng.uniform(-3, 3)
+ scene.camera.position = (0, y, z)
+ scene.camera.look_at((0, 0, 0))
+elif FLAGS.camera == "linear_movement":
+ camera_start, camera_end = get_linear_camera_motion_start_end(
+ movement_speed=rng.uniform(low=0., high=FLAGS.max_camera_movement)
+ )
+ # linearly interpolate the camera position between these two points
+ # while keeping it focused on the center of the scene
+ # we start one frame early and end one frame late to ensure that
+ # forward and backward flow are still consistent for the last and first frames
+ for frame in range(FLAGS.frame_start - 1, FLAGS.frame_end + 2):
+ interp = ((frame - FLAGS.frame_start + 1) /
+ (FLAGS.frame_end - FLAGS.frame_start + 3))
+ scene.camera.position = (interp * np.array(camera_start) +
+ (1 - interp) * np.array(camera_end))
+ scene.camera.look_at((0, 0, 0))
+ scene.camera.keyframe_insert("position", frame)
+ scene.camera.keyframe_insert("quaternion", frame)
+
+
+# Add random objects
+train_split, test_split = gso.get_test_split(fraction=0.)
+# if FLAGS.objects_split == "train":
+logging.info("Choosing one of the %d training objects...", len(train_split))
+# active_split = train_split
+active_split = list(GSO_dict.keys())
+
+num_objects = rng.randint(FLAGS.min_num_objects,
+ FLAGS.max_num_objects+1 - 2)
+
+logging.info("Step 1: Randomly placing %d objects:", num_objects)
+object_state_save_dict = {}
+object_state_ref_dict = {}
+
+
+# not resample objects
+# object_id_list = random.sample(active_split, num_objects+1)
+object_id_list = sample_unique_items(GSO_dict, num_objects+1)
+
+
+for i in range(num_objects):
+ # object_id = rng.choice(active_split)
+ object_id = object_id_list[i]
+ obj = gso.create(asset_id=object_id)
+
+
+ assert isinstance(obj, kb.FileBasedObject)
+ scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+ obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+
+
+ obj_pos_z = - get_obj_z(obj.bounds, obj.scale)
+ SPAWN_REGION_OBJ[0][2], SPAWN_REGION_OBJ[1][2] = obj_pos_z, obj_pos_z
+ obj.position = rng.uniform(*SPAWN_REGION_OBJ)
+
+ obj.metadata["scale"] = scale
+ scene += obj
+ move_until_no_overlap(obj, simulator, spawn_region=SPAWN_REGION_OBJ, rng=rng)
+ # initialize velocity randomly but biased towards center
+ # obj.velocity = (rng.uniform(*VELOCITY_RANGE) -
+ # [obj.position[0], obj.position[1], 0])
+ # print(obj.position)
+ obj.velocity = [0, 0, 0]
+ logging.info(" Added %s at %s", obj.asset_id, obj.position)
+ object_state_save_dict[i] = {'object_id': object_id,
+ 'object_scale': obj.scale,
+ 'object_quaternion': obj.quaternion,
+ 'object_bounds': obj.bounds}
+ object_state_ref_dict[i] = {'object': obj}
+
+
+ref_object = object_state_ref_dict[rng.choice(list(object_state_ref_dict.keys()))]['object'] # random choose an reference object
+ref_object_name = GSO_dict[ref_object.asset_id]
+ref_location = ref_object.position
+# random choose two location
+# LOC_SET = ['front', 'behind', 'left', 'right', 'on']
+LOC_SET = ['further right', 'further left', 'further away', 'closer']
+ref_location1 = random.sample(LOC_SET, 1)[0]
+if ref_location1 == 'further right':
+ ref_location2 = 'further left'
+elif ref_location1 == 'further left':
+ ref_location2 = 'further right'
+elif ref_location1 == 'further away':
+ ref_location2 = 'closer'
+elif ref_location1 == 'closer':
+ ref_location2 = 'further away'
+
+# 1st
+print('Generate the first scene.')
+# object_id = rng.choice(active_split)
+object_id = object_id_list[-1]
+obj = gso.create(asset_id=object_id)
+scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+obj.metadata["scale"] = scale
+
+new_object_name = GSO_dict[obj.asset_id]
+print('Add new object {}'.format(new_object_name))
+
+
+scene = add_new_obj(scene, obj, ref_location1, ref_object, rng, max_trails=500)
+if scene is None:
+ exit()
+frame = renderer.render_still()
+
+os.makedirs(output_dir/'{}'.format(FLAGS.generate_idx), exist_ok=True)
+kb.write_png(frame["rgba"], output_dir/"{}/image0.png".format(FLAGS.generate_idx))
+# caption_1 = gen_caption(new_object_name, obj.metadata["scale"], ref_object_name, ref_object.metadata["scale"], ref_location1)
+# print(caption_1)
+
+
+# save meta ann
+object_state_save_dict[i+1] = {'object_id': object_id,
+ 'object_scale': obj.scale,
+ 'object_pos': obj.position,
+ 'object_quaternion': obj.quaternion,
+ 'object_bounds': obj.bounds}
+# import json
+# json.dump(object_state_save_dict, open(output_dir/'{}/meta_ann1.json'.format(FLAGS.generate_idx), 'w'))
+# np.save(output_dir/'{}/meta_ann1.npy'.format(FLAGS.generate_idx), object_state_save_dict)
+# renderer.save_state(output_dir/'{}/image1.blend'.format(FLAGS.generate_idx))
+
+
+
+# 2nd
+print('Generate the second scene.')
+# delete the last object to generate the second frame
+# import pdb; pdb.set_trace()
+# scene.remove(obj)
+# scene= add_new_obj(scene, obj, ref_location2, ref_object, rng, max_trails=100)
+ref_obj_pos = ref_object.position
+ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+logging.info(f'Object position: {obj.position}')
+# new_obj_pos = get_new_pos(obj.bounds, obj.scale, ref_location2, obj.position, ref_obj_z_up, ref_object, rng)
+# logging.info(f'New object position: {new_obj_pos}')
+# obj.position = new_obj_pos
+
+text2rotation = {
+ "flipped upside down": [rotation(axis='X', degrees=180), rotation(axis='Y', degrees=180)],
+ # "turn around": [rotation(axis='Z', degrees=180)],
+ # "turn left": [rotation(axis='Z', degrees=-90)],
+ # "turn righ": [rotation(axis='Z', degrees=90)],
+ # "fall down": [rotation(axis='X', degrees=90), rotation(axis='Y', degrees=90), rotation(axis='X', degrees=90), rotation(axis='Y', degrees=90)]
+}
+
+nope = ['towel', 'cloth', 'tape']
+round_words = ['mug', 'bowl', 'plate', 'pot', 'saucer', 'hat', 'tape', 'mat', 'bottle', 'pan', 'ramekin']
+can_fall = ['pot', 'mug', 'figure', 'toy', 'boot', 'bottle', 'lamp', 'refrigerator']
+
+nope_cond, round_cond, fall_cond = False, False, False
+for token in new_object_name.split():
+ if token in nope:
+ nope_cond = True
+ if token in round_words:
+ round_cond = True
+ if token in can_fall:
+ fall_cond = True
+
+if nope_cond:
+ exit()
+
+if not round_cond:
+ text2rotation.update({
+ "turn around": [rotation(axis='Z', degrees=180)],
+ "turn left": [rotation(axis='Z', degrees=-90)],
+ "turn right": [rotation(axis='Z', degrees=90)]
+ })
+
+if fall_cond:
+ text2rotation.update({
+ "fall down": [rotation(axis='X', degrees=90), rotation(axis='Y', degrees=90), rotation(axis='X', degrees=90), rotation(axis='Y', degrees=90)]
+ })
+
+sampled = random.sample(list(text2rotation.keys()), 1)
+rotation_func = text2rotation[sampled[0]][random.randint(0, len(sampled)-1)]
+obj.quaternion = rotation_func
+
+frame = renderer.render_still()
+kb.write_png(frame["rgba"], output_dir/"{}/image1.png".format(FLAGS.generate_idx))
+caption_2 = gen_caption(new_object_name, obj.metadata["scale"], ref_object_name, ref_object.metadata["scale"], sampled[0])
+print(caption_2)
+
+# save meta ann
+object_state_save_dict[i+1] = {'object_id': object_id,
+ 'object_scale': obj.scale,
+ 'object_pos': obj.position,
+ 'object_quaternion': obj.quaternion,
+ 'object_bounds': obj.bounds}
+# import json
+# json.dump(object_state_save_dict, open(output_dir/'{}/meta_ann2.json'.format(FLAGS.generate_idx), 'w'))
+# np.save(output_dir/'{}/meta_ann2.npy'.format(FLAGS.generate_idx), object_state_save_dict)
+# renderer.save_state(output_dir/'{}/image2.blend'.format(FLAGS.generate_idx))
+
+
+# save json
+# local_ann = {'image0':"{}/image0.png".format(FLAGS.generate_idx), 'caption0':caption_1,
+# 'image1':"{}/image1.png".format(FLAGS.generate_idx), 'caption1':caption_2,
+# 'ann_path':"{}/ann.json".format(FLAGS.generate_idx),
+# 'obj_num':num_objects+1}
+# json.dump(local_ann, open("{}/{}/ann.json".format(str(output_dir), FLAGS.generate_idx), 'w'))
+
+# import pdb; pdb.set_trace()
+# if not os.path.exists("{}/global_ann.json".format(str(output_dir))):
+# json.dump([], open("{}/global_ann.json".format(str(output_dir)), 'w'))
+# with open("{}/global_ann.json".format(str(output_dir)), 'r') as f:
+# old_data = json.load(f)
+# old_data.append(local_ann)
+# with open("{}/global_ann.json".format(str(output_dir)), "w") as f:
+# json.dump(old_data, f)
+
+local_ann = [{
+ 'input': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx),
+ 'output': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx),
+ 'instruction': caption_2,
+ }
+ # {
+ # 'input': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx),
+ # 'output': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx),
+ # 'instruction': caption_1,
+ # }
+]
+save_scene_instruction(f"{output_dir}/eq_kubric_{DATASET_TYPE}.json", local_ann, DATASET_TYPE, FLAGS.generate_idx)
+
+kb.done()
diff --git a/eq-kubric/utils/__init__.py b/eq-kubric/utils/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..20a9ac0b681b27c967b1736c41b2c75f0992144a
--- /dev/null
+++ b/eq-kubric/utils/__init__.py
@@ -0,0 +1,49 @@
+import os
+import shutil
+import json
+
+def setup_output_files(dataset_type: str) -> None:
+ """
+ Sets up the necessary directories and files for the script to run.
+ """
+ setup_logs()
+ start_output_file(dataset_type)
+
+def setup_logs(log_dir="logs") -> None:
+ """
+ Sets up the logging directory by removing it if it exists and then recreating it.
+
+ Args:
+ log_dir (str): The path to the log directory to set up.
+ """
+ if os.path.exists(log_dir):
+ shutil.rmtree(log_dir)
+ os.makedirs(log_dir, exist_ok=True)
+
+def start_output_file(dataset_type: str) -> None:
+ output_json = f"output/{dataset_type}/eq_kubric_{dataset_type}.json"
+ os.makedirs(f"output/{dataset_type}", exist_ok=True)
+ with open(output_json, "w") as response_file:
+ response_file.write("[\n")
+
+def end_output_file(dataset_type: str) -> None:
+ output_json = f"output/{dataset_type}/eq_kubric_{dataset_type}.json"
+ with open(output_json, "ab+") as response_file:
+ response_file.seek(-2, os.SEEK_END)
+ response_file.truncate()
+ response_file.write(b"\n]")
+
+def dataset_dir(dataset_type: str) -> str:
+ return f"../../change_descriptions/eqmod/{dataset_type}/"
+
+def save_scene_instruction(output_file_path: str, entries: list, dataset_type: str, index: int, log_file="logs/error_log.txt") -> None:
+ try:
+ for entry in entries:
+ with open(output_file_path, "a") as file:
+ json_string = json.dumps(entry, indent=4)
+ indented_json_string = "\n ".join(json_string.splitlines())
+ file.write(f" {indented_json_string},\n")
+ except Exception as e:
+ error_message = f"{e}\nFailed to save a scene text: Index: {index+1}, Dataset Type: '{dataset_type}'."
+ with open(log_file, "a") as file:
+ file.write(f"{error_message}\n")
diff --git a/eval_disc_edit.py b/eval_disc_edit.py
new file mode 100644
index 0000000000000000000000000000000000000000..44be9d7c4986cd2e21651f5cec20e60cc0186e2c
--- /dev/null
+++ b/eval_disc_edit.py
@@ -0,0 +1,33 @@
+import json
+import math
+
+tasks = ['whatsup', 'something', 'ag', 'kubric', 'clevr']
+ckpts = [
+ 'checkpoints_magic_reproduce_epoch=000047-step=000012999.ckpt_results.json',
+ 'logs_logs_finetune_magicbrush_ag_something_kubric_15-15-1-1_init-magic_first_checkpoints_trainstep_checkpoints_step=000041999.ckpt_results.json'
+]
+
+for ckpt in ckpts:
+ print(ckpt)
+ skill_scores_latent_l2 = {task: [] for task in tasks}
+ for task in tasks:
+ results = json.load(open(f'itm_evaluation/test/{task}/{ckpt}'))
+ samples = 4
+
+ for idx, result in results.items():
+ pos_latent_l2s = result['pos']['latent_l2']
+ neg_latent_l2s = result['neg']['latent_l2']
+ if task == 'flickr_edit':
+ skills = result['task'].split(',')
+ skills = [skill.strip() for skill in skills]
+ for skill in skills:
+ skill_scores_latent_l2[skill] += [1 if pos_latent_l2s[i] < neg_latent_l2s[i] else 0 for i in range(len(pos_latent_l2s))]
+ skill_scores_latent_l2[task] += [1 if pos_latent_l2s[i] < neg_latent_l2s[i] else 0 for i in range(len(pos_latent_l2s))]
+
+ # make latex row with each task's score
+ row = ''
+ for k, v in skill_scores_latent_l2.items():
+ final_score = sum(v) / len(v)
+ se = math.sqrt(final_score * (1 - final_score) / len(v))
+ row += f' & {final_score:.3f} \pm {se:.3f}'
+ print(row)
diff --git a/hf_push.py b/hf_push.py
new file mode 100644
index 0000000000000000000000000000000000000000..f19d1e4039c4bbf0fa4e97b8e9aadb9c4d8a5c07
--- /dev/null
+++ b/hf_push.py
@@ -0,0 +1,15 @@
+from huggingface_hub import HfApi
+
+model_name = "AURORA"
+
+api = HfApi()
+#api.create_repo("yfqiu-nlp/"+model_name.replace('+', '-'), repo_type="model")
+
+from huggingface_hub import HfApi
+
+api = HfApi()
+api.upload_large_folder(
+ folder_path='./',
+ repo_id="yfqiu-nlp/AURORA",
+ repo_type="dataset",
+)
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000000000000000000000000000000000000..d3f2d4a5493ed082c7c28796352866953f787643
--- /dev/null
+++ b/main.py
@@ -0,0 +1,800 @@
+import argparse, os, sys, datetime, glob
+import numpy as np
+import time
+import torch
+import torchvision
+import pytorch_lightning as pl
+import json
+import pickle
+
+from packaging import version
+from omegaconf import OmegaConf
+from torch.utils.data import DataLoader, Dataset
+from functools import partial
+from PIL import Image
+
+import torch.distributed as dist
+from pytorch_lightning import seed_everything
+from pytorch_lightning.trainer import Trainer
+from pytorch_lightning.callbacks import ModelCheckpoint, Callback, LearningRateMonitor
+from pytorch_lightning.utilities.distributed import rank_zero_only
+from pytorch_lightning.utilities import rank_zero_info
+from pytorch_lightning.plugins import DDPPlugin
+
+sys.path.append("./stable_diffusion")
+
+from ldm.data.base import Txt2ImgIterableBaseDataset
+from ldm.util import instantiate_from_config
+
+
+def get_parser(**parser_kwargs):
+ def str2bool(v):
+ if isinstance(v, bool):
+ return v
+ if v.lower() in ("yes", "true", "t", "y", "1"):
+ return True
+ elif v.lower() in ("no", "false", "f", "n", "0"):
+ return False
+ else:
+ raise argparse.ArgumentTypeError("Boolean value expected.")
+
+ parser = argparse.ArgumentParser(**parser_kwargs)
+ parser.add_argument(
+ "-n",
+ "--name",
+ type=str,
+ const=True,
+ default="train",
+ nargs="?",
+ help="postfix for logdir",
+ )
+ parser.add_argument(
+ "-r",
+ "--resume",
+ type=str,
+ const=True,
+ default="",
+ nargs="?",
+ help="resume from logdir or checkpoint in logdir",
+ )
+ parser.add_argument(
+ "-b",
+ "--base",
+ nargs="*",
+ default='configs/finetune_magicbrush_ag_something_kubric_15-15-1-1_init-magic.yaml',
+ help="paths to base configs. Loaded from left-to-right."
+ "Parameters can be overwritten or added with command-line options of the form `--key value`.",
+ )
+ parser.add_argument(
+ "-t",
+ "--train",
+ type=str2bool,
+ const=True,
+ default=True,
+ nargs="?",
+ help="train",
+ )
+ parser.add_argument(
+ "--no-test",
+ type=str2bool,
+ const=True,
+ default=False,
+ nargs="?",
+ help="disable test",
+ )
+ parser.add_argument(
+ "-p",
+ "--project",
+ help="name of new or path to existing project"
+ )
+ parser.add_argument(
+ "-d",
+ "--debug",
+ type=str2bool,
+ nargs="?",
+ const=True,
+ default=False,
+ help="enable post-mortem debugging",
+ )
+ parser.add_argument(
+ "-s",
+ "--seed",
+ type=int,
+ default=23,
+ help="seed for seed_everything",
+ )
+ parser.add_argument(
+ "-f",
+ "--postfix",
+ type=str,
+ default="",
+ help="post-postfix for default name",
+ )
+ parser.add_argument(
+ "-l",
+ "--logdir",
+ type=str,
+ default="/mnt/research/scratch/bkroje/logs",
+ help="directory for logging dat shit",
+ )
+ parser.add_argument(
+ "--scale_lr",
+ action="store_true",
+ default=False,
+ help="scale base-lr by ngpu * batch_size * n_accumulate",
+ )
+ return parser
+
+
+def nondefault_trainer_args(opt):
+ parser = argparse.ArgumentParser()
+ parser = Trainer.add_argparse_args(parser)
+ args = parser.parse_args([])
+ return sorted(k for k in vars(args) if getattr(opt, k) != getattr(args, k))
+
+
+class WrappedDataset(Dataset):
+ """Wraps an arbitrary object with __len__ and __getitem__ into a pytorch dataset"""
+
+ def __init__(self, dataset):
+ self.data = dataset
+
+ def __len__(self):
+ return len(self.data)
+
+ def __getitem__(self, idx):
+ return self.data[idx]
+
+
+def worker_init_fn(_):
+ worker_info = torch.utils.data.get_worker_info()
+
+ dataset = worker_info.dataset
+ worker_id = worker_info.id
+
+ if isinstance(dataset, Txt2ImgIterableBaseDataset):
+ split_size = dataset.num_records // worker_info.num_workers
+ # reset num_records to the true number to retain reliable length information
+ dataset.sample_ids = dataset.valid_ids[worker_id * split_size:(worker_id + 1) * split_size]
+ current_id = np.random.choice(len(np.random.get_state()[1]), 1)
+ return np.random.seed(np.random.get_state()[1][current_id] + worker_id)
+ else:
+ return np.random.seed(np.random.get_state()[1][0] + worker_id)
+
+
+class DataModuleFromConfig(pl.LightningDataModule):
+ def __init__(self, batch_size, train=None, validation=None, test=None, predict=None,
+ wrap=False, num_workers=None, shuffle_test_loader=False, use_worker_init_fn=False,
+ shuffle_val_dataloader=False):
+ super().__init__()
+ self.batch_size = batch_size
+ self.dataset_configs = dict()
+ self.num_workers = num_workers if num_workers is not None else batch_size * 2
+ self.use_worker_init_fn = use_worker_init_fn
+ if train is not None:
+ self.dataset_configs["train"] = train
+ self.train_dataloader = self._train_dataloader
+ if validation is not None:
+ self.dataset_configs["validation"] = validation
+ self.val_dataloader = partial(self._val_dataloader, shuffle=shuffle_val_dataloader)
+ if test is not None:
+ self.dataset_configs["test"] = test
+ self.test_dataloader = partial(self._test_dataloader, shuffle=shuffle_test_loader)
+ if predict is not None:
+ self.dataset_configs["predict"] = predict
+ self.predict_dataloader = self._predict_dataloader
+ self.wrap = wrap
+
+ def prepare_data(self):
+ for data_cfg in self.dataset_configs.values():
+ instantiate_from_config(data_cfg)
+
+ def setup(self, stage=None):
+ self.datasets = dict(
+ (k, instantiate_from_config(self.dataset_configs[k]))
+ for k in self.dataset_configs)
+ if self.wrap:
+ for k in self.datasets:
+ self.datasets[k] = WrappedDataset(self.datasets[k])
+
+ def _train_dataloader(self):
+ is_iterable_dataset = isinstance(self.datasets['train'], Txt2ImgIterableBaseDataset)
+ if is_iterable_dataset or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["train"], batch_size=self.batch_size,
+ num_workers=self.num_workers, shuffle=False if is_iterable_dataset else True,
+ worker_init_fn=init_fn, persistent_workers=True)
+
+ def _val_dataloader(self, shuffle=False):
+ if isinstance(self.datasets['validation'], Txt2ImgIterableBaseDataset) or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["validation"],
+ batch_size=self.batch_size,
+ num_workers=self.num_workers,
+ worker_init_fn=init_fn,
+ shuffle=shuffle, persistent_workers=True)
+
+ def _test_dataloader(self, shuffle=False):
+ is_iterable_dataset = isinstance(self.datasets['train'], Txt2ImgIterableBaseDataset)
+ if is_iterable_dataset or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+
+ # do not shuffle dataloader for iterable dataset
+ shuffle = shuffle and (not is_iterable_dataset)
+
+ return DataLoader(self.datasets["test"], batch_size=self.batch_size,
+ num_workers=self.num_workers, worker_init_fn=init_fn, shuffle=shuffle, persistent_workers=True)
+
+ def _predict_dataloader(self, shuffle=False):
+ if isinstance(self.datasets['predict'], Txt2ImgIterableBaseDataset) or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["predict"], batch_size=self.batch_size,
+ num_workers=self.num_workers, worker_init_fn=init_fn, persistent_workers=True)
+
+
+class SetupCallback(Callback):
+ def __init__(self, resume, now, logdir, ckptdir, cfgdir, config, lightning_config):
+ super().__init__()
+ self.resume = resume
+ self.now = now
+ self.logdir = logdir
+ self.ckptdir = ckptdir
+ self.cfgdir = cfgdir
+ self.config = config
+ self.lightning_config = lightning_config
+
+ def on_keyboard_interrupt(self, trainer, pl_module):
+ if trainer.global_rank == 0:
+ print("Summoning checkpoint.")
+ ckpt_path = os.path.join(self.ckptdir, "last.ckpt")
+ trainer.save_checkpoint(ckpt_path)
+
+ def on_pretrain_routine_start(self, trainer, pl_module):
+ if trainer.global_rank == 0:
+ # Create logdirs and save configs
+ # os.makedirs(self.logdir, exist_ok=True)
+ # os.makedirs(self.ckptdir, exist_ok=True)
+ # os.makedirs(self.cfgdir, exist_ok=True)
+
+ if "callbacks" in self.lightning_config:
+ if 'metrics_over_trainsteps_checkpoint' in self.lightning_config['callbacks']:
+ os.makedirs(os.path.join(self.ckptdir, 'trainstep_checkpoints'), exist_ok=True)
+ print("Project config")
+ print(OmegaConf.to_yaml(self.config))
+ OmegaConf.save(self.config,
+ os.path.join(self.cfgdir, "{}-project.yaml".format(self.now)))
+
+ print("Lightning config")
+ print(OmegaConf.to_yaml(self.lightning_config))
+ OmegaConf.save(OmegaConf.create({"lightning": self.lightning_config}),
+ os.path.join(self.cfgdir, "{}-lightning.yaml".format(self.now)))
+
+def get_world_size():
+ if not dist.is_available():
+ return 1
+ if not dist.is_initialized():
+ return 1
+ return dist.get_world_size()
+
+def all_gather(data):
+ """
+ Run all_gather on arbitrary picklable data (not necessarily tensors)
+ Args:
+ data: any picklable object
+ Returns:
+ list[data]: list of data gathered from each rank
+ """
+ world_size = get_world_size()
+ if world_size == 1:
+ return [data]
+
+ # serialized to a Tensor
+ origin_size = None
+ if not isinstance(data, torch.Tensor):
+ buffer = pickle.dumps(data)
+ storage = torch.ByteStorage.from_buffer(buffer)
+ tensor = torch.ByteTensor(storage).to("cuda")
+ else:
+ origin_size = data.size()
+ tensor = data.reshape(-1)
+
+ tensor_type = tensor.dtype
+
+ # obtain Tensor size of each rank
+ local_size = torch.LongTensor([tensor.numel()]).to("cuda")
+ size_list = [torch.LongTensor([0]).to("cuda") for _ in range(world_size)]
+ dist.all_gather(size_list, local_size)
+ size_list = [int(size.item()) for size in size_list]
+ max_size = max(size_list)
+
+ # receiving Tensor from all ranks
+ # we pad the tensor because torch all_gather does not support
+ # gathering tensors of different shapes
+ tensor_list = []
+ for _ in size_list:
+ tensor_list.append(torch.FloatTensor(size=(max_size,)).cuda().to(tensor_type))
+ if local_size != max_size:
+ padding = torch.FloatTensor(size=(max_size - local_size,)).cuda().to(tensor_type)
+ tensor = torch.cat((tensor, padding), dim=0)
+ dist.all_gather(tensor_list, tensor)
+
+ data_list = []
+ for size, tensor in zip(size_list, tensor_list):
+ if origin_size is None:
+ buffer = tensor.cpu().numpy().tobytes()[:size]
+ data_list.append(pickle.loads(buffer))
+ else:
+ buffer = tensor[:size]
+ data_list.append(buffer)
+
+ if origin_size is not None:
+ new_shape = [-1] + list(origin_size[1:])
+ resized_list = []
+ for data in data_list:
+ # suppose the difference of tensor size exist in first dimension
+ data = data.reshape(new_shape)
+ resized_list.append(data)
+
+ return resized_list
+ else:
+ return data_list
+
+class ImageLogger(Callback):
+ def __init__(self, batch_frequency, max_images, clamp=True, increase_log_steps=True,
+ rescale=True, disabled=False, log_on_batch_idx=False, log_first_step=False,
+ log_images_kwargs=None):
+ super().__init__()
+ self.rescale = rescale
+ self.batch_freq = batch_frequency
+ self.max_images = max_images
+ self.logger_log_images = {
+ pl.loggers.TestTubeLogger: self._testtube,
+ }
+ self.log_steps = [2 ** n for n in range(6, int(np.log2(self.batch_freq)) + 1)]
+ if not increase_log_steps:
+ self.log_steps = [self.batch_freq]
+ self.clamp = clamp
+ self.disabled = disabled
+ self.log_on_batch_idx = log_on_batch_idx
+ self.log_images_kwargs = log_images_kwargs if log_images_kwargs else {}
+ self.log_first_step = log_first_step
+
+ @rank_zero_only
+ def _testtube(self, pl_module, images, batch_idx, split):
+ for k in images:
+ grid = torchvision.utils.make_grid(images[k])
+ grid = (grid + 1.0) / 2.0 # -1,1 -> 0,1; c,h,w
+
+ tag = f"{split}/{k}"
+ pl_module.logger.experiment.add_image(
+ tag, grid,
+ global_step=pl_module.global_step)
+
+ @rank_zero_only
+ def log_local(self, save_dir, split, images, prompts,
+ global_step, current_epoch, batch_idx):
+ root = os.path.join(save_dir, "images", split)
+ names = {"reals": "before", "inputs": "after", "reconstruction": "before-vq", "samples": "after-gen"}
+ # print(root)
+ for k in images:
+ grid = torchvision.utils.make_grid(images[k], nrow=8)
+ if self.rescale:
+ grid = (grid + 1.0) / 2.0 # -1,1 -> 0,1; c,h,w
+ grid = grid.transpose(0, 1).transpose(1, 2).squeeze(-1)
+ grid = grid.numpy()
+ grid = (grid * 255).astype(np.uint8)
+ filename = "global_step-{:06}_epoch-{:06}_batch-{:06}_{}.png".format(
+ global_step,
+ current_epoch,
+ batch_idx,
+ names[k])
+ path = os.path.join(root, filename)
+ os.makedirs(os.path.split(path)[0], exist_ok=True)
+ # print(path)
+ Image.fromarray(grid).save(path)
+
+ filename = "global_step-{:06}_epoch-{:06}_batch-{:06}_prompt.json".format(
+ global_step,
+ current_epoch,
+ batch_idx)
+ path = os.path.join(root, filename)
+ with open(path, "w") as f:
+ for p in prompts:
+ f.write(f"{json.dumps(p)}\n")
+
+ def log_img(self, pl_module, batch, batch_idx, split="train"):
+ check_idx = batch_idx if self.log_on_batch_idx else pl_module.global_step
+ if (self.check_frequency(check_idx) and # batch_idx % self.batch_freq == 0
+ hasattr(pl_module, "log_images") and
+ callable(pl_module.log_images) and
+ self.max_images > 0) or (split == "val" and batch_idx == 0):
+ logger = type(pl_module.logger)
+
+ is_train = pl_module.training
+ if is_train:
+ pl_module.eval()
+
+ with torch.no_grad():
+ images = pl_module.log_images(batch, split=split, **self.log_images_kwargs)
+
+ prompts = batch["edit"]["c_crossattn"][:self.max_images]
+ prompts = [p for ps in all_gather(prompts) for p in ps]
+
+ for k in images:
+ N = min(images[k].shape[0], self.max_images)
+ images[k] = images[k][:N]
+ images[k] = torch.cat(all_gather(images[k][:N]))
+ if isinstance(images[k], torch.Tensor):
+ images[k] = images[k].detach().cpu()
+ if self.clamp:
+ images[k] = torch.clamp(images[k], -1., 1.)
+
+ self.log_local(pl_module.logger.save_dir, split, images, prompts,
+ pl_module.global_step, pl_module.current_epoch, batch_idx)
+
+ logger_log_images = self.logger_log_images.get(logger, lambda *args, **kwargs: None)
+ logger_log_images(pl_module, images, pl_module.global_step, split)
+
+ if is_train:
+ pl_module.train()
+
+ def check_frequency(self, check_idx):
+ if ((check_idx % self.batch_freq) == 0 or (check_idx in self.log_steps)) and (
+ check_idx > 0 or self.log_first_step):
+ if len(self.log_steps) > 0:
+ self.log_steps.pop(0)
+ return True
+ return False
+
+ # def on_train_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
+ # if not self.disabled and (pl_module.global_step > 0 or self.log_first_step):
+ # self.log_img(pl_module, batch, batch_idx, split="train")
+
+ # def on_validation_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
+ # if not self.disabled and pl_module.global_step > 0:
+ # self.log_img(pl_module, batch, batch_idx, split="val")
+ # if hasattr(pl_module, 'calibrate_grad_norm'):
+ # if (pl_module.calibrate_grad_norm and batch_idx % 25 == 0) and batch_idx > 0:
+ # self.log_gradients(trainer, pl_module, batch_idx=batch_idx)
+
+
+class CUDACallback(Callback):
+ # see https://github.com/SeanNaren/minGPT/blob/master/mingpt/callback.py
+ def on_train_epoch_start(self, trainer, pl_module):
+ # Reset the memory use counter
+ torch.cuda.reset_peak_memory_stats(trainer.root_gpu)
+ torch.cuda.synchronize(trainer.root_gpu)
+ self.start_time = time.time()
+
+ def on_train_epoch_end(self, trainer, pl_module, outputs):
+ torch.cuda.synchronize(trainer.root_gpu)
+ max_memory = torch.cuda.max_memory_allocated(trainer.root_gpu) / 2 ** 20
+ epoch_time = time.time() - self.start_time
+
+ try:
+ max_memory = trainer.training_type_plugin.reduce(max_memory)
+ epoch_time = trainer.training_type_plugin.reduce(epoch_time)
+
+ rank_zero_info(f"Average Epoch time: {epoch_time:.2f} seconds")
+ rank_zero_info(f"Average Peak memory {max_memory:.2f}MiB")
+ except AttributeError:
+ pass
+
+
+if __name__ == "__main__":
+ # custom parser to specify config files, train, test and debug mode,
+ # postfix, resume.
+ # `--key value` arguments are interpreted as arguments to the trainer.
+ # `nested.key=value` arguments are interpreted as config parameters.
+ # configs are merged from left-to-right followed by command line parameters.
+
+ # model:
+ # base_learning_rate: float
+ # target: path to lightning module
+ # params:
+ # key: value
+ # data:
+ # target: main.DataModuleFromConfig
+ # params:
+ # batch_size: int
+ # wrap: bool
+ # train:
+ # target: path to train dataset
+ # params:
+ # key: value
+ # validation:
+ # target: path to validation dataset
+ # params:
+ # key: value
+ # test:
+ # target: path to test dataset
+ # params:
+ # key: value
+ # lightning: (optional, has sane defaults and can be specified on cmdline)
+ # trainer:
+ # additional arguments to trainer
+ # logger:
+ # logger to instantiate
+ # modelcheckpoint:
+ # modelcheckpoint to instantiate
+ # callbacks:
+ # callback1:
+ # target: importpath
+ # params:
+ # key: value
+
+ now = datetime.datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
+
+ # add cwd for convenience and to make classes in this file available when
+ # running as `python main.py`
+ # (in particular `main.DataModuleFromConfig`)
+ sys.path.append(os.getcwd())
+
+ parser = get_parser()
+ parser = Trainer.add_argparse_args(parser)
+
+ opt, unknown = parser.parse_known_args()
+
+ assert opt.name
+ cfg_fname = os.path.split(opt.base[0])[-1]
+ cfg_name = os.path.splitext(cfg_fname)[0]
+ nowname = f"{cfg_name}_{opt.name}"
+ logdir = os.path.join(opt.logdir, nowname)
+ ckpt = os.path.join(logdir, "checkpoints", "last.ckpt")
+ resume = False
+
+ if os.path.isfile(ckpt):
+ opt.resume_from_checkpoint = ckpt
+ base_configs = sorted(glob.glob(os.path.join(logdir, "configs/*.yaml")))
+ opt.base = base_configs + opt.base
+ _tmp = logdir.split("/")
+ nowname = _tmp[-1]
+ resume = True
+
+ ckptdir = os.path.join(logdir, "checkpoints")
+ cfgdir = os.path.join(logdir, "configs")
+
+ os.makedirs(logdir, exist_ok=True)
+ os.makedirs(ckptdir, exist_ok=True)
+ os.makedirs(cfgdir, exist_ok=True)
+
+ try:
+ # init and save configs
+ configs = [OmegaConf.load(opt.base)]
+ cli = OmegaConf.from_dotlist(unknown)
+ config = OmegaConf.merge(*configs, cli)
+
+ if resume:
+ # By default, when finetuning from Stable Diffusion, we load the EMA-only checkpoint to initialize all weights.
+ # If resuming InstructPix2Pix from a finetuning checkpoint, instead load both EMA and non-EMA weights.
+ config.model.params.load_ema = True
+
+ lightning_config = config.pop("lightning", OmegaConf.create())
+ # merge trainer cli with config
+ trainer_config = lightning_config.get("trainer", OmegaConf.create())
+ # default to ddp
+ trainer_config["accelerator"] = "ddp"
+ for k in nondefault_trainer_args(opt):
+ trainer_config[k] = getattr(opt, k)
+ if not "gpus" in trainer_config:
+ del trainer_config["accelerator"]
+ cpu = True
+ else:
+ gpuinfo = trainer_config["gpus"]
+ print(f"Running on GPUs {gpuinfo}")
+ cpu = False
+ trainer_opt = argparse.Namespace(**trainer_config)
+ lightning_config.trainer = trainer_config
+
+ # model
+ model = instantiate_from_config(config.model)
+
+ # trainer and callbacks
+ trainer_kwargs = dict()
+
+ # default logger configs
+ default_logger_cfgs = {
+ "wandb": {
+ "target": "pytorch_lightning.loggers.WandbLogger",
+ "params": {
+ "name": nowname,
+ "save_dir": logdir,
+ "id": nowname,
+ }
+ },
+ "testtube": {
+ "target": "pytorch_lightning.loggers.TestTubeLogger",
+ "params": {
+ "name": "testtube",
+ "save_dir": logdir,
+ }
+ },
+ }
+ default_logger_cfg = default_logger_cfgs["wandb"]
+ if "logger" in lightning_config:
+ logger_cfg = lightning_config.logger
+ else:
+ logger_cfg = OmegaConf.create()
+ logger_cfg = OmegaConf.merge(default_logger_cfg, logger_cfg)
+ trainer_kwargs["logger"] = instantiate_from_config(logger_cfg)
+
+ # modelcheckpoint - use TrainResult/EvalResult(checkpoint_on=metric) to
+ # specify which metric is used to determine best models
+ default_modelckpt_cfg = {
+ "target": "pytorch_lightning.callbacks.ModelCheckpoint",
+ "params": {
+ "dirpath": ckptdir,
+ "filename": "{epoch:06}",
+ 'filename': 'last',
+ "verbose": True,
+ "save_last": True,
+ "save_top_k": 0,
+ }
+ }
+
+ if "modelcheckpoint" in lightning_config:
+ modelckpt_cfg = lightning_config.modelcheckpoint
+ else:
+ modelckpt_cfg = OmegaConf.create()
+ modelckpt_cfg = OmegaConf.merge(default_modelckpt_cfg, modelckpt_cfg)
+ print(f"Merged modelckpt-cfg: \n{modelckpt_cfg}")
+ if version.parse(pl.__version__) < version.parse('1.4.0'):
+ trainer_kwargs["checkpoint_callback"] = instantiate_from_config(modelckpt_cfg)
+
+ # add callback which sets up log directory
+ default_callbacks_cfg = {
+ "setup_callback": {
+ "target": "main.SetupCallback",
+ "params": {
+ "resume": opt.resume,
+ "now": now,
+ "logdir": logdir,
+ "ckptdir": ckptdir,
+ "cfgdir": cfgdir,
+ "config": config,
+ "lightning_config": lightning_config,
+ }
+ },
+ "image_logger": {
+ "target": "main.ImageLogger",
+ "params": {
+ "batch_frequency": 750,
+ "max_images": 8,
+ "clamp": True
+ }
+ },
+ "learning_rate_logger": {
+ "target": "main.LearningRateMonitor",
+ "params": {
+ "logging_interval": "step",
+ # "log_momentum": True
+ }
+ },
+ "cuda_callback": {
+ "target": "main.CUDACallback"
+ },
+ }
+ if version.parse(pl.__version__) >= version.parse('1.4.0'):
+ default_callbacks_cfg.update({'checkpoint_callback': modelckpt_cfg})
+
+ if "callbacks" in lightning_config:
+ callbacks_cfg = lightning_config.callbacks
+ else:
+ callbacks_cfg = OmegaConf.create()
+
+ print(
+ 'Caution: Saving checkpoints every n train steps without deleting. This might require some free space.')
+ default_metrics_over_trainsteps_ckpt_dict = {
+ 'metrics_over_trainsteps_checkpoint': {
+ "target": 'pytorch_lightning.callbacks.ModelCheckpoint',
+ 'params': {
+ "dirpath": os.path.join(ckptdir, 'trainstep_checkpoints'),
+ "filename": "{epoch:06}-{step:09}",
+ "verbose": True,
+ 'save_top_k': -1,
+ 'every_n_train_steps': 1000,
+ 'save_weights_only': True
+ }
+ }
+ }
+ default_callbacks_cfg.update(default_metrics_over_trainsteps_ckpt_dict)
+
+ callbacks_cfg = OmegaConf.merge(default_callbacks_cfg, callbacks_cfg)
+ if 'ignore_keys_callback' in callbacks_cfg and hasattr(trainer_opt, 'resume_from_checkpoint'):
+ callbacks_cfg.ignore_keys_callback.params['ckpt_path'] = trainer_opt.resume_from_checkpoint
+ elif 'ignore_keys_callback' in callbacks_cfg:
+ del callbacks_cfg['ignore_keys_callback']
+
+ trainer_kwargs["callbacks"] = [instantiate_from_config(callbacks_cfg[k]) for k in callbacks_cfg]
+
+ trainer = Trainer.from_argparse_args(trainer_opt, plugins=DDPPlugin(find_unused_parameters=False), **trainer_kwargs)
+ trainer.logdir = logdir ###
+
+ # data
+ data = instantiate_from_config(config.data)
+ # NOTE according to https://pytorch-lightning.readthedocs.io/en/latest/datamodules.html
+ # calling these ourselves should not be necessary but it is.
+ # lightning still takes care of proper multiprocessing though
+ data.prepare_data()
+ data.setup()
+ print("#### Data #####")
+ for k in data.datasets:
+ print(f"{k}, {data.datasets[k].__class__.__name__}, {len(data.datasets[k])}")
+
+ # configure learning rate
+ bs, base_lr = config.data.params.batch_size, config.model.base_learning_rate
+ if not cpu:
+ ngpu = len(lightning_config.trainer.gpus.strip(",").split(','))
+ else:
+ ngpu = 1
+ if 'accumulate_grad_batches' in lightning_config.trainer:
+ accumulate_grad_batches = lightning_config.trainer.accumulate_grad_batches
+ else:
+ accumulate_grad_batches = 1
+ print(f"accumulate_grad_batches = {accumulate_grad_batches}")
+ lightning_config.trainer.accumulate_grad_batches = accumulate_grad_batches
+ if opt.scale_lr:
+ model.learning_rate = accumulate_grad_batches * ngpu * bs * base_lr
+ print(
+ "Setting learning rate to {:.2e} = {} (accumulate_grad_batches) * {} (num_gpus) * {} (batchsize) * {:.2e} (base_lr)".format(
+ model.learning_rate, accumulate_grad_batches, ngpu, bs, base_lr))
+ else:
+ model.learning_rate = base_lr
+ print("++++ NOT USING LR SCALING ++++")
+ print(f"Setting learning rate to {model.learning_rate:.2e}")
+
+
+ # allow checkpointing via USR1
+ def melk(*args, **kwargs):
+ # run all checkpoint hooks
+ if trainer.global_rank == 0:
+ print("Summoning checkpoint.")
+ ckpt_path = os.path.join(ckptdir, "last.ckpt")
+ trainer.save_checkpoint(ckpt_path)
+
+
+ def divein(*args, **kwargs):
+ if trainer.global_rank == 0:
+ import pudb;
+ pudb.set_trace()
+
+
+ import signal
+
+ signal.signal(signal.SIGUSR1, melk)
+ signal.signal(signal.SIGUSR2, divein)
+
+ # run
+ if opt.train:
+ try:
+ trainer.fit(model, data)
+ except Exception:
+ melk()
+ raise
+ if not opt.no_test and not trainer.interrupted:
+ trainer.test(model, data)
+ except Exception:
+ if opt.debug and trainer.global_rank == 0:
+ try:
+ import pudb as debugger
+ except ImportError:
+ import pdb as debugger
+ debugger.post_mortem()
+ raise
+ finally:
+ # move newly created debug project to debug_runs
+ if opt.debug and not opt.resume and trainer.global_rank == 0:
+ dst, name = os.path.split(logdir)
+ dst = os.path.join(dst, "debug_runs", name)
+ os.makedirs(os.path.split(dst)[0], exist_ok=True)
+ os.rename(logdir, dst)
+ if trainer.global_rank == 0:
+ print(trainer.profiler.summary())
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..14b6626ff6a7895d7fc325052c510e6077228997
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,229 @@
+absl-py==2.0.0
+accelerate==0.26.1
+addict==2.4.0
+aiofiles==23.2.1
+aiohttp==3.9.1
+aiosignal==1.3.1
+albumentations==0.4.3
+altair==5.2.0
+annotated-types==0.6.0
+antlr4-python3-runtime==4.8
+anyio==4.2.0
+appdirs==1.4.4
+asttokens==2.4.1
+async-timeout==4.0.3
+attrs==23.2.0
+beautifulsoup4==4.12.2
+blinker==1.7.0
+cachetools==5.3.2
+certifi==2023.11.17
+charset-normalizer==3.3.2
+clean-fid==0.1.35
+click==8.1.7
+-e git+https://github.com/openai/CLIP.git@a1d071733d7111c9c014f024669f959182114e33#egg=clip
+clip-anytorch==2.5.2
+cmake==3.28.1
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+datasets==2.17.1
+dctorch==0.1.2
+diffusers==0.25.0
+dill==0.3.6
+distro==1.9.0
+docker-pycreds==0.4.0
+easydict==1.12
+einops==0.3.0
+exceptiongroup==1.2.0
+executing==2.0.1
+facexlib==0.3.0
+fancycompleter==0.9.1
+fastapi==0.109.0
+ffmpy==0.3.1
+filelock==3.13.1
+filterpy==1.4.5
+fonttools==4.47.2
+frozenlist==1.4.1
+fschat==0.2.35
+fsspec==2023.10.0
+ftfy==6.1.3
+future==0.18.3
+gdown==4.7.1
+gitdb==4.0.11
+GitPython==3.1.41
+google-auth==2.26.2
+google-auth-oauthlib==1.2.0
+gradio==3.50.2
+gradio_client==0.6.1
+grpcio==1.60.0
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.26.0
+huggingface-hub==0.20.2
+icecream==2.1.3
+idna==3.6
+imageio==2.9.0
+imageio-ffmpeg==0.4.2
+imgaug==0.2.6
+importlib-metadata==7.0.1
+importlib-resources==6.1.1
+inquirerpy==0.3.4
+invisible-watermark==0.2.0
+Jinja2==3.1.3
+joblib==1.4.2
+jsonmerge==1.9.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.12.1
+k-diffusion @ git+https://github.com/crowsonkb/k-diffusion.git@cc49cf6182284e577e896943f8e29c7c9d1a7f2c
+kiwisolver==1.4.5
+kornia==0.6.0
+lazy_loader==0.3
+lit==17.0.6
+llvmlite==0.42.0
+lmdb==1.4.1
+Markdown==3.5.2
+markdown-it-py==3.0.0
+markdown2==2.4.12
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.4
+multiprocess==0.70.14
+networkx==3.2.1
+nh3==0.2.15
+numba==0.59.1
+numpy==1.24.4
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu11==10.9.0.58
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu11==10.2.10.91
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu11==2.14.3
+nvidia-nccl-cu12==2.18.1
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu11==11.7.91
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+omegaconf==2.1.1
+open-clip-torch==2.24.0
+openai==1.7.0
+openai-clip==1.0.1
+opencv-python==4.9.0.80
+opencv-python-headless==4.9.0.80
+orjson==3.9.10
+packaging==23.2
+pandas==2.1.4
+patsy==0.5.6
+peft==0.8.1
+pfzy==0.3.4
+pillow==10.2.0
+platformdirs==4.2.1
+prompt-toolkit==3.0.43
+protobuf==4.23.4
+psutil==5.9.7
+pudb==2019.2
+pyarrow==14.0.2
+pyarrow-hotfix==0.6
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+pydantic==1.10.14
+pydantic_core==2.14.6
+pydeck==0.8.1b0
+pyDeprecate==0.3.1
+pydub==0.25.1
+Pygments==2.17.2
+pyiqa==0.1.11
+pyparsing==3.1.1
+pyrepl==0.9.0
+PySocks==1.7.1
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytorch-lightning==1.4.2
+pytube==15.0.0
+pytz==2023.3.post1
+PyWavelets==1.5.0
+PyYAML==6.0.1
+referencing==0.32.1
+regex==2023.12.25
+requests==2.31.0
+requests-oauthlib==1.3.1
+responses==0.18.0
+rich==13.7.0
+rpds-py==0.16.2
+rsa==4.9
+safetensors==0.4.1
+scikit-image==0.20.0
+scipy==1.9.1
+seaborn==0.13.1
+semantic-version==2.10.0
+sentencepiece==0.1.99
+sentry-sdk==1.39.2
+setproctitle==1.3.3
+shellingham==1.5.4
+shortuuid==1.0.11
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soupsieve==2.5
+starlette==0.35.1
+statsmodels==0.14.2
+streamlit==1.30.0
+svgwrite==1.4.3
+sympy==1.12
+-e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
+tenacity==8.2.3
+tensorboard==2.15.1
+tensorboard-data-server==0.7.2
+test_tube==0.7.5
+tifffile==2023.12.9
+tiktoken==0.5.2
+timm==0.9.12
+tokenizers==0.15.1
+toml==0.10.2
+tomli==2.0.1
+tomlkit==0.12.0
+toolz==0.12.0
+torch==2.0.1
+torch-fidelity==0.3.0
+torchdiffeq==0.2.3
+torchmetrics==0.6.0
+torchsde==0.2.6
+torchvision==0.15.2
+tornado==6.4
+tqdm==4.66.1
+trampoline==0.1.2
+transformers==4.37.2
+triton==2.0.0
+typer==0.9.0
+typing_extensions==4.9.0
+tzdata==2023.4
+tzlocal==5.2
+urllib3==2.1.0
+urwid==2.4.2
+uvicorn==0.25.0
+validators==0.22.0
+wandb==0.16.3
+watchdog==3.0.0
+wavedrom==2.0.3.post3
+wcwidth==0.2.13
+websockets==11.0.3
+Werkzeug==3.0.1
+wmctrl==0.5
+xxhash==3.4.1
+yapf==0.40.2
+yarl==1.9.4
+zipp==3.17.0
diff --git a/stable_diffusion/LICENSE b/stable_diffusion/LICENSE
new file mode 100644
index 0000000000000000000000000000000000000000..0e609df0d8cd3b5d11a1ea962a56b604b70846a5
--- /dev/null
+++ b/stable_diffusion/LICENSE
@@ -0,0 +1,82 @@
+Copyright (c) 2022 Robin Rombach and Patrick Esser and contributors
+
+CreativeML Open RAIL-M
+dated August 22, 2022
+
+Section I: PREAMBLE
+
+Multimodal generative models are being widely adopted and used, and have the potential to transform the way artists, among other individuals, conceive and benefit from AI or ML technologies as a tool for content creation.
+
+Notwithstanding the current and potential benefits that these artifacts can bring to society at large, there are also concerns about potential misuses of them, either due to their technical limitations or ethical considerations.
+
+In short, this license strives for both the open and responsible downstream use of the accompanying model. When it comes to the open character, we took inspiration from open source permissive licenses regarding the grant of IP rights. Referring to the downstream responsible use, we added use-based restrictions not permitting the use of the Model in very specific scenarios, in order for the licensor to be able to enforce the license in case potential misuses of the Model may occur. At the same time, we strive to promote open and responsible research on generative models for art and content generation.
+
+Even though downstream derivative versions of the model could be released under different licensing terms, the latter will always have to include - at minimum - the same use-based restrictions as the ones in the original license (this license). We believe in the intersection between open and responsible AI development; thus, this License aims to strike a balance between both in order to enable responsible open-science in the field of AI.
+
+This License governs the use of the model (and its derivatives) and is informed by the model card associated with the model.
+
+NOW THEREFORE, You and Licensor agree as follows:
+
+1. Definitions
+
+- "License" means the terms and conditions for use, reproduction, and Distribution as defined in this document.
+- "Data" means a collection of information and/or content extracted from the dataset used with the Model, including to train, pretrain, or otherwise evaluate the Model. The Data is not licensed under this License.
+- "Output" means the results of operating a Model as embodied in informational content resulting therefrom.
+- "Model" means any accompanying machine-learning based assemblies (including checkpoints), consisting of learnt weights, parameters (including optimizer states), corresponding to the model architecture as embodied in the Complementary Material, that have been trained or tuned, in whole or in part on the Data, using the Complementary Material.
+- "Derivatives of the Model" means all modifications to the Model, works based on the Model, or any other model which is created or initialized by transfer of patterns of the weights, parameters, activations or output of the Model, to the other model, in order to cause the other model to perform similarly to the Model, including - but not limited to - distillation methods entailing the use of intermediate data representations or methods based on the generation of synthetic data by the Model for training the other model.
+- "Complementary Material" means the accompanying source code and scripts used to define, run, load, benchmark or evaluate the Model, and used to prepare data for training or evaluation, if any. This includes any accompanying documentation, tutorials, examples, etc, if any.
+- "Distribution" means any transmission, reproduction, publication or other sharing of the Model or Derivatives of the Model to a third party, including providing the Model as a hosted service made available by electronic or other remote means - e.g. API-based or web access.
+- "Licensor" means the copyright owner or entity authorized by the copyright owner that is granting the License, including the persons or entities that may have rights in the Model and/or distributing the Model.
+- "You" (or "Your") means an individual or Legal Entity exercising permissions granted by this License and/or making use of the Model for whichever purpose and in any field of use, including usage of the Model in an end-use application - e.g. chatbot, translator, image generator.
+- "Third Parties" means individuals or legal entities that are not under common control with Licensor or You.
+- "Contribution" means any work of authorship, including the original version of the Model and any modifications or additions to that Model or Derivatives of the Model thereof, that is intentionally submitted to Licensor for inclusion in the Model by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Model, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
+- "Contributor" means Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Model.
+
+Section II: INTELLECTUAL PROPERTY RIGHTS
+
+Both copyright and patent grants apply to the Model, Derivatives of the Model and Complementary Material. The Model and Derivatives of the Model are subject to additional terms as described in Section III.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare, publicly display, publicly perform, sublicense, and distribute the Complementary Material, the Model, and Derivatives of the Model.
+3. Grant of Patent License. Subject to the terms and conditions of this License and where and as applicable, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this paragraph) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Model and the Complementary Material, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Model to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Model and/or Complementary Material or a Contribution incorporated within the Model and/or Complementary Material constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for the Model and/or Work shall terminate as of the date such litigation is asserted or filed.
+
+Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
+
+4. Distribution and Redistribution. You may host for Third Party remote access purposes (e.g. software-as-a-service), reproduce and distribute copies of the Model or Derivatives of the Model thereof in any medium, with or without modifications, provided that You meet the following conditions:
+Use-based restrictions as referenced in paragraph 5 MUST be included as an enforceable provision by You in any type of legal agreement (e.g. a license) governing the use and/or distribution of the Model or Derivatives of the Model, and You shall give notice to subsequent users You Distribute to, that the Model or Derivatives of the Model are subject to paragraph 5. This provision does not apply to the use of Complementary Material.
+You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License;
+You must cause any modified files to carry prominent notices stating that You changed the files;
+You must retain all copyright, patent, trademark, and attribution notices excluding those notices that do not pertain to any part of the Model, Derivatives of the Model.
+You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions - respecting paragraph 4.a. - for use, reproduction, or Distribution of Your modifications, or for any such Derivatives of the Model as a whole, provided Your use, reproduction, and Distribution of the Model otherwise complies with the conditions stated in this License.
+5. Use-based restrictions. The restrictions set forth in Attachment A are considered Use-based restrictions. Therefore You cannot use the Model and the Derivatives of the Model for the specified restricted uses. You may use the Model subject to this License, including only for lawful purposes and in accordance with the License. Use may include creating any content with, finetuning, updating, running, training, evaluating and/or reparametrizing the Model. You shall require all of Your users who use the Model or a Derivative of the Model to comply with the terms of this paragraph (paragraph 5).
+6. The Output You Generate. Except as set forth herein, Licensor claims no rights in the Output You generate using the Model. You are accountable for the Output you generate and its subsequent uses. No use of the output can contravene any provision as stated in the License.
+
+Section IV: OTHER PROVISIONS
+
+7. Updates and Runtime Restrictions. To the maximum extent permitted by law, Licensor reserves the right to restrict (remotely or otherwise) usage of the Model in violation of this License, update the Model through electronic means, or modify the Output of the Model based on updates. You shall undertake reasonable efforts to use the latest version of the Model.
+8. Trademarks and related. Nothing in this License permits You to make use of Licensors’ trademarks, trade names, logos or to otherwise suggest endorsement or misrepresent the relationship between the parties; and any rights not expressly granted herein are reserved by the Licensors.
+9. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Model and the Complementary Material (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Model, Derivatives of the Model, and the Complementary Material and assume any risks associated with Your exercise of permissions under this License.
+10. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Model and the Complementary Material (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
+11. Accepting Warranty or Additional Liability. While redistributing the Model, Derivatives of the Model and the Complementary Material thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
+12. If any provision of this License is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein.
+
+END OF TERMS AND CONDITIONS
+
+
+
+
+Attachment A
+
+Use Restrictions
+
+You agree not to use the Model or Derivatives of the Model:
+- In any way that violates any applicable national, federal, state, local or international law or regulation;
+- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
+- To generate or disseminate verifiably false information and/or content with the purpose of harming others;
+- To generate or disseminate personal identifiable information that can be used to harm an individual;
+- To defame, disparage or otherwise harass others;
+- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
+- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
+- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
+- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
+- To provide medical advice and medical results interpretation;
+- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
diff --git a/stable_diffusion/README.md b/stable_diffusion/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..c9e6c3bb13a18fc5fc0f31ab819bf6eccda81bf0
--- /dev/null
+++ b/stable_diffusion/README.md
@@ -0,0 +1,215 @@
+# Stable Diffusion
+*Stable Diffusion was made possible thanks to a collaboration with [Stability AI](https://stability.ai/) and [Runway](https://runwayml.com/) and builds upon our previous work:*
+
+[**High-Resolution Image Synthesis with Latent Diffusion Models**](https://ommer-lab.com/research/latent-diffusion-models/)
+[Robin Rombach](https://github.com/rromb)\*,
+[Andreas Blattmann](https://github.com/ablattmann)\*,
+[Dominik Lorenz](https://github.com/qp-qp)\,
+[Patrick Esser](https://github.com/pesser),
+[Björn Ommer](https://hci.iwr.uni-heidelberg.de/Staff/bommer)
+_[CVPR '22 Oral](https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html) |
+[GitHub](https://github.com/CompVis/latent-diffusion) | [arXiv](https://arxiv.org/abs/2112.10752) | [Project page](https://ommer-lab.com/research/latent-diffusion-models/)_
+
+
+[Stable Diffusion](#stable-diffusion-v1) is a latent text-to-image diffusion
+model.
+Thanks to a generous compute donation from [Stability AI](https://stability.ai/) and support from [LAION](https://laion.ai/), we were able to train a Latent Diffusion Model on 512x512 images from a subset of the [LAION-5B](https://laion.ai/blog/laion-5b/) database.
+Similar to Google's [Imagen](https://arxiv.org/abs/2205.11487),
+this model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts.
+With its 860M UNet and 123M text encoder, the model is relatively lightweight and runs on a GPU with at least 10GB VRAM.
+See [this section](#stable-diffusion-v1) below and the [model card](https://huggingface.co/CompVis/stable-diffusion).
+
+
+## Requirements
+A suitable [conda](https://conda.io/) environment named `ldm` can be created
+and activated with:
+
+```
+conda env create -f environment.yaml
+conda activate ldm
+```
+
+You can also update an existing [latent diffusion](https://github.com/CompVis/latent-diffusion) environment by running
+
+```
+conda install pytorch torchvision -c pytorch
+pip install transformers==4.19.2 diffusers invisible-watermark
+pip install -e .
+```
+
+
+## Stable Diffusion v1
+
+Stable Diffusion v1 refers to a specific configuration of the model
+architecture that uses a downsampling-factor 8 autoencoder with an 860M UNet
+and CLIP ViT-L/14 text encoder for the diffusion model. The model was pretrained on 256x256 images and
+then finetuned on 512x512 images.
+
+*Note: Stable Diffusion v1 is a general text-to-image diffusion model and therefore mirrors biases and (mis-)conceptions that are present
+in its training data.
+Details on the training procedure and data, as well as the intended use of the model can be found in the corresponding [model card](Stable_Diffusion_v1_Model_Card.md).*
+
+The weights are available via [the CompVis organization at Hugging Face](https://huggingface.co/CompVis) under [a license which contains specific use-based restrictions to prevent misuse and harm as informed by the model card, but otherwise remains permissive](LICENSE). While commercial use is permitted under the terms of the license, **we do not recommend using the provided weights for services or products without additional safety mechanisms and considerations**, since there are [known limitations and biases](Stable_Diffusion_v1_Model_Card.md#limitations-and-bias) of the weights, and research on safe and ethical deployment of general text-to-image models is an ongoing effort. **The weights are research artifacts and should be treated as such.**
+
+[The CreativeML OpenRAIL M license](LICENSE) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](/static-proxy?url=https%3A%2F%2Fbigscience.huggingface.co%2F) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](/static-proxy?url=https%3A%2F%2Fbigscience.huggingface.co%2Fblog%2Fthe-bigscience-rail-license) on which our license is based.
+
+### Weights
+
+We currently provide the following checkpoints:
+
+- `sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).
+ 194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).
+- `sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`.
+ 515k steps at resolution `512x512` on [laion-aesthetics v2 5+](https://laion.ai/blog/laion-aesthetics/) (a subset of laion2B-en with estimated aesthetics score `> 5.0`, and additionally
+filtered to images with an original size `>= 512x512`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the [LAION-5B](https://laion.ai/blog/laion-5b/) metadata, the aesthetics score is estimated using the [LAION-Aesthetics Predictor V2](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
+- `sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+- `sd-v1-4.ckpt`: Resumed from `sd-v1-2.ckpt`. 225k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+
+Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
+5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling
+steps show the relative improvements of the checkpoints:
+
+
+
+
+### Text-to-Image with Stable Diffusion
+
+
+
+Stable Diffusion is a latent diffusion model conditioned on the (non-pooled) text embeddings of a CLIP ViT-L/14 text encoder.
+We provide a [reference script for sampling](#reference-sampling-script), but
+there also exists a [diffusers integration](#diffusers-integration), which we
+expect to see more active community development.
+
+#### Reference Sampling Script
+
+We provide a reference sampling script, which incorporates
+
+- a [Safety Checker Module](https://github.com/CompVis/stable-diffusion/pull/36),
+ to reduce the probability of explicit outputs,
+- an [invisible watermarking](https://github.com/ShieldMnt/invisible-watermark)
+ of the outputs, to help viewers [identify the images as machine-generated](scripts/tests/test_watermark.py).
+
+After [obtaining the `stable-diffusion-v1-*-original` weights](#weights), link them
+```
+mkdir -p models/ldm/stable-diffusion-v1/
+ln -s models/ldm/stable-diffusion-v1/model.ckpt
+```
+and sample with
+```
+python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms
+```
+
+By default, this uses a guidance scale of `--scale 7.5`, [Katherine Crowson's implementation](https://github.com/CompVis/latent-diffusion/pull/51) of the [PLMS](https://arxiv.org/abs/2202.09778) sampler,
+and renders images of size 512x512 (which it was trained on) in 50 steps. All supported arguments are listed below (type `python scripts/txt2img.py --help`).
+
+
+```commandline
+usage: txt2img.py [-h] [--prompt [PROMPT]] [--outdir [OUTDIR]] [--skip_grid] [--skip_save] [--ddim_steps DDIM_STEPS] [--plms] [--laion400m] [--fixed_code] [--ddim_eta DDIM_ETA]
+ [--n_iter N_ITER] [--H H] [--W W] [--C C] [--f F] [--n_samples N_SAMPLES] [--n_rows N_ROWS] [--scale SCALE] [--from-file FROM_FILE] [--config CONFIG] [--ckpt CKPT]
+ [--seed SEED] [--precision {full,autocast}]
+
+optional arguments:
+ -h, --help show this help message and exit
+ --prompt [PROMPT] the prompt to render
+ --outdir [OUTDIR] dir to write results to
+ --skip_grid do not save a grid, only individual samples. Helpful when evaluating lots of samples
+ --skip_save do not save individual samples. For speed measurements.
+ --ddim_steps DDIM_STEPS
+ number of ddim sampling steps
+ --plms use plms sampling
+ --laion400m uses the LAION400M model
+ --fixed_code if enabled, uses the same starting code across samples
+ --ddim_eta DDIM_ETA ddim eta (eta=0.0 corresponds to deterministic sampling
+ --n_iter N_ITER sample this often
+ --H H image height, in pixel space
+ --W W image width, in pixel space
+ --C C latent channels
+ --f F downsampling factor
+ --n_samples N_SAMPLES
+ how many samples to produce for each given prompt. A.k.a. batch size
+ --n_rows N_ROWS rows in the grid (default: n_samples)
+ --scale SCALE unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))
+ --from-file FROM_FILE
+ if specified, load prompts from this file
+ --config CONFIG path to config which constructs model
+ --ckpt CKPT path to checkpoint of model
+ --seed SEED the seed (for reproducible sampling)
+ --precision {full,autocast}
+ evaluate at this precision
+```
+Note: The inference config for all v1 versions is designed to be used with EMA-only checkpoints.
+For this reason `use_ema=False` is set in the configuration, otherwise the code will try to switch from
+non-EMA to EMA weights. If you want to examine the effect of EMA vs no EMA, we provide "full" checkpoints
+which contain both types of weights. For these, `use_ema=False` will load and use the non-EMA weights.
+
+
+#### Diffusers Integration
+
+A simple way to download and sample Stable Diffusion is by using the [diffusers library](https://github.com/huggingface/diffusers/tree/main#new--stable-diffusion-is-now-fully-compatible-with-diffusers):
+```py
+# make sure you're logged in with `huggingface-cli login`
+from torch import autocast
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+ "CompVis/stable-diffusion-v1-4",
+ use_auth_token=True
+).to("cuda")
+
+prompt = "a photo of an astronaut riding a horse on mars"
+with autocast("cuda"):
+ image = pipe(prompt)["sample"][0]
+
+image.save("astronaut_rides_horse.png")
+```
+
+
+### Image Modification with Stable Diffusion
+
+By using a diffusion-denoising mechanism as first proposed by [SDEdit](https://arxiv.org/abs/2108.01073), the model can be used for different
+tasks such as text-guided image-to-image translation and upscaling. Similar to the txt2img sampling script,
+we provide a script to perform image modification with Stable Diffusion.
+
+The following describes an example where a rough sketch made in [Pinta](https://www.pinta-project.com/) is converted into a detailed artwork.
+```
+python scripts/img2img.py --prompt "A fantasy landscape, trending on artstation" --init-img --strength 0.8
+```
+Here, strength is a value between 0.0 and 1.0, that controls the amount of noise that is added to the input image.
+Values that approach 1.0 allow for lots of variations but will also produce images that are not semantically consistent with the input. See the following example.
+
+**Input**
+
+
+
+**Outputs**
+
+
+
+
+This procedure can, for example, also be used to upscale samples from the base model.
+
+
+## Comments
+
+- Our codebase for the diffusion models builds heavily on [OpenAI's ADM codebase](https://github.com/openai/guided-diffusion)
+and [https://github.com/lucidrains/denoising-diffusion-pytorch](https://github.com/lucidrains/denoising-diffusion-pytorch).
+Thanks for open-sourcing!
+
+- The implementation of the transformer encoder is from [x-transformers](https://github.com/lucidrains/x-transformers) by [lucidrains](https://github.com/lucidrains?tab=repositories).
+
+
+## BibTeX
+
+```
+@misc{rombach2021highresolution,
+ title={High-Resolution Image Synthesis with Latent Diffusion Models},
+ author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},
+ year={2021},
+ eprint={2112.10752},
+ archivePrefix={arXiv},
+ primaryClass={cs.CV}
+}
+```
+
+
diff --git a/stable_diffusion/Stable_Diffusion_v1_Model_Card.md b/stable_diffusion/Stable_Diffusion_v1_Model_Card.md
new file mode 100644
index 0000000000000000000000000000000000000000..ad76ad2ee6da62ad21c8a92e9082a31b272740f3
--- /dev/null
+++ b/stable_diffusion/Stable_Diffusion_v1_Model_Card.md
@@ -0,0 +1,144 @@
+# Stable Diffusion v1 Model Card
+This model card focuses on the model associated with the Stable Diffusion model, available [here](https://github.com/CompVis/stable-diffusion).
+
+## Model Details
+- **Developed by:** Robin Rombach, Patrick Esser
+- **Model type:** Diffusion-based text-to-image generation model
+- **Language(s):** English
+- **License:** [Proprietary](LICENSE)
+- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([CLIP ViT-L/14](https://arxiv.org/abs/2103.00020)) as suggested in the [Imagen paper](https://arxiv.org/abs/2205.11487).
+- **Resources for more information:** [GitHub Repository](https://github.com/CompVis/stable-diffusion), [Paper](https://arxiv.org/abs/2112.10752).
+- **Cite as:**
+
+ @InProceedings{Rombach_2022_CVPR,
+ author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
+ title = {High-Resolution Image Synthesis With Latent Diffusion Models},
+ booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+ month = {June},
+ year = {2022},
+ pages = {10684-10695}
+ }
+
+# Uses
+
+## Direct Use
+The model is intended for research purposes only. Possible research areas and
+tasks include
+
+- Safe deployment of models which have the potential to generate harmful content.
+- Probing and understanding the limitations and biases of generative models.
+- Generation of artworks and use in design and other artistic processes.
+- Applications in educational or creative tools.
+- Research on generative models.
+
+Excluded uses are described below.
+
+ ### Misuse, Malicious Use, and Out-of-Scope Use
+_Note: This section is taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), but applies in the same way to Stable Diffusion v1_.
+
+The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
+
+#### Out-of-Scope Use
+The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
+
+#### Misuse and Malicious Use
+Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
+
+- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
+- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
+- Impersonating individuals without their consent.
+- Sexual content without consent of the people who might see it.
+- Mis- and disinformation
+- Representations of egregious violence and gore
+- Sharing of copyrighted or licensed material in violation of its terms of use.
+- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
+
+## Limitations and Bias
+
+### Limitations
+
+- The model does not achieve perfect photorealism
+- The model cannot render legible text
+- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
+- Faces and people in general may not be generated properly.
+- The model was trained mainly with English captions and will not work as well in other languages.
+- The autoencoding part of the model is lossy
+- The model was trained on a large-scale dataset
+ [LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material
+ and is not fit for product use without additional safety mechanisms and
+ considerations.
+- No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data.
+ The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images.
+
+### Bias
+While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
+Stable Diffusion v1 was primarily trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
+which consists of images that are limited to English descriptions.
+Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
+This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
+ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
+Stable Diffusion v1 mirrors and exacerbates biases to such a degree that viewer discretion must be advised irrespective of the input or its intent.
+
+
+## Training
+
+**Training Data**
+The model developers used the following dataset for training the model:
+
+- LAION-5B and subsets thereof (see next section)
+
+**Training Procedure**
+Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
+
+- Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
+- Text prompts are encoded through a ViT-L/14 text-encoder.
+- The non-pooled output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention.
+- The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet.
+
+We currently provide the following checkpoints:
+
+- `sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).
+ 194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).
+- `sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`.
+ 515k steps at resolution `512x512` on [laion-aesthetics v2 5+](https://laion.ai/blog/laion-aesthetics/) (a subset of laion2B-en with estimated aesthetics score `> 5.0`, and additionally
+filtered to images with an original size `>= 512x512`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the [LAION-5B](https://laion.ai/blog/laion-5b/) metadata, the aesthetics score is estimated using the [LAION-Aesthetics Predictor V2](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
+- `sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+- `sd-v1-4.ckpt`: Resumed from `sd-v1-2.ckpt`. 225k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+
+- **Hardware:** 32 x 8 x A100 GPUs
+- **Optimizer:** AdamW
+- **Gradient Accumulations**: 2
+- **Batch:** 32 x 8 x 2 x 4 = 2048
+- **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant
+
+## Evaluation Results
+Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
+5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling
+steps show the relative improvements of the checkpoints:
+
+
+
+Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores.
+
+## Environmental Impact
+
+**Stable Diffusion v1** **Estimated Emissions**
+Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.
+
+- **Hardware Type:** A100 PCIe 40GB
+- **Hours used:** 150000
+- **Cloud Provider:** AWS
+- **Compute Region:** US-east
+- **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 11250 kg CO2 eq.
+
+## Citation
+ @InProceedings{Rombach_2022_CVPR,
+ author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
+ title = {High-Resolution Image Synthesis With Latent Diffusion Models},
+ booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+ month = {June},
+ year = {2022},
+ pages = {10684-10695}
+ }
+
+*This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*
diff --git a/stable_diffusion/assets/stable-samples/txt2img/merged-0006.png.REMOVED.git-id b/stable_diffusion/assets/stable-samples/txt2img/merged-0006.png.REMOVED.git-id
new file mode 100644
index 0000000000000000000000000000000000000000..7ef20e4e5e0d85104320b1b4e20d9679039095a8
--- /dev/null
+++ b/stable_diffusion/assets/stable-samples/txt2img/merged-0006.png.REMOVED.git-id
@@ -0,0 +1 @@
+999f3703230580e8c89e9081abd6a1f8f50896d4
\ No newline at end of file
diff --git a/stable_diffusion/assets/stable-samples/txt2img/merged-0007.png.REMOVED.git-id b/stable_diffusion/assets/stable-samples/txt2img/merged-0007.png.REMOVED.git-id
new file mode 100644
index 0000000000000000000000000000000000000000..8fbb31f3c6294c6dc625fcc173efefda6e3d4f4a
--- /dev/null
+++ b/stable_diffusion/assets/stable-samples/txt2img/merged-0007.png.REMOVED.git-id
@@ -0,0 +1 @@
+af390acaf601283782d6f479d4cade4d78e30b26
\ No newline at end of file
diff --git a/stable_diffusion/assets/txt2img-preview.png.REMOVED.git-id b/stable_diffusion/assets/txt2img-preview.png.REMOVED.git-id
new file mode 100644
index 0000000000000000000000000000000000000000..61a349bd4de776be6a457158fc7bb6804f85fd0c
--- /dev/null
+++ b/stable_diffusion/assets/txt2img-preview.png.REMOVED.git-id
@@ -0,0 +1 @@
+51ee1c235dfdc63d4c41de7d303d03730e43c33c
\ No newline at end of file
diff --git a/stable_diffusion/configs/autoencoder/autoencoder_kl_16x16x16.yaml b/stable_diffusion/configs/autoencoder/autoencoder_kl_16x16x16.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..5f1d10ec75e5de5932cdcf0e8d3c712feac7578e
--- /dev/null
+++ b/stable_diffusion/configs/autoencoder/autoencoder_kl_16x16x16.yaml
@@ -0,0 +1,54 @@
+model:
+ base_learning_rate: 4.5e-6
+ target: ldm.models.autoencoder.AutoencoderKL
+ params:
+ monitor: "val/rec_loss"
+ embed_dim: 16
+ lossconfig:
+ target: ldm.modules.losses.LPIPSWithDiscriminator
+ params:
+ disc_start: 50001
+ kl_weight: 0.000001
+ disc_weight: 0.5
+
+ ddconfig:
+ double_z: True
+ z_channels: 16
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult: [ 1,1,2,2,4] # num_down = len(ch_mult)-1
+ num_res_blocks: 2
+ attn_resolutions: [16]
+ dropout: 0.0
+
+
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 12
+ wrap: True
+ train:
+ target: ldm.data.imagenet.ImageNetSRTrain
+ params:
+ size: 256
+ degradation: pil_nearest
+ validation:
+ target: ldm.data.imagenet.ImageNetSRValidation
+ params:
+ size: 256
+ degradation: pil_nearest
+
+lightning:
+ callbacks:
+ image_logger:
+ target: main.ImageLogger
+ params:
+ batch_frequency: 1000
+ max_images: 8
+ increase_log_steps: True
+
+ trainer:
+ benchmark: True
+ accumulate_grad_batches: 2
diff --git a/stable_diffusion/configs/autoencoder/autoencoder_kl_32x32x4.yaml b/stable_diffusion/configs/autoencoder/autoencoder_kl_32x32x4.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..ab8b36fe6e3e95df2942a437b7d9c919b60d5c86
--- /dev/null
+++ b/stable_diffusion/configs/autoencoder/autoencoder_kl_32x32x4.yaml
@@ -0,0 +1,53 @@
+model:
+ base_learning_rate: 4.5e-6
+ target: ldm.models.autoencoder.AutoencoderKL
+ params:
+ monitor: "val/rec_loss"
+ embed_dim: 4
+ lossconfig:
+ target: ldm.modules.losses.LPIPSWithDiscriminator
+ params:
+ disc_start: 50001
+ kl_weight: 0.000001
+ disc_weight: 0.5
+
+ ddconfig:
+ double_z: True
+ z_channels: 4
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult: [ 1,2,4,4 ] # num_down = len(ch_mult)-1
+ num_res_blocks: 2
+ attn_resolutions: [ ]
+ dropout: 0.0
+
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 12
+ wrap: True
+ train:
+ target: ldm.data.imagenet.ImageNetSRTrain
+ params:
+ size: 256
+ degradation: pil_nearest
+ validation:
+ target: ldm.data.imagenet.ImageNetSRValidation
+ params:
+ size: 256
+ degradation: pil_nearest
+
+lightning:
+ callbacks:
+ image_logger:
+ target: main.ImageLogger
+ params:
+ batch_frequency: 1000
+ max_images: 8
+ increase_log_steps: True
+
+ trainer:
+ benchmark: True
+ accumulate_grad_batches: 2
diff --git a/stable_diffusion/data/example_conditioning/text_conditional/sample_0.txt b/stable_diffusion/data/example_conditioning/text_conditional/sample_0.txt
new file mode 100644
index 0000000000000000000000000000000000000000..de60c5c9a38bbead2956aa0c60129a26985cbf6d
--- /dev/null
+++ b/stable_diffusion/data/example_conditioning/text_conditional/sample_0.txt
@@ -0,0 +1 @@
+A basket of cerries
diff --git a/stable_diffusion/ldm/data/__init__.py b/stable_diffusion/ldm/data/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/stable_diffusion/ldm/data/base.py b/stable_diffusion/ldm/data/base.py
new file mode 100644
index 0000000000000000000000000000000000000000..b196c2f7aa583a3e8bc4aad9f943df0c4dae0da7
--- /dev/null
+++ b/stable_diffusion/ldm/data/base.py
@@ -0,0 +1,23 @@
+from abc import abstractmethod
+from torch.utils.data import Dataset, ConcatDataset, ChainDataset, IterableDataset
+
+
+class Txt2ImgIterableBaseDataset(IterableDataset):
+ '''
+ Define an interface to make the IterableDatasets for text2img data chainable
+ '''
+ def __init__(self, num_records=0, valid_ids=None, size=256):
+ super().__init__()
+ self.num_records = num_records
+ self.valid_ids = valid_ids
+ self.sample_ids = valid_ids
+ self.size = size
+
+ print(f'{self.__class__.__name__} dataset contains {self.__len__()} examples.')
+
+ def __len__(self):
+ return self.num_records
+
+ @abstractmethod
+ def __iter__(self):
+ pass
\ No newline at end of file
diff --git a/stable_diffusion/ldm/data/imagenet.py b/stable_diffusion/ldm/data/imagenet.py
new file mode 100644
index 0000000000000000000000000000000000000000..1c473f9c6965b22315dbb289eff8247c71bdc790
--- /dev/null
+++ b/stable_diffusion/ldm/data/imagenet.py
@@ -0,0 +1,394 @@
+import os, yaml, pickle, shutil, tarfile, glob
+import cv2
+import albumentations
+import PIL
+import numpy as np
+import torchvision.transforms.functional as TF
+from omegaconf import OmegaConf
+from functools import partial
+from PIL import Image
+from tqdm import tqdm
+from torch.utils.data import Dataset, Subset
+
+import taming.data.utils as tdu
+from taming.data.imagenet import str_to_indices, give_synsets_from_indices, download, retrieve
+from taming.data.imagenet import ImagePaths
+
+from ldm.modules.image_degradation import degradation_fn_bsr, degradation_fn_bsr_light
+
+
+def synset2idx(path_to_yaml="data/index_synset.yaml"):
+ with open(path_to_yaml) as f:
+ di2s = yaml.load(f)
+ return dict((v,k) for k,v in di2s.items())
+
+
+class ImageNetBase(Dataset):
+ def __init__(self, config=None):
+ self.config = config or OmegaConf.create()
+ if not type(self.config)==dict:
+ self.config = OmegaConf.to_container(self.config)
+ self.keep_orig_class_label = self.config.get("keep_orig_class_label", False)
+ self.process_images = True # if False we skip loading & processing images and self.data contains filepaths
+ self._prepare()
+ self._prepare_synset_to_human()
+ self._prepare_idx_to_synset()
+ self._prepare_human_to_integer_label()
+ self._load()
+
+ def __len__(self):
+ return len(self.data)
+
+ def __getitem__(self, i):
+ return self.data[i]
+
+ def _prepare(self):
+ raise NotImplementedError()
+
+ def _filter_relpaths(self, relpaths):
+ ignore = set([
+ "n06596364_9591.JPEG",
+ ])
+ relpaths = [rpath for rpath in relpaths if not rpath.split("/")[-1] in ignore]
+ if "sub_indices" in self.config:
+ indices = str_to_indices(self.config["sub_indices"])
+ synsets = give_synsets_from_indices(indices, path_to_yaml=self.idx2syn) # returns a list of strings
+ self.synset2idx = synset2idx(path_to_yaml=self.idx2syn)
+ files = []
+ for rpath in relpaths:
+ syn = rpath.split("/")[0]
+ if syn in synsets:
+ files.append(rpath)
+ return files
+ else:
+ return relpaths
+
+ def _prepare_synset_to_human(self):
+ SIZE = 2655750
+ URL = "https://heibox.uni-heidelberg.de/f/9f28e956cd304264bb82/?dl=1"
+ self.human_dict = os.path.join(self.root, "synset_human.txt")
+ if (not os.path.exists(self.human_dict) or
+ not os.path.getsize(self.human_dict)==SIZE):
+ download(URL, self.human_dict)
+
+ def _prepare_idx_to_synset(self):
+ URL = "https://heibox.uni-heidelberg.de/f/d835d5b6ceda4d3aa910/?dl=1"
+ self.idx2syn = os.path.join(self.root, "index_synset.yaml")
+ if (not os.path.exists(self.idx2syn)):
+ download(URL, self.idx2syn)
+
+ def _prepare_human_to_integer_label(self):
+ URL = "https://heibox.uni-heidelberg.de/f/2362b797d5be43b883f6/?dl=1"
+ self.human2integer = os.path.join(self.root, "imagenet1000_clsidx_to_labels.txt")
+ if (not os.path.exists(self.human2integer)):
+ download(URL, self.human2integer)
+ with open(self.human2integer, "r") as f:
+ lines = f.read().splitlines()
+ assert len(lines) == 1000
+ self.human2integer_dict = dict()
+ for line in lines:
+ value, key = line.split(":")
+ self.human2integer_dict[key] = int(value)
+
+ def _load(self):
+ with open(self.txt_filelist, "r") as f:
+ self.relpaths = f.read().splitlines()
+ l1 = len(self.relpaths)
+ self.relpaths = self._filter_relpaths(self.relpaths)
+ print("Removed {} files from filelist during filtering.".format(l1 - len(self.relpaths)))
+
+ self.synsets = [p.split("/")[0] for p in self.relpaths]
+ self.abspaths = [os.path.join(self.datadir, p) for p in self.relpaths]
+
+ unique_synsets = np.unique(self.synsets)
+ class_dict = dict((synset, i) for i, synset in enumerate(unique_synsets))
+ if not self.keep_orig_class_label:
+ self.class_labels = [class_dict[s] for s in self.synsets]
+ else:
+ self.class_labels = [self.synset2idx[s] for s in self.synsets]
+
+ with open(self.human_dict, "r") as f:
+ human_dict = f.read().splitlines()
+ human_dict = dict(line.split(maxsplit=1) for line in human_dict)
+
+ self.human_labels = [human_dict[s] for s in self.synsets]
+
+ labels = {
+ "relpath": np.array(self.relpaths),
+ "synsets": np.array(self.synsets),
+ "class_label": np.array(self.class_labels),
+ "human_label": np.array(self.human_labels),
+ }
+
+ if self.process_images:
+ self.size = retrieve(self.config, "size", default=256)
+ self.data = ImagePaths(self.abspaths,
+ labels=labels,
+ size=self.size,
+ random_crop=self.random_crop,
+ )
+ else:
+ self.data = self.abspaths
+
+
+class ImageNetTrain(ImageNetBase):
+ NAME = "ILSVRC2012_train"
+ URL = "http://www.image-net.org/challenges/LSVRC/2012/"
+ AT_HASH = "a306397ccf9c2ead27155983c254227c0fd938e2"
+ FILES = [
+ "ILSVRC2012_img_train.tar",
+ ]
+ SIZES = [
+ 147897477120,
+ ]
+
+ def __init__(self, process_images=True, data_root=None, **kwargs):
+ self.process_images = process_images
+ self.data_root = data_root
+ super().__init__(**kwargs)
+
+ def _prepare(self):
+ if self.data_root:
+ self.root = os.path.join(self.data_root, self.NAME)
+ else:
+ cachedir = os.environ.get("XDG_CACHE_HOME", os.path.expanduser("~/.cache"))
+ self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
+
+ self.datadir = os.path.join(self.root, "data")
+ self.txt_filelist = os.path.join(self.root, "filelist.txt")
+ self.expected_length = 1281167
+ self.random_crop = retrieve(self.config, "ImageNetTrain/random_crop",
+ default=True)
+ if not tdu.is_prepared(self.root):
+ # prep
+ print("Preparing dataset {} in {}".format(self.NAME, self.root))
+
+ datadir = self.datadir
+ if not os.path.exists(datadir):
+ path = os.path.join(self.root, self.FILES[0])
+ if not os.path.exists(path) or not os.path.getsize(path)==self.SIZES[0]:
+ import academictorrents as at
+ atpath = at.get(self.AT_HASH, datastore=self.root)
+ assert atpath == path
+
+ print("Extracting {} to {}".format(path, datadir))
+ os.makedirs(datadir, exist_ok=True)
+ with tarfile.open(path, "r:") as tar:
+ tar.extractall(path=datadir)
+
+ print("Extracting sub-tars.")
+ subpaths = sorted(glob.glob(os.path.join(datadir, "*.tar")))
+ for subpath in tqdm(subpaths):
+ subdir = subpath[:-len(".tar")]
+ os.makedirs(subdir, exist_ok=True)
+ with tarfile.open(subpath, "r:") as tar:
+ tar.extractall(path=subdir)
+
+ filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
+ filelist = [os.path.relpath(p, start=datadir) for p in filelist]
+ filelist = sorted(filelist)
+ filelist = "\n".join(filelist)+"\n"
+ with open(self.txt_filelist, "w") as f:
+ f.write(filelist)
+
+ tdu.mark_prepared(self.root)
+
+
+class ImageNetValidation(ImageNetBase):
+ NAME = "ILSVRC2012_validation"
+ URL = "http://www.image-net.org/challenges/LSVRC/2012/"
+ AT_HASH = "5d6d0df7ed81efd49ca99ea4737e0ae5e3a5f2e5"
+ VS_URL = "https://heibox.uni-heidelberg.de/f/3e0f6e9c624e45f2bd73/?dl=1"
+ FILES = [
+ "ILSVRC2012_img_val.tar",
+ "validation_synset.txt",
+ ]
+ SIZES = [
+ 6744924160,
+ 1950000,
+ ]
+
+ def __init__(self, process_images=True, data_root=None, **kwargs):
+ self.data_root = data_root
+ self.process_images = process_images
+ super().__init__(**kwargs)
+
+ def _prepare(self):
+ if self.data_root:
+ self.root = os.path.join(self.data_root, self.NAME)
+ else:
+ cachedir = os.environ.get("XDG_CACHE_HOME", os.path.expanduser("~/.cache"))
+ self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
+ self.datadir = os.path.join(self.root, "data")
+ self.txt_filelist = os.path.join(self.root, "filelist.txt")
+ self.expected_length = 50000
+ self.random_crop = retrieve(self.config, "ImageNetValidation/random_crop",
+ default=False)
+ if not tdu.is_prepared(self.root):
+ # prep
+ print("Preparing dataset {} in {}".format(self.NAME, self.root))
+
+ datadir = self.datadir
+ if not os.path.exists(datadir):
+ path = os.path.join(self.root, self.FILES[0])
+ if not os.path.exists(path) or not os.path.getsize(path)==self.SIZES[0]:
+ import academictorrents as at
+ atpath = at.get(self.AT_HASH, datastore=self.root)
+ assert atpath == path
+
+ print("Extracting {} to {}".format(path, datadir))
+ os.makedirs(datadir, exist_ok=True)
+ with tarfile.open(path, "r:") as tar:
+ tar.extractall(path=datadir)
+
+ vspath = os.path.join(self.root, self.FILES[1])
+ if not os.path.exists(vspath) or not os.path.getsize(vspath)==self.SIZES[1]:
+ download(self.VS_URL, vspath)
+
+ with open(vspath, "r") as f:
+ synset_dict = f.read().splitlines()
+ synset_dict = dict(line.split() for line in synset_dict)
+
+ print("Reorganizing into synset folders")
+ synsets = np.unique(list(synset_dict.values()))
+ for s in synsets:
+ os.makedirs(os.path.join(datadir, s), exist_ok=True)
+ for k, v in synset_dict.items():
+ src = os.path.join(datadir, k)
+ dst = os.path.join(datadir, v)
+ shutil.move(src, dst)
+
+ filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
+ filelist = [os.path.relpath(p, start=datadir) for p in filelist]
+ filelist = sorted(filelist)
+ filelist = "\n".join(filelist)+"\n"
+ with open(self.txt_filelist, "w") as f:
+ f.write(filelist)
+
+ tdu.mark_prepared(self.root)
+
+
+
+class ImageNetSR(Dataset):
+ def __init__(self, size=None,
+ degradation=None, downscale_f=4, min_crop_f=0.5, max_crop_f=1.,
+ random_crop=True):
+ """
+ Imagenet Superresolution Dataloader
+ Performs following ops in order:
+ 1. crops a crop of size s from image either as random or center crop
+ 2. resizes crop to size with cv2.area_interpolation
+ 3. degrades resized crop with degradation_fn
+
+ :param size: resizing to size after cropping
+ :param degradation: degradation_fn, e.g. cv_bicubic or bsrgan_light
+ :param downscale_f: Low Resolution Downsample factor
+ :param min_crop_f: determines crop size s,
+ where s = c * min_img_side_len with c sampled from interval (min_crop_f, max_crop_f)
+ :param max_crop_f: ""
+ :param data_root:
+ :param random_crop:
+ """
+ self.base = self.get_base()
+ assert size
+ assert (size / downscale_f).is_integer()
+ self.size = size
+ self.LR_size = int(size / downscale_f)
+ self.min_crop_f = min_crop_f
+ self.max_crop_f = max_crop_f
+ assert(max_crop_f <= 1.)
+ self.center_crop = not random_crop
+
+ self.image_rescaler = albumentations.SmallestMaxSize(max_size=size, interpolation=cv2.INTER_AREA)
+
+ self.pil_interpolation = False # gets reset later if incase interp_op is from pillow
+
+ if degradation == "bsrgan":
+ self.degradation_process = partial(degradation_fn_bsr, sf=downscale_f)
+
+ elif degradation == "bsrgan_light":
+ self.degradation_process = partial(degradation_fn_bsr_light, sf=downscale_f)
+
+ else:
+ interpolation_fn = {
+ "cv_nearest": cv2.INTER_NEAREST,
+ "cv_bilinear": cv2.INTER_LINEAR,
+ "cv_bicubic": cv2.INTER_CUBIC,
+ "cv_area": cv2.INTER_AREA,
+ "cv_lanczos": cv2.INTER_LANCZOS4,
+ "pil_nearest": PIL.Image.NEAREST,
+ "pil_bilinear": PIL.Image.BILINEAR,
+ "pil_bicubic": PIL.Image.BICUBIC,
+ "pil_box": PIL.Image.BOX,
+ "pil_hamming": PIL.Image.HAMMING,
+ "pil_lanczos": PIL.Image.LANCZOS,
+ }[degradation]
+
+ self.pil_interpolation = degradation.startswith("pil_")
+
+ if self.pil_interpolation:
+ self.degradation_process = partial(TF.resize, size=self.LR_size, interpolation=interpolation_fn)
+
+ else:
+ self.degradation_process = albumentations.SmallestMaxSize(max_size=self.LR_size,
+ interpolation=interpolation_fn)
+
+ def __len__(self):
+ return len(self.base)
+
+ def __getitem__(self, i):
+ example = self.base[i]
+ image = Image.open(example["file_path_"])
+
+ if not image.mode == "RGB":
+ image = image.convert("RGB")
+
+ image = np.array(image).astype(np.uint8)
+
+ min_side_len = min(image.shape[:2])
+ crop_side_len = min_side_len * np.random.uniform(self.min_crop_f, self.max_crop_f, size=None)
+ crop_side_len = int(crop_side_len)
+
+ if self.center_crop:
+ self.cropper = albumentations.CenterCrop(height=crop_side_len, width=crop_side_len)
+
+ else:
+ self.cropper = albumentations.RandomCrop(height=crop_side_len, width=crop_side_len)
+
+ image = self.cropper(image=image)["image"]
+ image = self.image_rescaler(image=image)["image"]
+
+ if self.pil_interpolation:
+ image_pil = PIL.Image.fromarray(image)
+ LR_image = self.degradation_process(image_pil)
+ LR_image = np.array(LR_image).astype(np.uint8)
+
+ else:
+ LR_image = self.degradation_process(image=image)["image"]
+
+ example["image"] = (image/127.5 - 1.0).astype(np.float32)
+ example["LR_image"] = (LR_image/127.5 - 1.0).astype(np.float32)
+
+ return example
+
+
+class ImageNetSRTrain(ImageNetSR):
+ def __init__(self, **kwargs):
+ super().__init__(**kwargs)
+
+ def get_base(self):
+ with open("data/imagenet_train_hr_indices.p", "rb") as f:
+ indices = pickle.load(f)
+ dset = ImageNetTrain(process_images=False,)
+ return Subset(dset, indices)
+
+
+class ImageNetSRValidation(ImageNetSR):
+ def __init__(self, **kwargs):
+ super().__init__(**kwargs)
+
+ def get_base(self):
+ with open("data/imagenet_val_hr_indices.p", "rb") as f:
+ indices = pickle.load(f)
+ dset = ImageNetValidation(process_images=False,)
+ return Subset(dset, indices)
diff --git a/stable_diffusion/ldm/data/lsun.py b/stable_diffusion/ldm/data/lsun.py
new file mode 100644
index 0000000000000000000000000000000000000000..6256e45715ff0b57c53f985594d27cbbbff0e68e
--- /dev/null
+++ b/stable_diffusion/ldm/data/lsun.py
@@ -0,0 +1,92 @@
+import os
+import numpy as np
+import PIL
+from PIL import Image
+from torch.utils.data import Dataset
+from torchvision import transforms
+
+
+class LSUNBase(Dataset):
+ def __init__(self,
+ txt_file,
+ data_root,
+ size=None,
+ interpolation="bicubic",
+ flip_p=0.5
+ ):
+ self.data_paths = txt_file
+ self.data_root = data_root
+ with open(self.data_paths, "r") as f:
+ self.image_paths = f.read().splitlines()
+ self._length = len(self.image_paths)
+ self.labels = {
+ "relative_file_path_": [l for l in self.image_paths],
+ "file_path_": [os.path.join(self.data_root, l)
+ for l in self.image_paths],
+ }
+
+ self.size = size
+ self.interpolation = {"linear": PIL.Image.LINEAR,
+ "bilinear": PIL.Image.BILINEAR,
+ "bicubic": PIL.Image.BICUBIC,
+ "lanczos": PIL.Image.LANCZOS,
+ }[interpolation]
+ self.flip = transforms.RandomHorizontalFlip(p=flip_p)
+
+ def __len__(self):
+ return self._length
+
+ def __getitem__(self, i):
+ example = dict((k, self.labels[k][i]) for k in self.labels)
+ image = Image.open(example["file_path_"])
+ if not image.mode == "RGB":
+ image = image.convert("RGB")
+
+ # default to score-sde preprocessing
+ img = np.array(image).astype(np.uint8)
+ crop = min(img.shape[0], img.shape[1])
+ h, w, = img.shape[0], img.shape[1]
+ img = img[(h - crop) // 2:(h + crop) // 2,
+ (w - crop) // 2:(w + crop) // 2]
+
+ image = Image.fromarray(img)
+ if self.size is not None:
+ image = image.resize((self.size, self.size), resample=self.interpolation)
+
+ image = self.flip(image)
+ image = np.array(image).astype(np.uint8)
+ example["image"] = (image / 127.5 - 1.0).astype(np.float32)
+ return example
+
+
+class LSUNChurchesTrain(LSUNBase):
+ def __init__(self, **kwargs):
+ super().__init__(txt_file="data/lsun/church_outdoor_train.txt", data_root="data/lsun/churches", **kwargs)
+
+
+class LSUNChurchesValidation(LSUNBase):
+ def __init__(self, flip_p=0., **kwargs):
+ super().__init__(txt_file="data/lsun/church_outdoor_val.txt", data_root="data/lsun/churches",
+ flip_p=flip_p, **kwargs)
+
+
+class LSUNBedroomsTrain(LSUNBase):
+ def __init__(self, **kwargs):
+ super().__init__(txt_file="data/lsun/bedrooms_train.txt", data_root="data/lsun/bedrooms", **kwargs)
+
+
+class LSUNBedroomsValidation(LSUNBase):
+ def __init__(self, flip_p=0.0, **kwargs):
+ super().__init__(txt_file="data/lsun/bedrooms_val.txt", data_root="data/lsun/bedrooms",
+ flip_p=flip_p, **kwargs)
+
+
+class LSUNCatsTrain(LSUNBase):
+ def __init__(self, **kwargs):
+ super().__init__(txt_file="data/lsun/cat_train.txt", data_root="data/lsun/cats", **kwargs)
+
+
+class LSUNCatsValidation(LSUNBase):
+ def __init__(self, flip_p=0., **kwargs):
+ super().__init__(txt_file="data/lsun/cat_val.txt", data_root="data/lsun/cats",
+ flip_p=flip_p, **kwargs)
diff --git a/stable_diffusion/ldm/lr_scheduler.py b/stable_diffusion/ldm/lr_scheduler.py
new file mode 100644
index 0000000000000000000000000000000000000000..be39da9ca6dacc22bf3df9c7389bbb403a4a3ade
--- /dev/null
+++ b/stable_diffusion/ldm/lr_scheduler.py
@@ -0,0 +1,98 @@
+import numpy as np
+
+
+class LambdaWarmUpCosineScheduler:
+ """
+ note: use with a base_lr of 1.0
+ """
+ def __init__(self, warm_up_steps, lr_min, lr_max, lr_start, max_decay_steps, verbosity_interval=0):
+ self.lr_warm_up_steps = warm_up_steps
+ self.lr_start = lr_start
+ self.lr_min = lr_min
+ self.lr_max = lr_max
+ self.lr_max_decay_steps = max_decay_steps
+ self.last_lr = 0.
+ self.verbosity_interval = verbosity_interval
+
+ def schedule(self, n, **kwargs):
+ if self.verbosity_interval > 0:
+ if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_lr}")
+ if n < self.lr_warm_up_steps:
+ lr = (self.lr_max - self.lr_start) / self.lr_warm_up_steps * n + self.lr_start
+ self.last_lr = lr
+ return lr
+ else:
+ t = (n - self.lr_warm_up_steps) / (self.lr_max_decay_steps - self.lr_warm_up_steps)
+ t = min(t, 1.0)
+ lr = self.lr_min + 0.5 * (self.lr_max - self.lr_min) * (
+ 1 + np.cos(t * np.pi))
+ self.last_lr = lr
+ return lr
+
+ def __call__(self, n, **kwargs):
+ return self.schedule(n,**kwargs)
+
+
+class LambdaWarmUpCosineScheduler2:
+ """
+ supports repeated iterations, configurable via lists
+ note: use with a base_lr of 1.0.
+ """
+ def __init__(self, warm_up_steps, f_min, f_max, f_start, cycle_lengths, verbosity_interval=0):
+ assert len(warm_up_steps) == len(f_min) == len(f_max) == len(f_start) == len(cycle_lengths)
+ self.lr_warm_up_steps = warm_up_steps
+ self.f_start = f_start
+ self.f_min = f_min
+ self.f_max = f_max
+ self.cycle_lengths = cycle_lengths
+ self.cum_cycles = np.cumsum([0] + list(self.cycle_lengths))
+ self.last_f = 0.
+ self.verbosity_interval = verbosity_interval
+
+ def find_in_interval(self, n):
+ interval = 0
+ for cl in self.cum_cycles[1:]:
+ if n <= cl:
+ return interval
+ interval += 1
+
+ def schedule(self, n, **kwargs):
+ cycle = self.find_in_interval(n)
+ n = n - self.cum_cycles[cycle]
+ if self.verbosity_interval > 0:
+ if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_f}, "
+ f"current cycle {cycle}")
+ if n < self.lr_warm_up_steps[cycle]:
+ f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[cycle] * n + self.f_start[cycle]
+ self.last_f = f
+ return f
+ else:
+ t = (n - self.lr_warm_up_steps[cycle]) / (self.cycle_lengths[cycle] - self.lr_warm_up_steps[cycle])
+ t = min(t, 1.0)
+ f = self.f_min[cycle] + 0.5 * (self.f_max[cycle] - self.f_min[cycle]) * (
+ 1 + np.cos(t * np.pi))
+ self.last_f = f
+ return f
+
+ def __call__(self, n, **kwargs):
+ return self.schedule(n, **kwargs)
+
+
+class LambdaLinearScheduler(LambdaWarmUpCosineScheduler2):
+
+ def schedule(self, n, **kwargs):
+ cycle = self.find_in_interval(n)
+ n = n - self.cum_cycles[cycle]
+ if self.verbosity_interval > 0:
+ if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_f}, "
+ f"current cycle {cycle}")
+
+ if n < self.lr_warm_up_steps[cycle]:
+ f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[cycle] * n + self.f_start[cycle]
+ self.last_f = f
+ return f
+ else:
+ f = self.f_min[cycle] + (self.f_max[cycle] - self.f_min[cycle]) * (self.cycle_lengths[cycle] - n) / (self.cycle_lengths[cycle])
+ self.last_f = f
+ return f
+
diff --git a/stable_diffusion/ldm/models/diffusion/__init__.py b/stable_diffusion/ldm/models/diffusion/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/stable_diffusion/ldm/models/diffusion/ddim.py b/stable_diffusion/ldm/models/diffusion/ddim.py
new file mode 100644
index 0000000000000000000000000000000000000000..fb31215db5c3f3f703f15987d7eee6a179c9f7ec
--- /dev/null
+++ b/stable_diffusion/ldm/models/diffusion/ddim.py
@@ -0,0 +1,241 @@
+"""SAMPLING ONLY."""
+
+import torch
+import numpy as np
+from tqdm import tqdm
+from functools import partial
+
+from ldm.modules.diffusionmodules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like, \
+ extract_into_tensor
+
+
+class DDIMSampler(object):
+ def __init__(self, model, schedule="linear", **kwargs):
+ super().__init__()
+ self.model = model
+ self.ddpm_num_timesteps = model.num_timesteps
+ self.schedule = schedule
+
+ def register_buffer(self, name, attr):
+ if type(attr) == torch.Tensor:
+ if attr.device != torch.device("cuda"):
+ attr = attr.to(torch.device("cuda"))
+ setattr(self, name, attr)
+
+ def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True):
+ self.ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps,
+ num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose)
+ alphas_cumprod = self.model.alphas_cumprod
+ assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep'
+ to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.model.device)
+
+ self.register_buffer('betas', to_torch(self.model.betas))
+ self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+ self.register_buffer('alphas_cumprod_prev', to_torch(self.model.alphas_cumprod_prev))
+
+ # calculations for diffusion q(x_t | x_{t-1}) and others
+ self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod.cpu())))
+ self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu())))
+ self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu())))
+ self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu())))
+ self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1)))
+
+ # ddim sampling parameters
+ ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(),
+ ddim_timesteps=self.ddim_timesteps,
+ eta=ddim_eta,verbose=verbose)
+ self.register_buffer('ddim_sigmas', ddim_sigmas)
+ self.register_buffer('ddim_alphas', ddim_alphas)
+ self.register_buffer('ddim_alphas_prev', ddim_alphas_prev)
+ self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas))
+ sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt(
+ (1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * (
+ 1 - self.alphas_cumprod / self.alphas_cumprod_prev))
+ self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps)
+
+ @torch.no_grad()
+ def sample(self,
+ S,
+ batch_size,
+ shape,
+ conditioning=None,
+ callback=None,
+ normals_sequence=None,
+ img_callback=None,
+ quantize_x0=False,
+ eta=0.,
+ mask=None,
+ x0=None,
+ temperature=1.,
+ noise_dropout=0.,
+ score_corrector=None,
+ corrector_kwargs=None,
+ verbose=True,
+ x_T=None,
+ log_every_t=100,
+ unconditional_guidance_scale=1.,
+ unconditional_conditioning=None,
+ # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
+ **kwargs
+ ):
+ if conditioning is not None:
+ if isinstance(conditioning, dict):
+ cbs = conditioning[list(conditioning.keys())[0]].shape[0]
+ if cbs != batch_size:
+ print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
+ else:
+ if conditioning.shape[0] != batch_size:
+ print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
+
+ self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
+ # sampling
+ C, H, W = shape
+ size = (batch_size, C, H, W)
+ print(f'Data shape for DDIM sampling is {size}, eta {eta}')
+
+ samples, intermediates = self.ddim_sampling(conditioning, size,
+ callback=callback,
+ img_callback=img_callback,
+ quantize_denoised=quantize_x0,
+ mask=mask, x0=x0,
+ ddim_use_original_steps=False,
+ noise_dropout=noise_dropout,
+ temperature=temperature,
+ score_corrector=score_corrector,
+ corrector_kwargs=corrector_kwargs,
+ x_T=x_T,
+ log_every_t=log_every_t,
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ unconditional_conditioning=unconditional_conditioning,
+ )
+ return samples, intermediates
+
+ @torch.no_grad()
+ def ddim_sampling(self, cond, shape,
+ x_T=None, ddim_use_original_steps=False,
+ callback=None, timesteps=None, quantize_denoised=False,
+ mask=None, x0=None, img_callback=None, log_every_t=100,
+ temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
+ unconditional_guidance_scale=1., unconditional_conditioning=None,):
+ device = self.model.betas.device
+ b = shape[0]
+ if x_T is None:
+ img = torch.randn(shape, device=device)
+ else:
+ img = x_T
+
+ if timesteps is None:
+ timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps
+ elif timesteps is not None and not ddim_use_original_steps:
+ subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1
+ timesteps = self.ddim_timesteps[:subset_end]
+
+ intermediates = {'x_inter': [img], 'pred_x0': [img]}
+ time_range = reversed(range(0,timesteps)) if ddim_use_original_steps else np.flip(timesteps)
+ total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0]
+ print(f"Running DDIM Sampling with {total_steps} timesteps")
+
+ iterator = tqdm(time_range, desc='DDIM Sampler', total=total_steps)
+
+ for i, step in enumerate(iterator):
+ index = total_steps - i - 1
+ ts = torch.full((b,), step, device=device, dtype=torch.long)
+
+ if mask is not None:
+ assert x0 is not None
+ img_orig = self.model.q_sample(x0, ts) # TODO: deterministic forward pass?
+ img = img_orig * mask + (1. - mask) * img
+
+ outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
+ quantize_denoised=quantize_denoised, temperature=temperature,
+ noise_dropout=noise_dropout, score_corrector=score_corrector,
+ corrector_kwargs=corrector_kwargs,
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ unconditional_conditioning=unconditional_conditioning)
+ img, pred_x0 = outs
+ if callback: callback(i)
+ if img_callback: img_callback(pred_x0, i)
+
+ if index % log_every_t == 0 or index == total_steps - 1:
+ intermediates['x_inter'].append(img)
+ intermediates['pred_x0'].append(pred_x0)
+
+ return img, intermediates
+
+ @torch.no_grad()
+ def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
+ temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
+ unconditional_guidance_scale=1., unconditional_conditioning=None):
+ b, *_, device = *x.shape, x.device
+
+ if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
+ e_t = self.model.apply_model(x, t, c)
+ else:
+ x_in = torch.cat([x] * 2)
+ t_in = torch.cat([t] * 2)
+ c_in = torch.cat([unconditional_conditioning, c])
+ e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
+ e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
+
+ if score_corrector is not None:
+ assert self.model.parameterization == "eps"
+ e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
+
+ alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
+ alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
+ sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
+ sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
+ # select parameters corresponding to the currently considered timestep
+ a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
+ a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
+ sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
+ sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
+
+ # current prediction for x_0
+ pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
+ if quantize_denoised:
+ pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
+ # direction pointing to x_t
+ dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
+ noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
+ if noise_dropout > 0.:
+ noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+ x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
+ return x_prev, pred_x0
+
+ @torch.no_grad()
+ def stochastic_encode(self, x0, t, use_original_steps=False, noise=None):
+ # fast, but does not allow for exact reconstruction
+ # t serves as an index to gather the correct alphas
+ if use_original_steps:
+ sqrt_alphas_cumprod = self.sqrt_alphas_cumprod
+ sqrt_one_minus_alphas_cumprod = self.sqrt_one_minus_alphas_cumprod
+ else:
+ sqrt_alphas_cumprod = torch.sqrt(self.ddim_alphas)
+ sqrt_one_minus_alphas_cumprod = self.ddim_sqrt_one_minus_alphas
+
+ if noise is None:
+ noise = torch.randn_like(x0)
+ return (extract_into_tensor(sqrt_alphas_cumprod, t, x0.shape) * x0 +
+ extract_into_tensor(sqrt_one_minus_alphas_cumprod, t, x0.shape) * noise)
+
+ @torch.no_grad()
+ def decode(self, x_latent, cond, t_start, unconditional_guidance_scale=1.0, unconditional_conditioning=None,
+ use_original_steps=False):
+
+ timesteps = np.arange(self.ddpm_num_timesteps) if use_original_steps else self.ddim_timesteps
+ timesteps = timesteps[:t_start]
+
+ time_range = np.flip(timesteps)
+ total_steps = timesteps.shape[0]
+ print(f"Running DDIM Sampling with {total_steps} timesteps")
+
+ iterator = tqdm(time_range, desc='Decoding image', total=total_steps)
+ x_dec = x_latent
+ for i, step in enumerate(iterator):
+ index = total_steps - i - 1
+ ts = torch.full((x_latent.shape[0],), step, device=x_latent.device, dtype=torch.long)
+ x_dec, _ = self.p_sample_ddim(x_dec, cond, ts, index=index, use_original_steps=use_original_steps,
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ unconditional_conditioning=unconditional_conditioning)
+ return x_dec
\ No newline at end of file
diff --git a/stable_diffusion/ldm/models/diffusion/ddpm.py b/stable_diffusion/ldm/models/diffusion/ddpm.py
new file mode 100644
index 0000000000000000000000000000000000000000..bbedd04cfd6f736ac066434a75618b9ba5125be7
--- /dev/null
+++ b/stable_diffusion/ldm/models/diffusion/ddpm.py
@@ -0,0 +1,1445 @@
+"""
+wild mixture of
+https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
+https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py
+https://github.com/CompVis/taming-transformers
+-- merci
+"""
+
+import torch
+import torch.nn as nn
+import numpy as np
+import pytorch_lightning as pl
+from torch.optim.lr_scheduler import LambdaLR
+from einops import rearrange, repeat
+from contextlib import contextmanager
+from functools import partial
+from tqdm import tqdm
+from torchvision.utils import make_grid
+from pytorch_lightning.utilities.distributed import rank_zero_only
+
+from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
+from ldm.modules.ema import LitEma
+from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
+from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
+from ldm.models.diffusion.ddim import DDIMSampler
+
+
+__conditioning_keys__ = {'concat': 'c_concat',
+ 'crossattn': 'c_crossattn',
+ 'adm': 'y'}
+
+
+def disabled_train(self, mode=True):
+ """Overwrite model.train with this function to make sure train/eval mode
+ does not change anymore."""
+ return self
+
+
+def uniform_on_device(r1, r2, shape, device):
+ return (r1 - r2) * torch.rand(*shape, device=device) + r2
+
+
+class DDPM(pl.LightningModule):
+ # classic DDPM with Gaussian diffusion, in image space
+ def __init__(self,
+ unet_config,
+ timesteps=1000,
+ beta_schedule="linear",
+ loss_type="l2",
+ ckpt_path=None,
+ ignore_keys=[],
+ load_only_unet=False,
+ monitor="val/loss",
+ use_ema=True,
+ first_stage_key="image",
+ image_size=256,
+ channels=3,
+ log_every_t=100,
+ clip_denoised=True,
+ linear_start=1e-4,
+ linear_end=2e-2,
+ cosine_s=8e-3,
+ given_betas=None,
+ original_elbo_weight=0.,
+ v_posterior=0., # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
+ l_simple_weight=1.,
+ conditioning_key=None,
+ parameterization="eps", # all assuming fixed variance schedules
+ scheduler_config=None,
+ use_positional_encodings=False,
+ learn_logvar=False,
+ logvar_init=0.,
+ ):
+ super().__init__()
+ assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
+ self.parameterization = parameterization
+ print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
+ self.cond_stage_model = None
+ self.clip_denoised = clip_denoised
+ self.log_every_t = log_every_t
+ self.first_stage_key = first_stage_key
+ self.image_size = image_size # try conv?
+ self.channels = channels
+ self.use_positional_encodings = use_positional_encodings
+ self.model = DiffusionWrapper(unet_config, conditioning_key)
+ count_params(self.model, verbose=True)
+ self.use_ema = use_ema
+ if self.use_ema:
+ self.model_ema = LitEma(self.model)
+ print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+ self.use_scheduler = scheduler_config is not None
+ if self.use_scheduler:
+ self.scheduler_config = scheduler_config
+
+ self.v_posterior = v_posterior
+ self.original_elbo_weight = original_elbo_weight
+ self.l_simple_weight = l_simple_weight
+
+ if monitor is not None:
+ self.monitor = monitor
+ if ckpt_path is not None:
+ self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+
+ self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
+ linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
+
+ self.loss_type = loss_type
+
+ self.learn_logvar = learn_logvar
+ self.logvar = torch.full(fill_value=logvar_init, size=(self.num_timesteps,))
+ if self.learn_logvar:
+ self.logvar = nn.Parameter(self.logvar, requires_grad=True)
+
+
+ def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
+ linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+ if exists(given_betas):
+ betas = given_betas
+ else:
+ betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end,
+ cosine_s=cosine_s)
+ alphas = 1. - betas
+ alphas_cumprod = np.cumprod(alphas, axis=0)
+ alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])
+
+ timesteps, = betas.shape
+ self.num_timesteps = int(timesteps)
+ self.linear_start = linear_start
+ self.linear_end = linear_end
+ assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'
+
+ to_torch = partial(torch.tensor, dtype=torch.float32)
+
+ self.register_buffer('betas', to_torch(betas))
+ self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+ self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))
+
+ # calculations for diffusion q(x_t | x_{t-1}) and others
+ self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
+ self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
+ self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
+ self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
+ self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))
+
+ # calculations for posterior q(x_{t-1} | x_t, x_0)
+ posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / (
+ 1. - alphas_cumprod) + self.v_posterior * betas
+ # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
+ self.register_buffer('posterior_variance', to_torch(posterior_variance))
+ # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
+ self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
+ self.register_buffer('posterior_mean_coef1', to_torch(
+ betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
+ self.register_buffer('posterior_mean_coef2', to_torch(
+ (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))
+
+ if self.parameterization == "eps":
+ lvlb_weights = self.betas ** 2 / (
+ 2 * self.posterior_variance * to_torch(alphas) * (1 - self.alphas_cumprod))
+ elif self.parameterization == "x0":
+ lvlb_weights = 0.5 * np.sqrt(torch.Tensor(alphas_cumprod)) / (2. * 1 - torch.Tensor(alphas_cumprod))
+ else:
+ raise NotImplementedError("mu not supported")
+ # TODO how to choose this term
+ lvlb_weights[0] = lvlb_weights[1]
+ self.register_buffer('lvlb_weights', lvlb_weights, persistent=False)
+ assert not torch.isnan(self.lvlb_weights).all()
+
+ @contextmanager
+ def ema_scope(self, context=None):
+ if self.use_ema:
+ self.model_ema.store(self.model.parameters())
+ self.model_ema.copy_to(self.model)
+ if context is not None:
+ print(f"{context}: Switched to EMA weights")
+ try:
+ yield None
+ finally:
+ if self.use_ema:
+ self.model_ema.restore(self.model.parameters())
+ if context is not None:
+ print(f"{context}: Restored training weights")
+
+ def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+ sd = torch.load(path, map_location="cpu")
+ if "state_dict" in list(sd.keys()):
+ sd = sd["state_dict"]
+ keys = list(sd.keys())
+ for k in keys:
+ for ik in ignore_keys:
+ if k.startswith(ik):
+ print("Deleting key {} from state_dict.".format(k))
+ del sd[k]
+ missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
+ sd, strict=False)
+ print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
+ if len(missing) > 0:
+ print(f"Missing Keys: {missing}")
+ if len(unexpected) > 0:
+ print(f"Unexpected Keys: {unexpected}")
+
+ def q_mean_variance(self, x_start, t):
+ """
+ Get the distribution q(x_t | x_0).
+ :param x_start: the [N x C x ...] tensor of noiseless inputs.
+ :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
+ :return: A tuple (mean, variance, log_variance), all of x_start's shape.
+ """
+ mean = (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start)
+ variance = extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
+ log_variance = extract_into_tensor(self.log_one_minus_alphas_cumprod, t, x_start.shape)
+ return mean, variance, log_variance
+
+ def predict_start_from_noise(self, x_t, t, noise):
+ return (
+ extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
+ extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
+ )
+
+ def q_posterior(self, x_start, x_t, t):
+ posterior_mean = (
+ extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start +
+ extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
+ )
+ posterior_variance = extract_into_tensor(self.posterior_variance, t, x_t.shape)
+ posterior_log_variance_clipped = extract_into_tensor(self.posterior_log_variance_clipped, t, x_t.shape)
+ return posterior_mean, posterior_variance, posterior_log_variance_clipped
+
+ def p_mean_variance(self, x, t, clip_denoised: bool):
+ model_out = self.model(x, t)
+ if self.parameterization == "eps":
+ x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+ elif self.parameterization == "x0":
+ x_recon = model_out
+ if clip_denoised:
+ x_recon.clamp_(-1., 1.)
+
+ model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+ return model_mean, posterior_variance, posterior_log_variance
+
+ @torch.no_grad()
+ def p_sample(self, x, t, clip_denoised=True, repeat_noise=False):
+ b, *_, device = *x.shape, x.device
+ model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, clip_denoised=clip_denoised)
+ noise = noise_like(x.shape, device, repeat_noise)
+ # no noise when t == 0
+ nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+ @torch.no_grad()
+ def p_sample_loop(self, shape, return_intermediates=False):
+ device = self.betas.device
+ b = shape[0]
+ img = torch.randn(shape, device=device)
+ intermediates = [img]
+ for i in tqdm(reversed(range(0, self.num_timesteps)), desc='Sampling t', total=self.num_timesteps):
+ img = self.p_sample(img, torch.full((b,), i, device=device, dtype=torch.long),
+ clip_denoised=self.clip_denoised)
+ if i % self.log_every_t == 0 or i == self.num_timesteps - 1:
+ intermediates.append(img)
+ if return_intermediates:
+ return img, intermediates
+ return img
+
+ @torch.no_grad()
+ def sample(self, batch_size=16, return_intermediates=False):
+ image_size = self.image_size
+ channels = self.channels
+ return self.p_sample_loop((batch_size, channels, image_size, image_size),
+ return_intermediates=return_intermediates)
+
+ def q_sample(self, x_start, t, noise=None):
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
+ extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
+
+ def get_loss(self, pred, target, mean=True):
+ if self.loss_type == 'l1':
+ loss = (target - pred).abs()
+ if mean:
+ loss = loss.mean()
+ elif self.loss_type == 'l2':
+ if mean:
+ loss = torch.nn.functional.mse_loss(target, pred)
+ else:
+ loss = torch.nn.functional.mse_loss(target, pred, reduction='none')
+ else:
+ raise NotImplementedError("unknown loss type '{loss_type}'")
+
+ return loss
+
+ def p_losses(self, x_start, t, noise=None):
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+ model_out = self.model(x_noisy, t)
+
+ loss_dict = {}
+ if self.parameterization == "eps":
+ target = noise
+ elif self.parameterization == "x0":
+ target = x_start
+ else:
+ raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+
+ loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
+
+ log_prefix = 'train' if self.training else 'val'
+
+ loss_dict.update({f'{log_prefix}/loss_simple': loss.mean()})
+ loss_simple = loss.mean() * self.l_simple_weight
+
+ loss_vlb = (self.lvlb_weights[t] * loss).mean()
+ loss_dict.update({f'{log_prefix}/loss_vlb': loss_vlb})
+
+ loss = loss_simple + self.original_elbo_weight * loss_vlb
+
+ loss_dict.update({f'{log_prefix}/loss': loss})
+
+ return loss, loss_dict
+
+ def forward(self, x, *args, **kwargs):
+ # b, c, h, w, device, img_size, = *x.shape, x.device, self.image_size
+ # assert h == img_size and w == img_size, f'height and width of image must be {img_size}'
+ t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+ return self.p_losses(x, t, *args, **kwargs)
+
+ def get_input(self, batch, k):
+ x = batch[k]
+ if len(x.shape) == 3:
+ x = x[..., None]
+ x = rearrange(x, 'b h w c -> b c h w')
+ x = x.to(memory_format=torch.contiguous_format).float()
+ return x
+
+ def shared_step(self, batch):
+ x = self.get_input(batch, self.first_stage_key)
+ loss, loss_dict = self(x)
+ return loss, loss_dict
+
+ def training_step(self, batch, batch_idx):
+ loss, loss_dict = self.shared_step(batch)
+
+ self.log_dict(loss_dict, prog_bar=True,
+ logger=True, on_step=True, on_epoch=True)
+
+ self.log("global_step", self.global_step,
+ prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+ if self.use_scheduler:
+ lr = self.optimizers().param_groups[0]['lr']
+ self.log('lr_abs', lr, prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+ return loss
+
+ @torch.no_grad()
+ def validation_step(self, batch, batch_idx):
+ _, loss_dict_no_ema = self.shared_step(batch)
+ with self.ema_scope():
+ _, loss_dict_ema = self.shared_step(batch)
+ loss_dict_ema = {key + '_ema': loss_dict_ema[key] for key in loss_dict_ema}
+ self.log_dict(loss_dict_no_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+ self.log_dict(loss_dict_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+
+ def on_train_batch_end(self, *args, **kwargs):
+ if self.use_ema:
+ self.model_ema(self.model)
+
+ def _get_rows_from_list(self, samples):
+ n_imgs_per_row = len(samples)
+ denoise_grid = rearrange(samples, 'n b c h w -> b n c h w')
+ denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+ denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+ return denoise_grid
+
+ @torch.no_grad()
+ def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
+ log = dict()
+ x = self.get_input(batch, self.first_stage_key)
+ N = min(x.shape[0], N)
+ n_row = min(x.shape[0], n_row)
+ x = x.to(self.device)[:N]
+ log["inputs"] = x
+
+ # get diffusion row
+ diffusion_row = list()
+ x_start = x[:n_row]
+
+ for t in range(self.num_timesteps):
+ if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+ t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+ t = t.to(self.device).long()
+ noise = torch.randn_like(x_start)
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+ diffusion_row.append(x_noisy)
+
+ log["diffusion_row"] = self._get_rows_from_list(diffusion_row)
+
+ if sample:
+ # get denoise row
+ with self.ema_scope("Plotting"):
+ samples, denoise_row = self.sample(batch_size=N, return_intermediates=True)
+
+ log["samples"] = samples
+ log["denoise_row"] = self._get_rows_from_list(denoise_row)
+
+ if return_keys:
+ if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+ return log
+ else:
+ return {key: log[key] for key in return_keys}
+ return log
+
+ def configure_optimizers(self):
+ lr = self.learning_rate
+ params = list(self.model.parameters())
+ if self.learn_logvar:
+ params = params + [self.logvar]
+ opt = torch.optim.AdamW(params, lr=lr)
+ return opt
+
+
+class LatentDiffusion(DDPM):
+ """main class"""
+ def __init__(self,
+ first_stage_config,
+ cond_stage_config,
+ num_timesteps_cond=None,
+ cond_stage_key="image",
+ cond_stage_trainable=False,
+ concat_mode=True,
+ cond_stage_forward=None,
+ conditioning_key=None,
+ scale_factor=1.0,
+ scale_by_std=False,
+ *args, **kwargs):
+ self.num_timesteps_cond = default(num_timesteps_cond, 1)
+ self.scale_by_std = scale_by_std
+ assert self.num_timesteps_cond <= kwargs['timesteps']
+ # for backwards compatibility after implementation of DiffusionWrapper
+ if conditioning_key is None:
+ conditioning_key = 'concat' if concat_mode else 'crossattn'
+ if cond_stage_config == '__is_unconditional__':
+ conditioning_key = None
+ ckpt_path = kwargs.pop("ckpt_path", None)
+ ignore_keys = kwargs.pop("ignore_keys", [])
+ super().__init__(conditioning_key=conditioning_key, *args, **kwargs)
+ self.concat_mode = concat_mode
+ self.cond_stage_trainable = cond_stage_trainable
+ self.cond_stage_key = cond_stage_key
+ try:
+ self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
+ except:
+ self.num_downs = 0
+ if not scale_by_std:
+ self.scale_factor = scale_factor
+ else:
+ self.register_buffer('scale_factor', torch.tensor(scale_factor))
+ self.instantiate_first_stage(first_stage_config)
+ self.instantiate_cond_stage(cond_stage_config)
+ self.cond_stage_forward = cond_stage_forward
+ self.clip_denoised = False
+ self.bbox_tokenizer = None
+
+ self.restarted_from_ckpt = False
+ if ckpt_path is not None:
+ self.init_from_ckpt(ckpt_path, ignore_keys)
+ self.restarted_from_ckpt = True
+
+ def make_cond_schedule(self, ):
+ self.cond_ids = torch.full(size=(self.num_timesteps,), fill_value=self.num_timesteps - 1, dtype=torch.long)
+ ids = torch.round(torch.linspace(0, self.num_timesteps - 1, self.num_timesteps_cond)).long()
+ self.cond_ids[:self.num_timesteps_cond] = ids
+
+ @rank_zero_only
+ @torch.no_grad()
+ def on_train_batch_start(self, batch, batch_idx, dataloader_idx):
+ # only for very first batch
+ if self.scale_by_std and self.current_epoch == 0 and self.global_step == 0 and batch_idx == 0 and not self.restarted_from_ckpt:
+ assert self.scale_factor == 1., 'rather not use custom rescaling and std-rescaling simultaneously'
+ # set rescale weight to 1./std of encodings
+ print("### USING STD-RESCALING ###")
+ x = super().get_input(batch, self.first_stage_key)
+ x = x.to(self.device)
+ encoder_posterior = self.encode_first_stage(x)
+ z = self.get_first_stage_encoding(encoder_posterior).detach()
+ del self.scale_factor
+ self.register_buffer('scale_factor', 1. / z.flatten().std())
+ print(f"setting self.scale_factor to {self.scale_factor}")
+ print("### USING STD-RESCALING ###")
+
+ def register_schedule(self,
+ given_betas=None, beta_schedule="linear", timesteps=1000,
+ linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+ super().register_schedule(given_betas, beta_schedule, timesteps, linear_start, linear_end, cosine_s)
+
+ self.shorten_cond_schedule = self.num_timesteps_cond > 1
+ if self.shorten_cond_schedule:
+ self.make_cond_schedule()
+
+ def instantiate_first_stage(self, config):
+ model = instantiate_from_config(config)
+ self.first_stage_model = model.eval()
+ self.first_stage_model.train = disabled_train
+ for param in self.first_stage_model.parameters():
+ param.requires_grad = False
+
+ def instantiate_cond_stage(self, config):
+ if not self.cond_stage_trainable:
+ if config == "__is_first_stage__":
+ print("Using first stage also as cond stage.")
+ self.cond_stage_model = self.first_stage_model
+ elif config == "__is_unconditional__":
+ print(f"Training {self.__class__.__name__} as an unconditional model.")
+ self.cond_stage_model = None
+ # self.be_unconditional = True
+ else:
+ model = instantiate_from_config(config)
+ self.cond_stage_model = model.eval()
+ self.cond_stage_model.train = disabled_train
+ for param in self.cond_stage_model.parameters():
+ param.requires_grad = False
+ else:
+ assert config != '__is_first_stage__'
+ assert config != '__is_unconditional__'
+ model = instantiate_from_config(config)
+ self.cond_stage_model = model
+
+ def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
+ denoise_row = []
+ for zd in tqdm(samples, desc=desc):
+ denoise_row.append(self.decode_first_stage(zd.to(self.device),
+ force_not_quantize=force_no_decoder_quantization))
+ n_imgs_per_row = len(denoise_row)
+ denoise_row = torch.stack(denoise_row) # n_log_step, n_row, C, H, W
+ denoise_grid = rearrange(denoise_row, 'n b c h w -> b n c h w')
+ denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+ denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+ return denoise_grid
+
+ def get_first_stage_encoding(self, encoder_posterior):
+ if isinstance(encoder_posterior, DiagonalGaussianDistribution):
+ z = encoder_posterior.sample()
+ elif isinstance(encoder_posterior, torch.Tensor):
+ z = encoder_posterior
+ else:
+ raise NotImplementedError(f"encoder_posterior of type '{type(encoder_posterior)}' not yet implemented")
+ return self.scale_factor * z
+
+ def get_learned_conditioning(self, c):
+ if self.cond_stage_forward is None:
+ if hasattr(self.cond_stage_model, 'encode') and callable(self.cond_stage_model.encode):
+ c = self.cond_stage_model.encode(c)
+ if isinstance(c, DiagonalGaussianDistribution):
+ c = c.mode()
+ else:
+ c = self.cond_stage_model(c)
+ else:
+ assert hasattr(self.cond_stage_model, self.cond_stage_forward)
+ c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
+ return c
+
+ def meshgrid(self, h, w):
+ y = torch.arange(0, h).view(h, 1, 1).repeat(1, w, 1)
+ x = torch.arange(0, w).view(1, w, 1).repeat(h, 1, 1)
+
+ arr = torch.cat([y, x], dim=-1)
+ return arr
+
+ def delta_border(self, h, w):
+ """
+ :param h: height
+ :param w: width
+ :return: normalized distance to image border,
+ wtith min distance = 0 at border and max dist = 0.5 at image center
+ """
+ lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
+ arr = self.meshgrid(h, w) / lower_right_corner
+ dist_left_up = torch.min(arr, dim=-1, keepdims=True)[0]
+ dist_right_down = torch.min(1 - arr, dim=-1, keepdims=True)[0]
+ edge_dist = torch.min(torch.cat([dist_left_up, dist_right_down], dim=-1), dim=-1)[0]
+ return edge_dist
+
+ def get_weighting(self, h, w, Ly, Lx, device):
+ weighting = self.delta_border(h, w)
+ weighting = torch.clip(weighting, self.split_input_params["clip_min_weight"],
+ self.split_input_params["clip_max_weight"], )
+ weighting = weighting.view(1, h * w, 1).repeat(1, 1, Ly * Lx).to(device)
+
+ if self.split_input_params["tie_braker"]:
+ L_weighting = self.delta_border(Ly, Lx)
+ L_weighting = torch.clip(L_weighting,
+ self.split_input_params["clip_min_tie_weight"],
+ self.split_input_params["clip_max_tie_weight"])
+
+ L_weighting = L_weighting.view(1, 1, Ly * Lx).to(device)
+ weighting = weighting * L_weighting
+ return weighting
+
+ def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1): # todo load once not every time, shorten code
+ """
+ :param x: img of size (bs, c, h, w)
+ :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
+ """
+ bs, nc, h, w = x.shape
+
+ # number of crops in image
+ Ly = (h - kernel_size[0]) // stride[0] + 1
+ Lx = (w - kernel_size[1]) // stride[1] + 1
+
+ if uf == 1 and df == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)
+
+ weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h, w) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))
+
+ elif uf > 1 and df == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
+ dilation=1, padding=0,
+ stride=(stride[0] * uf, stride[1] * uf))
+ fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)
+
+ weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h * uf, w * uf) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))
+
+ elif df > 1 and uf == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
+ dilation=1, padding=0,
+ stride=(stride[0] // df, stride[1] // df))
+ fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)
+
+ weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h // df, w // df) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))
+
+ else:
+ raise NotImplementedError
+
+ return fold, unfold, normalization, weighting
+
+ @torch.no_grad()
+ def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,
+ cond_key=None, return_original_cond=False, bs=None):
+ x = super().get_input(batch, k)
+ if bs is not None:
+ x = x[:bs]
+ x = x.to(self.device)
+ encoder_posterior = self.encode_first_stage(x)
+ z = self.get_first_stage_encoding(encoder_posterior).detach()
+
+ if self.model.conditioning_key is not None:
+ if cond_key is None:
+ cond_key = self.cond_stage_key
+ if cond_key != self.first_stage_key:
+ if cond_key in ['caption', 'coordinates_bbox']:
+ xc = batch[cond_key]
+ elif cond_key == 'class_label':
+ xc = batch
+ else:
+ xc = super().get_input(batch, cond_key).to(self.device)
+ else:
+ xc = x
+ if not self.cond_stage_trainable or force_c_encode:
+ if isinstance(xc, dict) or isinstance(xc, list):
+ # import pudb; pudb.set_trace()
+ c = self.get_learned_conditioning(xc)
+ else:
+ c = self.get_learned_conditioning(xc.to(self.device))
+ else:
+ c = xc
+ if bs is not None:
+ c = c[:bs]
+
+ if self.use_positional_encodings:
+ pos_x, pos_y = self.compute_latent_shifts(batch)
+ ckey = __conditioning_keys__[self.model.conditioning_key]
+ c = {ckey: c, 'pos_x': pos_x, 'pos_y': pos_y}
+
+ else:
+ c = None
+ xc = None
+ if self.use_positional_encodings:
+ pos_x, pos_y = self.compute_latent_shifts(batch)
+ c = {'pos_x': pos_x, 'pos_y': pos_y}
+ out = [z, c]
+ if return_first_stage_outputs:
+ xrec = self.decode_first_stage(z)
+ out.extend([x, xrec])
+ if return_original_cond:
+ out.append(xc)
+ return out
+
+ @torch.no_grad()
+ def decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+ if predict_cids:
+ if z.dim() == 4:
+ z = torch.argmax(z.exp(), dim=1).long()
+ z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+ z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+ z = 1. / self.scale_factor * z
+
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ uf = self.split_input_params["vqf"]
+ bs, nc, h, w = z.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+ z = unfold(z) # (bn, nc * prod(**ks), L)
+ # 1. Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ # 2. apply model loop over last dim
+ if isinstance(self.first_stage_model, VQModelInterface):
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+ force_not_quantize=predict_cids or force_not_quantize)
+ for i in range(z.shape[-1])]
+ else:
+
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1) # # (bn, nc, ks[0], ks[1], L)
+ o = o * weighting
+ # Reverse 1. reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization # norm is shape (1, 1, h, w)
+ return decoded
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ # same as above but without decorator
+ def differentiable_decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+ if predict_cids:
+ if z.dim() == 4:
+ z = torch.argmax(z.exp(), dim=1).long()
+ z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+ z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+ z = 1. / self.scale_factor * z
+
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ uf = self.split_input_params["vqf"]
+ bs, nc, h, w = z.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+ z = unfold(z) # (bn, nc * prod(**ks), L)
+ # 1. Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ # 2. apply model loop over last dim
+ if isinstance(self.first_stage_model, VQModelInterface):
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+ force_not_quantize=predict_cids or force_not_quantize)
+ for i in range(z.shape[-1])]
+ else:
+
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1) # # (bn, nc, ks[0], ks[1], L)
+ o = o * weighting
+ # Reverse 1. reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization # norm is shape (1, 1, h, w)
+ return decoded
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ @torch.no_grad()
+ def encode_first_stage(self, x):
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ df = self.split_input_params["vqf"]
+ self.split_input_params['original_image_size'] = x.shape[-2:]
+ bs, nc, h, w = x.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(x, ks, stride, df=df)
+ z = unfold(x) # (bn, nc * prod(**ks), L)
+ # Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ output_list = [self.first_stage_model.encode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1)
+ o = o * weighting
+
+ # Reverse reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization
+ return decoded
+
+ else:
+ return self.first_stage_model.encode(x)
+ else:
+ return self.first_stage_model.encode(x)
+
+ def shared_step(self, batch, **kwargs):
+ x, c = self.get_input(batch, self.first_stage_key)
+ loss = self(x, c)
+ return loss
+
+ def forward(self, x, c, *args, **kwargs):
+ t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+ if self.model.conditioning_key is not None:
+ assert c is not None
+ if self.cond_stage_trainable:
+ c = self.get_learned_conditioning(c)
+ if self.shorten_cond_schedule: # TODO: drop this option
+ tc = self.cond_ids[t].to(self.device)
+ c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
+ return self.p_losses(x, c, t, *args, **kwargs)
+
+ def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset
+ def rescale_bbox(bbox):
+ x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
+ y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
+ w = min(bbox[2] / crop_coordinates[2], 1 - x0)
+ h = min(bbox[3] / crop_coordinates[3], 1 - y0)
+ return x0, y0, w, h
+
+ return [rescale_bbox(b) for b in bboxes]
+
+ def apply_model(self, x_noisy, t, cond, return_ids=False):
+
+ if isinstance(cond, dict):
+ # hybrid case, cond is exptected to be a dict
+ pass
+ else:
+ if not isinstance(cond, list):
+ cond = [cond]
+ key = 'c_concat' if self.model.conditioning_key == 'concat' else 'c_crossattn'
+ cond = {key: cond}
+
+ if hasattr(self, "split_input_params"):
+ assert len(cond) == 1 # todo can only deal with one conditioning atm
+ assert not return_ids
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+
+ h, w = x_noisy.shape[-2:]
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(x_noisy, ks, stride)
+
+ z = unfold(x_noisy) # (bn, nc * prod(**ks), L)
+ # Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+ z_list = [z[:, :, :, :, i] for i in range(z.shape[-1])]
+
+ if self.cond_stage_key in ["image", "LR_image", "segmentation",
+ 'bbox_img'] and self.model.conditioning_key: # todo check for completeness
+ c_key = next(iter(cond.keys())) # get key
+ c = next(iter(cond.values())) # get value
+ assert (len(c) == 1) # todo extend to list with more than one elem
+ c = c[0] # get element
+
+ c = unfold(c)
+ c = c.view((c.shape[0], -1, ks[0], ks[1], c.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
+
+ elif self.cond_stage_key == 'coordinates_bbox':
+ assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+
+ # assuming padding of unfold is always 0 and its dilation is always 1
+ n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
+ full_img_h, full_img_w = self.split_input_params['original_image_size']
+ # as we are operating on latents, we need the factor from the original image size to the
+ # spatial latent size to properly rescale the crops for regenerating the bbox annotations
+ num_downs = self.first_stage_model.encoder.num_resolutions - 1
+ rescale_latent = 2 ** (num_downs)
+
+ # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+ # need to rescale the tl patch coordinates to be in between (0,1)
+ tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
+ rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)
+ for patch_nr in range(z.shape[-1])]
+
+ # patch_limits are tl_coord, width and height coordinates as (x_tl, y_tl, h, w)
+ patch_limits = [(x_tl, y_tl,
+ rescale_latent * ks[0] / full_img_w,
+ rescale_latent * ks[1] / full_img_h) for x_tl, y_tl in tl_patch_coordinates]
+ # patch_values = [(np.arange(x_tl,min(x_tl+ks, 1.)),np.arange(y_tl,min(y_tl+ks, 1.))) for x_tl, y_tl in tl_patch_coordinates]
+
+ # tokenize crop coordinates for the bounding boxes of the respective patches
+ patch_limits_tknzd = [torch.LongTensor(self.bbox_tokenizer._crop_encoder(bbox))[None].to(self.device)
+ for bbox in patch_limits] # list of length l with tensors of shape (1, 2)
+ print(patch_limits_tknzd[0].shape)
+ # cut tknzd crop position from conditioning
+ assert isinstance(cond, dict), 'cond must be dict to be fed into model'
+ cut_cond = cond['c_crossattn'][0][..., :-2].to(self.device)
+ print(cut_cond.shape)
+
+ adapted_cond = torch.stack([torch.cat([cut_cond, p], dim=1) for p in patch_limits_tknzd])
+ adapted_cond = rearrange(adapted_cond, 'l b n -> (l b) n')
+ print(adapted_cond.shape)
+ adapted_cond = self.get_learned_conditioning(adapted_cond)
+ print(adapted_cond.shape)
+ adapted_cond = rearrange(adapted_cond, '(l b) n d -> l b n d', l=z.shape[-1])
+ print(adapted_cond.shape)
+
+ cond_list = [{'c_crossattn': [e]} for e in adapted_cond]
+
+ else:
+ cond_list = [cond for i in range(z.shape[-1])] # Todo make this more efficient
+
+ # apply model by loop over crops
+ output_list = [self.model(z_list[i], t, **cond_list[i]) for i in range(z.shape[-1])]
+ assert not isinstance(output_list[0],
+ tuple) # todo cant deal with multiple model outputs check this never happens
+
+ o = torch.stack(output_list, axis=-1)
+ o = o * weighting
+ # Reverse reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ x_recon = fold(o) / normalization
+
+ else:
+ x_recon = self.model(x_noisy, t, **cond)
+
+ if isinstance(x_recon, tuple) and not return_ids:
+ return x_recon[0]
+ else:
+ return x_recon
+
+ def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
+ return (extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - pred_xstart) / \
+ extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)
+
+ def _prior_bpd(self, x_start):
+ """
+ Get the prior KL term for the variational lower-bound, measured in
+ bits-per-dim.
+ This term can't be optimized, as it only depends on the encoder.
+ :param x_start: the [N x C x ...] tensor of inputs.
+ :return: a batch of [N] KL values (in bits), one per batch element.
+ """
+ batch_size = x_start.shape[0]
+ t = torch.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
+ qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
+ kl_prior = normal_kl(mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0)
+ return mean_flat(kl_prior) / np.log(2.0)
+
+ def p_losses(self, x_start, cond, t, noise=None):
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+ model_output = self.apply_model(x_noisy, t, cond)
+
+ loss_dict = {}
+ prefix = 'train' if self.training else 'val'
+
+ if self.parameterization == "x0":
+ target = x_start
+ elif self.parameterization == "eps":
+ target = noise
+ else:
+ raise NotImplementedError()
+
+ loss_simple = self.get_loss(model_output, target, mean=False).mean([1, 2, 3])
+ loss_dict.update({f'{prefix}/loss_simple': loss_simple.mean()})
+
+ logvar_t = self.logvar[t].to(self.device)
+ loss = loss_simple / torch.exp(logvar_t) + logvar_t
+ # loss = loss_simple / torch.exp(self.logvar) + self.logvar
+ if self.learn_logvar:
+ loss_dict.update({f'{prefix}/loss_gamma': loss.mean()})
+ loss_dict.update({'logvar': self.logvar.data.mean()})
+
+ loss = self.l_simple_weight * loss.mean()
+
+ loss_vlb = self.get_loss(model_output, target, mean=False).mean(dim=(1, 2, 3))
+ loss_vlb = (self.lvlb_weights[t] * loss_vlb).mean()
+ loss_dict.update({f'{prefix}/loss_vlb': loss_vlb})
+ loss += (self.original_elbo_weight * loss_vlb)
+ loss_dict.update({f'{prefix}/loss': loss})
+
+ return loss, loss_dict
+
+ def p_mean_variance(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
+ return_x0=False, score_corrector=None, corrector_kwargs=None):
+ t_in = t
+ model_out = self.apply_model(x, t_in, c, return_ids=return_codebook_ids)
+
+ if score_corrector is not None:
+ assert self.parameterization == "eps"
+ model_out = score_corrector.modify_score(self, model_out, x, t, c, **corrector_kwargs)
+
+ if return_codebook_ids:
+ model_out, logits = model_out
+
+ if self.parameterization == "eps":
+ x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+ elif self.parameterization == "x0":
+ x_recon = model_out
+ else:
+ raise NotImplementedError()
+
+ if clip_denoised:
+ x_recon.clamp_(-1., 1.)
+ if quantize_denoised:
+ x_recon, _, [_, _, indices] = self.first_stage_model.quantize(x_recon)
+ model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+ if return_codebook_ids:
+ return model_mean, posterior_variance, posterior_log_variance, logits
+ elif return_x0:
+ return model_mean, posterior_variance, posterior_log_variance, x_recon
+ else:
+ return model_mean, posterior_variance, posterior_log_variance
+
+ @torch.no_grad()
+ def p_sample(self, x, c, t, clip_denoised=False, repeat_noise=False,
+ return_codebook_ids=False, quantize_denoised=False, return_x0=False,
+ temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None):
+ b, *_, device = *x.shape, x.device
+ outputs = self.p_mean_variance(x=x, c=c, t=t, clip_denoised=clip_denoised,
+ return_codebook_ids=return_codebook_ids,
+ quantize_denoised=quantize_denoised,
+ return_x0=return_x0,
+ score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+ if return_codebook_ids:
+ raise DeprecationWarning("Support dropped.")
+ model_mean, _, model_log_variance, logits = outputs
+ elif return_x0:
+ model_mean, _, model_log_variance, x0 = outputs
+ else:
+ model_mean, _, model_log_variance = outputs
+
+ noise = noise_like(x.shape, device, repeat_noise) * temperature
+ if noise_dropout > 0.:
+ noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+ # no noise when t == 0
+ nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+
+ if return_codebook_ids:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, logits.argmax(dim=1)
+ if return_x0:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, x0
+ else:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+ @torch.no_grad()
+ def progressive_denoising(self, cond, shape, verbose=True, callback=None, quantize_denoised=False,
+ img_callback=None, mask=None, x0=None, temperature=1., noise_dropout=0.,
+ score_corrector=None, corrector_kwargs=None, batch_size=None, x_T=None, start_T=None,
+ log_every_t=None):
+ if not log_every_t:
+ log_every_t = self.log_every_t
+ timesteps = self.num_timesteps
+ if batch_size is not None:
+ b = batch_size if batch_size is not None else shape[0]
+ shape = [batch_size] + list(shape)
+ else:
+ b = batch_size = shape[0]
+ if x_T is None:
+ img = torch.randn(shape, device=self.device)
+ else:
+ img = x_T
+ intermediates = []
+ if cond is not None:
+ if isinstance(cond, dict):
+ cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+ list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+ else:
+ cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+
+ if start_T is not None:
+ timesteps = min(timesteps, start_T)
+ iterator = tqdm(reversed(range(0, timesteps)), desc='Progressive Generation',
+ total=timesteps) if verbose else reversed(
+ range(0, timesteps))
+ if type(temperature) == float:
+ temperature = [temperature] * timesteps
+
+ for i in iterator:
+ ts = torch.full((b,), i, device=self.device, dtype=torch.long)
+ if self.shorten_cond_schedule:
+ assert self.model.conditioning_key != 'hybrid'
+ tc = self.cond_ids[ts].to(cond.device)
+ cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+ img, x0_partial = self.p_sample(img, cond, ts,
+ clip_denoised=self.clip_denoised,
+ quantize_denoised=quantize_denoised, return_x0=True,
+ temperature=temperature[i], noise_dropout=noise_dropout,
+ score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+ if mask is not None:
+ assert x0 is not None
+ img_orig = self.q_sample(x0, ts)
+ img = img_orig * mask + (1. - mask) * img
+
+ if i % log_every_t == 0 or i == timesteps - 1:
+ intermediates.append(x0_partial)
+ if callback: callback(i)
+ if img_callback: img_callback(img, i)
+ return img, intermediates
+
+ @torch.no_grad()
+ def p_sample_loop(self, cond, shape, return_intermediates=False,
+ x_T=None, verbose=True, callback=None, timesteps=None, quantize_denoised=False,
+ mask=None, x0=None, img_callback=None, start_T=None,
+ log_every_t=None):
+
+ if not log_every_t:
+ log_every_t = self.log_every_t
+ device = self.betas.device
+ b = shape[0]
+ if x_T is None:
+ img = torch.randn(shape, device=device)
+ else:
+ img = x_T
+
+ intermediates = [img]
+ if timesteps is None:
+ timesteps = self.num_timesteps
+
+ if start_T is not None:
+ timesteps = min(timesteps, start_T)
+ iterator = tqdm(reversed(range(0, timesteps)), desc='Sampling t', total=timesteps) if verbose else reversed(
+ range(0, timesteps))
+
+ if mask is not None:
+ assert x0 is not None
+ assert x0.shape[2:3] == mask.shape[2:3] # spatial size has to match
+
+ for i in iterator:
+ ts = torch.full((b,), i, device=device, dtype=torch.long)
+ if self.shorten_cond_schedule:
+ assert self.model.conditioning_key != 'hybrid'
+ tc = self.cond_ids[ts].to(cond.device)
+ cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+ img = self.p_sample(img, cond, ts,
+ clip_denoised=self.clip_denoised,
+ quantize_denoised=quantize_denoised)
+ if mask is not None:
+ img_orig = self.q_sample(x0, ts)
+ img = img_orig * mask + (1. - mask) * img
+
+ if i % log_every_t == 0 or i == timesteps - 1:
+ intermediates.append(img)
+ if callback: callback(i)
+ if img_callback: img_callback(img, i)
+
+ if return_intermediates:
+ return img, intermediates
+ return img
+
+ @torch.no_grad()
+ def sample(self, cond, batch_size=16, return_intermediates=False, x_T=None,
+ verbose=True, timesteps=None, quantize_denoised=False,
+ mask=None, x0=None, shape=None,**kwargs):
+ if shape is None:
+ shape = (batch_size, self.channels, self.image_size, self.image_size)
+ if cond is not None:
+ if isinstance(cond, dict):
+ cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+ list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+ else:
+ cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+ return self.p_sample_loop(cond,
+ shape,
+ return_intermediates=return_intermediates, x_T=x_T,
+ verbose=verbose, timesteps=timesteps, quantize_denoised=quantize_denoised,
+ mask=mask, x0=x0)
+
+ @torch.no_grad()
+ def sample_log(self,cond,batch_size,ddim, ddim_steps,**kwargs):
+
+ if ddim:
+ ddim_sampler = DDIMSampler(self)
+ shape = (self.channels, self.image_size, self.image_size)
+ samples, intermediates =ddim_sampler.sample(ddim_steps,batch_size,
+ shape,cond,verbose=False,**kwargs)
+
+ else:
+ samples, intermediates = self.sample(cond=cond, batch_size=batch_size,
+ return_intermediates=True,**kwargs)
+
+ return samples, intermediates
+
+
+ @torch.no_grad()
+ def log_images(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
+ quantize_denoised=True, inpaint=True, plot_denoise_rows=False, plot_progressive_rows=True,
+ plot_diffusion_rows=True, **kwargs):
+
+ use_ddim = ddim_steps is not None
+
+ log = dict()
+ z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
+ return_first_stage_outputs=True,
+ force_c_encode=True,
+ return_original_cond=True,
+ bs=N)
+ N = min(x.shape[0], N)
+ n_row = min(x.shape[0], n_row)
+ log["inputs"] = x
+ log["reconstruction"] = xrec
+ if self.model.conditioning_key is not None:
+ if hasattr(self.cond_stage_model, "decode"):
+ xc = self.cond_stage_model.decode(c)
+ log["conditioning"] = xc
+ elif self.cond_stage_key in ["caption"]:
+ xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["caption"])
+ log["conditioning"] = xc
+ elif self.cond_stage_key == 'class_label':
+ xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"])
+ log['conditioning'] = xc
+ elif isimage(xc):
+ log["conditioning"] = xc
+ if ismap(xc):
+ log["original_conditioning"] = self.to_rgb(xc)
+
+ if plot_diffusion_rows:
+ # get diffusion row
+ diffusion_row = list()
+ z_start = z[:n_row]
+ for t in range(self.num_timesteps):
+ if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+ t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+ t = t.to(self.device).long()
+ noise = torch.randn_like(z_start)
+ z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
+ diffusion_row.append(self.decode_first_stage(z_noisy))
+
+ diffusion_row = torch.stack(diffusion_row) # n_log_step, n_row, C, H, W
+ diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
+ diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
+ diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
+ log["diffusion_row"] = diffusion_grid
+
+ if sample:
+ # get denoise row
+ with self.ema_scope("Plotting"):
+ samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+ ddim_steps=ddim_steps,eta=ddim_eta)
+ # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
+ x_samples = self.decode_first_stage(samples)
+ log["samples"] = x_samples
+ if plot_denoise_rows:
+ denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
+ log["denoise_row"] = denoise_grid
+
+ if quantize_denoised and not isinstance(self.first_stage_model, AutoencoderKL) and not isinstance(
+ self.first_stage_model, IdentityFirstStage):
+ # also display when quantizing x0 while sampling
+ with self.ema_scope("Plotting Quantized Denoised"):
+ samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+ ddim_steps=ddim_steps,eta=ddim_eta,
+ quantize_denoised=True)
+ # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True,
+ # quantize_denoised=True)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_x0_quantized"] = x_samples
+
+ if inpaint:
+ # make a simple center square
+ b, h, w = z.shape[0], z.shape[2], z.shape[3]
+ mask = torch.ones(N, h, w).to(self.device)
+ # zeros will be filled in
+ mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
+ mask = mask[:, None, ...]
+ with self.ema_scope("Plotting Inpaint"):
+
+ samples, _ = self.sample_log(cond=c,batch_size=N,ddim=use_ddim, eta=ddim_eta,
+ ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_inpainting"] = x_samples
+ log["mask"] = mask
+
+ # outpaint
+ with self.ema_scope("Plotting Outpaint"):
+ samples, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,eta=ddim_eta,
+ ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_outpainting"] = x_samples
+
+ if plot_progressive_rows:
+ with self.ema_scope("Plotting Progressives"):
+ img, progressives = self.progressive_denoising(c,
+ shape=(self.channels, self.image_size, self.image_size),
+ batch_size=N)
+ prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
+ log["progressive_row"] = prog_row
+
+ if return_keys:
+ if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+ return log
+ else:
+ return {key: log[key] for key in return_keys}
+ return log
+
+ def configure_optimizers(self):
+ lr = self.learning_rate
+ params = list(self.model.parameters())
+ if self.cond_stage_trainable:
+ print(f"{self.__class__.__name__}: Also optimizing conditioner params!")
+ params = params + list(self.cond_stage_model.parameters())
+ if self.learn_logvar:
+ print('Diffusion model optimizing logvar')
+ params.append(self.logvar)
+ opt = torch.optim.AdamW(params, lr=lr)
+ if self.use_scheduler:
+ assert 'target' in self.scheduler_config
+ scheduler = instantiate_from_config(self.scheduler_config)
+
+ print("Setting up LambdaLR scheduler...")
+ scheduler = [
+ {
+ 'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule),
+ 'interval': 'step',
+ 'frequency': 1
+ }]
+ return [opt], scheduler
+ return opt
+
+ @torch.no_grad()
+ def to_rgb(self, x):
+ x = x.float()
+ if not hasattr(self, "colorize"):
+ self.colorize = torch.randn(3, x.shape[1], 1, 1).to(x)
+ x = nn.functional.conv2d(x, weight=self.colorize)
+ x = 2. * (x - x.min()) / (x.max() - x.min()) - 1.
+ return x
+
+
+class DiffusionWrapper(pl.LightningModule):
+ def __init__(self, diff_model_config, conditioning_key):
+ super().__init__()
+ self.diffusion_model = instantiate_from_config(diff_model_config)
+ self.conditioning_key = conditioning_key
+ assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm']
+
+ def forward(self, x, t, c_concat: list = None, c_crossattn: list = None):
+ if self.conditioning_key is None:
+ out = self.diffusion_model(x, t)
+ elif self.conditioning_key == 'concat':
+ xc = torch.cat([x] + c_concat, dim=1)
+ out = self.diffusion_model(xc, t)
+ elif self.conditioning_key == 'crossattn':
+ cc = torch.cat(c_crossattn, 1)
+ out = self.diffusion_model(x, t, context=cc)
+ elif self.conditioning_key == 'hybrid':
+ xc = torch.cat([x] + c_concat, dim=1)
+ cc = torch.cat(c_crossattn, 1)
+ out = self.diffusion_model(xc, t, context=cc)
+ elif self.conditioning_key == 'adm':
+ cc = c_crossattn[0]
+ out = self.diffusion_model(x, t, y=cc)
+ else:
+ raise NotImplementedError()
+
+ return out
+
+
+class Layout2ImgDiffusion(LatentDiffusion):
+ # TODO: move all layout-specific hacks to this class
+ def __init__(self, cond_stage_key, *args, **kwargs):
+ assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
+ super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+
+ def log_images(self, batch, N=8, *args, **kwargs):
+ logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+
+ key = 'train' if self.training else 'validation'
+ dset = self.trainer.datamodule.datasets[key]
+ mapper = dset.conditional_builders[self.cond_stage_key]
+
+ bbox_imgs = []
+ map_fn = lambda catno: dset.get_textual_label(dset.get_category_id(catno))
+ for tknzd_bbox in batch[self.cond_stage_key][:N]:
+ bboximg = mapper.plot(tknzd_bbox.detach().cpu(), map_fn, (256, 256))
+ bbox_imgs.append(bboximg)
+
+ cond_img = torch.stack(bbox_imgs, dim=0)
+ logs['bbox_image'] = cond_img
+ return logs
diff --git a/stable_diffusion/ldm/models/diffusion/ddpm_edit.py b/stable_diffusion/ldm/models/diffusion/ddpm_edit.py
new file mode 100644
index 0000000000000000000000000000000000000000..1f0478ba0907060cad631a655b152ddf8d6ac8a1
--- /dev/null
+++ b/stable_diffusion/ldm/models/diffusion/ddpm_edit.py
@@ -0,0 +1,1459 @@
+"""
+wild mixture of
+https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
+https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py
+https://github.com/CompVis/taming-transformers
+-- merci
+"""
+
+# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
+# See more details in LICENSE.
+
+import torch
+import torch.nn as nn
+import numpy as np
+import pytorch_lightning as pl
+from torch.optim.lr_scheduler import LambdaLR
+from einops import rearrange, repeat
+from contextlib import contextmanager
+from functools import partial
+from tqdm import tqdm
+from torchvision.utils import make_grid
+from pytorch_lightning.utilities.distributed import rank_zero_only
+
+from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
+from ldm.modules.ema import LitEma
+from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
+from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
+from ldm.models.diffusion.ddim import DDIMSampler
+
+
+__conditioning_keys__ = {'concat': 'c_concat',
+ 'crossattn': 'c_crossattn',
+ 'adm': 'y'}
+
+
+def disabled_train(self, mode=True):
+ """Overwrite model.train with this function to make sure train/eval mode
+ does not change anymore."""
+ return self
+
+
+def uniform_on_device(r1, r2, shape, device):
+ return (r1 - r2) * torch.rand(*shape, device=device) + r2
+
+
+class DDPM(pl.LightningModule):
+ # classic DDPM with Gaussian diffusion, in image space
+ def __init__(self,
+ unet_config,
+ timesteps=1000,
+ beta_schedule="linear",
+ loss_type="l2",
+ ckpt_path=None,
+ ignore_keys=[],
+ load_only_unet=False,
+ monitor="val/loss",
+ use_ema=True,
+ first_stage_key="image",
+ image_size=256,
+ channels=3,
+ log_every_t=100,
+ clip_denoised=True,
+ linear_start=1e-4,
+ linear_end=2e-2,
+ cosine_s=8e-3,
+ given_betas=None,
+ original_elbo_weight=0.,
+ v_posterior=0., # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
+ l_simple_weight=1.,
+ conditioning_key=None,
+ parameterization="eps", # all assuming fixed variance schedules
+ scheduler_config=None,
+ use_positional_encodings=False,
+ learn_logvar=False,
+ logvar_init=0.,
+ load_ema=True,
+ ):
+ super().__init__()
+ assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
+ self.parameterization = parameterization
+ print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
+ self.cond_stage_model = None
+ self.clip_denoised = clip_denoised
+ self.log_every_t = log_every_t
+ self.first_stage_key = first_stage_key
+ self.image_size = image_size # try conv?
+ self.channels = channels
+ self.use_positional_encodings = use_positional_encodings
+ self.model = DiffusionWrapper(unet_config, conditioning_key)
+ count_params(self.model, verbose=True)
+ self.use_ema = use_ema
+
+ self.use_scheduler = scheduler_config is not None
+ if self.use_scheduler:
+ self.scheduler_config = scheduler_config
+
+ self.v_posterior = v_posterior
+ self.original_elbo_weight = original_elbo_weight
+ self.l_simple_weight = l_simple_weight
+
+ if monitor is not None:
+ self.monitor = monitor
+
+ if self.use_ema and load_ema:
+ self.model_ema = LitEma(self.model)
+ print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+ if ckpt_path is not None:
+ self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+
+ # If initialing from EMA-only checkpoint, create EMA model after loading.
+ if self.use_ema and not load_ema:
+ self.model_ema = LitEma(self.model)
+ print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+ self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
+ linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
+
+ self.loss_type = loss_type
+
+ self.learn_logvar = learn_logvar
+ self.logvar = torch.full(fill_value=logvar_init, size=(self.num_timesteps,))
+ if self.learn_logvar:
+ self.logvar = nn.Parameter(self.logvar, requires_grad=True)
+
+
+ def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
+ linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+ if exists(given_betas):
+ betas = given_betas
+ else:
+ betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end,
+ cosine_s=cosine_s)
+ alphas = 1. - betas
+ alphas_cumprod = np.cumprod(alphas, axis=0)
+ alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])
+
+ timesteps, = betas.shape
+ self.num_timesteps = int(timesteps)
+ self.linear_start = linear_start
+ self.linear_end = linear_end
+ assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'
+
+ to_torch = partial(torch.tensor, dtype=torch.float32)
+
+ self.register_buffer('betas', to_torch(betas))
+ self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+ self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))
+
+ # calculations for diffusion q(x_t | x_{t-1}) and others
+ self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
+ self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
+ self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
+ self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
+ self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))
+
+ # calculations for posterior q(x_{t-1} | x_t, x_0)
+ posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / (
+ 1. - alphas_cumprod) + self.v_posterior * betas
+ # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
+ self.register_buffer('posterior_variance', to_torch(posterior_variance))
+ # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
+ self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
+ self.register_buffer('posterior_mean_coef1', to_torch(
+ betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
+ self.register_buffer('posterior_mean_coef2', to_torch(
+ (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))
+
+ if self.parameterization == "eps":
+ lvlb_weights = self.betas ** 2 / (
+ 2 * self.posterior_variance * to_torch(alphas) * (1 - self.alphas_cumprod))
+ elif self.parameterization == "x0":
+ lvlb_weights = 0.5 * np.sqrt(torch.Tensor(alphas_cumprod)) / (2. * 1 - torch.Tensor(alphas_cumprod))
+ else:
+ raise NotImplementedError("mu not supported")
+ # TODO how to choose this term
+ lvlb_weights[0] = lvlb_weights[1]
+ self.register_buffer('lvlb_weights', lvlb_weights, persistent=False)
+ assert not torch.isnan(self.lvlb_weights).all()
+
+ @contextmanager
+ def ema_scope(self, context=None):
+ if self.use_ema:
+ self.model_ema.store(self.model.parameters())
+ self.model_ema.copy_to(self.model)
+ if context is not None:
+ print(f"{context}: Switched to EMA weights")
+ try:
+ yield None
+ finally:
+ if self.use_ema:
+ self.model_ema.restore(self.model.parameters())
+ if context is not None:
+ print(f"{context}: Restored training weights")
+
+ def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+ sd = torch.load(path, map_location="cpu")
+ if "state_dict" in list(sd.keys()):
+ sd = sd["state_dict"]
+ keys = list(sd.keys())
+
+ # Our model adds additional channels to the first layer to condition on an input image.
+ # For the first layer, copy existing channel weights and initialize new channel weights to zero.
+ input_keys = [
+ "model.diffusion_model.input_blocks.0.0.weight",
+ "model_ema.diffusion_modelinput_blocks00weight",
+ ]
+
+ self_sd = self.state_dict()
+ for input_key in input_keys:
+ if input_key not in sd or input_key not in self_sd:
+ continue
+
+ input_weight = self_sd[input_key]
+
+ if input_weight.size() != sd[input_key].size():
+ print(f"Manual init: {input_key}")
+ input_weight.zero_()
+ input_weight[:, :4, :, :].copy_(sd[input_key])
+ ignore_keys.append(input_key)
+
+ for k in keys:
+ for ik in ignore_keys:
+ if k.startswith(ik):
+ print("Deleting key {} from state_dict.".format(k))
+ del sd[k]
+ missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
+ sd, strict=False)
+ print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
+ if len(missing) > 0:
+ print(f"Missing Keys: {missing}")
+ if len(unexpected) > 0:
+ print(f"Unexpected Keys: {unexpected}")
+
+ def q_mean_variance(self, x_start, t):
+ """
+ Get the distribution q(x_t | x_0).
+ :param x_start: the [N x C x ...] tensor of noiseless inputs.
+ :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
+ :return: A tuple (mean, variance, log_variance), all of x_start's shape.
+ """
+ mean = (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start)
+ variance = extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
+ log_variance = extract_into_tensor(self.log_one_minus_alphas_cumprod, t, x_start.shape)
+ return mean, variance, log_variance
+
+ def predict_start_from_noise(self, x_t, t, noise):
+ return (
+ extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
+ extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
+ )
+
+ def q_posterior(self, x_start, x_t, t):
+ posterior_mean = (
+ extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start +
+ extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
+ )
+ posterior_variance = extract_into_tensor(self.posterior_variance, t, x_t.shape)
+ posterior_log_variance_clipped = extract_into_tensor(self.posterior_log_variance_clipped, t, x_t.shape)
+ return posterior_mean, posterior_variance, posterior_log_variance_clipped
+
+ def p_mean_variance(self, x, t, clip_denoised: bool):
+ model_out = self.model(x, t)
+ if self.parameterization == "eps":
+ x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+ elif self.parameterization == "x0":
+ x_recon = model_out
+ if clip_denoised:
+ x_recon.clamp_(-1., 1.)
+
+ model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+ return model_mean, posterior_variance, posterior_log_variance
+
+ @torch.no_grad()
+ def p_sample(self, x, t, clip_denoised=True, repeat_noise=False):
+ b, *_, device = *x.shape, x.device
+ model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, clip_denoised=clip_denoised)
+ noise = noise_like(x.shape, device, repeat_noise)
+ # no noise when t == 0
+ nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+ @torch.no_grad()
+ def p_sample_loop(self, shape, return_intermediates=False):
+ device = self.betas.device
+ b = shape[0]
+ img = torch.randn(shape, device=device)
+ intermediates = [img]
+ for i in tqdm(reversed(range(0, self.num_timesteps)), desc='Sampling t', total=self.num_timesteps):
+ img = self.p_sample(img, torch.full((b,), i, device=device, dtype=torch.long),
+ clip_denoised=self.clip_denoised)
+ if i % self.log_every_t == 0 or i == self.num_timesteps - 1:
+ intermediates.append(img)
+ if return_intermediates:
+ return img, intermediates
+ return img
+
+ @torch.no_grad()
+ def sample(self, batch_size=16, return_intermediates=False):
+ image_size = self.image_size
+ channels = self.channels
+ return self.p_sample_loop((batch_size, channels, image_size, image_size),
+ return_intermediates=return_intermediates)
+
+ def q_sample(self, x_start, t, noise=None):
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
+ extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
+
+ def get_loss(self, pred, target, mean=True):
+ if self.loss_type == 'l1':
+ loss = (target - pred).abs()
+ if mean:
+ loss = loss.mean()
+ elif self.loss_type == 'l2':
+ if mean:
+ loss = torch.nn.functional.mse_loss(target, pred)
+ else:
+ loss = torch.nn.functional.mse_loss(target, pred, reduction='none')
+ else:
+ raise NotImplementedError("unknown loss type '{loss_type}'")
+
+ return loss
+
+ def p_losses(self, x_start, t, noise=None):
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+ model_out = self.model(x_noisy, t)
+
+ loss_dict = {}
+ if self.parameterization == "eps":
+ target = noise
+ elif self.parameterization == "x0":
+ target = x_start
+ else:
+ raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+
+ loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
+
+ log_prefix = 'train' if self.training else 'val'
+
+ loss_dict.update({f'{log_prefix}/loss_simple': loss.mean()})
+ loss_simple = loss.mean() * self.l_simple_weight
+
+ loss_vlb = (self.lvlb_weights[t] * loss).mean()
+ loss_dict.update({f'{log_prefix}/loss_vlb': loss_vlb})
+
+ loss = loss_simple + self.original_elbo_weight * loss_vlb
+
+ loss_dict.update({f'{log_prefix}/loss': loss})
+
+ return loss, loss_dict
+
+ def forward(self, x, *args, **kwargs):
+ # b, c, h, w, device, img_size, = *x.shape, x.device, self.image_size
+ # assert h == img_size and w == img_size, f'height and width of image must be {img_size}'
+ t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+ return self.p_losses(x, t, *args, **kwargs)
+
+ def get_input(self, batch, k):
+ return batch[k]
+
+ def shared_step(self, batch):
+ x = self.get_input(batch, self.first_stage_key)
+ loss, loss_dict = self(x)
+ return loss, loss_dict
+
+ def training_step(self, batch, batch_idx):
+ loss, loss_dict = self.shared_step(batch)
+
+ self.log_dict(loss_dict, prog_bar=True,
+ logger=True, on_step=True, on_epoch=True)
+
+ self.log("global_step", self.global_step,
+ prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+ if self.use_scheduler:
+ lr = self.optimizers().param_groups[0]['lr']
+ self.log('lr_abs', lr, prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+ return loss
+
+ @torch.no_grad()
+ def validation_step(self, batch, batch_idx):
+ _, loss_dict_no_ema = self.shared_step(batch)
+ with self.ema_scope():
+ _, loss_dict_ema = self.shared_step(batch)
+ loss_dict_ema = {key + '_ema': loss_dict_ema[key] for key in loss_dict_ema}
+ self.log_dict(loss_dict_no_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+ self.log_dict(loss_dict_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+
+ def on_train_batch_end(self, *args, **kwargs):
+ if self.use_ema:
+ self.model_ema(self.model)
+
+ def _get_rows_from_list(self, samples):
+ n_imgs_per_row = len(samples)
+ denoise_grid = rearrange(samples, 'n b c h w -> b n c h w')
+ denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+ denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+ return denoise_grid
+
+ @torch.no_grad()
+ def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
+ log = dict()
+ x = self.get_input(batch, self.first_stage_key)
+ N = min(x.shape[0], N)
+ n_row = min(x.shape[0], n_row)
+ x = x.to(self.device)[:N]
+ log["inputs"] = x
+
+ # get diffusion row
+ diffusion_row = list()
+ x_start = x[:n_row]
+
+ for t in range(self.num_timesteps):
+ if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+ t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+ t = t.to(self.device).long()
+ noise = torch.randn_like(x_start)
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+ diffusion_row.append(x_noisy)
+
+ log["diffusion_row"] = self._get_rows_from_list(diffusion_row)
+
+ if sample:
+ # get denoise row
+ with self.ema_scope("Plotting"):
+ samples, denoise_row = self.sample(batch_size=N, return_intermediates=True)
+
+ log["samples"] = samples
+ log["denoise_row"] = self._get_rows_from_list(denoise_row)
+
+ if return_keys:
+ if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+ return log
+ else:
+ return {key: log[key] for key in return_keys}
+ return log
+
+ def configure_optimizers(self):
+ lr = self.learning_rate
+ params = list(self.model.parameters())
+ if self.learn_logvar:
+ params = params + [self.logvar]
+ opt = torch.optim.AdamW(params, lr=lr)
+ return opt
+
+
+class LatentDiffusion(DDPM):
+ """main class"""
+ def __init__(self,
+ first_stage_config,
+ cond_stage_config,
+ num_timesteps_cond=None,
+ cond_stage_key="image",
+ cond_stage_trainable=False,
+ concat_mode=True,
+ cond_stage_forward=None,
+ conditioning_key=None,
+ scale_factor=1.0,
+ scale_by_std=False,
+ load_ema=True,
+ *args, **kwargs):
+ self.num_timesteps_cond = default(num_timesteps_cond, 1)
+ self.scale_by_std = scale_by_std
+ assert self.num_timesteps_cond <= kwargs['timesteps']
+ # for backwards compatibility after implementation of DiffusionWrapper
+ if conditioning_key is None:
+ conditioning_key = 'concat' if concat_mode else 'crossattn'
+ if cond_stage_config == '__is_unconditional__':
+ conditioning_key = None
+ ckpt_path = kwargs.pop("ckpt_path", None)
+ ignore_keys = kwargs.pop("ignore_keys", [])
+ super().__init__(conditioning_key=conditioning_key, *args, load_ema=load_ema, **kwargs)
+ self.concat_mode = concat_mode
+ self.cond_stage_trainable = cond_stage_trainable
+ self.cond_stage_key = cond_stage_key
+ try:
+ self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
+ except:
+ self.num_downs = 0
+ if not scale_by_std:
+ self.scale_factor = scale_factor
+ else:
+ self.register_buffer('scale_factor', torch.tensor(scale_factor))
+ self.instantiate_first_stage(first_stage_config)
+ self.instantiate_cond_stage(cond_stage_config)
+ self.cond_stage_forward = cond_stage_forward
+ self.clip_denoised = False
+ self.bbox_tokenizer = None
+
+ self.restarted_from_ckpt = False
+ if ckpt_path is not None:
+ self.init_from_ckpt(ckpt_path, ignore_keys)
+ self.restarted_from_ckpt = True
+
+ if self.use_ema and not load_ema:
+ self.model_ema = LitEma(self.model)
+ print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+ def make_cond_schedule(self, ):
+ self.cond_ids = torch.full(size=(self.num_timesteps,), fill_value=self.num_timesteps - 1, dtype=torch.long)
+ ids = torch.round(torch.linspace(0, self.num_timesteps - 1, self.num_timesteps_cond)).long()
+ self.cond_ids[:self.num_timesteps_cond] = ids
+
+ @rank_zero_only
+ @torch.no_grad()
+ def on_train_batch_start(self, batch, batch_idx, dataloader_idx):
+ # only for very first batch
+ if self.scale_by_std and self.current_epoch == 0 and self.global_step == 0 and batch_idx == 0 and not self.restarted_from_ckpt:
+ assert self.scale_factor == 1., 'rather not use custom rescaling and std-rescaling simultaneously'
+ # set rescale weight to 1./std of encodings
+ print("### USING STD-RESCALING ###")
+ x = super().get_input(batch, self.first_stage_key)
+ x = x.to(self.device)
+ encoder_posterior = self.encode_first_stage(x)
+ z = self.get_first_stage_encoding(encoder_posterior).detach()
+ del self.scale_factor
+ self.register_buffer('scale_factor', 1. / z.flatten().std())
+ print(f"setting self.scale_factor to {self.scale_factor}")
+ print("### USING STD-RESCALING ###")
+
+ def register_schedule(self,
+ given_betas=None, beta_schedule="linear", timesteps=1000,
+ linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+ super().register_schedule(given_betas, beta_schedule, timesteps, linear_start, linear_end, cosine_s)
+
+ self.shorten_cond_schedule = self.num_timesteps_cond > 1
+ if self.shorten_cond_schedule:
+ self.make_cond_schedule()
+
+ def instantiate_first_stage(self, config):
+ model = instantiate_from_config(config)
+ self.first_stage_model = model.eval()
+ self.first_stage_model.train = disabled_train
+ for param in self.first_stage_model.parameters():
+ param.requires_grad = False
+
+ def instantiate_cond_stage(self, config):
+ if not self.cond_stage_trainable:
+ if config == "__is_first_stage__":
+ print("Using first stage also as cond stage.")
+ self.cond_stage_model = self.first_stage_model
+ elif config == "__is_unconditional__":
+ print(f"Training {self.__class__.__name__} as an unconditional model.")
+ self.cond_stage_model = None
+ # self.be_unconditional = True
+ else:
+ model = instantiate_from_config(config)
+ self.cond_stage_model = model.eval()
+ self.cond_stage_model.train = disabled_train
+ for param in self.cond_stage_model.parameters():
+ param.requires_grad = False
+ else:
+ assert config != '__is_first_stage__'
+ assert config != '__is_unconditional__'
+ model = instantiate_from_config(config)
+ self.cond_stage_model = model
+
+ def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
+ denoise_row = []
+ for zd in tqdm(samples, desc=desc):
+ denoise_row.append(self.decode_first_stage(zd.to(self.device),
+ force_not_quantize=force_no_decoder_quantization))
+ n_imgs_per_row = len(denoise_row)
+ denoise_row = torch.stack(denoise_row) # n_log_step, n_row, C, H, W
+ denoise_grid = rearrange(denoise_row, 'n b c h w -> b n c h w')
+ denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+ denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+ return denoise_grid
+
+ def get_first_stage_encoding(self, encoder_posterior):
+ if isinstance(encoder_posterior, DiagonalGaussianDistribution):
+ z = encoder_posterior.sample()
+ elif isinstance(encoder_posterior, torch.Tensor):
+ z = encoder_posterior
+ else:
+ raise NotImplementedError(f"encoder_posterior of type '{type(encoder_posterior)}' not yet implemented")
+ return self.scale_factor * z
+
+ def get_learned_conditioning(self, c):
+ if self.cond_stage_forward is None:
+ if hasattr(self.cond_stage_model, 'encode') and callable(self.cond_stage_model.encode):
+ c = self.cond_stage_model.encode(c)
+ if isinstance(c, DiagonalGaussianDistribution):
+ c = c.mode()
+ else:
+ c = self.cond_stage_model(c)
+ else:
+ assert hasattr(self.cond_stage_model, self.cond_stage_forward)
+ c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
+ return c
+
+ def meshgrid(self, h, w):
+ y = torch.arange(0, h).view(h, 1, 1).repeat(1, w, 1)
+ x = torch.arange(0, w).view(1, w, 1).repeat(h, 1, 1)
+
+ arr = torch.cat([y, x], dim=-1)
+ return arr
+
+ def delta_border(self, h, w):
+ """
+ :param h: height
+ :param w: width
+ :return: normalized distance to image border,
+ wtith min distance = 0 at border and max dist = 0.5 at image center
+ """
+ lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
+ arr = self.meshgrid(h, w) / lower_right_corner
+ dist_left_up = torch.min(arr, dim=-1, keepdims=True)[0]
+ dist_right_down = torch.min(1 - arr, dim=-1, keepdims=True)[0]
+ edge_dist = torch.min(torch.cat([dist_left_up, dist_right_down], dim=-1), dim=-1)[0]
+ return edge_dist
+
+ def get_weighting(self, h, w, Ly, Lx, device):
+ weighting = self.delta_border(h, w)
+ weighting = torch.clip(weighting, self.split_input_params["clip_min_weight"],
+ self.split_input_params["clip_max_weight"], )
+ weighting = weighting.view(1, h * w, 1).repeat(1, 1, Ly * Lx).to(device)
+
+ if self.split_input_params["tie_braker"]:
+ L_weighting = self.delta_border(Ly, Lx)
+ L_weighting = torch.clip(L_weighting,
+ self.split_input_params["clip_min_tie_weight"],
+ self.split_input_params["clip_max_tie_weight"])
+
+ L_weighting = L_weighting.view(1, 1, Ly * Lx).to(device)
+ weighting = weighting * L_weighting
+ return weighting
+
+ def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1): # todo load once not every time, shorten code
+ """
+ :param x: img of size (bs, c, h, w)
+ :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
+ """
+ bs, nc, h, w = x.shape
+
+ # number of crops in image
+ Ly = (h - kernel_size[0]) // stride[0] + 1
+ Lx = (w - kernel_size[1]) // stride[1] + 1
+
+ if uf == 1 and df == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)
+
+ weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h, w) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))
+
+ elif uf > 1 and df == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
+ dilation=1, padding=0,
+ stride=(stride[0] * uf, stride[1] * uf))
+ fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)
+
+ weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h * uf, w * uf) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))
+
+ elif df > 1 and uf == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
+ dilation=1, padding=0,
+ stride=(stride[0] // df, stride[1] // df))
+ fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)
+
+ weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h // df, w // df) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))
+
+ else:
+ raise NotImplementedError
+
+ return fold, unfold, normalization, weighting
+
+ @torch.no_grad()
+ def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,
+ cond_key=None, return_original_cond=False, bs=None, uncond=0.05):
+ x = super().get_input(batch, k)
+ if bs is not None:
+ x = x[:bs]
+ x = x.to(self.device)
+ encoder_posterior = self.encode_first_stage(x)
+ z = self.get_first_stage_encoding(encoder_posterior).detach()
+ cond_key = cond_key or self.cond_stage_key
+ xc = super().get_input(batch, cond_key)
+ if bs is not None:
+ xc["c_crossattn"] = xc["c_crossattn"][:bs]
+ xc["c_concat"] = xc["c_concat"][:bs]
+ cond = {}
+
+ # To support classifier-free guidance, randomly drop out only text conditioning 5%, only image conditioning 5%, and both 5%.
+ random = torch.rand(x.size(0), device=x.device)
+ prompt_mask = rearrange(random < 2 * uncond, "n -> n 1 1")
+ input_mask = 1 - rearrange((random >= uncond).float() * (random < 3 * uncond).float(), "n -> n 1 1 1")
+
+ null_prompt = self.get_learned_conditioning([""])
+ cond["c_crossattn"] = [torch.where(prompt_mask, null_prompt, self.get_learned_conditioning(xc["c_crossattn"]).detach())]
+ cond["c_concat"] = [input_mask * self.encode_first_stage((xc["c_concat"].to(self.device))).mode().detach()]
+
+ out = [z, cond]
+ if return_first_stage_outputs:
+ xrec = self.decode_first_stage(z)
+ out.extend([x, xrec])
+ if return_original_cond:
+ out.append(xc)
+ return out
+
+ @torch.no_grad()
+ def decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+ if predict_cids:
+ if z.dim() == 4:
+ z = torch.argmax(z.exp(), dim=1).long()
+ z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+ z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+ z = 1. / self.scale_factor * z
+
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ uf = self.split_input_params["vqf"]
+ bs, nc, h, w = z.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+ z = unfold(z) # (bn, nc * prod(**ks), L)
+ # 1. Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ # 2. apply model loop over last dim
+ if isinstance(self.first_stage_model, VQModelInterface):
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+ force_not_quantize=predict_cids or force_not_quantize)
+ for i in range(z.shape[-1])]
+ else:
+
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1) # # (bn, nc, ks[0], ks[1], L)
+ o = o * weighting
+ # Reverse 1. reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization # norm is shape (1, 1, h, w)
+ return decoded
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ # same as above but without decorator
+ def differentiable_decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+ if predict_cids:
+ if z.dim() == 4:
+ z = torch.argmax(z.exp(), dim=1).long()
+ z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+ z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+ z = 1. / self.scale_factor * z
+
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ uf = self.split_input_params["vqf"]
+ bs, nc, h, w = z.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+ z = unfold(z) # (bn, nc * prod(**ks), L)
+ # 1. Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ # 2. apply model loop over last dim
+ if isinstance(self.first_stage_model, VQModelInterface):
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+ force_not_quantize=predict_cids or force_not_quantize)
+ for i in range(z.shape[-1])]
+ else:
+
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1) # # (bn, nc, ks[0], ks[1], L)
+ o = o * weighting
+ # Reverse 1. reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization # norm is shape (1, 1, h, w)
+ return decoded
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ @torch.no_grad()
+ def encode_first_stage(self, x):
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ df = self.split_input_params["vqf"]
+ self.split_input_params['original_image_size'] = x.shape[-2:]
+ bs, nc, h, w = x.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(x, ks, stride, df=df)
+ z = unfold(x) # (bn, nc * prod(**ks), L)
+ # Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ output_list = [self.first_stage_model.encode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1)
+ o = o * weighting
+
+ # Reverse reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization
+ return decoded
+
+ else:
+ return self.first_stage_model.encode(x)
+ else:
+ return self.first_stage_model.encode(x)
+
+ def shared_step(self, batch, **kwargs):
+ x, c = self.get_input(batch, self.first_stage_key)
+ loss = self(x, c)
+ return loss
+
+ def forward(self, x, c, *args, **kwargs):
+ t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+ if self.model.conditioning_key is not None:
+ assert c is not None
+ if self.cond_stage_trainable:
+ c = self.get_learned_conditioning(c)
+ if self.shorten_cond_schedule: # TODO: drop this option
+ tc = self.cond_ids[t].to(self.device)
+ c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
+ return self.p_losses(x, c, t, *args, **kwargs)
+
+ def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset
+ def rescale_bbox(bbox):
+ x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
+ y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
+ w = min(bbox[2] / crop_coordinates[2], 1 - x0)
+ h = min(bbox[3] / crop_coordinates[3], 1 - y0)
+ return x0, y0, w, h
+
+ return [rescale_bbox(b) for b in bboxes]
+
+ def apply_model(self, x_noisy, t, cond, return_ids=False):
+
+ if isinstance(cond, dict):
+ # hybrid case, cond is exptected to be a dict
+ pass
+ else:
+ if not isinstance(cond, list):
+ cond = [cond]
+ key = 'c_concat' if self.model.conditioning_key == 'concat' else 'c_crossattn'
+ cond = {key: cond}
+
+ if hasattr(self, "split_input_params"):
+ assert len(cond) == 1 # todo can only deal with one conditioning atm
+ assert not return_ids
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+
+ h, w = x_noisy.shape[-2:]
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(x_noisy, ks, stride)
+
+ z = unfold(x_noisy) # (bn, nc * prod(**ks), L)
+ # Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+ z_list = [z[:, :, :, :, i] for i in range(z.shape[-1])]
+
+ if self.cond_stage_key in ["image", "LR_image", "segmentation",
+ 'bbox_img'] and self.model.conditioning_key: # todo check for completeness
+ c_key = next(iter(cond.keys())) # get key
+ c = next(iter(cond.values())) # get value
+ assert (len(c) == 1) # todo extend to list with more than one elem
+ c = c[0] # get element
+
+ c = unfold(c)
+ c = c.view((c.shape[0], -1, ks[0], ks[1], c.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
+
+ elif self.cond_stage_key == 'coordinates_bbox':
+ assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+
+ # assuming padding of unfold is always 0 and its dilation is always 1
+ n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
+ full_img_h, full_img_w = self.split_input_params['original_image_size']
+ # as we are operating on latents, we need the factor from the original image size to the
+ # spatial latent size to properly rescale the crops for regenerating the bbox annotations
+ num_downs = self.first_stage_model.encoder.num_resolutions - 1
+ rescale_latent = 2 ** (num_downs)
+
+ # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+ # need to rescale the tl patch coordinates to be in between (0,1)
+ tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
+ rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)
+ for patch_nr in range(z.shape[-1])]
+
+ # patch_limits are tl_coord, width and height coordinates as (x_tl, y_tl, h, w)
+ patch_limits = [(x_tl, y_tl,
+ rescale_latent * ks[0] / full_img_w,
+ rescale_latent * ks[1] / full_img_h) for x_tl, y_tl in tl_patch_coordinates]
+ # patch_values = [(np.arange(x_tl,min(x_tl+ks, 1.)),np.arange(y_tl,min(y_tl+ks, 1.))) for x_tl, y_tl in tl_patch_coordinates]
+
+ # tokenize crop coordinates for the bounding boxes of the respective patches
+ patch_limits_tknzd = [torch.LongTensor(self.bbox_tokenizer._crop_encoder(bbox))[None].to(self.device)
+ for bbox in patch_limits] # list of length l with tensors of shape (1, 2)
+ print(patch_limits_tknzd[0].shape)
+ # cut tknzd crop position from conditioning
+ assert isinstance(cond, dict), 'cond must be dict to be fed into model'
+ cut_cond = cond['c_crossattn'][0][..., :-2].to(self.device)
+ print(cut_cond.shape)
+
+ adapted_cond = torch.stack([torch.cat([cut_cond, p], dim=1) for p in patch_limits_tknzd])
+ adapted_cond = rearrange(adapted_cond, 'l b n -> (l b) n')
+ print(adapted_cond.shape)
+ adapted_cond = self.get_learned_conditioning(adapted_cond)
+ print(adapted_cond.shape)
+ adapted_cond = rearrange(adapted_cond, '(l b) n d -> l b n d', l=z.shape[-1])
+ print(adapted_cond.shape)
+
+ cond_list = [{'c_crossattn': [e]} for e in adapted_cond]
+
+ else:
+ cond_list = [cond for i in range(z.shape[-1])] # Todo make this more efficient
+
+ # apply model by loop over crops
+ output_list = [self.model(z_list[i], t, **cond_list[i]) for i in range(z.shape[-1])]
+ assert not isinstance(output_list[0],
+ tuple) # todo cant deal with multiple model outputs check this never happens
+
+ o = torch.stack(output_list, axis=-1)
+ o = o * weighting
+ # Reverse reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ x_recon = fold(o) / normalization
+
+ else:
+ x_recon = self.model(x_noisy, t, **cond)
+
+ if isinstance(x_recon, tuple) and not return_ids:
+ return x_recon[0]
+ else:
+ return x_recon
+
+ def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
+ return (extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - pred_xstart) / \
+ extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)
+
+ def _prior_bpd(self, x_start):
+ """
+ Get the prior KL term for the variational lower-bound, measured in
+ bits-per-dim.
+ This term can't be optimized, as it only depends on the encoder.
+ :param x_start: the [N x C x ...] tensor of inputs.
+ :return: a batch of [N] KL values (in bits), one per batch element.
+ """
+ batch_size = x_start.shape[0]
+ t = torch.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
+ qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
+ kl_prior = normal_kl(mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0)
+ return mean_flat(kl_prior) / np.log(2.0)
+
+ def p_losses(self, x_start, cond, t, noise=None):
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+ model_output = self.apply_model(x_noisy, t, cond)
+
+ loss_dict = {}
+ prefix = 'train' if self.training else 'val'
+
+ if self.parameterization == "x0":
+ target = x_start
+ elif self.parameterization == "eps":
+ target = noise
+ else:
+ raise NotImplementedError()
+
+ loss_simple = self.get_loss(model_output, target, mean=False).mean([1, 2, 3])
+ loss_dict.update({f'{prefix}/loss_simple': loss_simple.mean()})
+ self.logvar = self.logvar.to(self.device)
+ logvar_t = self.logvar[t].to(self.device)
+ loss = loss_simple / torch.exp(logvar_t) + logvar_t
+ # loss = loss_simple / torch.exp(self.logvar) + self.logvar
+ if self.learn_logvar:
+ loss_dict.update({f'{prefix}/loss_gamma': loss.mean()})
+ loss_dict.update({'logvar': self.logvar.data.mean()})
+
+ loss = self.l_simple_weight * loss.mean()
+
+ loss_vlb = self.get_loss(model_output, target, mean=False).mean(dim=(1, 2, 3))
+ loss_vlb = (self.lvlb_weights[t] * loss_vlb).mean()
+ loss_dict.update({f'{prefix}/loss_vlb': loss_vlb})
+ loss += (self.original_elbo_weight * loss_vlb)
+ loss_dict.update({f'{prefix}/loss': loss})
+
+ return loss, loss_dict
+
+ def p_mean_variance(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
+ return_x0=False, score_corrector=None, corrector_kwargs=None):
+ t_in = t
+ model_out = self.apply_model(x, t_in, c, return_ids=return_codebook_ids)
+
+ if score_corrector is not None:
+ assert self.parameterization == "eps"
+ model_out = score_corrector.modify_score(self, model_out, x, t, c, **corrector_kwargs)
+
+ if return_codebook_ids:
+ model_out, logits = model_out
+
+ if self.parameterization == "eps":
+ x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+ elif self.parameterization == "x0":
+ x_recon = model_out
+ else:
+ raise NotImplementedError()
+
+ if clip_denoised:
+ x_recon.clamp_(-1., 1.)
+ if quantize_denoised:
+ x_recon, _, [_, _, indices] = self.first_stage_model.quantize(x_recon)
+ model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+ if return_codebook_ids:
+ return model_mean, posterior_variance, posterior_log_variance, logits
+ elif return_x0:
+ return model_mean, posterior_variance, posterior_log_variance, x_recon
+ else:
+ return model_mean, posterior_variance, posterior_log_variance
+
+ @torch.no_grad()
+ def p_sample(self, x, c, t, clip_denoised=False, repeat_noise=False,
+ return_codebook_ids=False, quantize_denoised=False, return_x0=False,
+ temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None):
+ b, *_, device = *x.shape, x.device
+ outputs = self.p_mean_variance(x=x, c=c, t=t, clip_denoised=clip_denoised,
+ return_codebook_ids=return_codebook_ids,
+ quantize_denoised=quantize_denoised,
+ return_x0=return_x0,
+ score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+ if return_codebook_ids:
+ raise DeprecationWarning("Support dropped.")
+ model_mean, _, model_log_variance, logits = outputs
+ elif return_x0:
+ model_mean, _, model_log_variance, x0 = outputs
+ else:
+ model_mean, _, model_log_variance = outputs
+
+ noise = noise_like(x.shape, device, repeat_noise) * temperature
+ if noise_dropout > 0.:
+ noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+ # no noise when t == 0
+ nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+
+ if return_codebook_ids:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, logits.argmax(dim=1)
+ if return_x0:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, x0
+ else:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+ @torch.no_grad()
+ def progressive_denoising(self, cond, shape, verbose=True, callback=None, quantize_denoised=False,
+ img_callback=None, mask=None, x0=None, temperature=1., noise_dropout=0.,
+ score_corrector=None, corrector_kwargs=None, batch_size=None, x_T=None, start_T=None,
+ log_every_t=None):
+ if not log_every_t:
+ log_every_t = self.log_every_t
+ timesteps = self.num_timesteps
+ if batch_size is not None:
+ b = batch_size if batch_size is not None else shape[0]
+ shape = [batch_size] + list(shape)
+ else:
+ b = batch_size = shape[0]
+ if x_T is None:
+ img = torch.randn(shape, device=self.device)
+ else:
+ img = x_T
+ intermediates = []
+ if cond is not None:
+ if isinstance(cond, dict):
+ cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+ list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+ else:
+ cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+
+ if start_T is not None:
+ timesteps = min(timesteps, start_T)
+ iterator = tqdm(reversed(range(0, timesteps)), desc='Progressive Generation',
+ total=timesteps) if verbose else reversed(
+ range(0, timesteps))
+ if type(temperature) == float:
+ temperature = [temperature] * timesteps
+
+ for i in iterator:
+ ts = torch.full((b,), i, device=self.device, dtype=torch.long)
+ if self.shorten_cond_schedule:
+ assert self.model.conditioning_key != 'hybrid'
+ tc = self.cond_ids[ts].to(cond.device)
+ cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+ img, x0_partial = self.p_sample(img, cond, ts,
+ clip_denoised=self.clip_denoised,
+ quantize_denoised=quantize_denoised, return_x0=True,
+ temperature=temperature[i], noise_dropout=noise_dropout,
+ score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+ if mask is not None:
+ assert x0 is not None
+ img_orig = self.q_sample(x0, ts)
+ img = img_orig * mask + (1. - mask) * img
+
+ if i % log_every_t == 0 or i == timesteps - 1:
+ intermediates.append(x0_partial)
+ if callback: callback(i)
+ if img_callback: img_callback(img, i)
+ return img, intermediates
+
+ @torch.no_grad()
+ def p_sample_loop(self, cond, shape, return_intermediates=False,
+ x_T=None, verbose=True, callback=None, timesteps=None, quantize_denoised=False,
+ mask=None, x0=None, img_callback=None, start_T=None,
+ log_every_t=None):
+
+ if not log_every_t:
+ log_every_t = self.log_every_t
+ device = self.betas.device
+ b = shape[0]
+ if x_T is None:
+ img = torch.randn(shape, device=device)
+ else:
+ img = x_T
+
+ intermediates = [img]
+ if timesteps is None:
+ timesteps = self.num_timesteps
+
+ if start_T is not None:
+ timesteps = min(timesteps, start_T)
+ iterator = tqdm(reversed(range(0, timesteps)), desc='Sampling t', total=timesteps) if verbose else reversed(
+ range(0, timesteps))
+
+ if mask is not None:
+ assert x0 is not None
+ assert x0.shape[2:3] == mask.shape[2:3] # spatial size has to match
+
+ for i in iterator:
+ ts = torch.full((b,), i, device=device, dtype=torch.long)
+ if self.shorten_cond_schedule:
+ assert self.model.conditioning_key != 'hybrid'
+ tc = self.cond_ids[ts].to(cond.device)
+ cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+ img = self.p_sample(img, cond, ts,
+ clip_denoised=self.clip_denoised,
+ quantize_denoised=quantize_denoised)
+ if mask is not None:
+ img_orig = self.q_sample(x0, ts)
+ img = img_orig * mask + (1. - mask) * img
+
+ if i % log_every_t == 0 or i == timesteps - 1:
+ intermediates.append(img)
+ if callback: callback(i)
+ if img_callback: img_callback(img, i)
+
+ if return_intermediates:
+ return img, intermediates
+ return img
+
+ @torch.no_grad()
+ def sample(self, cond, batch_size=16, return_intermediates=False, x_T=None,
+ verbose=True, timesteps=None, quantize_denoised=False,
+ mask=None, x0=None, shape=None,**kwargs):
+ if shape is None:
+ shape = (batch_size, self.channels, self.image_size, self.image_size)
+ if cond is not None:
+ if isinstance(cond, dict):
+ cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+ list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+ else:
+ cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+ return self.p_sample_loop(cond,
+ shape,
+ return_intermediates=return_intermediates, x_T=x_T,
+ verbose=verbose, timesteps=timesteps, quantize_denoised=quantize_denoised,
+ mask=mask, x0=x0)
+
+ @torch.no_grad()
+ def sample_log(self,cond,batch_size,ddim, ddim_steps,**kwargs):
+
+ if ddim:
+ ddim_sampler = DDIMSampler(self)
+ shape = (self.channels, self.image_size, self.image_size)
+ samples, intermediates =ddim_sampler.sample(ddim_steps,batch_size,
+ shape,cond,verbose=False,**kwargs)
+
+ else:
+ samples, intermediates = self.sample(cond=cond, batch_size=batch_size,
+ return_intermediates=True,**kwargs)
+
+ return samples, intermediates
+
+
+ @torch.no_grad()
+ def log_images(self, batch, N=4, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
+ quantize_denoised=True, inpaint=False, plot_denoise_rows=False, plot_progressive_rows=False,
+ plot_diffusion_rows=False, **kwargs):
+
+ use_ddim = False
+
+ log = dict()
+ z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
+ return_first_stage_outputs=True,
+ force_c_encode=True,
+ return_original_cond=True,
+ bs=N, uncond=0)
+ N = min(x.shape[0], N)
+ n_row = min(x.shape[0], n_row)
+ log["inputs"] = x
+ log["reals"] = xc["c_concat"]
+ log["reconstruction"] = xrec
+ if self.model.conditioning_key is not None:
+ if hasattr(self.cond_stage_model, "decode"):
+ xc = self.cond_stage_model.decode(c)
+ log["conditioning"] = xc
+ elif self.cond_stage_key in ["caption"]:
+ xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["caption"])
+ log["conditioning"] = xc
+ elif self.cond_stage_key == 'class_label':
+ xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"])
+ log['conditioning'] = xc
+ elif isimage(xc):
+ log["conditioning"] = xc
+ if ismap(xc):
+ log["original_conditioning"] = self.to_rgb(xc)
+
+ if plot_diffusion_rows:
+ # get diffusion row
+ diffusion_row = list()
+ z_start = z[:n_row]
+ for t in range(self.num_timesteps):
+ if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+ t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+ t = t.to(self.device).long()
+ noise = torch.randn_like(z_start)
+ z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
+ diffusion_row.append(self.decode_first_stage(z_noisy))
+
+ diffusion_row = torch.stack(diffusion_row) # n_log_step, n_row, C, H, W
+ diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
+ diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
+ diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
+ log["diffusion_row"] = diffusion_grid
+
+ if sample:
+ # get denoise row
+ with self.ema_scope("Plotting"):
+ samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+ ddim_steps=ddim_steps,eta=ddim_eta)
+ # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
+ x_samples = self.decode_first_stage(samples)
+ log["samples"] = x_samples
+ if plot_denoise_rows:
+ denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
+ log["denoise_row"] = denoise_grid
+
+ if quantize_denoised and not isinstance(self.first_stage_model, AutoencoderKL) and not isinstance(
+ self.first_stage_model, IdentityFirstStage):
+ # also display when quantizing x0 while sampling
+ with self.ema_scope("Plotting Quantized Denoised"):
+ samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+ ddim_steps=ddim_steps,eta=ddim_eta,
+ quantize_denoised=True)
+ # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True,
+ # quantize_denoised=True)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_x0_quantized"] = x_samples
+
+ if inpaint:
+ # make a simple center square
+ b, h, w = z.shape[0], z.shape[2], z.shape[3]
+ mask = torch.ones(N, h, w).to(self.device)
+ # zeros will be filled in
+ mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
+ mask = mask[:, None, ...]
+ with self.ema_scope("Plotting Inpaint"):
+
+ samples, _ = self.sample_log(cond=c,batch_size=N,ddim=use_ddim, eta=ddim_eta,
+ ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_inpainting"] = x_samples
+ log["mask"] = mask
+
+ # outpaint
+ with self.ema_scope("Plotting Outpaint"):
+ samples, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,eta=ddim_eta,
+ ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_outpainting"] = x_samples
+
+ if plot_progressive_rows:
+ with self.ema_scope("Plotting Progressives"):
+ img, progressives = self.progressive_denoising(c,
+ shape=(self.channels, self.image_size, self.image_size),
+ batch_size=N)
+ prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
+ log["progressive_row"] = prog_row
+
+ if return_keys:
+ if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+ return log
+ else:
+ return {key: log[key] for key in return_keys}
+ return log
+
+ def configure_optimizers(self):
+ lr = self.learning_rate
+ params = list(self.model.parameters())
+ if self.cond_stage_trainable:
+ print(f"{self.__class__.__name__}: Also optimizing conditioner params!")
+ params = params + list(self.cond_stage_model.parameters())
+ if self.learn_logvar:
+ print('Diffusion model optimizing logvar')
+ params.append(self.logvar)
+ opt = torch.optim.AdamW(params, lr=lr)
+ if self.use_scheduler:
+ assert 'target' in self.scheduler_config
+ scheduler = instantiate_from_config(self.scheduler_config)
+
+ print("Setting up LambdaLR scheduler...")
+ scheduler = [
+ {
+ 'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule),
+ 'interval': 'step',
+ 'frequency': 1
+ }]
+ return [opt], scheduler
+ return opt
+
+ @torch.no_grad()
+ def to_rgb(self, x):
+ x = x.float()
+ if not hasattr(self, "colorize"):
+ self.colorize = torch.randn(3, x.shape[1], 1, 1).to(x)
+ x = nn.functional.conv2d(x, weight=self.colorize)
+ x = 2. * (x - x.min()) / (x.max() - x.min()) - 1.
+ return x
+
+
+class DiffusionWrapper(pl.LightningModule):
+ def __init__(self, diff_model_config, conditioning_key):
+ super().__init__()
+ self.diffusion_model = instantiate_from_config(diff_model_config)
+ self.conditioning_key = conditioning_key
+ assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm']
+
+ def forward(self, x, t, c_concat: list = None, c_crossattn: list = None):
+ if self.conditioning_key is None:
+ out = self.diffusion_model(x, t)
+ elif self.conditioning_key == 'concat':
+ xc = torch.cat([x] + c_concat, dim=1)
+ out = self.diffusion_model(xc, t)
+ elif self.conditioning_key == 'crossattn':
+ cc = torch.cat(c_crossattn, 1)
+ out = self.diffusion_model(x, t, context=cc)
+ elif self.conditioning_key == 'hybrid':
+ xc = torch.cat([x] + c_concat, dim=1)
+ cc = torch.cat(c_crossattn, 1)
+ out = self.diffusion_model(xc, t, context=cc)
+ elif self.conditioning_key == 'adm':
+ cc = c_crossattn[0]
+ out = self.diffusion_model(x, t, y=cc)
+ else:
+ raise NotImplementedError()
+
+ return out
+
+
+class Layout2ImgDiffusion(LatentDiffusion):
+ # TODO: move all layout-specific hacks to this class
+ def __init__(self, cond_stage_key, *args, **kwargs):
+ assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
+ super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+
+ def log_images(self, batch, N=8, *args, **kwargs):
+ logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+
+ key = 'train' if self.training else 'validation'
+ dset = self.trainer.datamodule.datasets[key]
+ mapper = dset.conditional_builders[self.cond_stage_key]
+
+ bbox_imgs = []
+ map_fn = lambda catno: dset.get_textual_label(dset.get_category_id(catno))
+ for tknzd_bbox in batch[self.cond_stage_key][:N]:
+ bboximg = mapper.plot(tknzd_bbox.detach().cpu(), map_fn, (256, 256))
+ bbox_imgs.append(bboximg)
+
+ cond_img = torch.stack(bbox_imgs, dim=0)
+ logs['bbox_image'] = cond_img
+ return logs
\ No newline at end of file
diff --git a/stable_diffusion/ldm/models/diffusion/ddpm_edit_disc.py b/stable_diffusion/ldm/models/diffusion/ddpm_edit_disc.py
new file mode 100644
index 0000000000000000000000000000000000000000..2b6a4b442b7505c2df161b53337eefe18e57c48c
--- /dev/null
+++ b/stable_diffusion/ldm/models/diffusion/ddpm_edit_disc.py
@@ -0,0 +1,1669 @@
+"""
+wild mixture of
+https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
+https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py
+https://github.com/CompVis/taming-transformers
+-- merci
+"""
+
+# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
+# See more details in LICENSE.
+
+import os
+import numpy as np
+import torchvision
+import pytorch_lightning as pl
+import json
+from PIL import Image
+import pickle
+import torch.distributed as dist
+
+import torch
+import torch.nn as nn
+import numpy as np
+import pytorch_lightning as pl
+from torch.optim.lr_scheduler import LambdaLR
+from einops import rearrange, repeat
+from contextlib import contextmanager
+from functools import partial
+from tqdm import tqdm
+from torchvision.utils import make_grid
+from pytorch_lightning.utilities.distributed import rank_zero_only
+
+from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
+from ldm.modules.ema import LitEma
+from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
+from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
+from ldm.models.diffusion.ddim import DDIMSampler
+
+
+__conditioning_keys__ = {'concat': 'c_concat',
+ 'crossattn': 'c_crossattn',
+ 'adm': 'y'}
+
+def get_world_size():
+ if not dist.is_available():
+ return 1
+ if not dist.is_initialized():
+ return 1
+ return dist.get_world_size()
+
+def all_gather(data):
+ """
+ Run all_gather on arbitrary picklable data (not necessarily tensors)
+ Args:
+ data: any picklable object
+ Returns:
+ list[data]: list of data gathered from each rank
+ """
+ world_size = get_world_size()
+ if world_size == 1:
+ return [data]
+
+ # serialized to a Tensor
+ origin_size = None
+ if not isinstance(data, torch.Tensor):
+ buffer = pickle.dumps(data)
+ storage = torch.ByteStorage.from_buffer(buffer)
+ tensor = torch.ByteTensor(storage).to("cuda")
+ else:
+ origin_size = data.size()
+ tensor = data.reshape(-1)
+
+ tensor_type = tensor.dtype
+
+ # obtain Tensor size of each rank
+ local_size = torch.LongTensor([tensor.numel()]).to("cuda")
+ size_list = [torch.LongTensor([0]).to("cuda") for _ in range(world_size)]
+ dist.all_gather(size_list, local_size)
+ size_list = [int(size.item()) for size in size_list]
+ max_size = max(size_list)
+
+ # receiving Tensor from all ranks
+ # we pad the tensor because torch all_gather does not support
+ # gathering tensors of different shapes
+ tensor_list = []
+ for _ in size_list:
+ tensor_list.append(torch.FloatTensor(size=(max_size,)).cuda().to(tensor_type))
+ if local_size != max_size:
+ padding = torch.FloatTensor(size=(max_size - local_size,)).cuda().to(tensor_type)
+ tensor = torch.cat((tensor, padding), dim=0)
+ dist.all_gather(tensor_list, tensor)
+
+ data_list = []
+ for size, tensor in zip(size_list, tensor_list):
+ if origin_size is None:
+ buffer = tensor.cpu().numpy().tobytes()[:size]
+ data_list.append(pickle.loads(buffer))
+ else:
+ buffer = tensor[:size]
+ data_list.append(buffer)
+
+ if origin_size is not None:
+ new_shape = [-1] + list(origin_size[1:])
+ resized_list = []
+ for data in data_list:
+ # suppose the difference of tensor size exist in first dimension
+ data = data.reshape(new_shape)
+ resized_list.append(data)
+
+ return resized_list
+ else:
+ return data_list
+
+def disabled_train(self, mode=True):
+ """Overwrite model.train with this function to make sure train/eval mode
+ does not change anymore."""
+ return self
+
+
+def uniform_on_device(r1, r2, shape, device):
+ return (r1 - r2) * torch.rand(*shape, device=device) + r2
+
+
+class DDPM(pl.LightningModule):
+ # classic DDPM with Gaussian diffusion, in image space
+ def __init__(self,
+ unet_config,
+ timesteps=1000,
+ beta_schedule="linear",
+ loss_type="l2",
+ ckpt_path=None,
+ ignore_keys=[],
+ load_only_unet=False,
+ monitor="val/loss",
+ use_ema=True,
+ first_stage_key="image",
+ image_size=256,
+ channels=3,
+ log_every_t=100,
+ clip_denoised=True,
+ linear_start=1e-4,
+ linear_end=2e-2,
+ cosine_s=8e-3,
+ given_betas=None,
+ original_elbo_weight=0.,
+ v_posterior=0., # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
+ l_simple_weight=1.,
+ conditioning_key=None,
+ parameterization="eps", # all assuming fixed variance schedules
+ scheduler_config=None,
+ use_positional_encodings=False,
+ learn_logvar=False,
+ logvar_init=0.,
+ load_ema=True,
+ ):
+ super().__init__()
+ assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
+ self.parameterization = parameterization
+ print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
+ self.cond_stage_model = None
+ self.clip_denoised = clip_denoised
+ self.log_every_t = log_every_t
+ self.first_stage_key = first_stage_key
+ self.image_size = image_size # try conv?
+ self.channels = channels
+ self.use_positional_encodings = use_positional_encodings
+ self.model = DiffusionWrapper(unet_config, conditioning_key)
+ count_params(self.model, verbose=True)
+ self.use_ema = use_ema
+
+ self.use_scheduler = scheduler_config is not None
+ if self.use_scheduler:
+ self.scheduler_config = scheduler_config
+
+ self.v_posterior = v_posterior
+ self.original_elbo_weight = original_elbo_weight
+ self.l_simple_weight = l_simple_weight
+
+ if monitor is not None:
+ self.monitor = monitor
+
+ if self.use_ema and load_ema:
+ self.model_ema = LitEma(self.model)
+ print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+ if ckpt_path is not None:
+ self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+
+ # If initialing from EMA-only checkpoint, create EMA model after loading.
+ if self.use_ema and not load_ema:
+ self.model_ema = LitEma(self.model)
+ print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+ self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
+ linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
+
+ self.loss_type = loss_type
+
+ self.learn_logvar = learn_logvar
+ self.logvar = torch.full(fill_value=logvar_init, size=(self.num_timesteps,))
+ if self.learn_logvar:
+ self.logvar = nn.Parameter(self.logvar, requires_grad=True)
+
+
+ def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
+ linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+ if exists(given_betas):
+ betas = given_betas
+ else:
+ betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end,
+ cosine_s=cosine_s)
+ alphas = 1. - betas
+ alphas_cumprod = np.cumprod(alphas, axis=0)
+ alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])
+
+ timesteps, = betas.shape
+ self.num_timesteps = int(timesteps)
+ self.linear_start = linear_start
+ self.linear_end = linear_end
+ assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'
+
+ to_torch = partial(torch.tensor, dtype=torch.float32)
+
+ self.register_buffer('betas', to_torch(betas))
+ self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+ self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))
+
+ # calculations for diffusion q(x_t | x_{t-1}) and others
+ self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
+ self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
+ self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
+ self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
+ self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))
+
+ # calculations for posterior q(x_{t-1} | x_t, x_0)
+ posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / (
+ 1. - alphas_cumprod) + self.v_posterior * betas
+ # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
+ self.register_buffer('posterior_variance', to_torch(posterior_variance))
+ # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
+ self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
+ self.register_buffer('posterior_mean_coef1', to_torch(
+ betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
+ self.register_buffer('posterior_mean_coef2', to_torch(
+ (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))
+
+ if self.parameterization == "eps":
+ lvlb_weights = self.betas ** 2 / (
+ 2 * self.posterior_variance * to_torch(alphas) * (1 - self.alphas_cumprod))
+ elif self.parameterization == "x0":
+ lvlb_weights = 0.5 * np.sqrt(torch.Tensor(alphas_cumprod)) / (2. * 1 - torch.Tensor(alphas_cumprod))
+ else:
+ raise NotImplementedError("mu not supported")
+ # TODO how to choose this term
+ lvlb_weights[0] = lvlb_weights[1]
+ self.register_buffer('lvlb_weights', lvlb_weights, persistent=False)
+ assert not torch.isnan(self.lvlb_weights).all()
+
+ @contextmanager
+ def ema_scope(self, context=None):
+ if self.use_ema:
+ self.model_ema.store(self.model.parameters())
+ self.model_ema.copy_to(self.model)
+ if context is not None:
+ print(f"{context}: Switched to EMA weights")
+ try:
+ yield None
+ finally:
+ if self.use_ema:
+ self.model_ema.restore(self.model.parameters())
+ if context is not None:
+ print(f"{context}: Restored training weights")
+
+ def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+ sd = torch.load(path, map_location="cpu")
+ if "state_dict" in list(sd.keys()):
+ sd = sd["state_dict"]
+ keys = list(sd.keys())
+
+ # Our model adds additional channels to the first layer to condition on an input image.
+ # For the first layer, copy existing channel weights and initialize new channel weights to zero.
+ input_keys = [
+ "model.diffusion_model.input_blocks.0.0.weight",
+ "model_ema.diffusion_modelinput_blocks00weight",
+ ]
+
+ self_sd = self.state_dict()
+ for input_key in input_keys:
+ if input_key not in sd or input_key not in self_sd:
+ continue
+
+ input_weight = self_sd[input_key]
+
+ if input_weight.size() != sd[input_key].size():
+ print(f"Manual init: {input_key}")
+ input_weight.zero_()
+ input_weight[:, :4, :, :].copy_(sd[input_key])
+ ignore_keys.append(input_key)
+
+ for k in keys:
+ for ik in ignore_keys:
+ if k.startswith(ik):
+ print("Deleting key {} from state_dict.".format(k))
+ del sd[k]
+ missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
+ sd, strict=False)
+ print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
+ if len(missing) > 0:
+ print(f"Missing Keys: {missing}")
+ if len(unexpected) > 0:
+ print(f"Unexpected Keys: {unexpected}")
+
+ def q_mean_variance(self, x_start, t):
+ """
+ Get the distribution q(x_t | x_0).
+ :param x_start: the [N x C x ...] tensor of noiseless inputs.
+ :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
+ :return: A tuple (mean, variance, log_variance), all of x_start's shape.
+ """
+ mean = (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start)
+ variance = extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
+ log_variance = extract_into_tensor(self.log_one_minus_alphas_cumprod, t, x_start.shape)
+ return mean, variance, log_variance
+
+ def predict_start_from_noise(self, x_t, t, noise):
+ return (
+ extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
+ extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
+ )
+
+ def q_posterior(self, x_start, x_t, t):
+ posterior_mean = (
+ extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start +
+ extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
+ )
+ posterior_variance = extract_into_tensor(self.posterior_variance, t, x_t.shape)
+ posterior_log_variance_clipped = extract_into_tensor(self.posterior_log_variance_clipped, t, x_t.shape)
+ return posterior_mean, posterior_variance, posterior_log_variance_clipped
+
+ def p_mean_variance(self, x, t, clip_denoised: bool):
+ model_out = self.model(x, t)
+ if self.parameterization == "eps":
+ x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+ elif self.parameterization == "x0":
+ x_recon = model_out
+ if clip_denoised:
+ x_recon.clamp_(-1., 1.)
+
+ model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+ return model_mean, posterior_variance, posterior_log_variance
+
+ @torch.no_grad()
+ def p_sample(self, x, t, clip_denoised=True, repeat_noise=False):
+ b, *_, device = *x.shape, x.device
+ model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, clip_denoised=clip_denoised)
+ noise = noise_like(x.shape, device, repeat_noise)
+ # no noise when t == 0
+ nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+ @torch.no_grad()
+ def p_sample_loop(self, shape, return_intermediates=False):
+ device = self.betas.device
+ b = shape[0]
+ img = torch.randn(shape, device=device)
+ intermediates = [img]
+ for i in tqdm(reversed(range(0, self.num_timesteps)), desc='Sampling t', total=self.num_timesteps):
+ img = self.p_sample(img, torch.full((b,), i, device=device, dtype=torch.long),
+ clip_denoised=self.clip_denoised)
+ if i % self.log_every_t == 0 or i == self.num_timesteps - 1:
+ intermediates.append(img)
+ if return_intermediates:
+ return img, intermediates
+ return img
+
+ @torch.no_grad()
+ def sample(self, batch_size=16, return_intermediates=False):
+ image_size = self.image_size
+ channels = self.channels
+ return self.p_sample_loop((batch_size, channels, image_size, image_size),
+ return_intermediates=return_intermediates)
+
+ def q_sample(self, x_start, t, noise=None):
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
+ extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
+
+ def get_loss(self, pred, target, mean=True):
+ if self.loss_type == 'l1':
+ loss = (target - pred).abs()
+ if mean:
+ loss = loss.mean()
+ elif self.loss_type == 'l2':
+ if mean:
+ loss = torch.nn.functional.mse_loss(target, pred)
+ else:
+ loss = torch.nn.functional.mse_loss(target, pred, reduction='none')
+ else:
+ raise NotImplementedError("unknown loss type '{loss_type}'")
+
+ return loss
+
+ def p_losses(self, x_start, t, noise=None):
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+ model_out = self.model(x_noisy, t)
+
+ loss_dict = {}
+ if self.parameterization == "eps":
+ target = noise
+ elif self.parameterization == "x0":
+ target = x_start
+ else:
+ raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+
+ loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
+
+ log_prefix = 'train' if self.training else 'val'
+
+ loss_dict.update({f'{log_prefix}/loss_simple': loss.mean()})
+ loss_simple = loss.mean() * self.l_simple_weight
+
+ loss_vlb = (self.lvlb_weights[t] * loss).mean()
+ loss_dict.update({f'{log_prefix}/loss_vlb': loss_vlb})
+
+ loss = loss_simple + self.original_elbo_weight * loss_vlb
+
+ loss_dict.update({f'{log_prefix}/loss': loss})
+
+ return loss, loss_dict
+
+ def forward(self, x, *args, **kwargs):
+ print('\n\n I made it here: forward of DDPM \n\n')
+ # b, c, h, w, device, img_size, = *x.shape, x.device, self.image_size
+ # assert h == img_size and w == img_size, f'height and width of image must be {img_size}'
+ t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+ return self.p_losses(x, t, *args, **kwargs)
+
+ def get_input(self, batch, k):
+ return batch[k]
+
+ def shared_step(self, batch, discriminate=False):
+ if discriminate:
+ new_batch = {'edited': None, 'edit': {'c_concat': None, 'c_crossattn': None}}
+ for i in batch['edited'].shape[0]:
+ new_batch['edited'] = batch['edited'][i].unsqueeze(0).repeat((10, 1, 1, 1))
+ new_batch['edit']['c_concat'] = batch['edit']['c_concat'][i].unsqueeze(0).repeat((10, 1, 1, 1))
+ new_batch['edit']['c_crossattn'] = batch['edit']['c_crossattn'][i]
+ x = self.get_input(new_batch, self.first_stage_key)
+ loss, loss_dict = self(x)
+ else:
+ x = self.get_input(batch, self.first_stage_key)
+ loss, loss_dict = self(x)
+ return loss, loss_dict
+
+ def training_step(self, batch, batch_idx):
+ loss, loss_dict = self.shared_step(batch)
+
+ self.log_dict(loss_dict, prog_bar=True,
+ logger=True, on_step=True, on_epoch=True)
+
+ self.log("global_step", self.global_step,
+ prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+ if self.use_scheduler:
+ lr = self.optimizers().param_groups[0]['lr']
+ self.log('lr_abs', lr, prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+ return loss
+
+ # def log_local(self, save_dir, split, images, prompts,
+ # global_step, current_epoch, batch_idx):
+ # root = os.path.join(save_dir, "images", split)
+ # names = {"reals": "before", "inputs": "after", "reconstruction": "before-vq", "samples": "after-gen"}
+ # # print(root)
+ # for k in images:
+ # grid = torchvision.utils.make_grid(images[k], nrow=8)
+ # if self.rescale:
+ # grid = (grid + 1.0) / 2.0 # -1,1 -> 0,1; c,h,w
+ # grid = grid.transpose(0, 1).transpose(1, 2).squeeze(-1)
+ # grid = grid.numpy()
+ # grid = (grid * 255).astype(np.uint8)
+ # filename = "gs-{:06}_e-{:06}_b-{:06}_{}.png".format(
+ # global_step,
+ # current_epoch,
+ # batch_idx,
+ # names[k])
+ # path = os.path.join(root, filename)
+ # os.makedirs(os.path.split(path)[0], exist_ok=True)
+ # # print(path)
+ # Image.fromarray(grid).save(path)
+
+ # filename = "gs-{:06}_e-{:06}_b-{:06}_prompt.json".format(
+ # global_step,
+ # current_epoch,
+ # batch_idx)
+ # path = os.path.join(root, filename)
+ # with open(path, "w") as f:
+ # for p in prompts:
+ # f.write(f"{json.dumps(p)}\n")
+
+ # def log_img(self, batch, batch_idx, split="val"):
+ # check_idx = batch_idx if self.log_on_batch_idx else self.global_step
+ # if (self.check_frequency(check_idx) and # batch_idx % self.batch_freq == 0
+ # hasattr(self, "log_images") and
+ # callable(self.log_images) and
+ # self.max_images > 0) or (split == "val" and batch_idx == 0):
+ # logger = type(self.logger)
+
+ # is_train = self.training
+ # if is_train:
+ # self.eval()
+
+ # with torch.no_grad():
+ # images = self.log_images(batch, split=split, **self.log_images_kwargs)
+
+ # prompts = batch["edit"]["c_crossattn"][:self.max_images]
+ # prompts = [p for ps in all_gather(prompts) for p in ps]
+
+ # for k in images:
+ # N = min(images[k].shape[0], self.max_images)
+ # images[k] = images[k][:N]
+ # images[k] = torch.cat(all_gather(images[k][:N]))
+ # if isinstance(images[k], torch.Tensor):
+ # images[k] = images[k].detach().cpu()
+ # if self.clamp:
+ # images[k] = torch.clamp(images[k], -1., 1.)
+
+ # self.log_local(self.logger.save_dir, split, images, prompts,
+ # self.global_step, self.current_epoch, batch_idx)
+
+ # logger_log_images = self.logger_log_images.get(logger, lambda *args, **kwargs: None)
+ # logger_log_images(self, images, self.global_step, split)
+
+ # if is_train:
+ # self.train()
+
+
+ @torch.no_grad()
+ def validation_step(self, batch, batch_idx, discriminate=False):
+ self.discriminate = discriminate
+ def calculate_accuracy(losses):
+ correct_count = 0
+ for loss in losses:
+ if loss[0] < min(loss[1:]):
+ correct_count += 1
+ return correct_count, len(losses) # Return counts for aggregation
+
+ # self.log_img(batch, batch_idx, split="val")
+ losses = self.shared_step(batch, discriminate=discriminate)
+ if discriminate:
+ correct_count, total_count = calculate_accuracy(losses)
+ return {'correct_count': correct_count, 'total_count': total_count}
+ else:
+ _, loss_dict_no_ema = self.shared_step(batch)
+ with self.ema_scope():
+ _, loss_dict_ema = self.shared_step(batch)
+ loss_dict_ema = {key + '_ema': loss_dict_ema[key] for key in loss_dict_ema}
+ self.log_dict(loss_dict_no_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+ self.log_dict(loss_dict_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+
+ def validation_epoch_end(self, outputs):
+ if self.discriminate:
+ correct_count = sum(x['correct_count'] for x in outputs)
+ total_count = sum(x['total_count'] for x in outputs)
+ overall_accuracy = (correct_count / total_count) * 100
+ print(f"Overall accuracy: {overall_accuracy:.2f}%")
+ import pdb; pdb.set_trace()
+ self.log('overall_accuracy', overall_accuracy, prog_bar=True, logger=True)
+
+ def on_train_batch_end(self, *args, **kwargs):
+ if self.use_ema:
+ self.model_ema(self.model)
+
+ def _get_rows_from_list(self, samples):
+ n_imgs_per_row = len(samples)
+ denoise_grid = rearrange(samples, 'n b c h w -> b n c h w')
+ denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+ denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+ return denoise_grid
+
+ @torch.no_grad()
+ def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
+ log = dict()
+ x = self.get_input(batch, self.first_stage_key)
+ N = min(x.shape[0], N)
+ n_row = min(x.shape[0], n_row)
+ x = x.to(self.device)[:N]
+ log["inputs"] = x
+
+ # get diffusion row
+ diffusion_row = list()
+ x_start = x[:n_row]
+
+ for t in range(self.num_timesteps):
+ if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+ t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+ t = t.to(self.device).long()
+ noise = torch.randn_like(x_start)
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+ diffusion_row.append(x_noisy)
+
+ log["diffusion_row"] = self._get_rows_from_list(diffusion_row)
+
+ if sample:
+ # get denoise row
+ with self.ema_scope("Plotting"):
+ samples, denoise_row = self.sample(batch_size=N, return_intermediates=True)
+
+ log["samples"] = samples
+ log["denoise_row"] = self._get_rows_from_list(denoise_row)
+
+ if return_keys:
+ if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+ return log
+ else:
+ return {key: log[key] for key in return_keys}
+ return log
+
+ def configure_optimizers(self):
+ lr = self.learning_rate
+ params = list(self.model.parameters())
+ if self.learn_logvar:
+ params = params + [self.logvar]
+ opt = torch.optim.AdamW(params, lr=lr)
+ return opt
+
+
+class LatentDiffusion(DDPM):
+ """main class"""
+ def __init__(self,
+ first_stage_config,
+ cond_stage_config,
+ num_timesteps_cond=None,
+ cond_stage_key="image",
+ cond_stage_trainable=False,
+ concat_mode=True,
+ cond_stage_forward=None,
+ conditioning_key=None,
+ scale_factor=1.0,
+ scale_by_std=False,
+ load_ema=True,
+ *args, **kwargs):
+ self.num_timesteps_cond = default(num_timesteps_cond, 1)
+ self.scale_by_std = scale_by_std
+ assert self.num_timesteps_cond <= kwargs['timesteps']
+ # for backwards compatibility after implementation of DiffusionWrapper
+ if conditioning_key is None:
+ conditioning_key = 'concat' if concat_mode else 'crossattn'
+ if cond_stage_config == '__is_unconditional__':
+ conditioning_key = None
+ ckpt_path = kwargs.pop("ckpt_path", None)
+ ignore_keys = kwargs.pop("ignore_keys", [])
+ super().__init__(conditioning_key=conditioning_key, *args, load_ema=load_ema, **kwargs)
+ self.concat_mode = concat_mode
+ self.cond_stage_trainable = cond_stage_trainable
+ self.cond_stage_key = cond_stage_key
+ try:
+ self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
+ except:
+ self.num_downs = 0
+ if not scale_by_std:
+ self.scale_factor = scale_factor
+ else:
+ self.register_buffer('scale_factor', torch.tensor(scale_factor))
+ self.instantiate_first_stage(first_stage_config)
+ self.instantiate_cond_stage(cond_stage_config)
+ self.cond_stage_forward = cond_stage_forward
+ self.clip_denoised = False
+ self.bbox_tokenizer = None
+
+ self.restarted_from_ckpt = False
+ if ckpt_path is not None:
+ self.init_from_ckpt(ckpt_path, ignore_keys)
+ self.restarted_from_ckpt = True
+
+ if self.use_ema and not load_ema:
+ self.model_ema = LitEma(self.model)
+ print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+ def make_cond_schedule(self, ):
+ self.cond_ids = torch.full(size=(self.num_timesteps,), fill_value=self.num_timesteps - 1, dtype=torch.long)
+ ids = torch.round(torch.linspace(0, self.num_timesteps - 1, self.num_timesteps_cond)).long()
+ self.cond_ids[:self.num_timesteps_cond] = ids
+
+ @rank_zero_only
+ @torch.no_grad()
+ def on_train_batch_start(self, batch, batch_idx, dataloader_idx):
+ # only for very first batch
+ if self.scale_by_std and self.current_epoch == 0 and self.global_step == 0 and batch_idx == 0 and not self.restarted_from_ckpt:
+ assert self.scale_factor == 1., 'rather not use custom rescaling and std-rescaling simultaneously'
+ # set rescale weight to 1./std of encodings
+ print("### USING STD-RESCALING ###")
+ x = super().get_input(batch, self.first_stage_key)
+ x = x.to(self.device)
+ encoder_posterior = self.encode_first_stage(x)
+ z = self.get_first_stage_encoding(encoder_posterior).detach()
+ del self.scale_factor
+ self.register_buffer('scale_factor', 1. / z.flatten().std())
+ print(f"setting self.scale_factor to {self.scale_factor}")
+ print("### USING STD-RESCALING ###")
+
+ def register_schedule(self,
+ given_betas=None, beta_schedule="linear", timesteps=1000,
+ linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+ super().register_schedule(given_betas, beta_schedule, timesteps, linear_start, linear_end, cosine_s)
+
+ self.shorten_cond_schedule = self.num_timesteps_cond > 1
+ if self.shorten_cond_schedule:
+ self.make_cond_schedule()
+
+ def instantiate_first_stage(self, config):
+ model = instantiate_from_config(config)
+ self.first_stage_model = model.eval()
+ self.first_stage_model.train = disabled_train
+ for param in self.first_stage_model.parameters():
+ param.requires_grad = False
+
+ def instantiate_cond_stage(self, config):
+ if not self.cond_stage_trainable:
+ if config == "__is_first_stage__":
+ print("Using first stage also as cond stage.")
+ self.cond_stage_model = self.first_stage_model
+ elif config == "__is_unconditional__":
+ print(f"Training {self.__class__.__name__} as an unconditional model.")
+ self.cond_stage_model = None
+ # self.be_unconditional = True
+ else:
+ model = instantiate_from_config(config)
+ self.cond_stage_model = model.eval()
+ self.cond_stage_model.train = disabled_train
+ for param in self.cond_stage_model.parameters():
+ param.requires_grad = False
+ else:
+ assert config != '__is_first_stage__'
+ assert config != '__is_unconditional__'
+ model = instantiate_from_config(config)
+ self.cond_stage_model = model
+
+ def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
+ denoise_row = []
+ for zd in tqdm(samples, desc=desc):
+ denoise_row.append(self.decode_first_stage(zd.to(self.device),
+ force_not_quantize=force_no_decoder_quantization))
+ n_imgs_per_row = len(denoise_row)
+ denoise_row = torch.stack(denoise_row) # n_log_step, n_row, C, H, W
+ denoise_grid = rearrange(denoise_row, 'n b c h w -> b n c h w')
+ denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+ denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+ return denoise_grid
+
+ def get_first_stage_encoding(self, encoder_posterior):
+ if isinstance(encoder_posterior, DiagonalGaussianDistribution):
+ z = encoder_posterior.sample()
+ elif isinstance(encoder_posterior, torch.Tensor):
+ z = encoder_posterior
+ else:
+ raise NotImplementedError(f"encoder_posterior of type '{type(encoder_posterior)}' not yet implemented")
+ return self.scale_factor * z
+
+ def get_learned_conditioning(self, c):
+ if self.cond_stage_forward is None:
+ if hasattr(self.cond_stage_model, 'encode') and callable(self.cond_stage_model.encode):
+ c = self.cond_stage_model.encode(c)
+ if isinstance(c, DiagonalGaussianDistribution):
+ c = c.mode()
+ else:
+ c = self.cond_stage_model(c)
+ else:
+ assert hasattr(self.cond_stage_model, self.cond_stage_forward)
+ c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
+ return c
+
+ def meshgrid(self, h, w):
+ y = torch.arange(0, h).view(h, 1, 1).repeat(1, w, 1)
+ x = torch.arange(0, w).view(1, w, 1).repeat(h, 1, 1)
+
+ arr = torch.cat([y, x], dim=-1)
+ return arr
+
+ def delta_border(self, h, w):
+ """
+ :param h: height
+ :param w: width
+ :return: normalized distance to image border,
+ wtith min distance = 0 at border and max dist = 0.5 at image center
+ """
+ lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
+ arr = self.meshgrid(h, w) / lower_right_corner
+ dist_left_up = torch.min(arr, dim=-1, keepdims=True)[0]
+ dist_right_down = torch.min(1 - arr, dim=-1, keepdims=True)[0]
+ edge_dist = torch.min(torch.cat([dist_left_up, dist_right_down], dim=-1), dim=-1)[0]
+ return edge_dist
+
+ def get_weighting(self, h, w, Ly, Lx, device):
+ weighting = self.delta_border(h, w)
+ weighting = torch.clip(weighting, self.split_input_params["clip_min_weight"],
+ self.split_input_params["clip_max_weight"], )
+ weighting = weighting.view(1, h * w, 1).repeat(1, 1, Ly * Lx).to(device)
+
+ if self.split_input_params["tie_braker"]:
+ L_weighting = self.delta_border(Ly, Lx)
+ L_weighting = torch.clip(L_weighting,
+ self.split_input_params["clip_min_tie_weight"],
+ self.split_input_params["clip_max_tie_weight"])
+
+ L_weighting = L_weighting.view(1, 1, Ly * Lx).to(device)
+ weighting = weighting * L_weighting
+ return weighting
+
+ def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1): # todo load once not every time, shorten code
+ """
+ :param x: img of size (bs, c, h, w)
+ :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
+ """
+ bs, nc, h, w = x.shape
+
+ # number of crops in image
+ Ly = (h - kernel_size[0]) // stride[0] + 1
+ Lx = (w - kernel_size[1]) // stride[1] + 1
+
+ if uf == 1 and df == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)
+
+ weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h, w) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))
+
+ elif uf > 1 and df == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
+ dilation=1, padding=0,
+ stride=(stride[0] * uf, stride[1] * uf))
+ fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)
+
+ weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h * uf, w * uf) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))
+
+ elif df > 1 and uf == 1:
+ fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+ unfold = torch.nn.Unfold(**fold_params)
+
+ fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
+ dilation=1, padding=0,
+ stride=(stride[0] // df, stride[1] // df))
+ fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)
+
+ weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
+ normalization = fold(weighting).view(1, 1, h // df, w // df) # normalizes the overlap
+ weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))
+
+ else:
+ raise NotImplementedError
+
+ return fold, unfold, normalization, weighting
+
+ @torch.no_grad()
+ def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,
+ cond_key=None, return_original_cond=False, bs=None, uncond=0.05):
+ x = super().get_input(batch, k)
+ if bs is not None:
+ x = x[:bs]
+ x = x.to(self.device)
+ encoder_posterior = self.encode_first_stage(x)
+ z = self.get_first_stage_encoding(encoder_posterior).detach()
+ cond_key = cond_key or self.cond_stage_key
+ xc = super().get_input(batch, cond_key)
+ if bs is not None:
+ xc["c_crossattn"] = xc["c_crossattn"][:bs]
+ xc["c_concat"] = xc["c_concat"][:bs]
+ cond = {}
+
+ # To support classifier-free guidance, randomly drop out only text conditioning 5%, only image conditioning 5%, and both 5%.
+ random = torch.rand(x.size(0), device=x.device)
+ prompt_mask = rearrange(random < 2 * uncond, "n -> n 1 1")
+ input_mask = 1 - rearrange((random >= uncond).float() * (random < 3 * uncond).float(), "n -> n 1 1 1")
+
+ null_prompt = self.get_learned_conditioning([""])
+ cond["c_crossattn"] = [torch.where(prompt_mask, null_prompt, self.get_learned_conditioning(xc["c_crossattn"]).detach())]
+ cond["c_concat"] = [input_mask * self.encode_first_stage((xc["c_concat"].to(self.device))).mode().detach()]
+
+ out = [z, cond]
+ if return_first_stage_outputs:
+ xrec = self.decode_first_stage(z)
+ out.extend([x, xrec])
+ if return_original_cond:
+ out.append(xc)
+ return out
+
+ @torch.no_grad()
+ def decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+ if predict_cids:
+ if z.dim() == 4:
+ z = torch.argmax(z.exp(), dim=1).long()
+ z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+ z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+ z = 1. / self.scale_factor * z
+
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ uf = self.split_input_params["vqf"]
+ bs, nc, h, w = z.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+ z = unfold(z) # (bn, nc * prod(**ks), L)
+ # 1. Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ # 2. apply model loop over last dim
+ if isinstance(self.first_stage_model, VQModelInterface):
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+ force_not_quantize=predict_cids or force_not_quantize)
+ for i in range(z.shape[-1])]
+ else:
+
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1) # # (bn, nc, ks[0], ks[1], L)
+ o = o * weighting
+ # Reverse 1. reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization # norm is shape (1, 1, h, w)
+ return decoded
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ # same as above but without decorator
+ def differentiable_decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+ if predict_cids:
+ if z.dim() == 4:
+ z = torch.argmax(z.exp(), dim=1).long()
+ z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+ z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+ z = 1. / self.scale_factor * z
+
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ uf = self.split_input_params["vqf"]
+ bs, nc, h, w = z.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+ z = unfold(z) # (bn, nc * prod(**ks), L)
+ # 1. Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ # 2. apply model loop over last dim
+ if isinstance(self.first_stage_model, VQModelInterface):
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+ force_not_quantize=predict_cids or force_not_quantize)
+ for i in range(z.shape[-1])]
+ else:
+
+ output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1) # # (bn, nc, ks[0], ks[1], L)
+ o = o * weighting
+ # Reverse 1. reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization # norm is shape (1, 1, h, w)
+ return decoded
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ else:
+ if isinstance(self.first_stage_model, VQModelInterface):
+ return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+ else:
+ return self.first_stage_model.decode(z)
+
+ @torch.no_grad()
+ def encode_first_stage(self, x):
+ if hasattr(self, "split_input_params"):
+ if self.split_input_params["patch_distributed_vq"]:
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+ df = self.split_input_params["vqf"]
+ self.split_input_params['original_image_size'] = x.shape[-2:]
+ bs, nc, h, w = x.shape
+ if ks[0] > h or ks[1] > w:
+ ks = (min(ks[0], h), min(ks[1], w))
+ print("reducing Kernel")
+
+ if stride[0] > h or stride[1] > w:
+ stride = (min(stride[0], h), min(stride[1], w))
+ print("reducing stride")
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(x, ks, stride, df=df)
+ z = unfold(x) # (bn, nc * prod(**ks), L)
+ # Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ output_list = [self.first_stage_model.encode(z[:, :, :, :, i])
+ for i in range(z.shape[-1])]
+
+ o = torch.stack(output_list, axis=-1)
+ o = o * weighting
+
+ # Reverse reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ decoded = fold(o)
+ decoded = decoded / normalization
+ return decoded
+
+ else:
+ return self.first_stage_model.encode(x)
+ else:
+ return self.first_stage_model.encode(x)
+
+ def shared_step(self, batch, discriminate=False, **kwargs):
+ if discriminate:
+ new_batch = {'edited': None, 'edit': {'c_concat': None, 'c_crossattn': None}}
+ losses = []
+ for i in range(batch['edited'].shape[0]):
+ new_batch['edited'] = batch['edited'][i].unsqueeze(0).repeat((10, 1, 1, 1))
+ new_batch['edit']['c_concat'] = batch['edit']['c_concat'][i].unsqueeze(0).repeat((10, 1, 1, 1))
+ losses_ = []
+ for k in range(len(batch['edit']['c_crossattn'])):
+ new_batch['edit']['c_crossattn'] = batch['edit']['c_crossattn'][k][i]
+ x, c = self.get_input(new_batch, self.first_stage_key, uncond=0.0)
+ loss = self(x, c, discriminate=discriminate)
+ loss = loss[1]['val/loss_simple']
+ losses_.append(loss)
+ losses.append(losses_)
+ return losses
+ else:
+ x, c = self.get_input(batch, self.first_stage_key)
+ loss = self(x, c)
+ return loss
+
+ def forward(self, x, c, discriminate=False, *args, **kwargs):
+ if discriminate:
+ t = torch.linspace(10, self.num_timesteps-10, steps=x.shape[0], device=self.device).long()
+ else:
+ t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+ if self.model.conditioning_key is not None:
+ assert c is not None
+ if self.cond_stage_trainable:
+ c = self.get_learned_conditioning(c)
+ if self.shorten_cond_schedule: # TODO: drop this option
+ tc = self.cond_ids[t].to(self.device)
+ c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
+ return self.p_losses(x, c, t, discriminate=True, *args, **kwargs)
+
+ def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset
+ def rescale_bbox(bbox):
+ x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
+ y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
+ w = min(bbox[2] / crop_coordinates[2], 1 - x0)
+ h = min(bbox[3] / crop_coordinates[3], 1 - y0)
+ return x0, y0, w, h
+
+ return [rescale_bbox(b) for b in bboxes]
+
+ def apply_model(self, x_noisy, t, cond, return_ids=False):
+
+ if isinstance(cond, dict):
+ # hybrid case, cond is exptected to be a dict
+ pass
+ else:
+ if not isinstance(cond, list):
+ cond = [cond]
+ key = 'c_concat' if self.model.conditioning_key == 'concat' else 'c_crossattn'
+ cond = {key: cond}
+
+ if hasattr(self, "split_input_params"):
+ assert len(cond) == 1 # todo can only deal with one conditioning atm
+ assert not return_ids
+ ks = self.split_input_params["ks"] # eg. (128, 128)
+ stride = self.split_input_params["stride"] # eg. (64, 64)
+
+ h, w = x_noisy.shape[-2:]
+
+ fold, unfold, normalization, weighting = self.get_fold_unfold(x_noisy, ks, stride)
+
+ z = unfold(x_noisy) # (bn, nc * prod(**ks), L)
+ # Reshape to img shape
+ z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+ z_list = [z[:, :, :, :, i] for i in range(z.shape[-1])]
+
+ if self.cond_stage_key in ["image", "LR_image", "segmentation",
+ 'bbox_img'] and self.model.conditioning_key: # todo check for completeness
+ c_key = next(iter(cond.keys())) # get key
+ c = next(iter(cond.values())) # get value
+ assert (len(c) == 1) # todo extend to list with more than one elem
+ c = c[0] # get element
+
+ c = unfold(c)
+ c = c.view((c.shape[0], -1, ks[0], ks[1], c.shape[-1])) # (bn, nc, ks[0], ks[1], L )
+
+ cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
+
+ elif self.cond_stage_key == 'coordinates_bbox':
+ assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+
+ # assuming padding of unfold is always 0 and its dilation is always 1
+ n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
+ full_img_h, full_img_w = self.split_input_params['original_image_size']
+ # as we are operating on latents, we need the factor from the original image size to the
+ # spatial latent size to properly rescale the crops for regenerating the bbox annotations
+ num_downs = self.first_stage_model.encoder.num_resolutions - 1
+ rescale_latent = 2 ** (num_downs)
+
+ # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+ # need to rescale the tl patch coordinates to be in between (0,1)
+ tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
+ rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)
+ for patch_nr in range(z.shape[-1])]
+
+ # patch_limits are tl_coord, width and height coordinates as (x_tl, y_tl, h, w)
+ patch_limits = [(x_tl, y_tl,
+ rescale_latent * ks[0] / full_img_w,
+ rescale_latent * ks[1] / full_img_h) for x_tl, y_tl in tl_patch_coordinates]
+ # patch_values = [(np.arange(x_tl,min(x_tl+ks, 1.)),np.arange(y_tl,min(y_tl+ks, 1.))) for x_tl, y_tl in tl_patch_coordinates]
+
+ # tokenize crop coordinates for the bounding boxes of the respective patches
+ patch_limits_tknzd = [torch.LongTensor(self.bbox_tokenizer._crop_encoder(bbox))[None].to(self.device)
+ for bbox in patch_limits] # list of length l with tensors of shape (1, 2)
+ print(patch_limits_tknzd[0].shape)
+ # cut tknzd crop position from conditioning
+ assert isinstance(cond, dict), 'cond must be dict to be fed into model'
+ cut_cond = cond['c_crossattn'][0][..., :-2].to(self.device)
+ print(cut_cond.shape)
+
+ adapted_cond = torch.stack([torch.cat([cut_cond, p], dim=1) for p in patch_limits_tknzd])
+ adapted_cond = rearrange(adapted_cond, 'l b n -> (l b) n')
+ print(adapted_cond.shape)
+ adapted_cond = self.get_learned_conditioning(adapted_cond)
+ print(adapted_cond.shape)
+ adapted_cond = rearrange(adapted_cond, '(l b) n d -> l b n d', l=z.shape[-1])
+ print(adapted_cond.shape)
+
+ cond_list = [{'c_crossattn': [e]} for e in adapted_cond]
+
+ else:
+ cond_list = [cond for i in range(z.shape[-1])] # Todo make this more efficient
+
+ # apply model by loop over crops
+ output_list = [self.model(z_list[i], t, **cond_list[i]) for i in range(z.shape[-1])]
+ assert not isinstance(output_list[0],
+ tuple) # todo cant deal with multiple model outputs check this never happens
+
+ o = torch.stack(output_list, axis=-1)
+ o = o * weighting
+ # Reverse reshape to img shape
+ o = o.view((o.shape[0], -1, o.shape[-1])) # (bn, nc * ks[0] * ks[1], L)
+ # stitch crops together
+ x_recon = fold(o) / normalization
+
+ else:
+ x_recon = self.model(x_noisy, t, **cond)
+
+ if isinstance(x_recon, tuple) and not return_ids:
+ return x_recon[0]
+ else:
+ return x_recon
+
+ def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
+ return (extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - pred_xstart) / \
+ extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)
+
+ def _prior_bpd(self, x_start):
+ """
+ Get the prior KL term for the variational lower-bound, measured in
+ bits-per-dim.
+ This term can't be optimized, as it only depends on the encoder.
+ :param x_start: the [N x C x ...] tensor of inputs.
+ :return: a batch of [N] KL values (in bits), one per batch element.
+ """
+ batch_size = x_start.shape[0]
+ t = torch.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
+ qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
+ kl_prior = normal_kl(mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0)
+ return mean_flat(kl_prior) / np.log(2.0)
+
+ def p_losses(self, x_start, cond, t, discriminate=False, noise=None):
+ if discriminate:
+ # set seed
+ torch.manual_seed(0)
+ noise = default(noise, lambda: torch.randn_like(x_start))
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+
+ #Override for debugging TODO: delete
+ # import pickle
+ # with open(os.path.expanduser("~/diffusion-itm/first_noise.pkl"), "rb") as f:
+ # noise = pickle.load(f)
+ # noise = noise.to(self.device).unsqueeze(0).repeat(x_start.shape[0], 1, 1, 1)
+ x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+
+ model_output = self.apply_model(x_noisy, t, cond)
+
+ loss_dict = {}
+ prefix = 'train' if self.training else 'val'
+
+ if self.parameterization == "x0":
+ target = x_start
+ elif self.parameterization == "eps":
+ target = noise
+ else:
+ raise NotImplementedError()
+
+ loss_simple = self.get_loss(model_output, target, mean=False).mean([1, 2, 3])
+ # loss_dict.update({f'{prefix}/loss_simple_list': loss_simple})
+ loss_dict.update({f'{prefix}/loss_simple': loss_simple.mean()})
+
+ logvar_t = self.logvar.to(self.device)[t]
+ loss = loss_simple / torch.exp(logvar_t) + logvar_t
+ # loss = loss_simple / torch.exp(self.logvar) + self.logvar
+ if self.learn_logvar:
+ loss_dict.update({f'{prefix}/loss_gamma': loss.mean()})
+ loss_dict.update({'logvar': self.logvar.data.mean()})
+
+ loss = self.l_simple_weight * loss.mean()
+
+ loss_vlb = self.get_loss(model_output, target, mean=False).mean(dim=(1, 2, 3))
+ loss_vlb = (self.lvlb_weights[t] * loss_vlb).mean()
+ loss_dict.update({f'{prefix}/loss_vlb': loss_vlb})
+ loss += (self.original_elbo_weight * loss_vlb)
+ loss_dict.update({f'{prefix}/loss': loss})
+
+ return loss, loss_dict
+
+ def p_mean_variance(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
+ return_x0=False, score_corrector=None, corrector_kwargs=None):
+ t_in = t
+ model_out = self.apply_model(x, t_in, c, return_ids=return_codebook_ids)
+
+ if score_corrector is not None:
+ assert self.parameterization == "eps"
+ model_out = score_corrector.modify_score(self, model_out, x, t, c, **corrector_kwargs)
+
+ if return_codebook_ids:
+ model_out, logits = model_out
+
+ if self.parameterization == "eps":
+ x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+ elif self.parameterization == "x0":
+ x_recon = model_out
+ else:
+ raise NotImplementedError()
+
+ if clip_denoised:
+ x_recon.clamp_(-1., 1.)
+ if quantize_denoised:
+ x_recon, _, [_, _, indices] = self.first_stage_model.quantize(x_recon)
+ model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+ if return_codebook_ids:
+ return model_mean, posterior_variance, posterior_log_variance, logits
+ elif return_x0:
+ return model_mean, posterior_variance, posterior_log_variance, x_recon
+ else:
+ return model_mean, posterior_variance, posterior_log_variance
+
+ @torch.no_grad()
+ def p_sample(self, x, c, t, clip_denoised=False, repeat_noise=False,
+ return_codebook_ids=False, quantize_denoised=False, return_x0=False,
+ temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None):
+ b, *_, device = *x.shape, x.device
+ outputs = self.p_mean_variance(x=x, c=c, t=t, clip_denoised=clip_denoised,
+ return_codebook_ids=return_codebook_ids,
+ quantize_denoised=quantize_denoised,
+ return_x0=return_x0,
+ score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+ if return_codebook_ids:
+ raise DeprecationWarning("Support dropped.")
+ model_mean, _, model_log_variance, logits = outputs
+ elif return_x0:
+ model_mean, _, model_log_variance, x0 = outputs
+ else:
+ model_mean, _, model_log_variance = outputs
+
+ noise = noise_like(x.shape, device, repeat_noise) * temperature
+ if noise_dropout > 0.:
+ noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+ # no noise when t == 0
+ nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+
+ if return_codebook_ids:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, logits.argmax(dim=1)
+ if return_x0:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, x0
+ else:
+ return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+ @torch.no_grad()
+ def progressive_denoising(self, cond, shape, verbose=True, callback=None, quantize_denoised=False,
+ img_callback=None, mask=None, x0=None, temperature=1., noise_dropout=0.,
+ score_corrector=None, corrector_kwargs=None, batch_size=None, x_T=None, start_T=None,
+ log_every_t=None):
+ if not log_every_t:
+ log_every_t = self.log_every_t
+ timesteps = self.num_timesteps
+ if batch_size is not None:
+ b = batch_size if batch_size is not None else shape[0]
+ shape = [batch_size] + list(shape)
+ else:
+ b = batch_size = shape[0]
+ if x_T is None:
+ img = torch.randn(shape, device=self.device)
+ else:
+ img = x_T
+ intermediates = []
+ if cond is not None:
+ if isinstance(cond, dict):
+ cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+ list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+ else:
+ cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+
+ if start_T is not None:
+ timesteps = min(timesteps, start_T)
+ iterator = tqdm(reversed(range(0, timesteps)), desc='Progressive Generation',
+ total=timesteps) if verbose else reversed(
+ range(0, timesteps))
+ if type(temperature) == float:
+ temperature = [temperature] * timesteps
+
+ for i in iterator:
+ ts = torch.full((b,), i, device=self.device, dtype=torch.long)
+ if self.shorten_cond_schedule:
+ assert self.model.conditioning_key != 'hybrid'
+ tc = self.cond_ids[ts].to(cond.device)
+ cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+ img, x0_partial = self.p_sample(img, cond, ts,
+ clip_denoised=self.clip_denoised,
+ quantize_denoised=quantize_denoised, return_x0=True,
+ temperature=temperature[i], noise_dropout=noise_dropout,
+ score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+ if mask is not None:
+ assert x0 is not None
+ img_orig = self.q_sample(x0, ts)
+ img = img_orig * mask + (1. - mask) * img
+
+ if i % log_every_t == 0 or i == timesteps - 1:
+ intermediates.append(x0_partial)
+ if callback: callback(i)
+ if img_callback: img_callback(img, i)
+ return img, intermediates
+
+ @torch.no_grad()
+ def p_sample_loop(self, cond, shape, return_intermediates=False,
+ x_T=None, verbose=True, callback=None, timesteps=None, quantize_denoised=False,
+ mask=None, x0=None, img_callback=None, start_T=None,
+ log_every_t=None):
+
+ if not log_every_t:
+ log_every_t = self.log_every_t
+ device = self.betas.device
+ b = shape[0]
+ if x_T is None:
+ img = torch.randn(shape, device=device)
+ else:
+ img = x_T
+
+ intermediates = [img]
+ if timesteps is None:
+ timesteps = self.num_timesteps
+
+ if start_T is not None:
+ timesteps = min(timesteps, start_T)
+ iterator = tqdm(reversed(range(0, timesteps)), desc='Sampling t', total=timesteps) if verbose else reversed(
+ range(0, timesteps))
+
+ if mask is not None:
+ assert x0 is not None
+ assert x0.shape[2:3] == mask.shape[2:3] # spatial size has to match
+
+ for i in iterator:
+ ts = torch.full((b,), i, device=device, dtype=torch.long)
+ if self.shorten_cond_schedule:
+ assert self.model.conditioning_key != 'hybrid'
+ tc = self.cond_ids[ts].to(cond.device)
+ cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+ img = self.p_sample(img, cond, ts,
+ clip_denoised=self.clip_denoised,
+ quantize_denoised=quantize_denoised)
+ if mask is not None:
+ img_orig = self.q_sample(x0, ts)
+ img = img_orig * mask + (1. - mask) * img
+
+ if i % log_every_t == 0 or i == timesteps - 1:
+ intermediates.append(img)
+ if callback: callback(i)
+ if img_callback: img_callback(img, i)
+
+ if return_intermediates:
+ return img, intermediates
+ return img
+
+ @torch.no_grad()
+ def sample(self, cond, batch_size=16, return_intermediates=False, x_T=None,
+ verbose=True, timesteps=None, quantize_denoised=False,
+ mask=None, x0=None, shape=None,**kwargs):
+ if shape is None:
+ shape = (batch_size, self.channels, self.image_size, self.image_size)
+ if cond is not None:
+ if isinstance(cond, dict):
+ cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+ list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+ else:
+ cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+ return self.p_sample_loop(cond,
+ shape,
+ return_intermediates=return_intermediates, x_T=x_T,
+ verbose=verbose, timesteps=timesteps, quantize_denoised=quantize_denoised,
+ mask=mask, x0=x0)
+
+ @torch.no_grad()
+ def sample_log(self,cond,batch_size,ddim, ddim_steps,**kwargs):
+
+ if ddim:
+ ddim_sampler = DDIMSampler(self)
+ shape = (self.channels, self.image_size, self.image_size)
+ samples, intermediates =ddim_sampler.sample(ddim_steps,batch_size,
+ shape,cond,verbose=False,**kwargs)
+
+ else:
+ samples, intermediates = self.sample(cond=cond, batch_size=batch_size,
+ return_intermediates=True,**kwargs)
+
+ return samples, intermediates
+
+
+ @torch.no_grad()
+ def log_images(self, batch, N=4, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
+ quantize_denoised=True, inpaint=False, plot_denoise_rows=False, plot_progressive_rows=False,
+ plot_diffusion_rows=False, **kwargs):
+
+ use_ddim = False
+
+ log = dict()
+ z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
+ return_first_stage_outputs=True,
+ force_c_encode=True,
+ return_original_cond=True,
+ bs=N, uncond=0)
+ N = min(x.shape[0], N)
+ n_row = min(x.shape[0], n_row)
+ log["inputs"] = x
+ log["reals"] = xc["c_concat"]
+ log["reconstruction"] = xrec
+ if self.model.conditioning_key is not None:
+ if hasattr(self.cond_stage_model, "decode"):
+ xc = self.cond_stage_model.decode(c)
+ log["conditioning"] = xc
+ elif self.cond_stage_key in ["caption"]:
+ xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["caption"])
+ log["conditioning"] = xc
+ elif self.cond_stage_key == 'class_label':
+ xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"])
+ log['conditioning'] = xc
+ elif isimage(xc):
+ log["conditioning"] = xc
+ if ismap(xc):
+ log["original_conditioning"] = self.to_rgb(xc)
+
+ if plot_diffusion_rows:
+ # get diffusion row
+ diffusion_row = list()
+ z_start = z[:n_row]
+ for t in range(self.num_timesteps):
+ if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+ t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+ t = t.to(self.device).long()
+ noise = torch.randn_like(z_start)
+ z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
+ diffusion_row.append(self.decode_first_stage(z_noisy))
+
+ diffusion_row = torch.stack(diffusion_row) # n_log_step, n_row, C, H, W
+ diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
+ diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
+ diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
+ log["diffusion_row"] = diffusion_grid
+
+ if sample:
+ # get denoise row
+ with self.ema_scope("Plotting"):
+ samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+ ddim_steps=ddim_steps,eta=ddim_eta)
+ # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
+ x_samples = self.decode_first_stage(samples)
+ log["samples"] = x_samples
+ if plot_denoise_rows:
+ denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
+ log["denoise_row"] = denoise_grid
+
+ if quantize_denoised and not isinstance(self.first_stage_model, AutoencoderKL) and not isinstance(
+ self.first_stage_model, IdentityFirstStage):
+ # also display when quantizing x0 while sampling
+ with self.ema_scope("Plotting Quantized Denoised"):
+ samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+ ddim_steps=ddim_steps,eta=ddim_eta,
+ quantize_denoised=True)
+ # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True,
+ # quantize_denoised=True)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_x0_quantized"] = x_samples
+
+ if inpaint:
+ # make a simple center square
+ b, h, w = z.shape[0], z.shape[2], z.shape[3]
+ mask = torch.ones(N, h, w).to(self.device)
+ # zeros will be filled in
+ mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
+ mask = mask[:, None, ...]
+ with self.ema_scope("Plotting Inpaint"):
+
+ samples, _ = self.sample_log(cond=c,batch_size=N,ddim=use_ddim, eta=ddim_eta,
+ ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_inpainting"] = x_samples
+ log["mask"] = mask
+
+ # outpaint
+ with self.ema_scope("Plotting Outpaint"):
+ samples, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,eta=ddim_eta,
+ ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+ x_samples = self.decode_first_stage(samples.to(self.device))
+ log["samples_outpainting"] = x_samples
+
+ if plot_progressive_rows:
+ with self.ema_scope("Plotting Progressives"):
+ img, progressives = self.progressive_denoising(c,
+ shape=(self.channels, self.image_size, self.image_size),
+ batch_size=N)
+ prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
+ log["progressive_row"] = prog_row
+
+ if return_keys:
+ if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+ return log
+ else:
+ return {key: log[key] for key in return_keys}
+ return log
+
+ def configure_optimizers(self):
+ lr = self.learning_rate
+ params = list(self.model.parameters())
+ if self.cond_stage_trainable:
+ print(f"{self.__class__.__name__}: Also optimizing conditioner params!")
+ params = params + list(self.cond_stage_model.parameters())
+ if self.learn_logvar:
+ print('Diffusion model optimizing logvar')
+ params.append(self.logvar)
+ opt = torch.optim.AdamW(params, lr=lr)
+ if self.use_scheduler:
+ assert 'target' in self.scheduler_config
+ scheduler = instantiate_from_config(self.scheduler_config)
+
+ print("Setting up LambdaLR scheduler...")
+ scheduler = [
+ {
+ 'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule),
+ 'interval': 'step',
+ 'frequency': 1
+ }]
+ return [opt], scheduler
+ return opt
+
+ @torch.no_grad()
+ def to_rgb(self, x):
+ x = x.float()
+ if not hasattr(self, "colorize"):
+ self.colorize = torch.randn(3, x.shape[1], 1, 1).to(x)
+ x = nn.functional.conv2d(x, weight=self.colorize)
+ x = 2. * (x - x.min()) / (x.max() - x.min()) - 1.
+ return x
+
+
+class DiffusionWrapper(pl.LightningModule):
+ def __init__(self, diff_model_config, conditioning_key):
+ super().__init__()
+ self.diffusion_model = instantiate_from_config(diff_model_config)
+ self.conditioning_key = conditioning_key
+ assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm']
+
+ def forward(self, x, t, c_concat: list = None, c_crossattn: list = None):
+ if self.conditioning_key is None:
+ out = self.diffusion_model(x, t)
+ elif self.conditioning_key == 'concat':
+ xc = torch.cat([x] + c_concat, dim=1)
+ out = self.diffusion_model(xc, t)
+ elif self.conditioning_key == 'crossattn':
+ cc = torch.cat(c_crossattn, 1)
+ out = self.diffusion_model(x, t, context=cc)
+ elif self.conditioning_key == 'hybrid':
+ xc = torch.cat([x] + c_concat, dim=1)
+ cc = torch.cat(c_crossattn, 1)
+ out = self.diffusion_model(xc, t, context=cc)
+ elif self.conditioning_key == 'adm':
+ cc = c_crossattn[0]
+ out = self.diffusion_model(x, t, y=cc)
+ else:
+ raise NotImplementedError()
+
+ return out
+
+
+class Layout2ImgDiffusion(LatentDiffusion):
+ # TODO: move all layout-specific hacks to this class
+ def __init__(self, cond_stage_key, *args, **kwargs):
+ assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
+ super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+
+ def log_images(self, batch, N=8, *args, **kwargs):
+ logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+
+ key = 'train' if self.training else 'validation'
+ dset = self.trainer.datamodule.datasets[key]
+ mapper = dset.conditional_builders[self.cond_stage_key]
+
+ bbox_imgs = []
+ map_fn = lambda catno: dset.get_textual_label(dset.get_category_id(catno))
+ for tknzd_bbox in batch[self.cond_stage_key][:N]:
+ bboximg = mapper.plot(tknzd_bbox.detach().cpu(), map_fn, (256, 256))
+ bbox_imgs.append(bboximg)
+
+ cond_img = torch.stack(bbox_imgs, dim=0)
+ logs['bbox_image'] = cond_img
+ return logs
diff --git a/stable_diffusion/ldm/models/diffusion/dpm_solver/__init__.py b/stable_diffusion/ldm/models/diffusion/dpm_solver/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..7427f38c07530afbab79154ea8aaf88c4bf70a08
--- /dev/null
+++ b/stable_diffusion/ldm/models/diffusion/dpm_solver/__init__.py
@@ -0,0 +1 @@
+from .sampler import DPMSolverSampler
\ No newline at end of file
diff --git a/stable_diffusion/ldm/models/diffusion/dpm_solver/dpm_solver.py b/stable_diffusion/ldm/models/diffusion/dpm_solver/dpm_solver.py
new file mode 100644
index 0000000000000000000000000000000000000000..bdb64e0c78cc3520f92d79db3124c85fc3cfb9b4
--- /dev/null
+++ b/stable_diffusion/ldm/models/diffusion/dpm_solver/dpm_solver.py
@@ -0,0 +1,1184 @@
+import torch
+import torch.nn.functional as F
+import math
+
+
+class NoiseScheduleVP:
+ def __init__(
+ self,
+ schedule='discrete',
+ betas=None,
+ alphas_cumprod=None,
+ continuous_beta_0=0.1,
+ continuous_beta_1=20.,
+ ):
+ """Create a wrapper class for the forward SDE (VP type).
+
+ ***
+ Update: We support discrete-time diffusion models by implementing a picewise linear interpolation for log_alpha_t.
+ We recommend to use schedule='discrete' for the discrete-time diffusion models, especially for high-resolution images.
+ ***
+
+ The forward SDE ensures that the condition distribution q_{t|0}(x_t | x_0) = N ( alpha_t * x_0, sigma_t^2 * I ).
+ We further define lambda_t = log(alpha_t) - log(sigma_t), which is the half-logSNR (described in the DPM-Solver paper).
+ Therefore, we implement the functions for computing alpha_t, sigma_t and lambda_t. For t in [0, T], we have:
+
+ log_alpha_t = self.marginal_log_mean_coeff(t)
+ sigma_t = self.marginal_std(t)
+ lambda_t = self.marginal_lambda(t)
+
+ Moreover, as lambda(t) is an invertible function, we also support its inverse function:
+
+ t = self.inverse_lambda(lambda_t)
+
+ ===============================================================
+
+ We support both discrete-time DPMs (trained on n = 0, 1, ..., N-1) and continuous-time DPMs (trained on t in [t_0, T]).
+
+ 1. For discrete-time DPMs:
+
+ For discrete-time DPMs trained on n = 0, 1, ..., N-1, we convert the discrete steps to continuous time steps by:
+ t_i = (i + 1) / N
+ e.g. for N = 1000, we have t_0 = 1e-3 and T = t_{N-1} = 1.
+ We solve the corresponding diffusion ODE from time T = 1 to time t_0 = 1e-3.
+
+ Args:
+ betas: A `torch.Tensor`. The beta array for the discrete-time DPM. (See the original DDPM paper for details)
+ alphas_cumprod: A `torch.Tensor`. The cumprod alphas for the discrete-time DPM. (See the original DDPM paper for details)
+
+ Note that we always have alphas_cumprod = cumprod(betas). Therefore, we only need to set one of `betas` and `alphas_cumprod`.
+
+ **Important**: Please pay special attention for the args for `alphas_cumprod`:
+ The `alphas_cumprod` is the \hat{alpha_n} arrays in the notations of DDPM. Specifically, DDPMs assume that
+ q_{t_n | 0}(x_{t_n} | x_0) = N ( \sqrt{\hat{alpha_n}} * x_0, (1 - \hat{alpha_n}) * I ).
+ Therefore, the notation \hat{alpha_n} is different from the notation alpha_t in DPM-Solver. In fact, we have
+ alpha_{t_n} = \sqrt{\hat{alpha_n}},
+ and
+ log(alpha_{t_n}) = 0.5 * log(\hat{alpha_n}).
+
+
+ 2. For continuous-time DPMs:
+
+ We support two types of VPSDEs: linear (DDPM) and cosine (improved-DDPM). The hyperparameters for the noise
+ schedule are the default settings in DDPM and improved-DDPM:
+
+ Args:
+ beta_min: A `float` number. The smallest beta for the linear schedule.
+ beta_max: A `float` number. The largest beta for the linear schedule.
+ cosine_s: A `float` number. The hyperparameter in the cosine schedule.
+ cosine_beta_max: A `float` number. The hyperparameter in the cosine schedule.
+ T: A `float` number. The ending time of the forward process.
+
+ ===============================================================
+
+ Args:
+ schedule: A `str`. The noise schedule of the forward SDE. 'discrete' for discrete-time DPMs,
+ 'linear' or 'cosine' for continuous-time DPMs.
+ Returns:
+ A wrapper object of the forward SDE (VP type).
+
+ ===============================================================
+
+ Example:
+
+ # For discrete-time DPMs, given betas (the beta array for n = 0, 1, ..., N - 1):
+ >>> ns = NoiseScheduleVP('discrete', betas=betas)
+
+ # For discrete-time DPMs, given alphas_cumprod (the \hat{alpha_n} array for n = 0, 1, ..., N - 1):
+ >>> ns = NoiseScheduleVP('discrete', alphas_cumprod=alphas_cumprod)
+
+ # For continuous-time DPMs (VPSDE), linear schedule:
+ >>> ns = NoiseScheduleVP('linear', continuous_beta_0=0.1, continuous_beta_1=20.)
+
+ """
+
+ if schedule not in ['discrete', 'linear', 'cosine']:
+ raise ValueError("Unsupported noise schedule {}. The schedule needs to be 'discrete' or 'linear' or 'cosine'".format(schedule))
+
+ self.schedule = schedule
+ if schedule == 'discrete':
+ if betas is not None:
+ log_alphas = 0.5 * torch.log(1 - betas).cumsum(dim=0)
+ else:
+ assert alphas_cumprod is not None
+ log_alphas = 0.5 * torch.log(alphas_cumprod)
+ self.total_N = len(log_alphas)
+ self.T = 1.
+ self.t_array = torch.linspace(0., 1., self.total_N + 1)[1:].reshape((1, -1))
+ self.log_alpha_array = log_alphas.reshape((1, -1,))
+ else:
+ self.total_N = 1000
+ self.beta_0 = continuous_beta_0
+ self.beta_1 = continuous_beta_1
+ self.cosine_s = 0.008
+ self.cosine_beta_max = 999.
+ self.cosine_t_max = math.atan(self.cosine_beta_max * (1. + self.cosine_s) / math.pi) * 2. * (1. + self.cosine_s) / math.pi - self.cosine_s
+ self.cosine_log_alpha_0 = math.log(math.cos(self.cosine_s / (1. + self.cosine_s) * math.pi / 2.))
+ self.schedule = schedule
+ if schedule == 'cosine':
+ # For the cosine schedule, T = 1 will have numerical issues. So we manually set the ending time T.
+ # Note that T = 0.9946 may be not the optimal setting. However, we find it works well.
+ self.T = 0.9946
+ else:
+ self.T = 1.
+
+ def marginal_log_mean_coeff(self, t):
+ """
+ Compute log(alpha_t) of a given continuous-time label t in [0, T].
+ """
+ if self.schedule == 'discrete':
+ return interpolate_fn(t.reshape((-1, 1)), self.t_array.to(t.device), self.log_alpha_array.to(t.device)).reshape((-1))
+ elif self.schedule == 'linear':
+ return -0.25 * t ** 2 * (self.beta_1 - self.beta_0) - 0.5 * t * self.beta_0
+ elif self.schedule == 'cosine':
+ log_alpha_fn = lambda s: torch.log(torch.cos((s + self.cosine_s) / (1. + self.cosine_s) * math.pi / 2.))
+ log_alpha_t = log_alpha_fn(t) - self.cosine_log_alpha_0
+ return log_alpha_t
+
+ def marginal_alpha(self, t):
+ """
+ Compute alpha_t of a given continuous-time label t in [0, T].
+ """
+ return torch.exp(self.marginal_log_mean_coeff(t))
+
+ def marginal_std(self, t):
+ """
+ Compute sigma_t of a given continuous-time label t in [0, T].
+ """
+ return torch.sqrt(1. - torch.exp(2. * self.marginal_log_mean_coeff(t)))
+
+ def marginal_lambda(self, t):
+ """
+ Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].
+ """
+ log_mean_coeff = self.marginal_log_mean_coeff(t)
+ log_std = 0.5 * torch.log(1. - torch.exp(2. * log_mean_coeff))
+ return log_mean_coeff - log_std
+
+ def inverse_lambda(self, lamb):
+ """
+ Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t.
+ """
+ if self.schedule == 'linear':
+ tmp = 2. * (self.beta_1 - self.beta_0) * torch.logaddexp(-2. * lamb, torch.zeros((1,)).to(lamb))
+ Delta = self.beta_0**2 + tmp
+ return tmp / (torch.sqrt(Delta) + self.beta_0) / (self.beta_1 - self.beta_0)
+ elif self.schedule == 'discrete':
+ log_alpha = -0.5 * torch.logaddexp(torch.zeros((1,)).to(lamb.device), -2. * lamb)
+ t = interpolate_fn(log_alpha.reshape((-1, 1)), torch.flip(self.log_alpha_array.to(lamb.device), [1]), torch.flip(self.t_array.to(lamb.device), [1]))
+ return t.reshape((-1,))
+ else:
+ log_alpha = -0.5 * torch.logaddexp(-2. * lamb, torch.zeros((1,)).to(lamb))
+ t_fn = lambda log_alpha_t: torch.arccos(torch.exp(log_alpha_t + self.cosine_log_alpha_0)) * 2. * (1. + self.cosine_s) / math.pi - self.cosine_s
+ t = t_fn(log_alpha)
+ return t
+
+
+def model_wrapper(
+ model,
+ noise_schedule,
+ model_type="noise",
+ model_kwargs={},
+ guidance_type="uncond",
+ condition=None,
+ unconditional_condition=None,
+ guidance_scale=1.,
+ classifier_fn=None,
+ classifier_kwargs={},
+):
+ """Create a wrapper function for the noise prediction model.
+
+ DPM-Solver needs to solve the continuous-time diffusion ODEs. For DPMs trained on discrete-time labels, we need to
+ firstly wrap the model function to a noise prediction model that accepts the continuous time as the input.
+
+ We support four types of the diffusion model by setting `model_type`:
+
+ 1. "noise": noise prediction model. (Trained by predicting noise).
+
+ 2. "x_start": data prediction model. (Trained by predicting the data x_0 at time 0).
+
+ 3. "v": velocity prediction model. (Trained by predicting the velocity).
+ The "v" prediction is derivation detailed in Appendix D of [1], and is used in Imagen-Video [2].
+
+ [1] Salimans, Tim, and Jonathan Ho. "Progressive distillation for fast sampling of diffusion models."
+ arXiv preprint arXiv:2202.00512 (2022).
+ [2] Ho, Jonathan, et al. "Imagen Video: High Definition Video Generation with Diffusion Models."
+ arXiv preprint arXiv:2210.02303 (2022).
+
+ 4. "score": marginal score function. (Trained by denoising score matching).
+ Note that the score function and the noise prediction model follows a simple relationship:
+ ```
+ noise(x_t, t) = -sigma_t * score(x_t, t)
+ ```
+
+ We support three types of guided sampling by DPMs by setting `guidance_type`:
+ 1. "uncond": unconditional sampling by DPMs.
+ The input `model` has the following format:
+ ``
+ model(x, t_input, **model_kwargs) -> noise | x_start | v | score
+ ``
+
+ 2. "classifier": classifier guidance sampling [3] by DPMs and another classifier.
+ The input `model` has the following format:
+ ``
+ model(x, t_input, **model_kwargs) -> noise | x_start | v | score
+ ``
+
+ The input `classifier_fn` has the following format:
+ ``
+ classifier_fn(x, t_input, cond, **classifier_kwargs) -> logits(x, t_input, cond)
+ ``
+
+ [3] P. Dhariwal and A. Q. Nichol, "Diffusion models beat GANs on image synthesis,"
+ in Advances in Neural Information Processing Systems, vol. 34, 2021, pp. 8780-8794.
+
+ 3. "classifier-free": classifier-free guidance sampling by conditional DPMs.
+ The input `model` has the following format:
+ ``
+ model(x, t_input, cond, **model_kwargs) -> noise | x_start | v | score
+ ``
+ And if cond == `unconditional_condition`, the model output is the unconditional DPM output.
+
+ [4] Ho, Jonathan, and Tim Salimans. "Classifier-free diffusion guidance."
+ arXiv preprint arXiv:2207.12598 (2022).
+
+
+ The `t_input` is the time label of the model, which may be discrete-time labels (i.e. 0 to 999)
+ or continuous-time labels (i.e. epsilon to T).
+
+ We wrap the model function to accept only `x` and `t_continuous` as inputs, and outputs the predicted noise:
+ ``
+ def model_fn(x, t_continuous) -> noise:
+ t_input = get_model_input_time(t_continuous)
+ return noise_pred(model, x, t_input, **model_kwargs)
+ ``
+ where `t_continuous` is the continuous time labels (i.e. epsilon to T). And we use `model_fn` for DPM-Solver.
+
+ ===============================================================
+
+ Args:
+ model: A diffusion model with the corresponding format described above.
+ noise_schedule: A noise schedule object, such as NoiseScheduleVP.
+ model_type: A `str`. The parameterization type of the diffusion model.
+ "noise" or "x_start" or "v" or "score".
+ model_kwargs: A `dict`. A dict for the other inputs of the model function.
+ guidance_type: A `str`. The type of the guidance for sampling.
+ "uncond" or "classifier" or "classifier-free".
+ condition: A pytorch tensor. The condition for the guided sampling.
+ Only used for "classifier" or "classifier-free" guidance type.
+ unconditional_condition: A pytorch tensor. The condition for the unconditional sampling.
+ Only used for "classifier-free" guidance type.
+ guidance_scale: A `float`. The scale for the guided sampling.
+ classifier_fn: A classifier function. Only used for the classifier guidance.
+ classifier_kwargs: A `dict`. A dict for the other inputs of the classifier function.
+ Returns:
+ A noise prediction model that accepts the noised data and the continuous time as the inputs.
+ """
+
+ def get_model_input_time(t_continuous):
+ """
+ Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time.
+ For discrete-time DPMs, we convert `t_continuous` in [1 / N, 1] to `t_input` in [0, 1000 * (N - 1) / N].
+ For continuous-time DPMs, we just use `t_continuous`.
+ """
+ if noise_schedule.schedule == 'discrete':
+ return (t_continuous - 1. / noise_schedule.total_N) * 1000.
+ else:
+ return t_continuous
+
+ def noise_pred_fn(x, t_continuous, cond=None):
+ if t_continuous.reshape((-1,)).shape[0] == 1:
+ t_continuous = t_continuous.expand((x.shape[0]))
+ t_input = get_model_input_time(t_continuous)
+ if cond is None:
+ output = model(x, t_input, **model_kwargs)
+ else:
+ output = model(x, t_input, cond, **model_kwargs)
+ if model_type == "noise":
+ return output
+ elif model_type == "x_start":
+ alpha_t, sigma_t = noise_schedule.marginal_alpha(t_continuous), noise_schedule.marginal_std(t_continuous)
+ dims = x.dim()
+ return (x - expand_dims(alpha_t, dims) * output) / expand_dims(sigma_t, dims)
+ elif model_type == "v":
+ alpha_t, sigma_t = noise_schedule.marginal_alpha(t_continuous), noise_schedule.marginal_std(t_continuous)
+ dims = x.dim()
+ return expand_dims(alpha_t, dims) * output + expand_dims(sigma_t, dims) * x
+ elif model_type == "score":
+ sigma_t = noise_schedule.marginal_std(t_continuous)
+ dims = x.dim()
+ return -expand_dims(sigma_t, dims) * output
+
+ def cond_grad_fn(x, t_input):
+ """
+ Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).
+ """
+ with torch.enable_grad():
+ x_in = x.detach().requires_grad_(True)
+ log_prob = classifier_fn(x_in, t_input, condition, **classifier_kwargs)
+ return torch.autograd.grad(log_prob.sum(), x_in)[0]
+
+ def model_fn(x, t_continuous):
+ """
+ The noise predicition model function that is used for DPM-Solver.
+ """
+ if t_continuous.reshape((-1,)).shape[0] == 1:
+ t_continuous = t_continuous.expand((x.shape[0]))
+ if guidance_type == "uncond":
+ return noise_pred_fn(x, t_continuous)
+ elif guidance_type == "classifier":
+ assert classifier_fn is not None
+ t_input = get_model_input_time(t_continuous)
+ cond_grad = cond_grad_fn(x, t_input)
+ sigma_t = noise_schedule.marginal_std(t_continuous)
+ noise = noise_pred_fn(x, t_continuous)
+ return noise - guidance_scale * expand_dims(sigma_t, dims=cond_grad.dim()) * cond_grad
+ elif guidance_type == "classifier-free":
+ if guidance_scale == 1. or unconditional_condition is None:
+ return noise_pred_fn(x, t_continuous, cond=condition)
+ else:
+ x_in = torch.cat([x] * 2)
+ t_in = torch.cat([t_continuous] * 2)
+ c_in = torch.cat([unconditional_condition, condition])
+ noise_uncond, noise = noise_pred_fn(x_in, t_in, cond=c_in).chunk(2)
+ return noise_uncond + guidance_scale * (noise - noise_uncond)
+
+ assert model_type in ["noise", "x_start", "v"]
+ assert guidance_type in ["uncond", "classifier", "classifier-free"]
+ return model_fn
+
+
+class DPM_Solver:
+ def __init__(self, model_fn, noise_schedule, predict_x0=False, thresholding=False, max_val=1.):
+ """Construct a DPM-Solver.
+
+ We support both the noise prediction model ("predicting epsilon") and the data prediction model ("predicting x0").
+ If `predict_x0` is False, we use the solver for the noise prediction model (DPM-Solver).
+ If `predict_x0` is True, we use the solver for the data prediction model (DPM-Solver++).
+ In such case, we further support the "dynamic thresholding" in [1] when `thresholding` is True.
+ The "dynamic thresholding" can greatly improve the sample quality for pixel-space DPMs with large guidance scales.
+
+ Args:
+ model_fn: A noise prediction model function which accepts the continuous-time input (t in [epsilon, T]):
+ ``
+ def model_fn(x, t_continuous):
+ return noise
+ ``
+ noise_schedule: A noise schedule object, such as NoiseScheduleVP.
+ predict_x0: A `bool`. If true, use the data prediction model; else, use the noise prediction model.
+ thresholding: A `bool`. Valid when `predict_x0` is True. Whether to use the "dynamic thresholding" in [1].
+ max_val: A `float`. Valid when both `predict_x0` and `thresholding` are True. The max value for thresholding.
+
+ [1] Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S Sara Mahdavi, Rapha Gontijo Lopes, et al. Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487, 2022b.
+ """
+ self.model = model_fn
+ self.noise_schedule = noise_schedule
+ self.predict_x0 = predict_x0
+ self.thresholding = thresholding
+ self.max_val = max_val
+
+ def noise_prediction_fn(self, x, t):
+ """
+ Return the noise prediction model.
+ """
+ return self.model(x, t)
+
+ def data_prediction_fn(self, x, t):
+ """
+ Return the data prediction model (with thresholding).
+ """
+ noise = self.noise_prediction_fn(x, t)
+ dims = x.dim()
+ alpha_t, sigma_t = self.noise_schedule.marginal_alpha(t), self.noise_schedule.marginal_std(t)
+ x0 = (x - expand_dims(sigma_t, dims) * noise) / expand_dims(alpha_t, dims)
+ if self.thresholding:
+ p = 0.995 # A hyperparameter in the paper of "Imagen" [1].
+ s = torch.quantile(torch.abs(x0).reshape((x0.shape[0], -1)), p, dim=1)
+ s = expand_dims(torch.maximum(s, self.max_val * torch.ones_like(s).to(s.device)), dims)
+ x0 = torch.clamp(x0, -s, s) / s
+ return x0
+
+ def model_fn(self, x, t):
+ """
+ Convert the model to the noise prediction model or the data prediction model.
+ """
+ if self.predict_x0:
+ return self.data_prediction_fn(x, t)
+ else:
+ return self.noise_prediction_fn(x, t)
+
+ def get_time_steps(self, skip_type, t_T, t_0, N, device):
+ """Compute the intermediate time steps for sampling.
+
+ Args:
+ skip_type: A `str`. The type for the spacing of the time steps. We support three types:
+ - 'logSNR': uniform logSNR for the time steps.
+ - 'time_uniform': uniform time for the time steps. (**Recommended for high-resolutional data**.)
+ - 'time_quadratic': quadratic time for the time steps. (Used in DDIM for low-resolutional data.)
+ t_T: A `float`. The starting time of the sampling (default is T).
+ t_0: A `float`. The ending time of the sampling (default is epsilon).
+ N: A `int`. The total number of the spacing of the time steps.
+ device: A torch device.
+ Returns:
+ A pytorch tensor of the time steps, with the shape (N + 1,).
+ """
+ if skip_type == 'logSNR':
+ lambda_T = self.noise_schedule.marginal_lambda(torch.tensor(t_T).to(device))
+ lambda_0 = self.noise_schedule.marginal_lambda(torch.tensor(t_0).to(device))
+ logSNR_steps = torch.linspace(lambda_T.cpu().item(), lambda_0.cpu().item(), N + 1).to(device)
+ return self.noise_schedule.inverse_lambda(logSNR_steps)
+ elif skip_type == 'time_uniform':
+ return torch.linspace(t_T, t_0, N + 1).to(device)
+ elif skip_type == 'time_quadratic':
+ t_order = 2
+ t = torch.linspace(t_T**(1. / t_order), t_0**(1. / t_order), N + 1).pow(t_order).to(device)
+ return t
+ else:
+ raise ValueError("Unsupported skip_type {}, need to be 'logSNR' or 'time_uniform' or 'time_quadratic'".format(skip_type))
+
+ def get_orders_and_timesteps_for_singlestep_solver(self, steps, order, skip_type, t_T, t_0, device):
+ """
+ Get the order of each step for sampling by the singlestep DPM-Solver.
+
+ We combine both DPM-Solver-1,2,3 to use all the function evaluations, which is named as "DPM-Solver-fast".
+ Given a fixed number of function evaluations by `steps`, the sampling procedure by DPM-Solver-fast is:
+ - If order == 1:
+ We take `steps` of DPM-Solver-1 (i.e. DDIM).
+ - If order == 2:
+ - Denote K = (steps // 2). We take K or (K + 1) intermediate time steps for sampling.
+ - If steps % 2 == 0, we use K steps of DPM-Solver-2.
+ - If steps % 2 == 1, we use K steps of DPM-Solver-2 and 1 step of DPM-Solver-1.
+ - If order == 3:
+ - Denote K = (steps // 3 + 1). We take K intermediate time steps for sampling.
+ - If steps % 3 == 0, we use (K - 2) steps of DPM-Solver-3, and 1 step of DPM-Solver-2 and 1 step of DPM-Solver-1.
+ - If steps % 3 == 1, we use (K - 1) steps of DPM-Solver-3 and 1 step of DPM-Solver-1.
+ - If steps % 3 == 2, we use (K - 1) steps of DPM-Solver-3 and 1 step of DPM-Solver-2.
+
+ ============================================
+ Args:
+ order: A `int`. The max order for the solver (2 or 3).
+ steps: A `int`. The total number of function evaluations (NFE).
+ skip_type: A `str`. The type for the spacing of the time steps. We support three types:
+ - 'logSNR': uniform logSNR for the time steps.
+ - 'time_uniform': uniform time for the time steps. (**Recommended for high-resolutional data**.)
+ - 'time_quadratic': quadratic time for the time steps. (Used in DDIM for low-resolutional data.)
+ t_T: A `float`. The starting time of the sampling (default is T).
+ t_0: A `float`. The ending time of the sampling (default is epsilon).
+ device: A torch device.
+ Returns:
+ orders: A list of the solver order of each step.
+ """
+ if order == 3:
+ K = steps // 3 + 1
+ if steps % 3 == 0:
+ orders = [3,] * (K - 2) + [2, 1]
+ elif steps % 3 == 1:
+ orders = [3,] * (K - 1) + [1]
+ else:
+ orders = [3,] * (K - 1) + [2]
+ elif order == 2:
+ if steps % 2 == 0:
+ K = steps // 2
+ orders = [2,] * K
+ else:
+ K = steps // 2 + 1
+ orders = [2,] * (K - 1) + [1]
+ elif order == 1:
+ K = 1
+ orders = [1,] * steps
+ else:
+ raise ValueError("'order' must be '1' or '2' or '3'.")
+ if skip_type == 'logSNR':
+ # To reproduce the results in DPM-Solver paper
+ timesteps_outer = self.get_time_steps(skip_type, t_T, t_0, K, device)
+ else:
+ timesteps_outer = self.get_time_steps(skip_type, t_T, t_0, steps, device)[torch.cumsum(torch.tensor([0,] + orders)).to(device)]
+ return timesteps_outer, orders
+
+ def denoise_to_zero_fn(self, x, s):
+ """
+ Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization.
+ """
+ return self.data_prediction_fn(x, s)
+
+ def dpm_solver_first_update(self, x, s, t, model_s=None, return_intermediate=False):
+ """
+ DPM-Solver-1 (equivalent to DDIM) from time `s` to time `t`.
+
+ Args:
+ x: A pytorch tensor. The initial value at time `s`.
+ s: A pytorch tensor. The starting time, with the shape (x.shape[0],).
+ t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+ model_s: A pytorch tensor. The model function evaluated at time `s`.
+ If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it.
+ return_intermediate: A `bool`. If true, also return the model value at time `s`.
+ Returns:
+ x_t: A pytorch tensor. The approximated solution at time `t`.
+ """
+ ns = self.noise_schedule
+ dims = x.dim()
+ lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t)
+ h = lambda_t - lambda_s
+ log_alpha_s, log_alpha_t = ns.marginal_log_mean_coeff(s), ns.marginal_log_mean_coeff(t)
+ sigma_s, sigma_t = ns.marginal_std(s), ns.marginal_std(t)
+ alpha_t = torch.exp(log_alpha_t)
+
+ if self.predict_x0:
+ phi_1 = torch.expm1(-h)
+ if model_s is None:
+ model_s = self.model_fn(x, s)
+ x_t = (
+ expand_dims(sigma_t / sigma_s, dims) * x
+ - expand_dims(alpha_t * phi_1, dims) * model_s
+ )
+ if return_intermediate:
+ return x_t, {'model_s': model_s}
+ else:
+ return x_t
+ else:
+ phi_1 = torch.expm1(h)
+ if model_s is None:
+ model_s = self.model_fn(x, s)
+ x_t = (
+ expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+ - expand_dims(sigma_t * phi_1, dims) * model_s
+ )
+ if return_intermediate:
+ return x_t, {'model_s': model_s}
+ else:
+ return x_t
+
+ def singlestep_dpm_solver_second_update(self, x, s, t, r1=0.5, model_s=None, return_intermediate=False, solver_type='dpm_solver'):
+ """
+ Singlestep solver DPM-Solver-2 from time `s` to time `t`.
+
+ Args:
+ x: A pytorch tensor. The initial value at time `s`.
+ s: A pytorch tensor. The starting time, with the shape (x.shape[0],).
+ t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+ r1: A `float`. The hyperparameter of the second-order solver.
+ model_s: A pytorch tensor. The model function evaluated at time `s`.
+ If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it.
+ return_intermediate: A `bool`. If true, also return the model value at time `s` and `s1` (the intermediate time).
+ solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+ The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+ Returns:
+ x_t: A pytorch tensor. The approximated solution at time `t`.
+ """
+ if solver_type not in ['dpm_solver', 'taylor']:
+ raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type))
+ if r1 is None:
+ r1 = 0.5
+ ns = self.noise_schedule
+ dims = x.dim()
+ lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t)
+ h = lambda_t - lambda_s
+ lambda_s1 = lambda_s + r1 * h
+ s1 = ns.inverse_lambda(lambda_s1)
+ log_alpha_s, log_alpha_s1, log_alpha_t = ns.marginal_log_mean_coeff(s), ns.marginal_log_mean_coeff(s1), ns.marginal_log_mean_coeff(t)
+ sigma_s, sigma_s1, sigma_t = ns.marginal_std(s), ns.marginal_std(s1), ns.marginal_std(t)
+ alpha_s1, alpha_t = torch.exp(log_alpha_s1), torch.exp(log_alpha_t)
+
+ if self.predict_x0:
+ phi_11 = torch.expm1(-r1 * h)
+ phi_1 = torch.expm1(-h)
+
+ if model_s is None:
+ model_s = self.model_fn(x, s)
+ x_s1 = (
+ expand_dims(sigma_s1 / sigma_s, dims) * x
+ - expand_dims(alpha_s1 * phi_11, dims) * model_s
+ )
+ model_s1 = self.model_fn(x_s1, s1)
+ if solver_type == 'dpm_solver':
+ x_t = (
+ expand_dims(sigma_t / sigma_s, dims) * x
+ - expand_dims(alpha_t * phi_1, dims) * model_s
+ - (0.5 / r1) * expand_dims(alpha_t * phi_1, dims) * (model_s1 - model_s)
+ )
+ elif solver_type == 'taylor':
+ x_t = (
+ expand_dims(sigma_t / sigma_s, dims) * x
+ - expand_dims(alpha_t * phi_1, dims) * model_s
+ + (1. / r1) * expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * (model_s1 - model_s)
+ )
+ else:
+ phi_11 = torch.expm1(r1 * h)
+ phi_1 = torch.expm1(h)
+
+ if model_s is None:
+ model_s = self.model_fn(x, s)
+ x_s1 = (
+ expand_dims(torch.exp(log_alpha_s1 - log_alpha_s), dims) * x
+ - expand_dims(sigma_s1 * phi_11, dims) * model_s
+ )
+ model_s1 = self.model_fn(x_s1, s1)
+ if solver_type == 'dpm_solver':
+ x_t = (
+ expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+ - expand_dims(sigma_t * phi_1, dims) * model_s
+ - (0.5 / r1) * expand_dims(sigma_t * phi_1, dims) * (model_s1 - model_s)
+ )
+ elif solver_type == 'taylor':
+ x_t = (
+ expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+ - expand_dims(sigma_t * phi_1, dims) * model_s
+ - (1. / r1) * expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * (model_s1 - model_s)
+ )
+ if return_intermediate:
+ return x_t, {'model_s': model_s, 'model_s1': model_s1}
+ else:
+ return x_t
+
+ def singlestep_dpm_solver_third_update(self, x, s, t, r1=1./3., r2=2./3., model_s=None, model_s1=None, return_intermediate=False, solver_type='dpm_solver'):
+ """
+ Singlestep solver DPM-Solver-3 from time `s` to time `t`.
+
+ Args:
+ x: A pytorch tensor. The initial value at time `s`.
+ s: A pytorch tensor. The starting time, with the shape (x.shape[0],).
+ t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+ r1: A `float`. The hyperparameter of the third-order solver.
+ r2: A `float`. The hyperparameter of the third-order solver.
+ model_s: A pytorch tensor. The model function evaluated at time `s`.
+ If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it.
+ model_s1: A pytorch tensor. The model function evaluated at time `s1` (the intermediate time given by `r1`).
+ If `model_s1` is None, we evaluate the model at `s1`; otherwise we directly use it.
+ return_intermediate: A `bool`. If true, also return the model value at time `s`, `s1` and `s2` (the intermediate times).
+ solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+ The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+ Returns:
+ x_t: A pytorch tensor. The approximated solution at time `t`.
+ """
+ if solver_type not in ['dpm_solver', 'taylor']:
+ raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type))
+ if r1 is None:
+ r1 = 1. / 3.
+ if r2 is None:
+ r2 = 2. / 3.
+ ns = self.noise_schedule
+ dims = x.dim()
+ lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t)
+ h = lambda_t - lambda_s
+ lambda_s1 = lambda_s + r1 * h
+ lambda_s2 = lambda_s + r2 * h
+ s1 = ns.inverse_lambda(lambda_s1)
+ s2 = ns.inverse_lambda(lambda_s2)
+ log_alpha_s, log_alpha_s1, log_alpha_s2, log_alpha_t = ns.marginal_log_mean_coeff(s), ns.marginal_log_mean_coeff(s1), ns.marginal_log_mean_coeff(s2), ns.marginal_log_mean_coeff(t)
+ sigma_s, sigma_s1, sigma_s2, sigma_t = ns.marginal_std(s), ns.marginal_std(s1), ns.marginal_std(s2), ns.marginal_std(t)
+ alpha_s1, alpha_s2, alpha_t = torch.exp(log_alpha_s1), torch.exp(log_alpha_s2), torch.exp(log_alpha_t)
+
+ if self.predict_x0:
+ phi_11 = torch.expm1(-r1 * h)
+ phi_12 = torch.expm1(-r2 * h)
+ phi_1 = torch.expm1(-h)
+ phi_22 = torch.expm1(-r2 * h) / (r2 * h) + 1.
+ phi_2 = phi_1 / h + 1.
+ phi_3 = phi_2 / h - 0.5
+
+ if model_s is None:
+ model_s = self.model_fn(x, s)
+ if model_s1 is None:
+ x_s1 = (
+ expand_dims(sigma_s1 / sigma_s, dims) * x
+ - expand_dims(alpha_s1 * phi_11, dims) * model_s
+ )
+ model_s1 = self.model_fn(x_s1, s1)
+ x_s2 = (
+ expand_dims(sigma_s2 / sigma_s, dims) * x
+ - expand_dims(alpha_s2 * phi_12, dims) * model_s
+ + r2 / r1 * expand_dims(alpha_s2 * phi_22, dims) * (model_s1 - model_s)
+ )
+ model_s2 = self.model_fn(x_s2, s2)
+ if solver_type == 'dpm_solver':
+ x_t = (
+ expand_dims(sigma_t / sigma_s, dims) * x
+ - expand_dims(alpha_t * phi_1, dims) * model_s
+ + (1. / r2) * expand_dims(alpha_t * phi_2, dims) * (model_s2 - model_s)
+ )
+ elif solver_type == 'taylor':
+ D1_0 = (1. / r1) * (model_s1 - model_s)
+ D1_1 = (1. / r2) * (model_s2 - model_s)
+ D1 = (r2 * D1_0 - r1 * D1_1) / (r2 - r1)
+ D2 = 2. * (D1_1 - D1_0) / (r2 - r1)
+ x_t = (
+ expand_dims(sigma_t / sigma_s, dims) * x
+ - expand_dims(alpha_t * phi_1, dims) * model_s
+ + expand_dims(alpha_t * phi_2, dims) * D1
+ - expand_dims(alpha_t * phi_3, dims) * D2
+ )
+ else:
+ phi_11 = torch.expm1(r1 * h)
+ phi_12 = torch.expm1(r2 * h)
+ phi_1 = torch.expm1(h)
+ phi_22 = torch.expm1(r2 * h) / (r2 * h) - 1.
+ phi_2 = phi_1 / h - 1.
+ phi_3 = phi_2 / h - 0.5
+
+ if model_s is None:
+ model_s = self.model_fn(x, s)
+ if model_s1 is None:
+ x_s1 = (
+ expand_dims(torch.exp(log_alpha_s1 - log_alpha_s), dims) * x
+ - expand_dims(sigma_s1 * phi_11, dims) * model_s
+ )
+ model_s1 = self.model_fn(x_s1, s1)
+ x_s2 = (
+ expand_dims(torch.exp(log_alpha_s2 - log_alpha_s), dims) * x
+ - expand_dims(sigma_s2 * phi_12, dims) * model_s
+ - r2 / r1 * expand_dims(sigma_s2 * phi_22, dims) * (model_s1 - model_s)
+ )
+ model_s2 = self.model_fn(x_s2, s2)
+ if solver_type == 'dpm_solver':
+ x_t = (
+ expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+ - expand_dims(sigma_t * phi_1, dims) * model_s
+ - (1. / r2) * expand_dims(sigma_t * phi_2, dims) * (model_s2 - model_s)
+ )
+ elif solver_type == 'taylor':
+ D1_0 = (1. / r1) * (model_s1 - model_s)
+ D1_1 = (1. / r2) * (model_s2 - model_s)
+ D1 = (r2 * D1_0 - r1 * D1_1) / (r2 - r1)
+ D2 = 2. * (D1_1 - D1_0) / (r2 - r1)
+ x_t = (
+ expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+ - expand_dims(sigma_t * phi_1, dims) * model_s
+ - expand_dims(sigma_t * phi_2, dims) * D1
+ - expand_dims(sigma_t * phi_3, dims) * D2
+ )
+
+ if return_intermediate:
+ return x_t, {'model_s': model_s, 'model_s1': model_s1, 'model_s2': model_s2}
+ else:
+ return x_t
+
+ def multistep_dpm_solver_second_update(self, x, model_prev_list, t_prev_list, t, solver_type="dpm_solver"):
+ """
+ Multistep solver DPM-Solver-2 from time `t_prev_list[-1]` to time `t`.
+
+ Args:
+ x: A pytorch tensor. The initial value at time `s`.
+ model_prev_list: A list of pytorch tensor. The previous computed model values.
+ t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],)
+ t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+ solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+ The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+ Returns:
+ x_t: A pytorch tensor. The approximated solution at time `t`.
+ """
+ if solver_type not in ['dpm_solver', 'taylor']:
+ raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type))
+ ns = self.noise_schedule
+ dims = x.dim()
+ model_prev_1, model_prev_0 = model_prev_list
+ t_prev_1, t_prev_0 = t_prev_list
+ lambda_prev_1, lambda_prev_0, lambda_t = ns.marginal_lambda(t_prev_1), ns.marginal_lambda(t_prev_0), ns.marginal_lambda(t)
+ log_alpha_prev_0, log_alpha_t = ns.marginal_log_mean_coeff(t_prev_0), ns.marginal_log_mean_coeff(t)
+ sigma_prev_0, sigma_t = ns.marginal_std(t_prev_0), ns.marginal_std(t)
+ alpha_t = torch.exp(log_alpha_t)
+
+ h_0 = lambda_prev_0 - lambda_prev_1
+ h = lambda_t - lambda_prev_0
+ r0 = h_0 / h
+ D1_0 = expand_dims(1. / r0, dims) * (model_prev_0 - model_prev_1)
+ if self.predict_x0:
+ if solver_type == 'dpm_solver':
+ x_t = (
+ expand_dims(sigma_t / sigma_prev_0, dims) * x
+ - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0
+ - 0.5 * expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * D1_0
+ )
+ elif solver_type == 'taylor':
+ x_t = (
+ expand_dims(sigma_t / sigma_prev_0, dims) * x
+ - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0
+ + expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * D1_0
+ )
+ else:
+ if solver_type == 'dpm_solver':
+ x_t = (
+ expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x
+ - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0
+ - 0.5 * expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * D1_0
+ )
+ elif solver_type == 'taylor':
+ x_t = (
+ expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x
+ - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0
+ - expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * D1_0
+ )
+ return x_t
+
+ def multistep_dpm_solver_third_update(self, x, model_prev_list, t_prev_list, t, solver_type='dpm_solver'):
+ """
+ Multistep solver DPM-Solver-3 from time `t_prev_list[-1]` to time `t`.
+
+ Args:
+ x: A pytorch tensor. The initial value at time `s`.
+ model_prev_list: A list of pytorch tensor. The previous computed model values.
+ t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],)
+ t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+ solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+ The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+ Returns:
+ x_t: A pytorch tensor. The approximated solution at time `t`.
+ """
+ ns = self.noise_schedule
+ dims = x.dim()
+ model_prev_2, model_prev_1, model_prev_0 = model_prev_list
+ t_prev_2, t_prev_1, t_prev_0 = t_prev_list
+ lambda_prev_2, lambda_prev_1, lambda_prev_0, lambda_t = ns.marginal_lambda(t_prev_2), ns.marginal_lambda(t_prev_1), ns.marginal_lambda(t_prev_0), ns.marginal_lambda(t)
+ log_alpha_prev_0, log_alpha_t = ns.marginal_log_mean_coeff(t_prev_0), ns.marginal_log_mean_coeff(t)
+ sigma_prev_0, sigma_t = ns.marginal_std(t_prev_0), ns.marginal_std(t)
+ alpha_t = torch.exp(log_alpha_t)
+
+ h_1 = lambda_prev_1 - lambda_prev_2
+ h_0 = lambda_prev_0 - lambda_prev_1
+ h = lambda_t - lambda_prev_0
+ r0, r1 = h_0 / h, h_1 / h
+ D1_0 = expand_dims(1. / r0, dims) * (model_prev_0 - model_prev_1)
+ D1_1 = expand_dims(1. / r1, dims) * (model_prev_1 - model_prev_2)
+ D1 = D1_0 + expand_dims(r0 / (r0 + r1), dims) * (D1_0 - D1_1)
+ D2 = expand_dims(1. / (r0 + r1), dims) * (D1_0 - D1_1)
+ if self.predict_x0:
+ x_t = (
+ expand_dims(sigma_t / sigma_prev_0, dims) * x
+ - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0
+ + expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * D1
+ - expand_dims(alpha_t * ((torch.exp(-h) - 1. + h) / h**2 - 0.5), dims) * D2
+ )
+ else:
+ x_t = (
+ expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x
+ - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0
+ - expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * D1
+ - expand_dims(sigma_t * ((torch.exp(h) - 1. - h) / h**2 - 0.5), dims) * D2
+ )
+ return x_t
+
+ def singlestep_dpm_solver_update(self, x, s, t, order, return_intermediate=False, solver_type='dpm_solver', r1=None, r2=None):
+ """
+ Singlestep DPM-Solver with the order `order` from time `s` to time `t`.
+
+ Args:
+ x: A pytorch tensor. The initial value at time `s`.
+ s: A pytorch tensor. The starting time, with the shape (x.shape[0],).
+ t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+ order: A `int`. The order of DPM-Solver. We only support order == 1 or 2 or 3.
+ return_intermediate: A `bool`. If true, also return the model value at time `s`, `s1` and `s2` (the intermediate times).
+ solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+ The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+ r1: A `float`. The hyperparameter of the second-order or third-order solver.
+ r2: A `float`. The hyperparameter of the third-order solver.
+ Returns:
+ x_t: A pytorch tensor. The approximated solution at time `t`.
+ """
+ if order == 1:
+ return self.dpm_solver_first_update(x, s, t, return_intermediate=return_intermediate)
+ elif order == 2:
+ return self.singlestep_dpm_solver_second_update(x, s, t, return_intermediate=return_intermediate, solver_type=solver_type, r1=r1)
+ elif order == 3:
+ return self.singlestep_dpm_solver_third_update(x, s, t, return_intermediate=return_intermediate, solver_type=solver_type, r1=r1, r2=r2)
+ else:
+ raise ValueError("Solver order must be 1 or 2 or 3, got {}".format(order))
+
+ def multistep_dpm_solver_update(self, x, model_prev_list, t_prev_list, t, order, solver_type='dpm_solver'):
+ """
+ Multistep DPM-Solver with the order `order` from time `t_prev_list[-1]` to time `t`.
+
+ Args:
+ x: A pytorch tensor. The initial value at time `s`.
+ model_prev_list: A list of pytorch tensor. The previous computed model values.
+ t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],)
+ t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+ order: A `int`. The order of DPM-Solver. We only support order == 1 or 2 or 3.
+ solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+ The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+ Returns:
+ x_t: A pytorch tensor. The approximated solution at time `t`.
+ """
+ if order == 1:
+ return self.dpm_solver_first_update(x, t_prev_list[-1], t, model_s=model_prev_list[-1])
+ elif order == 2:
+ return self.multistep_dpm_solver_second_update(x, model_prev_list, t_prev_list, t, solver_type=solver_type)
+ elif order == 3:
+ return self.multistep_dpm_solver_third_update(x, model_prev_list, t_prev_list, t, solver_type=solver_type)
+ else:
+ raise ValueError("Solver order must be 1 or 2 or 3, got {}".format(order))
+
+ def dpm_solver_adaptive(self, x, order, t_T, t_0, h_init=0.05, atol=0.0078, rtol=0.05, theta=0.9, t_err=1e-5, solver_type='dpm_solver'):
+ """
+ The adaptive step size solver based on singlestep DPM-Solver.
+
+ Args:
+ x: A pytorch tensor. The initial value at time `t_T`.
+ order: A `int`. The (higher) order of the solver. We only support order == 2 or 3.
+ t_T: A `float`. The starting time of the sampling (default is T).
+ t_0: A `float`. The ending time of the sampling (default is epsilon).
+ h_init: A `float`. The initial step size (for logSNR).
+ atol: A `float`. The absolute tolerance of the solver. For image data, the default setting is 0.0078, followed [1].
+ rtol: A `float`. The relative tolerance of the solver. The default setting is 0.05.
+ theta: A `float`. The safety hyperparameter for adapting the step size. The default setting is 0.9, followed [1].
+ t_err: A `float`. The tolerance for the time. We solve the diffusion ODE until the absolute error between the
+ current time and `t_0` is less than `t_err`. The default setting is 1e-5.
+ solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+ The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+ Returns:
+ x_0: A pytorch tensor. The approximated solution at time `t_0`.
+
+ [1] A. Jolicoeur-Martineau, K. Li, R. Piché-Taillefer, T. Kachman, and I. Mitliagkas, "Gotta go fast when generating data with score-based models," arXiv preprint arXiv:2105.14080, 2021.
+ """
+ ns = self.noise_schedule
+ s = t_T * torch.ones((x.shape[0],)).to(x)
+ lambda_s = ns.marginal_lambda(s)
+ lambda_0 = ns.marginal_lambda(t_0 * torch.ones_like(s).to(x))
+ h = h_init * torch.ones_like(s).to(x)
+ x_prev = x
+ nfe = 0
+ if order == 2:
+ r1 = 0.5
+ lower_update = lambda x, s, t: self.dpm_solver_first_update(x, s, t, return_intermediate=True)
+ higher_update = lambda x, s, t, **kwargs: self.singlestep_dpm_solver_second_update(x, s, t, r1=r1, solver_type=solver_type, **kwargs)
+ elif order == 3:
+ r1, r2 = 1. / 3., 2. / 3.
+ lower_update = lambda x, s, t: self.singlestep_dpm_solver_second_update(x, s, t, r1=r1, return_intermediate=True, solver_type=solver_type)
+ higher_update = lambda x, s, t, **kwargs: self.singlestep_dpm_solver_third_update(x, s, t, r1=r1, r2=r2, solver_type=solver_type, **kwargs)
+ else:
+ raise ValueError("For adaptive step size solver, order must be 2 or 3, got {}".format(order))
+ while torch.abs((s - t_0)).mean() > t_err:
+ t = ns.inverse_lambda(lambda_s + h)
+ x_lower, lower_noise_kwargs = lower_update(x, s, t)
+ x_higher = higher_update(x, s, t, **lower_noise_kwargs)
+ delta = torch.max(torch.ones_like(x).to(x) * atol, rtol * torch.max(torch.abs(x_lower), torch.abs(x_prev)))
+ norm_fn = lambda v: torch.sqrt(torch.square(v.reshape((v.shape[0], -1))).mean(dim=-1, keepdim=True))
+ E = norm_fn((x_higher - x_lower) / delta).max()
+ if torch.all(E <= 1.):
+ x = x_higher
+ s = t
+ x_prev = x_lower
+ lambda_s = ns.marginal_lambda(s)
+ h = torch.min(theta * h * torch.float_power(E, -1. / order).float(), lambda_0 - lambda_s)
+ nfe += order
+ print('adaptive solver nfe', nfe)
+ return x
+
+ def sample(self, x, steps=20, t_start=None, t_end=None, order=3, skip_type='time_uniform',
+ method='singlestep', lower_order_final=True, denoise_to_zero=False, solver_type='dpm_solver',
+ atol=0.0078, rtol=0.05,
+ ):
+ """
+ Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`.
+
+ =====================================================
+
+ We support the following algorithms for both noise prediction model and data prediction model:
+ - 'singlestep':
+ Singlestep DPM-Solver (i.e. "DPM-Solver-fast" in the paper), which combines different orders of singlestep DPM-Solver.
+ We combine all the singlestep solvers with order <= `order` to use up all the function evaluations (steps).
+ The total number of function evaluations (NFE) == `steps`.
+ Given a fixed NFE == `steps`, the sampling procedure is:
+ - If `order` == 1:
+ - Denote K = steps. We use K steps of DPM-Solver-1 (i.e. DDIM).
+ - If `order` == 2:
+ - Denote K = (steps // 2) + (steps % 2). We take K intermediate time steps for sampling.
+ - If steps % 2 == 0, we use K steps of singlestep DPM-Solver-2.
+ - If steps % 2 == 1, we use (K - 1) steps of singlestep DPM-Solver-2 and 1 step of DPM-Solver-1.
+ - If `order` == 3:
+ - Denote K = (steps // 3 + 1). We take K intermediate time steps for sampling.
+ - If steps % 3 == 0, we use (K - 2) steps of singlestep DPM-Solver-3, and 1 step of singlestep DPM-Solver-2 and 1 step of DPM-Solver-1.
+ - If steps % 3 == 1, we use (K - 1) steps of singlestep DPM-Solver-3 and 1 step of DPM-Solver-1.
+ - If steps % 3 == 2, we use (K - 1) steps of singlestep DPM-Solver-3 and 1 step of singlestep DPM-Solver-2.
+ - 'multistep':
+ Multistep DPM-Solver with the order of `order`. The total number of function evaluations (NFE) == `steps`.
+ We initialize the first `order` values by lower order multistep solvers.
+ Given a fixed NFE == `steps`, the sampling procedure is:
+ Denote K = steps.
+ - If `order` == 1:
+ - We use K steps of DPM-Solver-1 (i.e. DDIM).
+ - If `order` == 2:
+ - We firstly use 1 step of DPM-Solver-1, then use (K - 1) step of multistep DPM-Solver-2.
+ - If `order` == 3:
+ - We firstly use 1 step of DPM-Solver-1, then 1 step of multistep DPM-Solver-2, then (K - 2) step of multistep DPM-Solver-3.
+ - 'singlestep_fixed':
+ Fixed order singlestep DPM-Solver (i.e. DPM-Solver-1 or singlestep DPM-Solver-2 or singlestep DPM-Solver-3).
+ We use singlestep DPM-Solver-`order` for `order`=1 or 2 or 3, with total [`steps` // `order`] * `order` NFE.
+ - 'adaptive':
+ Adaptive step size DPM-Solver (i.e. "DPM-Solver-12" and "DPM-Solver-23" in the paper).
+ We ignore `steps` and use adaptive step size DPM-Solver with a higher order of `order`.
+ You can adjust the absolute tolerance `atol` and the relative tolerance `rtol` to balance the computatation costs
+ (NFE) and the sample quality.
+ - If `order` == 2, we use DPM-Solver-12 which combines DPM-Solver-1 and singlestep DPM-Solver-2.
+ - If `order` == 3, we use DPM-Solver-23 which combines singlestep DPM-Solver-2 and singlestep DPM-Solver-3.
+
+ =====================================================
+
+ Some advices for choosing the algorithm:
+ - For **unconditional sampling** or **guided sampling with small guidance scale** by DPMs:
+ Use singlestep DPM-Solver ("DPM-Solver-fast" in the paper) with `order = 3`.
+ e.g.
+ >>> dpm_solver = DPM_Solver(model_fn, noise_schedule, predict_x0=False)
+ >>> x_sample = dpm_solver.sample(x, steps=steps, t_start=t_start, t_end=t_end, order=3,
+ skip_type='time_uniform', method='singlestep')
+ - For **guided sampling with large guidance scale** by DPMs:
+ Use multistep DPM-Solver with `predict_x0 = True` and `order = 2`.
+ e.g.
+ >>> dpm_solver = DPM_Solver(model_fn, noise_schedule, predict_x0=True)
+ >>> x_sample = dpm_solver.sample(x, steps=steps, t_start=t_start, t_end=t_end, order=2,
+ skip_type='time_uniform', method='multistep')
+
+ We support three types of `skip_type`:
+ - 'logSNR': uniform logSNR for the time steps. **Recommended for low-resolutional images**
+ - 'time_uniform': uniform time for the time steps. **Recommended for high-resolutional images**.
+ - 'time_quadratic': quadratic time for the time steps.
+
+ =====================================================
+ Args:
+ x: A pytorch tensor. The initial value at time `t_start`
+ e.g. if `t_start` == T, then `x` is a sample from the standard normal distribution.
+ steps: A `int`. The total number of function evaluations (NFE).
+ t_start: A `float`. The starting time of the sampling.
+ If `T` is None, we use self.noise_schedule.T (default is 1.0).
+ t_end: A `float`. The ending time of the sampling.
+ If `t_end` is None, we use 1. / self.noise_schedule.total_N.
+ e.g. if total_N == 1000, we have `t_end` == 1e-3.
+ For discrete-time DPMs:
+ - We recommend `t_end` == 1. / self.noise_schedule.total_N.
+ For continuous-time DPMs:
+ - We recommend `t_end` == 1e-3 when `steps` <= 15; and `t_end` == 1e-4 when `steps` > 15.
+ order: A `int`. The order of DPM-Solver.
+ skip_type: A `str`. The type for the spacing of the time steps. 'time_uniform' or 'logSNR' or 'time_quadratic'.
+ method: A `str`. The method for sampling. 'singlestep' or 'multistep' or 'singlestep_fixed' or 'adaptive'.
+ denoise_to_zero: A `bool`. Whether to denoise to time 0 at the final step.
+ Default is `False`. If `denoise_to_zero` is `True`, the total NFE is (`steps` + 1).
+
+ This trick is firstly proposed by DDPM (https://arxiv.org/abs/2006.11239) and
+ score_sde (https://arxiv.org/abs/2011.13456). Such trick can improve the FID
+ for diffusion models sampling by diffusion SDEs for low-resolutional images
+ (such as CIFAR-10). However, we observed that such trick does not matter for
+ high-resolutional images. As it needs an additional NFE, we do not recommend
+ it for high-resolutional images.
+ lower_order_final: A `bool`. Whether to use lower order solvers at the final steps.
+ Only valid for `method=multistep` and `steps < 15`. We empirically find that
+ this trick is a key to stabilizing the sampling by DPM-Solver with very few steps
+ (especially for steps <= 10). So we recommend to set it to be `True`.
+ solver_type: A `str`. The taylor expansion type for the solver. `dpm_solver` or `taylor`. We recommend `dpm_solver`.
+ atol: A `float`. The absolute tolerance of the adaptive step size solver. Valid when `method` == 'adaptive'.
+ rtol: A `float`. The relative tolerance of the adaptive step size solver. Valid when `method` == 'adaptive'.
+ Returns:
+ x_end: A pytorch tensor. The approximated solution at time `t_end`.
+
+ """
+ t_0 = 1. / self.noise_schedule.total_N if t_end is None else t_end
+ t_T = self.noise_schedule.T if t_start is None else t_start
+ device = x.device
+ if method == 'adaptive':
+ with torch.no_grad():
+ x = self.dpm_solver_adaptive(x, order=order, t_T=t_T, t_0=t_0, atol=atol, rtol=rtol, solver_type=solver_type)
+ elif method == 'multistep':
+ assert steps >= order
+ timesteps = self.get_time_steps(skip_type=skip_type, t_T=t_T, t_0=t_0, N=steps, device=device)
+ assert timesteps.shape[0] - 1 == steps
+ with torch.no_grad():
+ vec_t = timesteps[0].expand((x.shape[0]))
+ model_prev_list = [self.model_fn(x, vec_t)]
+ t_prev_list = [vec_t]
+ # Init the first `order` values by lower order multistep DPM-Solver.
+ for init_order in range(1, order):
+ vec_t = timesteps[init_order].expand(x.shape[0])
+ x = self.multistep_dpm_solver_update(x, model_prev_list, t_prev_list, vec_t, init_order, solver_type=solver_type)
+ model_prev_list.append(self.model_fn(x, vec_t))
+ t_prev_list.append(vec_t)
+ # Compute the remaining values by `order`-th order multistep DPM-Solver.
+ for step in range(order, steps + 1):
+ vec_t = timesteps[step].expand(x.shape[0])
+ if lower_order_final and steps < 15:
+ step_order = min(order, steps + 1 - step)
+ else:
+ step_order = order
+ x = self.multistep_dpm_solver_update(x, model_prev_list, t_prev_list, vec_t, step_order, solver_type=solver_type)
+ for i in range(order - 1):
+ t_prev_list[i] = t_prev_list[i + 1]
+ model_prev_list[i] = model_prev_list[i + 1]
+ t_prev_list[-1] = vec_t
+ # We do not need to evaluate the final model value.
+ if step < steps:
+ model_prev_list[-1] = self.model_fn(x, vec_t)
+ elif method in ['singlestep', 'singlestep_fixed']:
+ if method == 'singlestep':
+ timesteps_outer, orders = self.get_orders_and_timesteps_for_singlestep_solver(steps=steps, order=order, skip_type=skip_type, t_T=t_T, t_0=t_0, device=device)
+ elif method == 'singlestep_fixed':
+ K = steps // order
+ orders = [order,] * K
+ timesteps_outer = self.get_time_steps(skip_type=skip_type, t_T=t_T, t_0=t_0, N=K, device=device)
+ for i, order in enumerate(orders):
+ t_T_inner, t_0_inner = timesteps_outer[i], timesteps_outer[i + 1]
+ timesteps_inner = self.get_time_steps(skip_type=skip_type, t_T=t_T_inner.item(), t_0=t_0_inner.item(), N=order, device=device)
+ lambda_inner = self.noise_schedule.marginal_lambda(timesteps_inner)
+ vec_s, vec_t = t_T_inner.tile(x.shape[0]), t_0_inner.tile(x.shape[0])
+ h = lambda_inner[-1] - lambda_inner[0]
+ r1 = None if order <= 1 else (lambda_inner[1] - lambda_inner[0]) / h
+ r2 = None if order <= 2 else (lambda_inner[2] - lambda_inner[0]) / h
+ x = self.singlestep_dpm_solver_update(x, vec_s, vec_t, order, solver_type=solver_type, r1=r1, r2=r2)
+ if denoise_to_zero:
+ x = self.denoise_to_zero_fn(x, torch.ones((x.shape[0],)).to(device) * t_0)
+ return x
+
+
+
+#############################################################
+# other utility functions
+#############################################################
+
+def interpolate_fn(x, xp, yp):
+ """
+ A piecewise linear function y = f(x), using xp and yp as keypoints.
+ We implement f(x) in a differentiable way (i.e. applicable for autograd).
+ The function f(x) is well-defined for all x-axis. (For x beyond the bounds of xp, we use the outmost points of xp to define the linear function.)
+
+ Args:
+ x: PyTorch tensor with shape [N, C], where N is the batch size, C is the number of channels (we use C = 1 for DPM-Solver).
+ xp: PyTorch tensor with shape [C, K], where K is the number of keypoints.
+ yp: PyTorch tensor with shape [C, K].
+ Returns:
+ The function values f(x), with shape [N, C].
+ """
+ N, K = x.shape[0], xp.shape[1]
+ all_x = torch.cat([x.unsqueeze(2), xp.unsqueeze(0).repeat((N, 1, 1))], dim=2)
+ sorted_all_x, x_indices = torch.sort(all_x, dim=2)
+ x_idx = torch.argmin(x_indices, dim=2)
+ cand_start_idx = x_idx - 1
+ start_idx = torch.where(
+ torch.eq(x_idx, 0),
+ torch.tensor(1, device=x.device),
+ torch.where(
+ torch.eq(x_idx, K), torch.tensor(K - 2, device=x.device), cand_start_idx,
+ ),
+ )
+ end_idx = torch.where(torch.eq(start_idx, cand_start_idx), start_idx + 2, start_idx + 1)
+ start_x = torch.gather(sorted_all_x, dim=2, index=start_idx.unsqueeze(2)).squeeze(2)
+ end_x = torch.gather(sorted_all_x, dim=2, index=end_idx.unsqueeze(2)).squeeze(2)
+ start_idx2 = torch.where(
+ torch.eq(x_idx, 0),
+ torch.tensor(0, device=x.device),
+ torch.where(
+ torch.eq(x_idx, K), torch.tensor(K - 2, device=x.device), cand_start_idx,
+ ),
+ )
+ y_positions_expanded = yp.unsqueeze(0).expand(N, -1, -1)
+ start_y = torch.gather(y_positions_expanded, dim=2, index=start_idx2.unsqueeze(2)).squeeze(2)
+ end_y = torch.gather(y_positions_expanded, dim=2, index=(start_idx2 + 1).unsqueeze(2)).squeeze(2)
+ cand = start_y + (x - start_x) * (end_y - start_y) / (end_x - start_x)
+ return cand
+
+
+def expand_dims(v, dims):
+ """
+ Expand the tensor `v` to the dim `dims`.
+
+ Args:
+ `v`: a PyTorch tensor with shape [N].
+ `dim`: a `int`.
+ Returns:
+ a PyTorch tensor with shape [N, 1, 1, ..., 1] and the total dimension is `dims`.
+ """
+ return v[(...,) + (None,)*(dims - 1)]
\ No newline at end of file
diff --git a/stable_diffusion/ldm/models/diffusion/dpm_solver/sampler.py b/stable_diffusion/ldm/models/diffusion/dpm_solver/sampler.py
new file mode 100644
index 0000000000000000000000000000000000000000..2c42d6f964d92658e769df95a81dec92250e5a99
--- /dev/null
+++ b/stable_diffusion/ldm/models/diffusion/dpm_solver/sampler.py
@@ -0,0 +1,82 @@
+"""SAMPLING ONLY."""
+
+import torch
+
+from .dpm_solver import NoiseScheduleVP, model_wrapper, DPM_Solver
+
+
+class DPMSolverSampler(object):
+ def __init__(self, model, **kwargs):
+ super().__init__()
+ self.model = model
+ to_torch = lambda x: x.clone().detach().to(torch.float32).to(model.device)
+ self.register_buffer('alphas_cumprod', to_torch(model.alphas_cumprod))
+
+ def register_buffer(self, name, attr):
+ if type(attr) == torch.Tensor:
+ if attr.device != torch.device("cuda"):
+ attr = attr.to(torch.device("cuda"))
+ setattr(self, name, attr)
+
+ @torch.no_grad()
+ def sample(self,
+ S,
+ batch_size,
+ shape,
+ conditioning=None,
+ callback=None,
+ normals_sequence=None,
+ img_callback=None,
+ quantize_x0=False,
+ eta=0.,
+ mask=None,
+ x0=None,
+ temperature=1.,
+ noise_dropout=0.,
+ score_corrector=None,
+ corrector_kwargs=None,
+ verbose=True,
+ x_T=None,
+ log_every_t=100,
+ unconditional_guidance_scale=1.,
+ unconditional_conditioning=None,
+ # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
+ **kwargs
+ ):
+ if conditioning is not None:
+ if isinstance(conditioning, dict):
+ cbs = conditioning[list(conditioning.keys())[0]].shape[0]
+ if cbs != batch_size:
+ print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
+ else:
+ if conditioning.shape[0] != batch_size:
+ print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
+
+ # sampling
+ C, H, W = shape
+ size = (batch_size, C, H, W)
+
+ # print(f'Data shape for DPM-Solver sampling is {size}, sampling steps {S}')
+
+ device = self.model.betas.device
+ if x_T is None:
+ img = torch.randn(size, device=device)
+ else:
+ img = x_T
+
+ ns = NoiseScheduleVP('discrete', alphas_cumprod=self.alphas_cumprod)
+
+ model_fn = model_wrapper(
+ lambda x, t, c: self.model.apply_model(x, t, c),
+ ns,
+ model_type="noise",
+ guidance_type="classifier-free",
+ condition=conditioning,
+ unconditional_condition=unconditional_conditioning,
+ guidance_scale=unconditional_guidance_scale,
+ )
+
+ dpm_solver = DPM_Solver(model_fn, ns, predict_x0=True, thresholding=False)
+ x = dpm_solver.sample(img, steps=S, skip_type="time_uniform", method="multistep", order=2, lower_order_final=True)
+
+ return x.to(device), None
diff --git a/stable_diffusion/ldm/models/diffusion/plms.py b/stable_diffusion/ldm/models/diffusion/plms.py
new file mode 100644
index 0000000000000000000000000000000000000000..78eeb1003aa45d27bdbfc6b4a1d7ccbff57cd2e3
--- /dev/null
+++ b/stable_diffusion/ldm/models/diffusion/plms.py
@@ -0,0 +1,236 @@
+"""SAMPLING ONLY."""
+
+import torch
+import numpy as np
+from tqdm import tqdm
+from functools import partial
+
+from ldm.modules.diffusionmodules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like
+
+
+class PLMSSampler(object):
+ def __init__(self, model, schedule="linear", **kwargs):
+ super().__init__()
+ self.model = model
+ self.ddpm_num_timesteps = model.num_timesteps
+ self.schedule = schedule
+
+ def register_buffer(self, name, attr):
+ if type(attr) == torch.Tensor:
+ if attr.device != torch.device("cuda"):
+ attr = attr.to(torch.device("cuda"))
+ setattr(self, name, attr)
+
+ def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True):
+ if ddim_eta != 0:
+ raise ValueError('ddim_eta must be 0 for PLMS')
+ self.ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps,
+ num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose)
+ alphas_cumprod = self.model.alphas_cumprod
+ assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep'
+ to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.model.device)
+
+ self.register_buffer('betas', to_torch(self.model.betas))
+ self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+ self.register_buffer('alphas_cumprod_prev', to_torch(self.model.alphas_cumprod_prev))
+
+ # calculations for diffusion q(x_t | x_{t-1}) and others
+ self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod.cpu())))
+ self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu())))
+ self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu())))
+ self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu())))
+ self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1)))
+
+ # ddim sampling parameters
+ ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(),
+ ddim_timesteps=self.ddim_timesteps,
+ eta=ddim_eta,verbose=verbose)
+ self.register_buffer('ddim_sigmas', ddim_sigmas)
+ self.register_buffer('ddim_alphas', ddim_alphas)
+ self.register_buffer('ddim_alphas_prev', ddim_alphas_prev)
+ self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas))
+ sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt(
+ (1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * (
+ 1 - self.alphas_cumprod / self.alphas_cumprod_prev))
+ self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps)
+
+ @torch.no_grad()
+ def sample(self,
+ S,
+ batch_size,
+ shape,
+ conditioning=None,
+ callback=None,
+ normals_sequence=None,
+ img_callback=None,
+ quantize_x0=False,
+ eta=0.,
+ mask=None,
+ x0=None,
+ temperature=1.,
+ noise_dropout=0.,
+ score_corrector=None,
+ corrector_kwargs=None,
+ verbose=True,
+ x_T=None,
+ log_every_t=100,
+ unconditional_guidance_scale=1.,
+ unconditional_conditioning=None,
+ # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
+ **kwargs
+ ):
+ if conditioning is not None:
+ if isinstance(conditioning, dict):
+ cbs = conditioning[list(conditioning.keys())[0]].shape[0]
+ if cbs != batch_size:
+ print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
+ else:
+ if conditioning.shape[0] != batch_size:
+ print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
+
+ self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
+ # sampling
+ C, H, W = shape
+ size = (batch_size, C, H, W)
+ print(f'Data shape for PLMS sampling is {size}')
+
+ samples, intermediates = self.plms_sampling(conditioning, size,
+ callback=callback,
+ img_callback=img_callback,
+ quantize_denoised=quantize_x0,
+ mask=mask, x0=x0,
+ ddim_use_original_steps=False,
+ noise_dropout=noise_dropout,
+ temperature=temperature,
+ score_corrector=score_corrector,
+ corrector_kwargs=corrector_kwargs,
+ x_T=x_T,
+ log_every_t=log_every_t,
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ unconditional_conditioning=unconditional_conditioning,
+ )
+ return samples, intermediates
+
+ @torch.no_grad()
+ def plms_sampling(self, cond, shape,
+ x_T=None, ddim_use_original_steps=False,
+ callback=None, timesteps=None, quantize_denoised=False,
+ mask=None, x0=None, img_callback=None, log_every_t=100,
+ temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
+ unconditional_guidance_scale=1., unconditional_conditioning=None,):
+ device = self.model.betas.device
+ b = shape[0]
+ if x_T is None:
+ img = torch.randn(shape, device=device)
+ else:
+ img = x_T
+
+ if timesteps is None:
+ timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps
+ elif timesteps is not None and not ddim_use_original_steps:
+ subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1
+ timesteps = self.ddim_timesteps[:subset_end]
+
+ intermediates = {'x_inter': [img], 'pred_x0': [img]}
+ time_range = list(reversed(range(0,timesteps))) if ddim_use_original_steps else np.flip(timesteps)
+ total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0]
+ print(f"Running PLMS Sampling with {total_steps} timesteps")
+
+ iterator = tqdm(time_range, desc='PLMS Sampler', total=total_steps)
+ old_eps = []
+
+ for i, step in enumerate(iterator):
+ index = total_steps - i - 1
+ ts = torch.full((b,), step, device=device, dtype=torch.long)
+ ts_next = torch.full((b,), time_range[min(i + 1, len(time_range) - 1)], device=device, dtype=torch.long)
+
+ if mask is not None:
+ assert x0 is not None
+ img_orig = self.model.q_sample(x0, ts) # TODO: deterministic forward pass?
+ img = img_orig * mask + (1. - mask) * img
+
+ outs = self.p_sample_plms(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
+ quantize_denoised=quantize_denoised, temperature=temperature,
+ noise_dropout=noise_dropout, score_corrector=score_corrector,
+ corrector_kwargs=corrector_kwargs,
+ unconditional_guidance_scale=unconditional_guidance_scale,
+ unconditional_conditioning=unconditional_conditioning,
+ old_eps=old_eps, t_next=ts_next)
+ img, pred_x0, e_t = outs
+ old_eps.append(e_t)
+ if len(old_eps) >= 4:
+ old_eps.pop(0)
+ if callback: callback(i)
+ if img_callback: img_callback(pred_x0, i)
+
+ if index % log_every_t == 0 or index == total_steps - 1:
+ intermediates['x_inter'].append(img)
+ intermediates['pred_x0'].append(pred_x0)
+
+ return img, intermediates
+
+ @torch.no_grad()
+ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
+ temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
+ unconditional_guidance_scale=1., unconditional_conditioning=None, old_eps=None, t_next=None):
+ b, *_, device = *x.shape, x.device
+
+ def get_model_output(x, t):
+ if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
+ e_t = self.model.apply_model(x, t, c)
+ else:
+ x_in = torch.cat([x] * 2)
+ t_in = torch.cat([t] * 2)
+ c_in = torch.cat([unconditional_conditioning, c])
+ e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
+ e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
+
+ if score_corrector is not None:
+ assert self.model.parameterization == "eps"
+ e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
+
+ return e_t
+
+ alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
+ alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
+ sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
+ sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
+
+ def get_x_prev_and_pred_x0(e_t, index):
+ # select parameters corresponding to the currently considered timestep
+ a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
+ a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
+ sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
+ sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
+
+ # current prediction for x_0
+ pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
+ if quantize_denoised:
+ pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
+ # direction pointing to x_t
+ dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
+ noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
+ if noise_dropout > 0.:
+ noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+ x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
+ return x_prev, pred_x0
+
+ e_t = get_model_output(x, t)
+ if len(old_eps) == 0:
+ # Pseudo Improved Euler (2nd order)
+ x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t, index)
+ e_t_next = get_model_output(x_prev, t_next)
+ e_t_prime = (e_t + e_t_next) / 2
+ elif len(old_eps) == 1:
+ # 2nd order Pseudo Linear Multistep (Adams-Bashforth)
+ e_t_prime = (3 * e_t - old_eps[-1]) / 2
+ elif len(old_eps) == 2:
+ # 3nd order Pseudo Linear Multistep (Adams-Bashforth)
+ e_t_prime = (23 * e_t - 16 * old_eps[-1] + 5 * old_eps[-2]) / 12
+ elif len(old_eps) >= 3:
+ # 4nd order Pseudo Linear Multistep (Adams-Bashforth)
+ e_t_prime = (55 * e_t - 59 * old_eps[-1] + 37 * old_eps[-2] - 9 * old_eps[-3]) / 24
+
+ x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t_prime, index)
+
+ return x_prev, pred_x0, e_t
diff --git a/stable_diffusion/ldm/modules/attention.py b/stable_diffusion/ldm/modules/attention.py
new file mode 100644
index 0000000000000000000000000000000000000000..96f8689eddbd3ecf251051a52386e6b82422eeb2
--- /dev/null
+++ b/stable_diffusion/ldm/modules/attention.py
@@ -0,0 +1,275 @@
+# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
+# See more details in LICENSE.
+
+from inspect import isfunction
+import math
+import torch
+import torch.nn.functional as F
+from torch import nn, einsum
+from einops import rearrange, repeat
+
+from ldm.modules.diffusionmodules.util import checkpoint
+
+
+def exists(val):
+ return val is not None
+
+
+def uniq(arr):
+ return{el: True for el in arr}.keys()
+
+
+def default(val, d):
+ if exists(val):
+ return val
+ return d() if isfunction(d) else d
+
+
+def max_neg_value(t):
+ return -torch.finfo(t.dtype).max
+
+
+def init_(tensor):
+ dim = tensor.shape[-1]
+ std = 1 / math.sqrt(dim)
+ tensor.uniform_(-std, std)
+ return tensor
+
+
+# feedforward
+class GEGLU(nn.Module):
+ def __init__(self, dim_in, dim_out):
+ super().__init__()
+ self.proj = nn.Linear(dim_in, dim_out * 2)
+
+ def forward(self, x):
+ x, gate = self.proj(x).chunk(2, dim=-1)
+ return x * F.gelu(gate)
+
+
+class FeedForward(nn.Module):
+ def __init__(self, dim, dim_out=None, mult=4, glu=False, dropout=0.):
+ super().__init__()
+ inner_dim = int(dim * mult)
+ dim_out = default(dim_out, dim)
+ project_in = nn.Sequential(
+ nn.Linear(dim, inner_dim),
+ nn.GELU()
+ ) if not glu else GEGLU(dim, inner_dim)
+
+ self.net = nn.Sequential(
+ project_in,
+ nn.Dropout(dropout),
+ nn.Linear(inner_dim, dim_out)
+ )
+
+ def forward(self, x):
+ return self.net(x)
+
+
+def zero_module(module):
+ """
+ Zero out the parameters of a module and return it.
+ """
+ for p in module.parameters():
+ p.detach().zero_()
+ return module
+
+
+def Normalize(in_channels):
+ return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
+
+
+class LinearAttention(nn.Module):
+ def __init__(self, dim, heads=4, dim_head=32):
+ super().__init__()
+ self.heads = heads
+ hidden_dim = dim_head * heads
+ self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias = False)
+ self.to_out = nn.Conv2d(hidden_dim, dim, 1)
+
+ def forward(self, x):
+ b, c, h, w = x.shape
+ qkv = self.to_qkv(x)
+ q, k, v = rearrange(qkv, 'b (qkv heads c) h w -> qkv b heads c (h w)', heads = self.heads, qkv=3)
+ k = k.softmax(dim=-1)
+ context = torch.einsum('bhdn,bhen->bhde', k, v)
+ out = torch.einsum('bhde,bhdn->bhen', context, q)
+ out = rearrange(out, 'b heads c (h w) -> b (heads c) h w', heads=self.heads, h=h, w=w)
+ return self.to_out(out)
+
+
+class SpatialSelfAttention(nn.Module):
+ def __init__(self, in_channels):
+ super().__init__()
+ self.in_channels = in_channels
+
+ self.norm = Normalize(in_channels)
+ self.q = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+ self.k = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+ self.v = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+ self.proj_out = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+
+ def forward(self, x):
+ h_ = x
+ h_ = self.norm(h_)
+ q = self.q(h_)
+ k = self.k(h_)
+ v = self.v(h_)
+
+ # compute attention
+ b,c,h,w = q.shape
+ q = rearrange(q, 'b c h w -> b (h w) c')
+ k = rearrange(k, 'b c h w -> b c (h w)')
+ w_ = torch.einsum('bij,bjk->bik', q, k)
+
+ w_ = w_ * (int(c)**(-0.5))
+ w_ = torch.nn.functional.softmax(w_, dim=2)
+
+ # attend to values
+ v = rearrange(v, 'b c h w -> b c (h w)')
+ w_ = rearrange(w_, 'b i j -> b j i')
+ h_ = torch.einsum('bij,bjk->bik', v, w_)
+ h_ = rearrange(h_, 'b c (h w) -> b c h w', h=h)
+ h_ = self.proj_out(h_)
+
+ return x+h_
+
+
+class CrossAttention(nn.Module):
+ def __init__(self, query_dim, context_dim=None, heads=8, dim_head=64, dropout=0.):
+ super().__init__()
+ inner_dim = dim_head * heads
+ context_dim = default(context_dim, query_dim)
+
+ self.scale = dim_head ** -0.5
+ self.heads = heads
+
+ self.to_q = nn.Linear(query_dim, inner_dim, bias=False)
+ self.to_k = nn.Linear(context_dim, inner_dim, bias=False)
+ self.to_v = nn.Linear(context_dim, inner_dim, bias=False)
+
+ self.to_out = nn.Sequential(
+ nn.Linear(inner_dim, query_dim),
+ nn.Dropout(dropout)
+ )
+
+ self.prompt_to_prompt = False
+
+ def forward(self, x, context=None, mask=None):
+ is_self_attn = context is None
+
+ h = self.heads
+
+ q = self.to_q(x)
+ context = default(context, x)
+ k = self.to_k(context)
+ v = self.to_v(context)
+
+ q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
+
+ sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
+
+ if self.prompt_to_prompt and is_self_attn:
+ # Unlike the original Prompt-to-Prompt which uses cross-attention layers, we copy attention maps for self-attention layers.
+ # There must be 4 elements in the batch: {conditional, unconditional} x {prompt 1, prompt 2}
+ assert x.size(0) == 4
+ sims = sim.chunk(4)
+ sim = torch.cat((sims[0], sims[0], sims[2], sims[2]))
+
+ if exists(mask):
+ mask = rearrange(mask, 'b ... -> b (...)')
+ max_neg_value = -torch.finfo(sim.dtype).max
+ mask = repeat(mask, 'b j -> (b h) () j', h=h)
+ sim.masked_fill_(~mask, max_neg_value)
+
+ # attention, what we cannot get enough of
+ attn = sim.softmax(dim=-1)
+
+ out = einsum('b i j, b j d -> b i d', attn, v)
+ out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
+ return self.to_out(out)
+
+
+class BasicTransformerBlock(nn.Module):
+ def __init__(self, dim, n_heads, d_head, dropout=0., context_dim=None, gated_ff=True, checkpoint=True):
+ super().__init__()
+ self.attn1 = CrossAttention(query_dim=dim, heads=n_heads, dim_head=d_head, dropout=dropout) # is a self-attention
+ self.ff = FeedForward(dim, dropout=dropout, glu=gated_ff)
+ self.attn2 = CrossAttention(query_dim=dim, context_dim=context_dim,
+ heads=n_heads, dim_head=d_head, dropout=dropout) # is self-attn if context is none
+ self.norm1 = nn.LayerNorm(dim)
+ self.norm2 = nn.LayerNorm(dim)
+ self.norm3 = nn.LayerNorm(dim)
+ self.checkpoint = checkpoint
+
+ def forward(self, x, context=None):
+ return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
+
+ def _forward(self, x, context=None):
+ x = self.attn1(self.norm1(x)) + x
+ x = self.attn2(self.norm2(x), context=context) + x
+ x = self.ff(self.norm3(x)) + x
+ return x
+
+
+class SpatialTransformer(nn.Module):
+ """
+ Transformer block for image-like data.
+ First, project the input (aka embedding)
+ and reshape to b, t, d.
+ Then apply standard transformer action.
+ Finally, reshape to image
+ """
+ def __init__(self, in_channels, n_heads, d_head,
+ depth=1, dropout=0., context_dim=None):
+ super().__init__()
+ self.in_channels = in_channels
+ inner_dim = n_heads * d_head
+ self.norm = Normalize(in_channels)
+
+ self.proj_in = nn.Conv2d(in_channels,
+ inner_dim,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+
+ self.transformer_blocks = nn.ModuleList(
+ [BasicTransformerBlock(inner_dim, n_heads, d_head, dropout=dropout, context_dim=context_dim)
+ for d in range(depth)]
+ )
+
+ self.proj_out = zero_module(nn.Conv2d(inner_dim,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0))
+
+ def forward(self, x, context=None):
+ # note: if no context is given, cross-attention defaults to self-attention
+ b, c, h, w = x.shape
+ x_in = x
+ x = self.norm(x)
+ x = self.proj_in(x)
+ x = rearrange(x, 'b c h w -> b (h w) c')
+ for block in self.transformer_blocks:
+ x = block(x, context=context)
+ x = rearrange(x, 'b (h w) c -> b c h w', h=h, w=w)
+ x = self.proj_out(x)
+ return x + x_in
diff --git a/stable_diffusion/ldm/modules/diffusionmodules/__init__.py b/stable_diffusion/ldm/modules/diffusionmodules/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/stable_diffusion/ldm/modules/diffusionmodules/model.py b/stable_diffusion/ldm/modules/diffusionmodules/model.py
new file mode 100644
index 0000000000000000000000000000000000000000..533e589a2024f1d7c52093d8c472c3b1b6617e26
--- /dev/null
+++ b/stable_diffusion/ldm/modules/diffusionmodules/model.py
@@ -0,0 +1,835 @@
+# pytorch_diffusion + derived encoder decoder
+import math
+import torch
+import torch.nn as nn
+import numpy as np
+from einops import rearrange
+
+from ldm.util import instantiate_from_config
+from ldm.modules.attention import LinearAttention
+
+
+def get_timestep_embedding(timesteps, embedding_dim):
+ """
+ This matches the implementation in Denoising Diffusion Probabilistic Models:
+ From Fairseq.
+ Build sinusoidal embeddings.
+ This matches the implementation in tensor2tensor, but differs slightly
+ from the description in Section 3.5 of "Attention Is All You Need".
+ """
+ assert len(timesteps.shape) == 1
+
+ half_dim = embedding_dim // 2
+ emb = math.log(10000) / (half_dim - 1)
+ emb = torch.exp(torch.arange(half_dim, dtype=torch.float32) * -emb)
+ emb = emb.to(device=timesteps.device)
+ emb = timesteps.float()[:, None] * emb[None, :]
+ emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=1)
+ if embedding_dim % 2 == 1: # zero pad
+ emb = torch.nn.functional.pad(emb, (0,1,0,0))
+ return emb
+
+
+def nonlinearity(x):
+ # swish
+ return x*torch.sigmoid(x)
+
+
+def Normalize(in_channels, num_groups=32):
+ return torch.nn.GroupNorm(num_groups=num_groups, num_channels=in_channels, eps=1e-6, affine=True)
+
+
+class Upsample(nn.Module):
+ def __init__(self, in_channels, with_conv):
+ super().__init__()
+ self.with_conv = with_conv
+ if self.with_conv:
+ self.conv = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ def forward(self, x):
+ x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
+ if self.with_conv:
+ x = self.conv(x)
+ return x
+
+
+class Downsample(nn.Module):
+ def __init__(self, in_channels, with_conv):
+ super().__init__()
+ self.with_conv = with_conv
+ if self.with_conv:
+ # no asymmetric padding in torch conv, must do it ourselves
+ self.conv = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=3,
+ stride=2,
+ padding=0)
+
+ def forward(self, x):
+ if self.with_conv:
+ pad = (0,1,0,1)
+ x = torch.nn.functional.pad(x, pad, mode="constant", value=0)
+ x = self.conv(x)
+ else:
+ x = torch.nn.functional.avg_pool2d(x, kernel_size=2, stride=2)
+ return x
+
+
+class ResnetBlock(nn.Module):
+ def __init__(self, *, in_channels, out_channels=None, conv_shortcut=False,
+ dropout, temb_channels=512):
+ super().__init__()
+ self.in_channels = in_channels
+ out_channels = in_channels if out_channels is None else out_channels
+ self.out_channels = out_channels
+ self.use_conv_shortcut = conv_shortcut
+
+ self.norm1 = Normalize(in_channels)
+ self.conv1 = torch.nn.Conv2d(in_channels,
+ out_channels,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+ if temb_channels > 0:
+ self.temb_proj = torch.nn.Linear(temb_channels,
+ out_channels)
+ self.norm2 = Normalize(out_channels)
+ self.dropout = torch.nn.Dropout(dropout)
+ self.conv2 = torch.nn.Conv2d(out_channels,
+ out_channels,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+ if self.in_channels != self.out_channels:
+ if self.use_conv_shortcut:
+ self.conv_shortcut = torch.nn.Conv2d(in_channels,
+ out_channels,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+ else:
+ self.nin_shortcut = torch.nn.Conv2d(in_channels,
+ out_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+
+ def forward(self, x, temb):
+ h = x
+ h = self.norm1(h)
+ h = nonlinearity(h)
+ h = self.conv1(h)
+
+ if temb is not None:
+ h = h + self.temb_proj(nonlinearity(temb))[:,:,None,None]
+
+ h = self.norm2(h)
+ h = nonlinearity(h)
+ h = self.dropout(h)
+ h = self.conv2(h)
+
+ if self.in_channels != self.out_channels:
+ if self.use_conv_shortcut:
+ x = self.conv_shortcut(x)
+ else:
+ x = self.nin_shortcut(x)
+
+ return x+h
+
+
+class LinAttnBlock(LinearAttention):
+ """to match AttnBlock usage"""
+ def __init__(self, in_channels):
+ super().__init__(dim=in_channels, heads=1, dim_head=in_channels)
+
+
+class AttnBlock(nn.Module):
+ def __init__(self, in_channels):
+ super().__init__()
+ self.in_channels = in_channels
+
+ self.norm = Normalize(in_channels)
+ self.q = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+ self.k = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+ self.v = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+ self.proj_out = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=1,
+ stride=1,
+ padding=0)
+
+
+ def forward(self, x):
+ h_ = x
+ h_ = self.norm(h_)
+ q = self.q(h_)
+ k = self.k(h_)
+ v = self.v(h_)
+
+ # compute attention
+ b,c,h,w = q.shape
+ q = q.reshape(b,c,h*w)
+ q = q.permute(0,2,1) # b,hw,c
+ k = k.reshape(b,c,h*w) # b,c,hw
+ w_ = torch.bmm(q,k) # b,hw,hw w[b,i,j]=sum_c q[b,i,c]k[b,c,j]
+ w_ = w_ * (int(c)**(-0.5))
+ w_ = torch.nn.functional.softmax(w_, dim=2)
+
+ # attend to values
+ v = v.reshape(b,c,h*w)
+ w_ = w_.permute(0,2,1) # b,hw,hw (first hw of k, second of q)
+ h_ = torch.bmm(v,w_) # b, c,hw (hw of q) h_[b,c,j] = sum_i v[b,c,i] w_[b,i,j]
+ h_ = h_.reshape(b,c,h,w)
+
+ h_ = self.proj_out(h_)
+
+ return x+h_
+
+
+def make_attn(in_channels, attn_type="vanilla"):
+ assert attn_type in ["vanilla", "linear", "none"], f'attn_type {attn_type} unknown'
+ print(f"making attention of type '{attn_type}' with {in_channels} in_channels")
+ if attn_type == "vanilla":
+ return AttnBlock(in_channels)
+ elif attn_type == "none":
+ return nn.Identity(in_channels)
+ else:
+ return LinAttnBlock(in_channels)
+
+
+class Model(nn.Module):
+ def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
+ attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
+ resolution, use_timestep=True, use_linear_attn=False, attn_type="vanilla"):
+ super().__init__()
+ if use_linear_attn: attn_type = "linear"
+ self.ch = ch
+ self.temb_ch = self.ch*4
+ self.num_resolutions = len(ch_mult)
+ self.num_res_blocks = num_res_blocks
+ self.resolution = resolution
+ self.in_channels = in_channels
+
+ self.use_timestep = use_timestep
+ if self.use_timestep:
+ # timestep embedding
+ self.temb = nn.Module()
+ self.temb.dense = nn.ModuleList([
+ torch.nn.Linear(self.ch,
+ self.temb_ch),
+ torch.nn.Linear(self.temb_ch,
+ self.temb_ch),
+ ])
+
+ # downsampling
+ self.conv_in = torch.nn.Conv2d(in_channels,
+ self.ch,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ curr_res = resolution
+ in_ch_mult = (1,)+tuple(ch_mult)
+ self.down = nn.ModuleList()
+ for i_level in range(self.num_resolutions):
+ block = nn.ModuleList()
+ attn = nn.ModuleList()
+ block_in = ch*in_ch_mult[i_level]
+ block_out = ch*ch_mult[i_level]
+ for i_block in range(self.num_res_blocks):
+ block.append(ResnetBlock(in_channels=block_in,
+ out_channels=block_out,
+ temb_channels=self.temb_ch,
+ dropout=dropout))
+ block_in = block_out
+ if curr_res in attn_resolutions:
+ attn.append(make_attn(block_in, attn_type=attn_type))
+ down = nn.Module()
+ down.block = block
+ down.attn = attn
+ if i_level != self.num_resolutions-1:
+ down.downsample = Downsample(block_in, resamp_with_conv)
+ curr_res = curr_res // 2
+ self.down.append(down)
+
+ # middle
+ self.mid = nn.Module()
+ self.mid.block_1 = ResnetBlock(in_channels=block_in,
+ out_channels=block_in,
+ temb_channels=self.temb_ch,
+ dropout=dropout)
+ self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
+ self.mid.block_2 = ResnetBlock(in_channels=block_in,
+ out_channels=block_in,
+ temb_channels=self.temb_ch,
+ dropout=dropout)
+
+ # upsampling
+ self.up = nn.ModuleList()
+ for i_level in reversed(range(self.num_resolutions)):
+ block = nn.ModuleList()
+ attn = nn.ModuleList()
+ block_out = ch*ch_mult[i_level]
+ skip_in = ch*ch_mult[i_level]
+ for i_block in range(self.num_res_blocks+1):
+ if i_block == self.num_res_blocks:
+ skip_in = ch*in_ch_mult[i_level]
+ block.append(ResnetBlock(in_channels=block_in+skip_in,
+ out_channels=block_out,
+ temb_channels=self.temb_ch,
+ dropout=dropout))
+ block_in = block_out
+ if curr_res in attn_resolutions:
+ attn.append(make_attn(block_in, attn_type=attn_type))
+ up = nn.Module()
+ up.block = block
+ up.attn = attn
+ if i_level != 0:
+ up.upsample = Upsample(block_in, resamp_with_conv)
+ curr_res = curr_res * 2
+ self.up.insert(0, up) # prepend to get consistent order
+
+ # end
+ self.norm_out = Normalize(block_in)
+ self.conv_out = torch.nn.Conv2d(block_in,
+ out_ch,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ def forward(self, x, t=None, context=None):
+ #assert x.shape[2] == x.shape[3] == self.resolution
+ if context is not None:
+ # assume aligned context, cat along channel axis
+ x = torch.cat((x, context), dim=1)
+ if self.use_timestep:
+ # timestep embedding
+ assert t is not None
+ temb = get_timestep_embedding(t, self.ch)
+ temb = self.temb.dense[0](temb)
+ temb = nonlinearity(temb)
+ temb = self.temb.dense[1](temb)
+ else:
+ temb = None
+
+ # downsampling
+ hs = [self.conv_in(x)]
+ for i_level in range(self.num_resolutions):
+ for i_block in range(self.num_res_blocks):
+ h = self.down[i_level].block[i_block](hs[-1], temb)
+ if len(self.down[i_level].attn) > 0:
+ h = self.down[i_level].attn[i_block](h)
+ hs.append(h)
+ if i_level != self.num_resolutions-1:
+ hs.append(self.down[i_level].downsample(hs[-1]))
+
+ # middle
+ h = hs[-1]
+ h = self.mid.block_1(h, temb)
+ h = self.mid.attn_1(h)
+ h = self.mid.block_2(h, temb)
+
+ # upsampling
+ for i_level in reversed(range(self.num_resolutions)):
+ for i_block in range(self.num_res_blocks+1):
+ h = self.up[i_level].block[i_block](
+ torch.cat([h, hs.pop()], dim=1), temb)
+ if len(self.up[i_level].attn) > 0:
+ h = self.up[i_level].attn[i_block](h)
+ if i_level != 0:
+ h = self.up[i_level].upsample(h)
+
+ # end
+ h = self.norm_out(h)
+ h = nonlinearity(h)
+ h = self.conv_out(h)
+ return h
+
+ def get_last_layer(self):
+ return self.conv_out.weight
+
+
+class Encoder(nn.Module):
+ def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
+ attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
+ resolution, z_channels, double_z=True, use_linear_attn=False, attn_type="vanilla",
+ **ignore_kwargs):
+ super().__init__()
+ if use_linear_attn: attn_type = "linear"
+ self.ch = ch
+ self.temb_ch = 0
+ self.num_resolutions = len(ch_mult)
+ self.num_res_blocks = num_res_blocks
+ self.resolution = resolution
+ self.in_channels = in_channels
+
+ # downsampling
+ self.conv_in = torch.nn.Conv2d(in_channels,
+ self.ch,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ curr_res = resolution
+ in_ch_mult = (1,)+tuple(ch_mult)
+ self.in_ch_mult = in_ch_mult
+ self.down = nn.ModuleList()
+ for i_level in range(self.num_resolutions):
+ block = nn.ModuleList()
+ attn = nn.ModuleList()
+ block_in = ch*in_ch_mult[i_level]
+ block_out = ch*ch_mult[i_level]
+ for i_block in range(self.num_res_blocks):
+ block.append(ResnetBlock(in_channels=block_in,
+ out_channels=block_out,
+ temb_channels=self.temb_ch,
+ dropout=dropout))
+ block_in = block_out
+ if curr_res in attn_resolutions:
+ attn.append(make_attn(block_in, attn_type=attn_type))
+ down = nn.Module()
+ down.block = block
+ down.attn = attn
+ if i_level != self.num_resolutions-1:
+ down.downsample = Downsample(block_in, resamp_with_conv)
+ curr_res = curr_res // 2
+ self.down.append(down)
+
+ # middle
+ self.mid = nn.Module()
+ self.mid.block_1 = ResnetBlock(in_channels=block_in,
+ out_channels=block_in,
+ temb_channels=self.temb_ch,
+ dropout=dropout)
+ self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
+ self.mid.block_2 = ResnetBlock(in_channels=block_in,
+ out_channels=block_in,
+ temb_channels=self.temb_ch,
+ dropout=dropout)
+
+ # end
+ self.norm_out = Normalize(block_in)
+ self.conv_out = torch.nn.Conv2d(block_in,
+ 2*z_channels if double_z else z_channels,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ def forward(self, x):
+ # timestep embedding
+ temb = None
+
+ # downsampling
+ hs = [self.conv_in(x)]
+ for i_level in range(self.num_resolutions):
+ for i_block in range(self.num_res_blocks):
+ h = self.down[i_level].block[i_block](hs[-1], temb)
+ if len(self.down[i_level].attn) > 0:
+ h = self.down[i_level].attn[i_block](h)
+ hs.append(h)
+ if i_level != self.num_resolutions-1:
+ hs.append(self.down[i_level].downsample(hs[-1]))
+
+ # middle
+ h = hs[-1]
+ h = self.mid.block_1(h, temb)
+ h = self.mid.attn_1(h)
+ h = self.mid.block_2(h, temb)
+
+ # end
+ h = self.norm_out(h)
+ h = nonlinearity(h)
+ h = self.conv_out(h)
+ return h
+
+
+class Decoder(nn.Module):
+ def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
+ attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
+ resolution, z_channels, give_pre_end=False, tanh_out=False, use_linear_attn=False,
+ attn_type="vanilla", **ignorekwargs):
+ super().__init__()
+ if use_linear_attn: attn_type = "linear"
+ self.ch = ch
+ self.temb_ch = 0
+ self.num_resolutions = len(ch_mult)
+ self.num_res_blocks = num_res_blocks
+ self.resolution = resolution
+ self.in_channels = in_channels
+ self.give_pre_end = give_pre_end
+ self.tanh_out = tanh_out
+
+ # compute in_ch_mult, block_in and curr_res at lowest res
+ in_ch_mult = (1,)+tuple(ch_mult)
+ block_in = ch*ch_mult[self.num_resolutions-1]
+ curr_res = resolution // 2**(self.num_resolutions-1)
+ self.z_shape = (1,z_channels,curr_res,curr_res)
+ print("Working with z of shape {} = {} dimensions.".format(
+ self.z_shape, np.prod(self.z_shape)))
+
+ # z to block_in
+ self.conv_in = torch.nn.Conv2d(z_channels,
+ block_in,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ # middle
+ self.mid = nn.Module()
+ self.mid.block_1 = ResnetBlock(in_channels=block_in,
+ out_channels=block_in,
+ temb_channels=self.temb_ch,
+ dropout=dropout)
+ self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
+ self.mid.block_2 = ResnetBlock(in_channels=block_in,
+ out_channels=block_in,
+ temb_channels=self.temb_ch,
+ dropout=dropout)
+
+ # upsampling
+ self.up = nn.ModuleList()
+ for i_level in reversed(range(self.num_resolutions)):
+ block = nn.ModuleList()
+ attn = nn.ModuleList()
+ block_out = ch*ch_mult[i_level]
+ for i_block in range(self.num_res_blocks+1):
+ block.append(ResnetBlock(in_channels=block_in,
+ out_channels=block_out,
+ temb_channels=self.temb_ch,
+ dropout=dropout))
+ block_in = block_out
+ if curr_res in attn_resolutions:
+ attn.append(make_attn(block_in, attn_type=attn_type))
+ up = nn.Module()
+ up.block = block
+ up.attn = attn
+ if i_level != 0:
+ up.upsample = Upsample(block_in, resamp_with_conv)
+ curr_res = curr_res * 2
+ self.up.insert(0, up) # prepend to get consistent order
+
+ # end
+ self.norm_out = Normalize(block_in)
+ self.conv_out = torch.nn.Conv2d(block_in,
+ out_ch,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ def forward(self, z):
+ #assert z.shape[1:] == self.z_shape[1:]
+ self.last_z_shape = z.shape
+
+ # timestep embedding
+ temb = None
+
+ # z to block_in
+ h = self.conv_in(z)
+
+ # middle
+ h = self.mid.block_1(h, temb)
+ h = self.mid.attn_1(h)
+ h = self.mid.block_2(h, temb)
+
+ # upsampling
+ for i_level in reversed(range(self.num_resolutions)):
+ for i_block in range(self.num_res_blocks+1):
+ h = self.up[i_level].block[i_block](h, temb)
+ if len(self.up[i_level].attn) > 0:
+ h = self.up[i_level].attn[i_block](h)
+ if i_level != 0:
+ h = self.up[i_level].upsample(h)
+
+ # end
+ if self.give_pre_end:
+ return h
+
+ h = self.norm_out(h)
+ h = nonlinearity(h)
+ h = self.conv_out(h)
+ if self.tanh_out:
+ h = torch.tanh(h)
+ return h
+
+
+class SimpleDecoder(nn.Module):
+ def __init__(self, in_channels, out_channels, *args, **kwargs):
+ super().__init__()
+ self.model = nn.ModuleList([nn.Conv2d(in_channels, in_channels, 1),
+ ResnetBlock(in_channels=in_channels,
+ out_channels=2 * in_channels,
+ temb_channels=0, dropout=0.0),
+ ResnetBlock(in_channels=2 * in_channels,
+ out_channels=4 * in_channels,
+ temb_channels=0, dropout=0.0),
+ ResnetBlock(in_channels=4 * in_channels,
+ out_channels=2 * in_channels,
+ temb_channels=0, dropout=0.0),
+ nn.Conv2d(2*in_channels, in_channels, 1),
+ Upsample(in_channels, with_conv=True)])
+ # end
+ self.norm_out = Normalize(in_channels)
+ self.conv_out = torch.nn.Conv2d(in_channels,
+ out_channels,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ def forward(self, x):
+ for i, layer in enumerate(self.model):
+ if i in [1,2,3]:
+ x = layer(x, None)
+ else:
+ x = layer(x)
+
+ h = self.norm_out(x)
+ h = nonlinearity(h)
+ x = self.conv_out(h)
+ return x
+
+
+class UpsampleDecoder(nn.Module):
+ def __init__(self, in_channels, out_channels, ch, num_res_blocks, resolution,
+ ch_mult=(2,2), dropout=0.0):
+ super().__init__()
+ # upsampling
+ self.temb_ch = 0
+ self.num_resolutions = len(ch_mult)
+ self.num_res_blocks = num_res_blocks
+ block_in = in_channels
+ curr_res = resolution // 2 ** (self.num_resolutions - 1)
+ self.res_blocks = nn.ModuleList()
+ self.upsample_blocks = nn.ModuleList()
+ for i_level in range(self.num_resolutions):
+ res_block = []
+ block_out = ch * ch_mult[i_level]
+ for i_block in range(self.num_res_blocks + 1):
+ res_block.append(ResnetBlock(in_channels=block_in,
+ out_channels=block_out,
+ temb_channels=self.temb_ch,
+ dropout=dropout))
+ block_in = block_out
+ self.res_blocks.append(nn.ModuleList(res_block))
+ if i_level != self.num_resolutions - 1:
+ self.upsample_blocks.append(Upsample(block_in, True))
+ curr_res = curr_res * 2
+
+ # end
+ self.norm_out = Normalize(block_in)
+ self.conv_out = torch.nn.Conv2d(block_in,
+ out_channels,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+
+ def forward(self, x):
+ # upsampling
+ h = x
+ for k, i_level in enumerate(range(self.num_resolutions)):
+ for i_block in range(self.num_res_blocks + 1):
+ h = self.res_blocks[i_level][i_block](h, None)
+ if i_level != self.num_resolutions - 1:
+ h = self.upsample_blocks[k](h)
+ h = self.norm_out(h)
+ h = nonlinearity(h)
+ h = self.conv_out(h)
+ return h
+
+
+class LatentRescaler(nn.Module):
+ def __init__(self, factor, in_channels, mid_channels, out_channels, depth=2):
+ super().__init__()
+ # residual block, interpolate, residual block
+ self.factor = factor
+ self.conv_in = nn.Conv2d(in_channels,
+ mid_channels,
+ kernel_size=3,
+ stride=1,
+ padding=1)
+ self.res_block1 = nn.ModuleList([ResnetBlock(in_channels=mid_channels,
+ out_channels=mid_channels,
+ temb_channels=0,
+ dropout=0.0) for _ in range(depth)])
+ self.attn = AttnBlock(mid_channels)
+ self.res_block2 = nn.ModuleList([ResnetBlock(in_channels=mid_channels,
+ out_channels=mid_channels,
+ temb_channels=0,
+ dropout=0.0) for _ in range(depth)])
+
+ self.conv_out = nn.Conv2d(mid_channels,
+ out_channels,
+ kernel_size=1,
+ )
+
+ def forward(self, x):
+ x = self.conv_in(x)
+ for block in self.res_block1:
+ x = block(x, None)
+ x = torch.nn.functional.interpolate(x, size=(int(round(x.shape[2]*self.factor)), int(round(x.shape[3]*self.factor))))
+ x = self.attn(x)
+ for block in self.res_block2:
+ x = block(x, None)
+ x = self.conv_out(x)
+ return x
+
+
+class MergedRescaleEncoder(nn.Module):
+ def __init__(self, in_channels, ch, resolution, out_ch, num_res_blocks,
+ attn_resolutions, dropout=0.0, resamp_with_conv=True,
+ ch_mult=(1,2,4,8), rescale_factor=1.0, rescale_module_depth=1):
+ super().__init__()
+ intermediate_chn = ch * ch_mult[-1]
+ self.encoder = Encoder(in_channels=in_channels, num_res_blocks=num_res_blocks, ch=ch, ch_mult=ch_mult,
+ z_channels=intermediate_chn, double_z=False, resolution=resolution,
+ attn_resolutions=attn_resolutions, dropout=dropout, resamp_with_conv=resamp_with_conv,
+ out_ch=None)
+ self.rescaler = LatentRescaler(factor=rescale_factor, in_channels=intermediate_chn,
+ mid_channels=intermediate_chn, out_channels=out_ch, depth=rescale_module_depth)
+
+ def forward(self, x):
+ x = self.encoder(x)
+ x = self.rescaler(x)
+ return x
+
+
+class MergedRescaleDecoder(nn.Module):
+ def __init__(self, z_channels, out_ch, resolution, num_res_blocks, attn_resolutions, ch, ch_mult=(1,2,4,8),
+ dropout=0.0, resamp_with_conv=True, rescale_factor=1.0, rescale_module_depth=1):
+ super().__init__()
+ tmp_chn = z_channels*ch_mult[-1]
+ self.decoder = Decoder(out_ch=out_ch, z_channels=tmp_chn, attn_resolutions=attn_resolutions, dropout=dropout,
+ resamp_with_conv=resamp_with_conv, in_channels=None, num_res_blocks=num_res_blocks,
+ ch_mult=ch_mult, resolution=resolution, ch=ch)
+ self.rescaler = LatentRescaler(factor=rescale_factor, in_channels=z_channels, mid_channels=tmp_chn,
+ out_channels=tmp_chn, depth=rescale_module_depth)
+
+ def forward(self, x):
+ x = self.rescaler(x)
+ x = self.decoder(x)
+ return x
+
+
+class Upsampler(nn.Module):
+ def __init__(self, in_size, out_size, in_channels, out_channels, ch_mult=2):
+ super().__init__()
+ assert out_size >= in_size
+ num_blocks = int(np.log2(out_size//in_size))+1
+ factor_up = 1.+ (out_size % in_size)
+ print(f"Building {self.__class__.__name__} with in_size: {in_size} --> out_size {out_size} and factor {factor_up}")
+ self.rescaler = LatentRescaler(factor=factor_up, in_channels=in_channels, mid_channels=2*in_channels,
+ out_channels=in_channels)
+ self.decoder = Decoder(out_ch=out_channels, resolution=out_size, z_channels=in_channels, num_res_blocks=2,
+ attn_resolutions=[], in_channels=None, ch=in_channels,
+ ch_mult=[ch_mult for _ in range(num_blocks)])
+
+ def forward(self, x):
+ x = self.rescaler(x)
+ x = self.decoder(x)
+ return x
+
+
+class Resize(nn.Module):
+ def __init__(self, in_channels=None, learned=False, mode="bilinear"):
+ super().__init__()
+ self.with_conv = learned
+ self.mode = mode
+ if self.with_conv:
+ print(f"Note: {self.__class__.__name} uses learned downsampling and will ignore the fixed {mode} mode")
+ raise NotImplementedError()
+ assert in_channels is not None
+ # no asymmetric padding in torch conv, must do it ourselves
+ self.conv = torch.nn.Conv2d(in_channels,
+ in_channels,
+ kernel_size=4,
+ stride=2,
+ padding=1)
+
+ def forward(self, x, scale_factor=1.0):
+ if scale_factor==1.0:
+ return x
+ else:
+ x = torch.nn.functional.interpolate(x, mode=self.mode, align_corners=False, scale_factor=scale_factor)
+ return x
+
+class FirstStagePostProcessor(nn.Module):
+
+ def __init__(self, ch_mult:list, in_channels,
+ pretrained_model:nn.Module=None,
+ reshape=False,
+ n_channels=None,
+ dropout=0.,
+ pretrained_config=None):
+ super().__init__()
+ if pretrained_config is None:
+ assert pretrained_model is not None, 'Either "pretrained_model" or "pretrained_config" must not be None'
+ self.pretrained_model = pretrained_model
+ else:
+ assert pretrained_config is not None, 'Either "pretrained_model" or "pretrained_config" must not be None'
+ self.instantiate_pretrained(pretrained_config)
+
+ self.do_reshape = reshape
+
+ if n_channels is None:
+ n_channels = self.pretrained_model.encoder.ch
+
+ self.proj_norm = Normalize(in_channels,num_groups=in_channels//2)
+ self.proj = nn.Conv2d(in_channels,n_channels,kernel_size=3,
+ stride=1,padding=1)
+
+ blocks = []
+ downs = []
+ ch_in = n_channels
+ for m in ch_mult:
+ blocks.append(ResnetBlock(in_channels=ch_in,out_channels=m*n_channels,dropout=dropout))
+ ch_in = m * n_channels
+ downs.append(Downsample(ch_in, with_conv=False))
+
+ self.model = nn.ModuleList(blocks)
+ self.downsampler = nn.ModuleList(downs)
+
+
+ def instantiate_pretrained(self, config):
+ model = instantiate_from_config(config)
+ self.pretrained_model = model.eval()
+ # self.pretrained_model.train = False
+ for param in self.pretrained_model.parameters():
+ param.requires_grad = False
+
+
+ @torch.no_grad()
+ def encode_with_pretrained(self,x):
+ c = self.pretrained_model.encode(x)
+ if isinstance(c, DiagonalGaussianDistribution):
+ c = c.mode()
+ return c
+
+ def forward(self,x):
+ z_fs = self.encode_with_pretrained(x)
+ z = self.proj_norm(z_fs)
+ z = self.proj(z)
+ z = nonlinearity(z)
+
+ for submodel, downmodel in zip(self.model,self.downsampler):
+ z = submodel(z,temb=None)
+ z = downmodel(z)
+
+ if self.do_reshape:
+ z = rearrange(z,'b c h w -> b (h w) c')
+ return z
+
diff --git a/stable_diffusion/ldm/modules/diffusionmodules/openaimodel.py b/stable_diffusion/ldm/modules/diffusionmodules/openaimodel.py
new file mode 100644
index 0000000000000000000000000000000000000000..fcf95d1ea8a078dd259915109203789f78f0643a
--- /dev/null
+++ b/stable_diffusion/ldm/modules/diffusionmodules/openaimodel.py
@@ -0,0 +1,961 @@
+from abc import abstractmethod
+from functools import partial
+import math
+from typing import Iterable
+
+import numpy as np
+import torch as th
+import torch.nn as nn
+import torch.nn.functional as F
+
+from ldm.modules.diffusionmodules.util import (
+ checkpoint,
+ conv_nd,
+ linear,
+ avg_pool_nd,
+ zero_module,
+ normalization,
+ timestep_embedding,
+)
+from ldm.modules.attention import SpatialTransformer
+
+
+# dummy replace
+def convert_module_to_f16(x):
+ pass
+
+def convert_module_to_f32(x):
+ pass
+
+
+## go
+class AttentionPool2d(nn.Module):
+ """
+ Adapted from CLIP: https://github.com/openai/CLIP/blob/main/clip/model.py
+ """
+
+ def __init__(
+ self,
+ spacial_dim: int,
+ embed_dim: int,
+ num_heads_channels: int,
+ output_dim: int = None,
+ ):
+ super().__init__()
+ self.positional_embedding = nn.Parameter(th.randn(embed_dim, spacial_dim ** 2 + 1) / embed_dim ** 0.5)
+ self.qkv_proj = conv_nd(1, embed_dim, 3 * embed_dim, 1)
+ self.c_proj = conv_nd(1, embed_dim, output_dim or embed_dim, 1)
+ self.num_heads = embed_dim // num_heads_channels
+ self.attention = QKVAttention(self.num_heads)
+
+ def forward(self, x):
+ b, c, *_spatial = x.shape
+ x = x.reshape(b, c, -1) # NC(HW)
+ x = th.cat([x.mean(dim=-1, keepdim=True), x], dim=-1) # NC(HW+1)
+ x = x + self.positional_embedding[None, :, :].to(x.dtype) # NC(HW+1)
+ x = self.qkv_proj(x)
+ x = self.attention(x)
+ x = self.c_proj(x)
+ return x[:, :, 0]
+
+
+class TimestepBlock(nn.Module):
+ """
+ Any module where forward() takes timestep embeddings as a second argument.
+ """
+
+ @abstractmethod
+ def forward(self, x, emb):
+ """
+ Apply the module to `x` given `emb` timestep embeddings.
+ """
+
+
+class TimestepEmbedSequential(nn.Sequential, TimestepBlock):
+ """
+ A sequential module that passes timestep embeddings to the children that
+ support it as an extra input.
+ """
+
+ def forward(self, x, emb, context=None):
+ for layer in self:
+ if isinstance(layer, TimestepBlock):
+ x = layer(x, emb)
+ elif isinstance(layer, SpatialTransformer):
+ x = layer(x, context)
+ else:
+ x = layer(x)
+ return x
+
+
+class Upsample(nn.Module):
+ """
+ An upsampling layer with an optional convolution.
+ :param channels: channels in the inputs and outputs.
+ :param use_conv: a bool determining if a convolution is applied.
+ :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
+ upsampling occurs in the inner-two dimensions.
+ """
+
+ def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1):
+ super().__init__()
+ self.channels = channels
+ self.out_channels = out_channels or channels
+ self.use_conv = use_conv
+ self.dims = dims
+ if use_conv:
+ self.conv = conv_nd(dims, self.channels, self.out_channels, 3, padding=padding)
+
+ def forward(self, x):
+ assert x.shape[1] == self.channels
+ if self.dims == 3:
+ x = F.interpolate(
+ x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode="nearest"
+ )
+ else:
+ x = F.interpolate(x, scale_factor=2, mode="nearest")
+ if self.use_conv:
+ x = self.conv(x)
+ return x
+
+class TransposedUpsample(nn.Module):
+ 'Learned 2x upsampling without padding'
+ def __init__(self, channels, out_channels=None, ks=5):
+ super().__init__()
+ self.channels = channels
+ self.out_channels = out_channels or channels
+
+ self.up = nn.ConvTranspose2d(self.channels,self.out_channels,kernel_size=ks,stride=2)
+
+ def forward(self,x):
+ return self.up(x)
+
+
+class Downsample(nn.Module):
+ """
+ A downsampling layer with an optional convolution.
+ :param channels: channels in the inputs and outputs.
+ :param use_conv: a bool determining if a convolution is applied.
+ :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
+ downsampling occurs in the inner-two dimensions.
+ """
+
+ def __init__(self, channels, use_conv, dims=2, out_channels=None,padding=1):
+ super().__init__()
+ self.channels = channels
+ self.out_channels = out_channels or channels
+ self.use_conv = use_conv
+ self.dims = dims
+ stride = 2 if dims != 3 else (1, 2, 2)
+ if use_conv:
+ self.op = conv_nd(
+ dims, self.channels, self.out_channels, 3, stride=stride, padding=padding
+ )
+ else:
+ assert self.channels == self.out_channels
+ self.op = avg_pool_nd(dims, kernel_size=stride, stride=stride)
+
+ def forward(self, x):
+ assert x.shape[1] == self.channels
+ return self.op(x)
+
+
+class ResBlock(TimestepBlock):
+ """
+ A residual block that can optionally change the number of channels.
+ :param channels: the number of input channels.
+ :param emb_channels: the number of timestep embedding channels.
+ :param dropout: the rate of dropout.
+ :param out_channels: if specified, the number of out channels.
+ :param use_conv: if True and out_channels is specified, use a spatial
+ convolution instead of a smaller 1x1 convolution to change the
+ channels in the skip connection.
+ :param dims: determines if the signal is 1D, 2D, or 3D.
+ :param use_checkpoint: if True, use gradient checkpointing on this module.
+ :param up: if True, use this block for upsampling.
+ :param down: if True, use this block for downsampling.
+ """
+
+ def __init__(
+ self,
+ channels,
+ emb_channels,
+ dropout,
+ out_channels=None,
+ use_conv=False,
+ use_scale_shift_norm=False,
+ dims=2,
+ use_checkpoint=False,
+ up=False,
+ down=False,
+ ):
+ super().__init__()
+ self.channels = channels
+ self.emb_channels = emb_channels
+ self.dropout = dropout
+ self.out_channels = out_channels or channels
+ self.use_conv = use_conv
+ self.use_checkpoint = use_checkpoint
+ self.use_scale_shift_norm = use_scale_shift_norm
+
+ self.in_layers = nn.Sequential(
+ normalization(channels),
+ nn.SiLU(),
+ conv_nd(dims, channels, self.out_channels, 3, padding=1),
+ )
+
+ self.updown = up or down
+
+ if up:
+ self.h_upd = Upsample(channels, False, dims)
+ self.x_upd = Upsample(channels, False, dims)
+ elif down:
+ self.h_upd = Downsample(channels, False, dims)
+ self.x_upd = Downsample(channels, False, dims)
+ else:
+ self.h_upd = self.x_upd = nn.Identity()
+
+ self.emb_layers = nn.Sequential(
+ nn.SiLU(),
+ linear(
+ emb_channels,
+ 2 * self.out_channels if use_scale_shift_norm else self.out_channels,
+ ),
+ )
+ self.out_layers = nn.Sequential(
+ normalization(self.out_channels),
+ nn.SiLU(),
+ nn.Dropout(p=dropout),
+ zero_module(
+ conv_nd(dims, self.out_channels, self.out_channels, 3, padding=1)
+ ),
+ )
+
+ if self.out_channels == channels:
+ self.skip_connection = nn.Identity()
+ elif use_conv:
+ self.skip_connection = conv_nd(
+ dims, channels, self.out_channels, 3, padding=1
+ )
+ else:
+ self.skip_connection = conv_nd(dims, channels, self.out_channels, 1)
+
+ def forward(self, x, emb):
+ """
+ Apply the block to a Tensor, conditioned on a timestep embedding.
+ :param x: an [N x C x ...] Tensor of features.
+ :param emb: an [N x emb_channels] Tensor of timestep embeddings.
+ :return: an [N x C x ...] Tensor of outputs.
+ """
+ return checkpoint(
+ self._forward, (x, emb), self.parameters(), self.use_checkpoint
+ )
+
+
+ def _forward(self, x, emb):
+ if self.updown:
+ in_rest, in_conv = self.in_layers[:-1], self.in_layers[-1]
+ h = in_rest(x)
+ h = self.h_upd(h)
+ x = self.x_upd(x)
+ h = in_conv(h)
+ else:
+ h = self.in_layers(x)
+ emb_out = self.emb_layers(emb).type(h.dtype)
+ while len(emb_out.shape) < len(h.shape):
+ emb_out = emb_out[..., None]
+ if self.use_scale_shift_norm:
+ out_norm, out_rest = self.out_layers[0], self.out_layers[1:]
+ scale, shift = th.chunk(emb_out, 2, dim=1)
+ h = out_norm(h) * (1 + scale) + shift
+ h = out_rest(h)
+ else:
+ h = h + emb_out
+ h = self.out_layers(h)
+ return self.skip_connection(x) + h
+
+
+class AttentionBlock(nn.Module):
+ """
+ An attention block that allows spatial positions to attend to each other.
+ Originally ported from here, but adapted to the N-d case.
+ https://github.com/hojonathanho/diffusion/blob/1e0dceb3b3495bbe19116a5e1b3596cd0706c543/diffusion_tf/models/unet.py#L66.
+ """
+
+ def __init__(
+ self,
+ channels,
+ num_heads=1,
+ num_head_channels=-1,
+ use_checkpoint=False,
+ use_new_attention_order=False,
+ ):
+ super().__init__()
+ self.channels = channels
+ if num_head_channels == -1:
+ self.num_heads = num_heads
+ else:
+ assert (
+ channels % num_head_channels == 0
+ ), f"q,k,v channels {channels} is not divisible by num_head_channels {num_head_channels}"
+ self.num_heads = channels // num_head_channels
+ self.use_checkpoint = use_checkpoint
+ self.norm = normalization(channels)
+ self.qkv = conv_nd(1, channels, channels * 3, 1)
+ if use_new_attention_order:
+ # split qkv before split heads
+ self.attention = QKVAttention(self.num_heads)
+ else:
+ # split heads before split qkv
+ self.attention = QKVAttentionLegacy(self.num_heads)
+
+ self.proj_out = zero_module(conv_nd(1, channels, channels, 1))
+
+ def forward(self, x):
+ return checkpoint(self._forward, (x,), self.parameters(), True) # TODO: check checkpoint usage, is True # TODO: fix the .half call!!!
+ #return pt_checkpoint(self._forward, x) # pytorch
+
+ def _forward(self, x):
+ b, c, *spatial = x.shape
+ x = x.reshape(b, c, -1)
+ qkv = self.qkv(self.norm(x))
+ h = self.attention(qkv)
+ h = self.proj_out(h)
+ return (x + h).reshape(b, c, *spatial)
+
+
+def count_flops_attn(model, _x, y):
+ """
+ A counter for the `thop` package to count the operations in an
+ attention operation.
+ Meant to be used like:
+ macs, params = thop.profile(
+ model,
+ inputs=(inputs, timestamps),
+ custom_ops={QKVAttention: QKVAttention.count_flops},
+ )
+ """
+ b, c, *spatial = y[0].shape
+ num_spatial = int(np.prod(spatial))
+ # We perform two matmuls with the same number of ops.
+ # The first computes the weight matrix, the second computes
+ # the combination of the value vectors.
+ matmul_ops = 2 * b * (num_spatial ** 2) * c
+ model.total_ops += th.DoubleTensor([matmul_ops])
+
+
+class QKVAttentionLegacy(nn.Module):
+ """
+ A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping
+ """
+
+ def __init__(self, n_heads):
+ super().__init__()
+ self.n_heads = n_heads
+
+ def forward(self, qkv):
+ """
+ Apply QKV attention.
+ :param qkv: an [N x (H * 3 * C) x T] tensor of Qs, Ks, and Vs.
+ :return: an [N x (H * C) x T] tensor after attention.
+ """
+ bs, width, length = qkv.shape
+ assert width % (3 * self.n_heads) == 0
+ ch = width // (3 * self.n_heads)
+ q, k, v = qkv.reshape(bs * self.n_heads, ch * 3, length).split(ch, dim=1)
+ scale = 1 / math.sqrt(math.sqrt(ch))
+ weight = th.einsum(
+ "bct,bcs->bts", q * scale, k * scale
+ ) # More stable with f16 than dividing afterwards
+ weight = th.softmax(weight.float(), dim=-1).type(weight.dtype)
+ a = th.einsum("bts,bcs->bct", weight, v)
+ return a.reshape(bs, -1, length)
+
+ @staticmethod
+ def count_flops(model, _x, y):
+ return count_flops_attn(model, _x, y)
+
+
+class QKVAttention(nn.Module):
+ """
+ A module which performs QKV attention and splits in a different order.
+ """
+
+ def __init__(self, n_heads):
+ super().__init__()
+ self.n_heads = n_heads
+
+ def forward(self, qkv):
+ """
+ Apply QKV attention.
+ :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs.
+ :return: an [N x (H * C) x T] tensor after attention.
+ """
+ bs, width, length = qkv.shape
+ assert width % (3 * self.n_heads) == 0
+ ch = width // (3 * self.n_heads)
+ q, k, v = qkv.chunk(3, dim=1)
+ scale = 1 / math.sqrt(math.sqrt(ch))
+ weight = th.einsum(
+ "bct,bcs->bts",
+ (q * scale).view(bs * self.n_heads, ch, length),
+ (k * scale).view(bs * self.n_heads, ch, length),
+ ) # More stable with f16 than dividing afterwards
+ weight = th.softmax(weight.float(), dim=-1).type(weight.dtype)
+ a = th.einsum("bts,bcs->bct", weight, v.reshape(bs * self.n_heads, ch, length))
+ return a.reshape(bs, -1, length)
+
+ @staticmethod
+ def count_flops(model, _x, y):
+ return count_flops_attn(model, _x, y)
+
+
+class UNetModel(nn.Module):
+ """
+ The full UNet model with attention and timestep embedding.
+ :param in_channels: channels in the input Tensor.
+ :param model_channels: base channel count for the model.
+ :param out_channels: channels in the output Tensor.
+ :param num_res_blocks: number of residual blocks per downsample.
+ :param attention_resolutions: a collection of downsample rates at which
+ attention will take place. May be a set, list, or tuple.
+ For example, if this contains 4, then at 4x downsampling, attention
+ will be used.
+ :param dropout: the dropout probability.
+ :param channel_mult: channel multiplier for each level of the UNet.
+ :param conv_resample: if True, use learned convolutions for upsampling and
+ downsampling.
+ :param dims: determines if the signal is 1D, 2D, or 3D.
+ :param num_classes: if specified (as an int), then this model will be
+ class-conditional with `num_classes` classes.
+ :param use_checkpoint: use gradient checkpointing to reduce memory usage.
+ :param num_heads: the number of attention heads in each attention layer.
+ :param num_heads_channels: if specified, ignore num_heads and instead use
+ a fixed channel width per attention head.
+ :param num_heads_upsample: works with num_heads to set a different number
+ of heads for upsampling. Deprecated.
+ :param use_scale_shift_norm: use a FiLM-like conditioning mechanism.
+ :param resblock_updown: use residual blocks for up/downsampling.
+ :param use_new_attention_order: use a different attention pattern for potentially
+ increased efficiency.
+ """
+
+ def __init__(
+ self,
+ image_size,
+ in_channels,
+ model_channels,
+ out_channels,
+ num_res_blocks,
+ attention_resolutions,
+ dropout=0,
+ channel_mult=(1, 2, 4, 8),
+ conv_resample=True,
+ dims=2,
+ num_classes=None,
+ use_checkpoint=False,
+ use_fp16=False,
+ num_heads=-1,
+ num_head_channels=-1,
+ num_heads_upsample=-1,
+ use_scale_shift_norm=False,
+ resblock_updown=False,
+ use_new_attention_order=False,
+ use_spatial_transformer=False, # custom transformer support
+ transformer_depth=1, # custom transformer support
+ context_dim=None, # custom transformer support
+ n_embed=None, # custom support for prediction of discrete ids into codebook of first stage vq model
+ legacy=True,
+ ):
+ super().__init__()
+ if use_spatial_transformer:
+ assert context_dim is not None, 'Fool!! You forgot to include the dimension of your cross-attention conditioning...'
+
+ if context_dim is not None:
+ assert use_spatial_transformer, 'Fool!! You forgot to use the spatial transformer for your cross-attention conditioning...'
+ from omegaconf.listconfig import ListConfig
+ if type(context_dim) == ListConfig:
+ context_dim = list(context_dim)
+
+ if num_heads_upsample == -1:
+ num_heads_upsample = num_heads
+
+ if num_heads == -1:
+ assert num_head_channels != -1, 'Either num_heads or num_head_channels has to be set'
+
+ if num_head_channels == -1:
+ assert num_heads != -1, 'Either num_heads or num_head_channels has to be set'
+
+ self.image_size = image_size
+ self.in_channels = in_channels
+ self.model_channels = model_channels
+ self.out_channels = out_channels
+ self.num_res_blocks = num_res_blocks
+ self.attention_resolutions = attention_resolutions
+ self.dropout = dropout
+ self.channel_mult = channel_mult
+ self.conv_resample = conv_resample
+ self.num_classes = num_classes
+ self.use_checkpoint = use_checkpoint
+ self.dtype = th.float16 if use_fp16 else th.float32
+ self.num_heads = num_heads
+ self.num_head_channels = num_head_channels
+ self.num_heads_upsample = num_heads_upsample
+ self.predict_codebook_ids = n_embed is not None
+
+ time_embed_dim = model_channels * 4
+ self.time_embed = nn.Sequential(
+ linear(model_channels, time_embed_dim),
+ nn.SiLU(),
+ linear(time_embed_dim, time_embed_dim),
+ )
+
+ if self.num_classes is not None:
+ self.label_emb = nn.Embedding(num_classes, time_embed_dim)
+
+ self.input_blocks = nn.ModuleList(
+ [
+ TimestepEmbedSequential(
+ conv_nd(dims, in_channels, model_channels, 3, padding=1)
+ )
+ ]
+ )
+ self._feature_size = model_channels
+ input_block_chans = [model_channels]
+ ch = model_channels
+ ds = 1
+ for level, mult in enumerate(channel_mult):
+ for _ in range(num_res_blocks):
+ layers = [
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ out_channels=mult * model_channels,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ )
+ ]
+ ch = mult * model_channels
+ if ds in attention_resolutions:
+ if num_head_channels == -1:
+ dim_head = ch // num_heads
+ else:
+ num_heads = ch // num_head_channels
+ dim_head = num_head_channels
+ if legacy:
+ #num_heads = 1
+ dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
+ layers.append(
+ AttentionBlock(
+ ch,
+ use_checkpoint=use_checkpoint,
+ num_heads=num_heads,
+ num_head_channels=dim_head,
+ use_new_attention_order=use_new_attention_order,
+ ) if not use_spatial_transformer else SpatialTransformer(
+ ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim
+ )
+ )
+ self.input_blocks.append(TimestepEmbedSequential(*layers))
+ self._feature_size += ch
+ input_block_chans.append(ch)
+ if level != len(channel_mult) - 1:
+ out_ch = ch
+ self.input_blocks.append(
+ TimestepEmbedSequential(
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ out_channels=out_ch,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ down=True,
+ )
+ if resblock_updown
+ else Downsample(
+ ch, conv_resample, dims=dims, out_channels=out_ch
+ )
+ )
+ )
+ ch = out_ch
+ input_block_chans.append(ch)
+ ds *= 2
+ self._feature_size += ch
+
+ if num_head_channels == -1:
+ dim_head = ch // num_heads
+ else:
+ num_heads = ch // num_head_channels
+ dim_head = num_head_channels
+ if legacy:
+ #num_heads = 1
+ dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
+ self.middle_block = TimestepEmbedSequential(
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ ),
+ AttentionBlock(
+ ch,
+ use_checkpoint=use_checkpoint,
+ num_heads=num_heads,
+ num_head_channels=dim_head,
+ use_new_attention_order=use_new_attention_order,
+ ) if not use_spatial_transformer else SpatialTransformer(
+ ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim
+ ),
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ ),
+ )
+ self._feature_size += ch
+
+ self.output_blocks = nn.ModuleList([])
+ for level, mult in list(enumerate(channel_mult))[::-1]:
+ for i in range(num_res_blocks + 1):
+ ich = input_block_chans.pop()
+ layers = [
+ ResBlock(
+ ch + ich,
+ time_embed_dim,
+ dropout,
+ out_channels=model_channels * mult,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ )
+ ]
+ ch = model_channels * mult
+ if ds in attention_resolutions:
+ if num_head_channels == -1:
+ dim_head = ch // num_heads
+ else:
+ num_heads = ch // num_head_channels
+ dim_head = num_head_channels
+ if legacy:
+ #num_heads = 1
+ dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
+ layers.append(
+ AttentionBlock(
+ ch,
+ use_checkpoint=use_checkpoint,
+ num_heads=num_heads_upsample,
+ num_head_channels=dim_head,
+ use_new_attention_order=use_new_attention_order,
+ ) if not use_spatial_transformer else SpatialTransformer(
+ ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim
+ )
+ )
+ if level and i == num_res_blocks:
+ out_ch = ch
+ layers.append(
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ out_channels=out_ch,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ up=True,
+ )
+ if resblock_updown
+ else Upsample(ch, conv_resample, dims=dims, out_channels=out_ch)
+ )
+ ds //= 2
+ self.output_blocks.append(TimestepEmbedSequential(*layers))
+ self._feature_size += ch
+
+ self.out = nn.Sequential(
+ normalization(ch),
+ nn.SiLU(),
+ zero_module(conv_nd(dims, model_channels, out_channels, 3, padding=1)),
+ )
+ if self.predict_codebook_ids:
+ self.id_predictor = nn.Sequential(
+ normalization(ch),
+ conv_nd(dims, model_channels, n_embed, 1),
+ #nn.LogSoftmax(dim=1) # change to cross_entropy and produce non-normalized logits
+ )
+
+ def convert_to_fp16(self):
+ """
+ Convert the torso of the model to float16.
+ """
+ self.input_blocks.apply(convert_module_to_f16)
+ self.middle_block.apply(convert_module_to_f16)
+ self.output_blocks.apply(convert_module_to_f16)
+
+ def convert_to_fp32(self):
+ """
+ Convert the torso of the model to float32.
+ """
+ self.input_blocks.apply(convert_module_to_f32)
+ self.middle_block.apply(convert_module_to_f32)
+ self.output_blocks.apply(convert_module_to_f32)
+
+ def forward(self, x, timesteps=None, context=None, y=None,**kwargs):
+ """
+ Apply the model to an input batch.
+ :param x: an [N x C x ...] Tensor of inputs.
+ :param timesteps: a 1-D batch of timesteps.
+ :param context: conditioning plugged in via crossattn
+ :param y: an [N] Tensor of labels, if class-conditional.
+ :return: an [N x C x ...] Tensor of outputs.
+ """
+ assert (y is not None) == (
+ self.num_classes is not None
+ ), "must specify y if and only if the model is class-conditional"
+ hs = []
+ t_emb = timestep_embedding(timesteps, self.model_channels, repeat_only=False)
+ emb = self.time_embed(t_emb)
+
+ if self.num_classes is not None:
+ assert y.shape == (x.shape[0],)
+ emb = emb + self.label_emb(y)
+
+ h = x.type(self.dtype)
+ for module in self.input_blocks:
+ h = module(h, emb, context)
+ hs.append(h)
+ h = self.middle_block(h, emb, context)
+ for module in self.output_blocks:
+ h = th.cat([h, hs.pop()], dim=1)
+ h = module(h, emb, context)
+ h = h.type(x.dtype)
+ if self.predict_codebook_ids:
+ return self.id_predictor(h)
+ else:
+ return self.out(h)
+
+
+class EncoderUNetModel(nn.Module):
+ """
+ The half UNet model with attention and timestep embedding.
+ For usage, see UNet.
+ """
+
+ def __init__(
+ self,
+ image_size,
+ in_channels,
+ model_channels,
+ out_channels,
+ num_res_blocks,
+ attention_resolutions,
+ dropout=0,
+ channel_mult=(1, 2, 4, 8),
+ conv_resample=True,
+ dims=2,
+ use_checkpoint=False,
+ use_fp16=False,
+ num_heads=1,
+ num_head_channels=-1,
+ num_heads_upsample=-1,
+ use_scale_shift_norm=False,
+ resblock_updown=False,
+ use_new_attention_order=False,
+ pool="adaptive",
+ *args,
+ **kwargs
+ ):
+ super().__init__()
+
+ if num_heads_upsample == -1:
+ num_heads_upsample = num_heads
+
+ self.in_channels = in_channels
+ self.model_channels = model_channels
+ self.out_channels = out_channels
+ self.num_res_blocks = num_res_blocks
+ self.attention_resolutions = attention_resolutions
+ self.dropout = dropout
+ self.channel_mult = channel_mult
+ self.conv_resample = conv_resample
+ self.use_checkpoint = use_checkpoint
+ self.dtype = th.float16 if use_fp16 else th.float32
+ self.num_heads = num_heads
+ self.num_head_channels = num_head_channels
+ self.num_heads_upsample = num_heads_upsample
+
+ time_embed_dim = model_channels * 4
+ self.time_embed = nn.Sequential(
+ linear(model_channels, time_embed_dim),
+ nn.SiLU(),
+ linear(time_embed_dim, time_embed_dim),
+ )
+
+ self.input_blocks = nn.ModuleList(
+ [
+ TimestepEmbedSequential(
+ conv_nd(dims, in_channels, model_channels, 3, padding=1)
+ )
+ ]
+ )
+ self._feature_size = model_channels
+ input_block_chans = [model_channels]
+ ch = model_channels
+ ds = 1
+ for level, mult in enumerate(channel_mult):
+ for _ in range(num_res_blocks):
+ layers = [
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ out_channels=mult * model_channels,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ )
+ ]
+ ch = mult * model_channels
+ if ds in attention_resolutions:
+ layers.append(
+ AttentionBlock(
+ ch,
+ use_checkpoint=use_checkpoint,
+ num_heads=num_heads,
+ num_head_channels=num_head_channels,
+ use_new_attention_order=use_new_attention_order,
+ )
+ )
+ self.input_blocks.append(TimestepEmbedSequential(*layers))
+ self._feature_size += ch
+ input_block_chans.append(ch)
+ if level != len(channel_mult) - 1:
+ out_ch = ch
+ self.input_blocks.append(
+ TimestepEmbedSequential(
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ out_channels=out_ch,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ down=True,
+ )
+ if resblock_updown
+ else Downsample(
+ ch, conv_resample, dims=dims, out_channels=out_ch
+ )
+ )
+ )
+ ch = out_ch
+ input_block_chans.append(ch)
+ ds *= 2
+ self._feature_size += ch
+
+ self.middle_block = TimestepEmbedSequential(
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ ),
+ AttentionBlock(
+ ch,
+ use_checkpoint=use_checkpoint,
+ num_heads=num_heads,
+ num_head_channels=num_head_channels,
+ use_new_attention_order=use_new_attention_order,
+ ),
+ ResBlock(
+ ch,
+ time_embed_dim,
+ dropout,
+ dims=dims,
+ use_checkpoint=use_checkpoint,
+ use_scale_shift_norm=use_scale_shift_norm,
+ ),
+ )
+ self._feature_size += ch
+ self.pool = pool
+ if pool == "adaptive":
+ self.out = nn.Sequential(
+ normalization(ch),
+ nn.SiLU(),
+ nn.AdaptiveAvgPool2d((1, 1)),
+ zero_module(conv_nd(dims, ch, out_channels, 1)),
+ nn.Flatten(),
+ )
+ elif pool == "attention":
+ assert num_head_channels != -1
+ self.out = nn.Sequential(
+ normalization(ch),
+ nn.SiLU(),
+ AttentionPool2d(
+ (image_size // ds), ch, num_head_channels, out_channels
+ ),
+ )
+ elif pool == "spatial":
+ self.out = nn.Sequential(
+ nn.Linear(self._feature_size, 2048),
+ nn.ReLU(),
+ nn.Linear(2048, self.out_channels),
+ )
+ elif pool == "spatial_v2":
+ self.out = nn.Sequential(
+ nn.Linear(self._feature_size, 2048),
+ normalization(2048),
+ nn.SiLU(),
+ nn.Linear(2048, self.out_channels),
+ )
+ else:
+ raise NotImplementedError(f"Unexpected {pool} pooling")
+
+ def convert_to_fp16(self):
+ """
+ Convert the torso of the model to float16.
+ """
+ self.input_blocks.apply(convert_module_to_f16)
+ self.middle_block.apply(convert_module_to_f16)
+
+ def convert_to_fp32(self):
+ """
+ Convert the torso of the model to float32.
+ """
+ self.input_blocks.apply(convert_module_to_f32)
+ self.middle_block.apply(convert_module_to_f32)
+
+ def forward(self, x, timesteps):
+ """
+ Apply the model to an input batch.
+ :param x: an [N x C x ...] Tensor of inputs.
+ :param timesteps: a 1-D batch of timesteps.
+ :return: an [N x K] Tensor of outputs.
+ """
+ emb = self.time_embed(timestep_embedding(timesteps, self.model_channels))
+
+ results = []
+ h = x.type(self.dtype)
+ for module in self.input_blocks:
+ h = module(h, emb)
+ if self.pool.startswith("spatial"):
+ results.append(h.type(x.dtype).mean(dim=(2, 3)))
+ h = self.middle_block(h, emb)
+ if self.pool.startswith("spatial"):
+ results.append(h.type(x.dtype).mean(dim=(2, 3)))
+ h = th.cat(results, axis=-1)
+ return self.out(h)
+ else:
+ h = h.type(x.dtype)
+ return self.out(h)
+
diff --git a/stable_diffusion/ldm/modules/distributions/__init__.py b/stable_diffusion/ldm/modules/distributions/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/stable_diffusion/ldm/modules/distributions/distributions.py b/stable_diffusion/ldm/modules/distributions/distributions.py
new file mode 100644
index 0000000000000000000000000000000000000000..f2b8ef901130efc171aa69742ca0244d94d3f2e9
--- /dev/null
+++ b/stable_diffusion/ldm/modules/distributions/distributions.py
@@ -0,0 +1,92 @@
+import torch
+import numpy as np
+
+
+class AbstractDistribution:
+ def sample(self):
+ raise NotImplementedError()
+
+ def mode(self):
+ raise NotImplementedError()
+
+
+class DiracDistribution(AbstractDistribution):
+ def __init__(self, value):
+ self.value = value
+
+ def sample(self):
+ return self.value
+
+ def mode(self):
+ return self.value
+
+
+class DiagonalGaussianDistribution(object):
+ def __init__(self, parameters, deterministic=False):
+ self.parameters = parameters
+ self.mean, self.logvar = torch.chunk(parameters, 2, dim=1)
+ self.logvar = torch.clamp(self.logvar, -30.0, 20.0)
+ self.deterministic = deterministic
+ self.std = torch.exp(0.5 * self.logvar)
+ self.var = torch.exp(self.logvar)
+ if self.deterministic:
+ self.var = self.std = torch.zeros_like(self.mean).to(device=self.parameters.device)
+
+ def sample(self):
+ x = self.mean + self.std * torch.randn(self.mean.shape).to(device=self.parameters.device)
+ return x
+
+ def kl(self, other=None):
+ if self.deterministic:
+ return torch.Tensor([0.])
+ else:
+ if other is None:
+ return 0.5 * torch.sum(torch.pow(self.mean, 2)
+ + self.var - 1.0 - self.logvar,
+ dim=[1, 2, 3])
+ else:
+ return 0.5 * torch.sum(
+ torch.pow(self.mean - other.mean, 2) / other.var
+ + self.var / other.var - 1.0 - self.logvar + other.logvar,
+ dim=[1, 2, 3])
+
+ def nll(self, sample, dims=[1,2,3]):
+ if self.deterministic:
+ return torch.Tensor([0.])
+ logtwopi = np.log(2.0 * np.pi)
+ return 0.5 * torch.sum(
+ logtwopi + self.logvar + torch.pow(sample - self.mean, 2) / self.var,
+ dim=dims)
+
+ def mode(self):
+ return self.mean
+
+
+def normal_kl(mean1, logvar1, mean2, logvar2):
+ """
+ source: https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/losses.py#L12
+ Compute the KL divergence between two gaussians.
+ Shapes are automatically broadcasted, so batches can be compared to
+ scalars, among other use cases.
+ """
+ tensor = None
+ for obj in (mean1, logvar1, mean2, logvar2):
+ if isinstance(obj, torch.Tensor):
+ tensor = obj
+ break
+ assert tensor is not None, "at least one argument must be a Tensor"
+
+ # Force variances to be Tensors. Broadcasting helps convert scalars to
+ # Tensors, but it does not work for torch.exp().
+ logvar1, logvar2 = [
+ x if isinstance(x, torch.Tensor) else torch.tensor(x).to(tensor)
+ for x in (logvar1, logvar2)
+ ]
+
+ return 0.5 * (
+ -1.0
+ + logvar2
+ - logvar1
+ + torch.exp(logvar1 - logvar2)
+ + ((mean1 - mean2) ** 2) * torch.exp(-logvar2)
+ )
diff --git a/stable_diffusion/ldm/modules/ema.py b/stable_diffusion/ldm/modules/ema.py
new file mode 100644
index 0000000000000000000000000000000000000000..c8c75af43565f6e140287644aaaefa97dd6e67c5
--- /dev/null
+++ b/stable_diffusion/ldm/modules/ema.py
@@ -0,0 +1,76 @@
+import torch
+from torch import nn
+
+
+class LitEma(nn.Module):
+ def __init__(self, model, decay=0.9999, use_num_upates=True):
+ super().__init__()
+ if decay < 0.0 or decay > 1.0:
+ raise ValueError('Decay must be between 0 and 1')
+
+ self.m_name2s_name = {}
+ self.register_buffer('decay', torch.tensor(decay, dtype=torch.float32))
+ self.register_buffer('num_updates', torch.tensor(0,dtype=torch.int) if use_num_upates
+ else torch.tensor(-1,dtype=torch.int))
+
+ for name, p in model.named_parameters():
+ if p.requires_grad:
+ #remove as '.'-character is not allowed in buffers
+ s_name = name.replace('.','')
+ self.m_name2s_name.update({name:s_name})
+ self.register_buffer(s_name,p.clone().detach().data)
+
+ self.collected_params = []
+
+ def forward(self,model):
+ decay = self.decay
+
+ if self.num_updates >= 0:
+ self.num_updates += 1
+ decay = min(self.decay,(1 + self.num_updates) / (10 + self.num_updates))
+
+ one_minus_decay = 1.0 - decay
+
+ with torch.no_grad():
+ m_param = dict(model.named_parameters())
+ shadow_params = dict(self.named_buffers())
+
+ for key in m_param:
+ if m_param[key].requires_grad:
+ sname = self.m_name2s_name[key]
+ shadow_params[sname] = shadow_params[sname].type_as(m_param[key])
+ shadow_params[sname].sub_(one_minus_decay * (shadow_params[sname] - m_param[key]))
+ else:
+ assert not key in self.m_name2s_name
+
+ def copy_to(self, model):
+ m_param = dict(model.named_parameters())
+ shadow_params = dict(self.named_buffers())
+ for key in m_param:
+ if m_param[key].requires_grad:
+ m_param[key].data.copy_(shadow_params[self.m_name2s_name[key]].data)
+ else:
+ assert not key in self.m_name2s_name
+
+ def store(self, parameters):
+ """
+ Save the current parameters for restoring later.
+ Args:
+ parameters: Iterable of `torch.nn.Parameter`; the parameters to be
+ temporarily stored.
+ """
+ self.collected_params = [param.clone() for param in parameters]
+
+ def restore(self, parameters):
+ """
+ Restore the parameters stored with the `store` method.
+ Useful to validate the model with EMA parameters without affecting the
+ original optimization process. Store the parameters before the
+ `copy_to` method. After validation (or model saving), use this to
+ restore the former parameters.
+ Args:
+ parameters: Iterable of `torch.nn.Parameter`; the parameters to be
+ updated with the stored parameters.
+ """
+ for c_param, param in zip(self.collected_params, parameters):
+ param.data.copy_(c_param.data)
diff --git a/stable_diffusion/ldm/modules/encoders/__init__.py b/stable_diffusion/ldm/modules/encoders/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/stable_diffusion/ldm/modules/image_degradation/bsrgan.py b/stable_diffusion/ldm/modules/image_degradation/bsrgan.py
new file mode 100644
index 0000000000000000000000000000000000000000..32ef56169978e550090261cddbcf5eb611a6173b
--- /dev/null
+++ b/stable_diffusion/ldm/modules/image_degradation/bsrgan.py
@@ -0,0 +1,730 @@
+# -*- coding: utf-8 -*-
+"""
+# --------------------------------------------
+# Super-Resolution
+# --------------------------------------------
+#
+# Kai Zhang (cskaizhang@gmail.com)
+# https://github.com/cszn
+# From 2019/03--2021/08
+# --------------------------------------------
+"""
+
+import numpy as np
+import cv2
+import torch
+
+from functools import partial
+import random
+from scipy import ndimage
+import scipy
+import scipy.stats as ss
+from scipy.interpolate import interp2d
+from scipy.linalg import orth
+import albumentations
+
+import ldm.modules.image_degradation.utils_image as util
+
+
+def modcrop_np(img, sf):
+ '''
+ Args:
+ img: numpy image, WxH or WxHxC
+ sf: scale factor
+ Return:
+ cropped image
+ '''
+ w, h = img.shape[:2]
+ im = np.copy(img)
+ return im[:w - w % sf, :h - h % sf, ...]
+
+
+"""
+# --------------------------------------------
+# anisotropic Gaussian kernels
+# --------------------------------------------
+"""
+
+
+def analytic_kernel(k):
+ """Calculate the X4 kernel from the X2 kernel (for proof see appendix in paper)"""
+ k_size = k.shape[0]
+ # Calculate the big kernels size
+ big_k = np.zeros((3 * k_size - 2, 3 * k_size - 2))
+ # Loop over the small kernel to fill the big one
+ for r in range(k_size):
+ for c in range(k_size):
+ big_k[2 * r:2 * r + k_size, 2 * c:2 * c + k_size] += k[r, c] * k
+ # Crop the edges of the big kernel to ignore very small values and increase run time of SR
+ crop = k_size // 2
+ cropped_big_k = big_k[crop:-crop, crop:-crop]
+ # Normalize to 1
+ return cropped_big_k / cropped_big_k.sum()
+
+
+def anisotropic_Gaussian(ksize=15, theta=np.pi, l1=6, l2=6):
+ """ generate an anisotropic Gaussian kernel
+ Args:
+ ksize : e.g., 15, kernel size
+ theta : [0, pi], rotation angle range
+ l1 : [0.1,50], scaling of eigenvalues
+ l2 : [0.1,l1], scaling of eigenvalues
+ If l1 = l2, will get an isotropic Gaussian kernel.
+ Returns:
+ k : kernel
+ """
+
+ v = np.dot(np.array([[np.cos(theta), -np.sin(theta)], [np.sin(theta), np.cos(theta)]]), np.array([1., 0.]))
+ V = np.array([[v[0], v[1]], [v[1], -v[0]]])
+ D = np.array([[l1, 0], [0, l2]])
+ Sigma = np.dot(np.dot(V, D), np.linalg.inv(V))
+ k = gm_blur_kernel(mean=[0, 0], cov=Sigma, size=ksize)
+
+ return k
+
+
+def gm_blur_kernel(mean, cov, size=15):
+ center = size / 2.0 + 0.5
+ k = np.zeros([size, size])
+ for y in range(size):
+ for x in range(size):
+ cy = y - center + 1
+ cx = x - center + 1
+ k[y, x] = ss.multivariate_normal.pdf([cx, cy], mean=mean, cov=cov)
+
+ k = k / np.sum(k)
+ return k
+
+
+def shift_pixel(x, sf, upper_left=True):
+ """shift pixel for super-resolution with different scale factors
+ Args:
+ x: WxHxC or WxH
+ sf: scale factor
+ upper_left: shift direction
+ """
+ h, w = x.shape[:2]
+ shift = (sf - 1) * 0.5
+ xv, yv = np.arange(0, w, 1.0), np.arange(0, h, 1.0)
+ if upper_left:
+ x1 = xv + shift
+ y1 = yv + shift
+ else:
+ x1 = xv - shift
+ y1 = yv - shift
+
+ x1 = np.clip(x1, 0, w - 1)
+ y1 = np.clip(y1, 0, h - 1)
+
+ if x.ndim == 2:
+ x = interp2d(xv, yv, x)(x1, y1)
+ if x.ndim == 3:
+ for i in range(x.shape[-1]):
+ x[:, :, i] = interp2d(xv, yv, x[:, :, i])(x1, y1)
+
+ return x
+
+
+def blur(x, k):
+ '''
+ x: image, NxcxHxW
+ k: kernel, Nx1xhxw
+ '''
+ n, c = x.shape[:2]
+ p1, p2 = (k.shape[-2] - 1) // 2, (k.shape[-1] - 1) // 2
+ x = torch.nn.functional.pad(x, pad=(p1, p2, p1, p2), mode='replicate')
+ k = k.repeat(1, c, 1, 1)
+ k = k.view(-1, 1, k.shape[2], k.shape[3])
+ x = x.view(1, -1, x.shape[2], x.shape[3])
+ x = torch.nn.functional.conv2d(x, k, bias=None, stride=1, padding=0, groups=n * c)
+ x = x.view(n, c, x.shape[2], x.shape[3])
+
+ return x
+
+
+def gen_kernel(k_size=np.array([15, 15]), scale_factor=np.array([4, 4]), min_var=0.6, max_var=10., noise_level=0):
+ """"
+ # modified version of https://github.com/assafshocher/BlindSR_dataset_generator
+ # Kai Zhang
+ # min_var = 0.175 * sf # variance of the gaussian kernel will be sampled between min_var and max_var
+ # max_var = 2.5 * sf
+ """
+ # Set random eigen-vals (lambdas) and angle (theta) for COV matrix
+ lambda_1 = min_var + np.random.rand() * (max_var - min_var)
+ lambda_2 = min_var + np.random.rand() * (max_var - min_var)
+ theta = np.random.rand() * np.pi # random theta
+ noise = -noise_level + np.random.rand(*k_size) * noise_level * 2
+
+ # Set COV matrix using Lambdas and Theta
+ LAMBDA = np.diag([lambda_1, lambda_2])
+ Q = np.array([[np.cos(theta), -np.sin(theta)],
+ [np.sin(theta), np.cos(theta)]])
+ SIGMA = Q @ LAMBDA @ Q.T
+ INV_SIGMA = np.linalg.inv(SIGMA)[None, None, :, :]
+
+ # Set expectation position (shifting kernel for aligned image)
+ MU = k_size // 2 - 0.5 * (scale_factor - 1) # - 0.5 * (scale_factor - k_size % 2)
+ MU = MU[None, None, :, None]
+
+ # Create meshgrid for Gaussian
+ [X, Y] = np.meshgrid(range(k_size[0]), range(k_size[1]))
+ Z = np.stack([X, Y], 2)[:, :, :, None]
+
+ # Calcualte Gaussian for every pixel of the kernel
+ ZZ = Z - MU
+ ZZ_t = ZZ.transpose(0, 1, 3, 2)
+ raw_kernel = np.exp(-0.5 * np.squeeze(ZZ_t @ INV_SIGMA @ ZZ)) * (1 + noise)
+
+ # shift the kernel so it will be centered
+ # raw_kernel_centered = kernel_shift(raw_kernel, scale_factor)
+
+ # Normalize the kernel and return
+ # kernel = raw_kernel_centered / np.sum(raw_kernel_centered)
+ kernel = raw_kernel / np.sum(raw_kernel)
+ return kernel
+
+
+def fspecial_gaussian(hsize, sigma):
+ hsize = [hsize, hsize]
+ siz = [(hsize[0] - 1.0) / 2.0, (hsize[1] - 1.0) / 2.0]
+ std = sigma
+ [x, y] = np.meshgrid(np.arange(-siz[1], siz[1] + 1), np.arange(-siz[0], siz[0] + 1))
+ arg = -(x * x + y * y) / (2 * std * std)
+ h = np.exp(arg)
+ h[h < scipy.finfo(float).eps * h.max()] = 0
+ sumh = h.sum()
+ if sumh != 0:
+ h = h / sumh
+ return h
+
+
+def fspecial_laplacian(alpha):
+ alpha = max([0, min([alpha, 1])])
+ h1 = alpha / (alpha + 1)
+ h2 = (1 - alpha) / (alpha + 1)
+ h = [[h1, h2, h1], [h2, -4 / (alpha + 1), h2], [h1, h2, h1]]
+ h = np.array(h)
+ return h
+
+
+def fspecial(filter_type, *args, **kwargs):
+ '''
+ python code from:
+ https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filter/matlab_fspecial.py
+ '''
+ if filter_type == 'gaussian':
+ return fspecial_gaussian(*args, **kwargs)
+ if filter_type == 'laplacian':
+ return fspecial_laplacian(*args, **kwargs)
+
+
+"""
+# --------------------------------------------
+# degradation models
+# --------------------------------------------
+"""
+
+
+def bicubic_degradation(x, sf=3):
+ '''
+ Args:
+ x: HxWxC image, [0, 1]
+ sf: down-scale factor
+ Return:
+ bicubicly downsampled LR image
+ '''
+ x = util.imresize_np(x, scale=1 / sf)
+ return x
+
+
+def srmd_degradation(x, k, sf=3):
+ ''' blur + bicubic downsampling
+ Args:
+ x: HxWxC image, [0, 1]
+ k: hxw, double
+ sf: down-scale factor
+ Return:
+ downsampled LR image
+ Reference:
+ @inproceedings{zhang2018learning,
+ title={Learning a single convolutional super-resolution network for multiple degradations},
+ author={Zhang, Kai and Zuo, Wangmeng and Zhang, Lei},
+ booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
+ pages={3262--3271},
+ year={2018}
+ }
+ '''
+ x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode='wrap') # 'nearest' | 'mirror'
+ x = bicubic_degradation(x, sf=sf)
+ return x
+
+
+def dpsr_degradation(x, k, sf=3):
+ ''' bicubic downsampling + blur
+ Args:
+ x: HxWxC image, [0, 1]
+ k: hxw, double
+ sf: down-scale factor
+ Return:
+ downsampled LR image
+ Reference:
+ @inproceedings{zhang2019deep,
+ title={Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels},
+ author={Zhang, Kai and Zuo, Wangmeng and Zhang, Lei},
+ booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
+ pages={1671--1681},
+ year={2019}
+ }
+ '''
+ x = bicubic_degradation(x, sf=sf)
+ x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode='wrap')
+ return x
+
+
+def classical_degradation(x, k, sf=3):
+ ''' blur + downsampling
+ Args:
+ x: HxWxC image, [0, 1]/[0, 255]
+ k: hxw, double
+ sf: down-scale factor
+ Return:
+ downsampled LR image
+ '''
+ x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode='wrap')
+ # x = filters.correlate(x, np.expand_dims(np.flip(k), axis=2))
+ st = 0
+ return x[st::sf, st::sf, ...]
+
+
+def add_sharpening(img, weight=0.5, radius=50, threshold=10):
+ """USM sharpening. borrowed from real-ESRGAN
+ Input image: I; Blurry image: B.
+ 1. K = I + weight * (I - B)
+ 2. Mask = 1 if abs(I - B) > threshold, else: 0
+ 3. Blur mask:
+ 4. Out = Mask * K + (1 - Mask) * I
+ Args:
+ img (Numpy array): Input image, HWC, BGR; float32, [0, 1].
+ weight (float): Sharp weight. Default: 1.
+ radius (float): Kernel size of Gaussian blur. Default: 50.
+ threshold (int):
+ """
+ if radius % 2 == 0:
+ radius += 1
+ blur = cv2.GaussianBlur(img, (radius, radius), 0)
+ residual = img - blur
+ mask = np.abs(residual) * 255 > threshold
+ mask = mask.astype('float32')
+ soft_mask = cv2.GaussianBlur(mask, (radius, radius), 0)
+
+ K = img + weight * residual
+ K = np.clip(K, 0, 1)
+ return soft_mask * K + (1 - soft_mask) * img
+
+
+def add_blur(img, sf=4):
+ wd2 = 4.0 + sf
+ wd = 2.0 + 0.2 * sf
+ if random.random() < 0.5:
+ l1 = wd2 * random.random()
+ l2 = wd2 * random.random()
+ k = anisotropic_Gaussian(ksize=2 * random.randint(2, 11) + 3, theta=random.random() * np.pi, l1=l1, l2=l2)
+ else:
+ k = fspecial('gaussian', 2 * random.randint(2, 11) + 3, wd * random.random())
+ img = ndimage.filters.convolve(img, np.expand_dims(k, axis=2), mode='mirror')
+
+ return img
+
+
+def add_resize(img, sf=4):
+ rnum = np.random.rand()
+ if rnum > 0.8: # up
+ sf1 = random.uniform(1, 2)
+ elif rnum < 0.7: # down
+ sf1 = random.uniform(0.5 / sf, 1)
+ else:
+ sf1 = 1.0
+ img = cv2.resize(img, (int(sf1 * img.shape[1]), int(sf1 * img.shape[0])), interpolation=random.choice([1, 2, 3]))
+ img = np.clip(img, 0.0, 1.0)
+
+ return img
+
+
+# def add_Gaussian_noise(img, noise_level1=2, noise_level2=25):
+# noise_level = random.randint(noise_level1, noise_level2)
+# rnum = np.random.rand()
+# if rnum > 0.6: # add color Gaussian noise
+# img += np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
+# elif rnum < 0.4: # add grayscale Gaussian noise
+# img += np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
+# else: # add noise
+# L = noise_level2 / 255.
+# D = np.diag(np.random.rand(3))
+# U = orth(np.random.rand(3, 3))
+# conv = np.dot(np.dot(np.transpose(U), D), U)
+# img += np.random.multivariate_normal([0, 0, 0], np.abs(L ** 2 * conv), img.shape[:2]).astype(np.float32)
+# img = np.clip(img, 0.0, 1.0)
+# return img
+
+def add_Gaussian_noise(img, noise_level1=2, noise_level2=25):
+ noise_level = random.randint(noise_level1, noise_level2)
+ rnum = np.random.rand()
+ if rnum > 0.6: # add color Gaussian noise
+ img = img + np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
+ elif rnum < 0.4: # add grayscale Gaussian noise
+ img = img + np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
+ else: # add noise
+ L = noise_level2 / 255.
+ D = np.diag(np.random.rand(3))
+ U = orth(np.random.rand(3, 3))
+ conv = np.dot(np.dot(np.transpose(U), D), U)
+ img = img + np.random.multivariate_normal([0, 0, 0], np.abs(L ** 2 * conv), img.shape[:2]).astype(np.float32)
+ img = np.clip(img, 0.0, 1.0)
+ return img
+
+
+def add_speckle_noise(img, noise_level1=2, noise_level2=25):
+ noise_level = random.randint(noise_level1, noise_level2)
+ img = np.clip(img, 0.0, 1.0)
+ rnum = random.random()
+ if rnum > 0.6:
+ img += img * np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
+ elif rnum < 0.4:
+ img += img * np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
+ else:
+ L = noise_level2 / 255.
+ D = np.diag(np.random.rand(3))
+ U = orth(np.random.rand(3, 3))
+ conv = np.dot(np.dot(np.transpose(U), D), U)
+ img += img * np.random.multivariate_normal([0, 0, 0], np.abs(L ** 2 * conv), img.shape[:2]).astype(np.float32)
+ img = np.clip(img, 0.0, 1.0)
+ return img
+
+
+def add_Poisson_noise(img):
+ img = np.clip((img * 255.0).round(), 0, 255) / 255.
+ vals = 10 ** (2 * random.random() + 2.0) # [2, 4]
+ if random.random() < 0.5:
+ img = np.random.poisson(img * vals).astype(np.float32) / vals
+ else:
+ img_gray = np.dot(img[..., :3], [0.299, 0.587, 0.114])
+ img_gray = np.clip((img_gray * 255.0).round(), 0, 255) / 255.
+ noise_gray = np.random.poisson(img_gray * vals).astype(np.float32) / vals - img_gray
+ img += noise_gray[:, :, np.newaxis]
+ img = np.clip(img, 0.0, 1.0)
+ return img
+
+
+def add_JPEG_noise(img):
+ quality_factor = random.randint(30, 95)
+ img = cv2.cvtColor(util.single2uint(img), cv2.COLOR_RGB2BGR)
+ result, encimg = cv2.imencode('.jpg', img, [int(cv2.IMWRITE_JPEG_QUALITY), quality_factor])
+ img = cv2.imdecode(encimg, 1)
+ img = cv2.cvtColor(util.uint2single(img), cv2.COLOR_BGR2RGB)
+ return img
+
+
+def random_crop(lq, hq, sf=4, lq_patchsize=64):
+ h, w = lq.shape[:2]
+ rnd_h = random.randint(0, h - lq_patchsize)
+ rnd_w = random.randint(0, w - lq_patchsize)
+ lq = lq[rnd_h:rnd_h + lq_patchsize, rnd_w:rnd_w + lq_patchsize, :]
+
+ rnd_h_H, rnd_w_H = int(rnd_h * sf), int(rnd_w * sf)
+ hq = hq[rnd_h_H:rnd_h_H + lq_patchsize * sf, rnd_w_H:rnd_w_H + lq_patchsize * sf, :]
+ return lq, hq
+
+
+def degradation_bsrgan(img, sf=4, lq_patchsize=72, isp_model=None):
+ """
+ This is the degradation model of BSRGAN from the paper
+ "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution"
+ ----------
+ img: HXWXC, [0, 1], its size should be large than (lq_patchsizexsf)x(lq_patchsizexsf)
+ sf: scale factor
+ isp_model: camera ISP model
+ Returns
+ -------
+ img: low-quality patch, size: lq_patchsizeXlq_patchsizeXC, range: [0, 1]
+ hq: corresponding high-quality patch, size: (lq_patchsizexsf)X(lq_patchsizexsf)XC, range: [0, 1]
+ """
+ isp_prob, jpeg_prob, scale2_prob = 0.25, 0.9, 0.25
+ sf_ori = sf
+
+ h1, w1 = img.shape[:2]
+ img = img.copy()[:w1 - w1 % sf, :h1 - h1 % sf, ...] # mod crop
+ h, w = img.shape[:2]
+
+ if h < lq_patchsize * sf or w < lq_patchsize * sf:
+ raise ValueError(f'img size ({h1}X{w1}) is too small!')
+
+ hq = img.copy()
+
+ if sf == 4 and random.random() < scale2_prob: # downsample1
+ if np.random.rand() < 0.5:
+ img = cv2.resize(img, (int(1 / 2 * img.shape[1]), int(1 / 2 * img.shape[0])),
+ interpolation=random.choice([1, 2, 3]))
+ else:
+ img = util.imresize_np(img, 1 / 2, True)
+ img = np.clip(img, 0.0, 1.0)
+ sf = 2
+
+ shuffle_order = random.sample(range(7), 7)
+ idx1, idx2 = shuffle_order.index(2), shuffle_order.index(3)
+ if idx1 > idx2: # keep downsample3 last
+ shuffle_order[idx1], shuffle_order[idx2] = shuffle_order[idx2], shuffle_order[idx1]
+
+ for i in shuffle_order:
+
+ if i == 0:
+ img = add_blur(img, sf=sf)
+
+ elif i == 1:
+ img = add_blur(img, sf=sf)
+
+ elif i == 2:
+ a, b = img.shape[1], img.shape[0]
+ # downsample2
+ if random.random() < 0.75:
+ sf1 = random.uniform(1, 2 * sf)
+ img = cv2.resize(img, (int(1 / sf1 * img.shape[1]), int(1 / sf1 * img.shape[0])),
+ interpolation=random.choice([1, 2, 3]))
+ else:
+ k = fspecial('gaussian', 25, random.uniform(0.1, 0.6 * sf))
+ k_shifted = shift_pixel(k, sf)
+ k_shifted = k_shifted / k_shifted.sum() # blur with shifted kernel
+ img = ndimage.filters.convolve(img, np.expand_dims(k_shifted, axis=2), mode='mirror')
+ img = img[0::sf, 0::sf, ...] # nearest downsampling
+ img = np.clip(img, 0.0, 1.0)
+
+ elif i == 3:
+ # downsample3
+ img = cv2.resize(img, (int(1 / sf * a), int(1 / sf * b)), interpolation=random.choice([1, 2, 3]))
+ img = np.clip(img, 0.0, 1.0)
+
+ elif i == 4:
+ # add Gaussian noise
+ img = add_Gaussian_noise(img, noise_level1=2, noise_level2=25)
+
+ elif i == 5:
+ # add JPEG noise
+ if random.random() < jpeg_prob:
+ img = add_JPEG_noise(img)
+
+ elif i == 6:
+ # add processed camera sensor noise
+ if random.random() < isp_prob and isp_model is not None:
+ with torch.no_grad():
+ img, hq = isp_model.forward(img.copy(), hq)
+
+ # add final JPEG compression noise
+ img = add_JPEG_noise(img)
+
+ # random crop
+ img, hq = random_crop(img, hq, sf_ori, lq_patchsize)
+
+ return img, hq
+
+
+# todo no isp_model?
+def degradation_bsrgan_variant(image, sf=4, isp_model=None):
+ """
+ This is the degradation model of BSRGAN from the paper
+ "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution"
+ ----------
+ sf: scale factor
+ isp_model: camera ISP model
+ Returns
+ -------
+ img: low-quality patch, size: lq_patchsizeXlq_patchsizeXC, range: [0, 1]
+ hq: corresponding high-quality patch, size: (lq_patchsizexsf)X(lq_patchsizexsf)XC, range: [0, 1]
+ """
+ image = util.uint2single(image)
+ isp_prob, jpeg_prob, scale2_prob = 0.25, 0.9, 0.25
+ sf_ori = sf
+
+ h1, w1 = image.shape[:2]
+ image = image.copy()[:w1 - w1 % sf, :h1 - h1 % sf, ...] # mod crop
+ h, w = image.shape[:2]
+
+ hq = image.copy()
+
+ if sf == 4 and random.random() < scale2_prob: # downsample1
+ if np.random.rand() < 0.5:
+ image = cv2.resize(image, (int(1 / 2 * image.shape[1]), int(1 / 2 * image.shape[0])),
+ interpolation=random.choice([1, 2, 3]))
+ else:
+ image = util.imresize_np(image, 1 / 2, True)
+ image = np.clip(image, 0.0, 1.0)
+ sf = 2
+
+ shuffle_order = random.sample(range(7), 7)
+ idx1, idx2 = shuffle_order.index(2), shuffle_order.index(3)
+ if idx1 > idx2: # keep downsample3 last
+ shuffle_order[idx1], shuffle_order[idx2] = shuffle_order[idx2], shuffle_order[idx1]
+
+ for i in shuffle_order:
+
+ if i == 0:
+ image = add_blur(image, sf=sf)
+
+ elif i == 1:
+ image = add_blur(image, sf=sf)
+
+ elif i == 2:
+ a, b = image.shape[1], image.shape[0]
+ # downsample2
+ if random.random() < 0.75:
+ sf1 = random.uniform(1, 2 * sf)
+ image = cv2.resize(image, (int(1 / sf1 * image.shape[1]), int(1 / sf1 * image.shape[0])),
+ interpolation=random.choice([1, 2, 3]))
+ else:
+ k = fspecial('gaussian', 25, random.uniform(0.1, 0.6 * sf))
+ k_shifted = shift_pixel(k, sf)
+ k_shifted = k_shifted / k_shifted.sum() # blur with shifted kernel
+ image = ndimage.filters.convolve(image, np.expand_dims(k_shifted, axis=2), mode='mirror')
+ image = image[0::sf, 0::sf, ...] # nearest downsampling
+ image = np.clip(image, 0.0, 1.0)
+
+ elif i == 3:
+ # downsample3
+ image = cv2.resize(image, (int(1 / sf * a), int(1 / sf * b)), interpolation=random.choice([1, 2, 3]))
+ image = np.clip(image, 0.0, 1.0)
+
+ elif i == 4:
+ # add Gaussian noise
+ image = add_Gaussian_noise(image, noise_level1=2, noise_level2=25)
+
+ elif i == 5:
+ # add JPEG noise
+ if random.random() < jpeg_prob:
+ image = add_JPEG_noise(image)
+
+ # elif i == 6:
+ # # add processed camera sensor noise
+ # if random.random() < isp_prob and isp_model is not None:
+ # with torch.no_grad():
+ # img, hq = isp_model.forward(img.copy(), hq)
+
+ # add final JPEG compression noise
+ image = add_JPEG_noise(image)
+ image = util.single2uint(image)
+ example = {"image":image}
+ return example
+
+
+# TODO incase there is a pickle error one needs to replace a += x with a = a + x in add_speckle_noise etc...
+def degradation_bsrgan_plus(img, sf=4, shuffle_prob=0.5, use_sharp=True, lq_patchsize=64, isp_model=None):
+ """
+ This is an extended degradation model by combining
+ the degradation models of BSRGAN and Real-ESRGAN
+ ----------
+ img: HXWXC, [0, 1], its size should be large than (lq_patchsizexsf)x(lq_patchsizexsf)
+ sf: scale factor
+ use_shuffle: the degradation shuffle
+ use_sharp: sharpening the img
+ Returns
+ -------
+ img: low-quality patch, size: lq_patchsizeXlq_patchsizeXC, range: [0, 1]
+ hq: corresponding high-quality patch, size: (lq_patchsizexsf)X(lq_patchsizexsf)XC, range: [0, 1]
+ """
+
+ h1, w1 = img.shape[:2]
+ img = img.copy()[:w1 - w1 % sf, :h1 - h1 % sf, ...] # mod crop
+ h, w = img.shape[:2]
+
+ if h < lq_patchsize * sf or w < lq_patchsize * sf:
+ raise ValueError(f'img size ({h1}X{w1}) is too small!')
+
+ if use_sharp:
+ img = add_sharpening(img)
+ hq = img.copy()
+
+ if random.random() < shuffle_prob:
+ shuffle_order = random.sample(range(13), 13)
+ else:
+ shuffle_order = list(range(13))
+ # local shuffle for noise, JPEG is always the last one
+ shuffle_order[2:6] = random.sample(shuffle_order[2:6], len(range(2, 6)))
+ shuffle_order[9:13] = random.sample(shuffle_order[9:13], len(range(9, 13)))
+
+ poisson_prob, speckle_prob, isp_prob = 0.1, 0.1, 0.1
+
+ for i in shuffle_order:
+ if i == 0:
+ img = add_blur(img, sf=sf)
+ elif i == 1:
+ img = add_resize(img, sf=sf)
+ elif i == 2:
+ img = add_Gaussian_noise(img, noise_level1=2, noise_level2=25)
+ elif i == 3:
+ if random.random() < poisson_prob:
+ img = add_Poisson_noise(img)
+ elif i == 4:
+ if random.random() < speckle_prob:
+ img = add_speckle_noise(img)
+ elif i == 5:
+ if random.random() < isp_prob and isp_model is not None:
+ with torch.no_grad():
+ img, hq = isp_model.forward(img.copy(), hq)
+ elif i == 6:
+ img = add_JPEG_noise(img)
+ elif i == 7:
+ img = add_blur(img, sf=sf)
+ elif i == 8:
+ img = add_resize(img, sf=sf)
+ elif i == 9:
+ img = add_Gaussian_noise(img, noise_level1=2, noise_level2=25)
+ elif i == 10:
+ if random.random() < poisson_prob:
+ img = add_Poisson_noise(img)
+ elif i == 11:
+ if random.random() < speckle_prob:
+ img = add_speckle_noise(img)
+ elif i == 12:
+ if random.random() < isp_prob and isp_model is not None:
+ with torch.no_grad():
+ img, hq = isp_model.forward(img.copy(), hq)
+ else:
+ print('check the shuffle!')
+
+ # resize to desired size
+ img = cv2.resize(img, (int(1 / sf * hq.shape[1]), int(1 / sf * hq.shape[0])),
+ interpolation=random.choice([1, 2, 3]))
+
+ # add final JPEG compression noise
+ img = add_JPEG_noise(img)
+
+ # random crop
+ img, hq = random_crop(img, hq, sf, lq_patchsize)
+
+ return img, hq
+
+
+if __name__ == '__main__':
+ print("hey")
+ img = util.imread_uint('utils/test.png', 3)
+ print(img)
+ img = util.uint2single(img)
+ print(img)
+ img = img[:448, :448]
+ h = img.shape[0] // 4
+ print("resizing to", h)
+ sf = 4
+ deg_fn = partial(degradation_bsrgan_variant, sf=sf)
+ for i in range(20):
+ print(i)
+ img_lq = deg_fn(img)
+ print(img_lq)
+ img_lq_bicubic = albumentations.SmallestMaxSize(max_size=h, interpolation=cv2.INTER_CUBIC)(image=img)["image"]
+ print(img_lq.shape)
+ print("bicubic", img_lq_bicubic.shape)
+ print(img_hq.shape)
+ lq_nearest = cv2.resize(util.single2uint(img_lq), (int(sf * img_lq.shape[1]), int(sf * img_lq.shape[0])),
+ interpolation=0)
+ lq_bicubic_nearest = cv2.resize(util.single2uint(img_lq_bicubic), (int(sf * img_lq.shape[1]), int(sf * img_lq.shape[0])),
+ interpolation=0)
+ img_concat = np.concatenate([lq_bicubic_nearest, lq_nearest, util.single2uint(img_hq)], axis=1)
+ util.imsave(img_concat, str(i) + '.png')
+
+
diff --git a/stable_diffusion/ldm/modules/losses/__init__.py b/stable_diffusion/ldm/modules/losses/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..876d7c5bd6e3245ee77feb4c482b7a8143604ad5
--- /dev/null
+++ b/stable_diffusion/ldm/modules/losses/__init__.py
@@ -0,0 +1 @@
+from ldm.modules.losses.contperceptual import LPIPSWithDiscriminator
\ No newline at end of file
diff --git a/stable_diffusion/ldm/modules/losses/contperceptual.py b/stable_diffusion/ldm/modules/losses/contperceptual.py
new file mode 100644
index 0000000000000000000000000000000000000000..672c1e32a1389def02461c0781339681060c540e
--- /dev/null
+++ b/stable_diffusion/ldm/modules/losses/contperceptual.py
@@ -0,0 +1,111 @@
+import torch
+import torch.nn as nn
+
+from taming.modules.losses.vqperceptual import * # TODO: taming dependency yes/no?
+
+
+class LPIPSWithDiscriminator(nn.Module):
+ def __init__(self, disc_start, logvar_init=0.0, kl_weight=1.0, pixelloss_weight=1.0,
+ disc_num_layers=3, disc_in_channels=3, disc_factor=1.0, disc_weight=1.0,
+ perceptual_weight=1.0, use_actnorm=False, disc_conditional=False,
+ disc_loss="hinge"):
+
+ super().__init__()
+ assert disc_loss in ["hinge", "vanilla"]
+ self.kl_weight = kl_weight
+ self.pixel_weight = pixelloss_weight
+ self.perceptual_loss = LPIPS().eval()
+ self.perceptual_weight = perceptual_weight
+ # output log variance
+ self.logvar = nn.Parameter(torch.ones(size=()) * logvar_init)
+
+ self.discriminator = NLayerDiscriminator(input_nc=disc_in_channels,
+ n_layers=disc_num_layers,
+ use_actnorm=use_actnorm
+ ).apply(weights_init)
+ self.discriminator_iter_start = disc_start
+ self.disc_loss = hinge_d_loss if disc_loss == "hinge" else vanilla_d_loss
+ self.disc_factor = disc_factor
+ self.discriminator_weight = disc_weight
+ self.disc_conditional = disc_conditional
+
+ def calculate_adaptive_weight(self, nll_loss, g_loss, last_layer=None):
+ if last_layer is not None:
+ nll_grads = torch.autograd.grad(nll_loss, last_layer, retain_graph=True)[0]
+ g_grads = torch.autograd.grad(g_loss, last_layer, retain_graph=True)[0]
+ else:
+ nll_grads = torch.autograd.grad(nll_loss, self.last_layer[0], retain_graph=True)[0]
+ g_grads = torch.autograd.grad(g_loss, self.last_layer[0], retain_graph=True)[0]
+
+ d_weight = torch.norm(nll_grads) / (torch.norm(g_grads) + 1e-4)
+ d_weight = torch.clamp(d_weight, 0.0, 1e4).detach()
+ d_weight = d_weight * self.discriminator_weight
+ return d_weight
+
+ def forward(self, inputs, reconstructions, posteriors, optimizer_idx,
+ global_step, last_layer=None, cond=None, split="train",
+ weights=None):
+ rec_loss = torch.abs(inputs.contiguous() - reconstructions.contiguous())
+ if self.perceptual_weight > 0:
+ p_loss = self.perceptual_loss(inputs.contiguous(), reconstructions.contiguous())
+ rec_loss = rec_loss + self.perceptual_weight * p_loss
+
+ nll_loss = rec_loss / torch.exp(self.logvar) + self.logvar
+ weighted_nll_loss = nll_loss
+ if weights is not None:
+ weighted_nll_loss = weights*nll_loss
+ weighted_nll_loss = torch.sum(weighted_nll_loss) / weighted_nll_loss.shape[0]
+ nll_loss = torch.sum(nll_loss) / nll_loss.shape[0]
+ kl_loss = posteriors.kl()
+ kl_loss = torch.sum(kl_loss) / kl_loss.shape[0]
+
+ # now the GAN part
+ if optimizer_idx == 0:
+ # generator update
+ if cond is None:
+ assert not self.disc_conditional
+ logits_fake = self.discriminator(reconstructions.contiguous())
+ else:
+ assert self.disc_conditional
+ logits_fake = self.discriminator(torch.cat((reconstructions.contiguous(), cond), dim=1))
+ g_loss = -torch.mean(logits_fake)
+
+ if self.disc_factor > 0.0:
+ try:
+ d_weight = self.calculate_adaptive_weight(nll_loss, g_loss, last_layer=last_layer)
+ except RuntimeError:
+ assert not self.training
+ d_weight = torch.tensor(0.0)
+ else:
+ d_weight = torch.tensor(0.0)
+
+ disc_factor = adopt_weight(self.disc_factor, global_step, threshold=self.discriminator_iter_start)
+ loss = weighted_nll_loss + self.kl_weight * kl_loss + d_weight * disc_factor * g_loss
+
+ log = {"{}/total_loss".format(split): loss.clone().detach().mean(), "{}/logvar".format(split): self.logvar.detach(),
+ "{}/kl_loss".format(split): kl_loss.detach().mean(), "{}/nll_loss".format(split): nll_loss.detach().mean(),
+ "{}/rec_loss".format(split): rec_loss.detach().mean(),
+ "{}/d_weight".format(split): d_weight.detach(),
+ "{}/disc_factor".format(split): torch.tensor(disc_factor),
+ "{}/g_loss".format(split): g_loss.detach().mean(),
+ }
+ return loss, log
+
+ if optimizer_idx == 1:
+ # second pass for discriminator update
+ if cond is None:
+ logits_real = self.discriminator(inputs.contiguous().detach())
+ logits_fake = self.discriminator(reconstructions.contiguous().detach())
+ else:
+ logits_real = self.discriminator(torch.cat((inputs.contiguous().detach(), cond), dim=1))
+ logits_fake = self.discriminator(torch.cat((reconstructions.contiguous().detach(), cond), dim=1))
+
+ disc_factor = adopt_weight(self.disc_factor, global_step, threshold=self.discriminator_iter_start)
+ d_loss = disc_factor * self.disc_loss(logits_real, logits_fake)
+
+ log = {"{}/disc_loss".format(split): d_loss.clone().detach().mean(),
+ "{}/logits_real".format(split): logits_real.detach().mean(),
+ "{}/logits_fake".format(split): logits_fake.detach().mean()
+ }
+ return d_loss, log
+
diff --git a/stable_diffusion/ldm/util.py b/stable_diffusion/ldm/util.py
new file mode 100644
index 0000000000000000000000000000000000000000..8ba38853e7a07228cc2c187742b5c45d7359b3f9
--- /dev/null
+++ b/stable_diffusion/ldm/util.py
@@ -0,0 +1,203 @@
+import importlib
+
+import torch
+import numpy as np
+from collections import abc
+from einops import rearrange
+from functools import partial
+
+import multiprocessing as mp
+from threading import Thread
+from queue import Queue
+
+from inspect import isfunction
+from PIL import Image, ImageDraw, ImageFont
+
+
+def log_txt_as_img(wh, xc, size=10):
+ # wh a tuple of (width, height)
+ # xc a list of captions to plot
+ b = len(xc)
+ txts = list()
+ for bi in range(b):
+ txt = Image.new("RGB", wh, color="white")
+ draw = ImageDraw.Draw(txt)
+ font = ImageFont.truetype('data/DejaVuSans.ttf', size=size)
+ nc = int(40 * (wh[0] / 256))
+ lines = "\n".join(xc[bi][start:start + nc] for start in range(0, len(xc[bi]), nc))
+
+ try:
+ draw.text((0, 0), lines, fill="black", font=font)
+ except UnicodeEncodeError:
+ print("Cant encode string for logging. Skipping.")
+
+ txt = np.array(txt).transpose(2, 0, 1) / 127.5 - 1.0
+ txts.append(txt)
+ txts = np.stack(txts)
+ txts = torch.tensor(txts)
+ return txts
+
+
+def ismap(x):
+ if not isinstance(x, torch.Tensor):
+ return False
+ return (len(x.shape) == 4) and (x.shape[1] > 3)
+
+
+def isimage(x):
+ if not isinstance(x, torch.Tensor):
+ return False
+ return (len(x.shape) == 4) and (x.shape[1] == 3 or x.shape[1] == 1)
+
+
+def exists(x):
+ return x is not None
+
+
+def default(val, d):
+ if exists(val):
+ return val
+ return d() if isfunction(d) else d
+
+
+def mean_flat(tensor):
+ """
+ https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/nn.py#L86
+ Take the mean over all non-batch dimensions.
+ """
+ return tensor.mean(dim=list(range(1, len(tensor.shape))))
+
+
+def count_params(model, verbose=False):
+ total_params = sum(p.numel() for p in model.parameters())
+ if verbose:
+ print(f"{model.__class__.__name__} has {total_params * 1.e-6:.2f} M params.")
+ return total_params
+
+
+def instantiate_from_config(config):
+ if not "target" in config:
+ if config == '__is_first_stage__':
+ return None
+ elif config == "__is_unconditional__":
+ return None
+ raise KeyError("Expected key `target` to instantiate.")
+ return get_obj_from_str(config["target"])(**config.get("params", dict()))
+
+
+def get_obj_from_str(string, reload=False):
+ module, cls = string.rsplit(".", 1)
+ if reload:
+ module_imp = importlib.import_module(module)
+ importlib.reload(module_imp)
+ return getattr(importlib.import_module(module, package=None), cls)
+
+
+def _do_parallel_data_prefetch(func, Q, data, idx, idx_to_fn=False):
+ # create dummy dataset instance
+
+ # run prefetching
+ if idx_to_fn:
+ res = func(data, worker_id=idx)
+ else:
+ res = func(data)
+ Q.put([idx, res])
+ Q.put("Done")
+
+
+def parallel_data_prefetch(
+ func: callable, data, n_proc, target_data_type="ndarray", cpu_intensive=True, use_worker_id=False
+):
+ # if target_data_type not in ["ndarray", "list"]:
+ # raise ValueError(
+ # "Data, which is passed to parallel_data_prefetch has to be either of type list or ndarray."
+ # )
+ if isinstance(data, np.ndarray) and target_data_type == "list":
+ raise ValueError("list expected but function got ndarray.")
+ elif isinstance(data, abc.Iterable):
+ if isinstance(data, dict):
+ print(
+ f'WARNING:"data" argument passed to parallel_data_prefetch is a dict: Using only its values and disregarding keys.'
+ )
+ data = list(data.values())
+ if target_data_type == "ndarray":
+ data = np.asarray(data)
+ else:
+ data = list(data)
+ else:
+ raise TypeError(
+ f"The data, that shall be processed parallel has to be either an np.ndarray or an Iterable, but is actually {type(data)}."
+ )
+
+ if cpu_intensive:
+ Q = mp.Queue(1000)
+ proc = mp.Process
+ else:
+ Q = Queue(1000)
+ proc = Thread
+ # spawn processes
+ if target_data_type == "ndarray":
+ arguments = [
+ [func, Q, part, i, use_worker_id]
+ for i, part in enumerate(np.array_split(data, n_proc))
+ ]
+ else:
+ step = (
+ int(len(data) / n_proc + 1)
+ if len(data) % n_proc != 0
+ else int(len(data) / n_proc)
+ )
+ arguments = [
+ [func, Q, part, i, use_worker_id]
+ for i, part in enumerate(
+ [data[i: i + step] for i in range(0, len(data), step)]
+ )
+ ]
+ processes = []
+ for i in range(n_proc):
+ p = proc(target=_do_parallel_data_prefetch, args=arguments[i])
+ processes += [p]
+
+ # start processes
+ print(f"Start prefetching...")
+ import time
+
+ start = time.time()
+ gather_res = [[] for _ in range(n_proc)]
+ try:
+ for p in processes:
+ p.start()
+
+ k = 0
+ while k < n_proc:
+ # get result
+ res = Q.get()
+ if res == "Done":
+ k += 1
+ else:
+ gather_res[res[0]] = res[1]
+
+ except Exception as e:
+ print("Exception: ", e)
+ for p in processes:
+ p.terminate()
+
+ raise e
+ finally:
+ for p in processes:
+ p.join()
+ print(f"Prefetching complete. [{time.time() - start} sec.]")
+
+ if target_data_type == 'ndarray':
+ if not isinstance(gather_res[0], np.ndarray):
+ return np.concatenate([np.asarray(r) for r in gather_res], axis=0)
+
+ # order outputs
+ return np.concatenate(gather_res, axis=0)
+ elif target_data_type == 'list':
+ out = []
+ for r in gather_res:
+ out.extend(r)
+ return out
+ else:
+ return gather_res
diff --git a/stable_diffusion/main copy.py b/stable_diffusion/main copy.py
new file mode 100644
index 0000000000000000000000000000000000000000..193c50a86a307bd69f52a0c3b89fb5368ed9a222
--- /dev/null
+++ b/stable_diffusion/main copy.py
@@ -0,0 +1,744 @@
+import argparse, os, sys, datetime, glob, importlib, csv
+import numpy as np
+import time
+import torch
+import torchvision
+import pytorch_lightning as pl
+
+from packaging import version
+from omegaconf import OmegaConf
+from torch.utils.data import random_split, DataLoader, Dataset, Subset
+from functools import partial
+from PIL import Image
+
+from pytorch_lightning import seed_everything
+from pytorch_lightning.trainer import Trainer
+from pytorch_lightning.callbacks import ModelCheckpoint, Callback, LearningRateMonitor
+from pytorch_lightning.utilities.distributed import rank_zero_only
+from pytorch_lightning.utilities import rank_zero_info
+
+from ldm.data.base import Txt2ImgIterableBaseDataset
+from ldm.util import instantiate_from_config
+
+
+def get_parser(**parser_kwargs):
+ def str2bool(v):
+ if isinstance(v, bool):
+ return v
+ if v.lower() in ("yes", "true", "t", "y", "1"):
+ return True
+ elif v.lower() in ("no", "false", "f", "n", "0"):
+ return False
+ else:
+ raise argparse.ArgumentTypeError("Boolean value expected.")
+
+ parser = argparse.ArgumentParser(**parser_kwargs)
+ parser.add_argument(
+ "-n",
+ "--name",
+ type=str,
+ const=True,
+ default="",
+ nargs="?",
+ help="postfix for logdir",
+ )
+ parser.add_argument(
+ "-r",
+ "--resume",
+ type=str,
+ const=True,
+ default="",
+ nargs="?",
+ help="resume from logdir or checkpoint in logdir",
+ )
+ parser.add_argument(
+ "-b",
+ "--base",
+ nargs="*",
+ metavar="base_config.yaml",
+ help="paths to base configs. Loaded from left-to-right. "
+ "Parameters can be overwritten or added with command-line options of the form `--key value`.",
+ default=list(),
+ )
+ parser.add_argument(
+ "-t",
+ "--train",
+ type=str2bool,
+ const=True,
+ default=False,
+ nargs="?",
+ help="train",
+ )
+ parser.add_argument(
+ "--no-test",
+ type=str2bool,
+ const=True,
+ default=False,
+ nargs="?",
+ help="disable test",
+ )
+ parser.add_argument(
+ "-p",
+ "--project",
+ help="name of new or path to existing project"
+ )
+ parser.add_argument(
+ "-d",
+ "--debug",
+ type=str2bool,
+ nargs="?",
+ const=True,
+ default=False,
+ help="enable post-mortem debugging",
+ )
+ parser.add_argument(
+ "-s",
+ "--seed",
+ type=int,
+ default=23,
+ help="seed for seed_everything",
+ )
+ parser.add_argument(
+ "-f",
+ "--postfix",
+ type=str,
+ default="",
+ help="post-postfix for default name",
+ )
+ parser.add_argument(
+ "-l",
+ "--logdir",
+ type=str,
+ default="logs",
+ help="directory for logging dat shit",
+ )
+ parser.add_argument(
+ "--scale_lr",
+ type=str2bool,
+ nargs="?",
+ const=True,
+ default=True,
+ help="scale base-lr by ngpu * batch_size * n_accumulate",
+ )
+ return parser
+
+
+def nondefault_trainer_args(opt):
+ parser = argparse.ArgumentParser()
+ parser = Trainer.add_argparse_args(parser)
+ args = parser.parse_args([])
+ return sorted(k for k in vars(args) if getattr(opt, k) != getattr(args, k))
+
+
+class WrappedDataset(Dataset):
+ """Wraps an arbitrary object with __len__ and __getitem__ into a pytorch dataset"""
+
+ def __init__(self, dataset):
+ self.data = dataset
+
+ def __len__(self):
+ return len(self.data)
+
+ def __getitem__(self, idx):
+ return self.data[idx]
+
+
+def worker_init_fn(_):
+ worker_info = torch.utils.data.get_worker_info()
+
+ dataset = worker_info.dataset
+ worker_id = worker_info.id
+
+ if isinstance(dataset, Txt2ImgIterableBaseDataset):
+ split_size = dataset.num_records // worker_info.num_workers
+ # reset num_records to the true number to retain reliable length information
+ dataset.sample_ids = dataset.valid_ids[worker_id * split_size:(worker_id + 1) * split_size]
+ current_id = np.random.choice(len(np.random.get_state()[1]), 1)
+ return np.random.seed(np.random.get_state()[1][current_id] + worker_id)
+ else:
+ return np.random.seed(np.random.get_state()[1][0] + worker_id)
+
+
+class DataModuleFromConfig(pl.LightningDataModule):
+ def __init__(self, batch_size, train=None, validation=None, test=None, predict=None,
+ wrap=False, num_workers=None, shuffle_test_loader=False, use_worker_init_fn=False,
+ shuffle_val_dataloader=False):
+ super().__init__()
+ self.batch_size = batch_size
+ self.dataset_configs = dict()
+ self.num_workers = num_workers if num_workers is not None else batch_size * 2
+ self.use_worker_init_fn = use_worker_init_fn
+ if train is not None:
+ self.dataset_configs["train"] = train
+ self.train_dataloader = self._train_dataloader
+ if validation is not None:
+ self.dataset_configs["validation"] = validation
+ self.val_dataloader = partial(self._val_dataloader, shuffle=shuffle_val_dataloader)
+ if test is not None:
+ self.dataset_configs["test"] = test
+ self.test_dataloader = partial(self._test_dataloader, shuffle=shuffle_test_loader)
+ if predict is not None:
+ self.dataset_configs["predict"] = predict
+ self.predict_dataloader = self._predict_dataloader
+ self.wrap = wrap
+
+ def prepare_data(self):
+ for data_cfg in self.dataset_configs.values():
+ instantiate_from_config(data_cfg)
+
+ def setup(self, stage=None):
+ self.datasets = dict(
+ (k, instantiate_from_config(self.dataset_configs[k]))
+ for k in self.dataset_configs)
+ if self.wrap:
+ for k in self.datasets:
+ self.datasets[k] = WrappedDataset(self.datasets[k])
+
+ def _train_dataloader(self):
+ is_iterable_dataset = isinstance(self.datasets['train'], Txt2ImgIterableBaseDataset)
+ if is_iterable_dataset or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["train"], batch_size=self.batch_size,
+ num_workers=self.num_workers, shuffle=False if is_iterable_dataset else True,
+ worker_init_fn=init_fn)
+
+ def _val_dataloader(self, shuffle=False):
+ if isinstance(self.datasets['validation'], Txt2ImgIterableBaseDataset) or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["validation"],
+ batch_size=self.batch_size,
+ num_workers=self.num_workers,
+ worker_init_fn=init_fn,
+ shuffle=shuffle)
+
+ def _test_dataloader(self, shuffle=False):
+ is_iterable_dataset = isinstance(self.datasets['train'], Txt2ImgIterableBaseDataset)
+ if is_iterable_dataset or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+
+ # do not shuffle dataloader for iterable dataset
+ shuffle = shuffle and (not is_iterable_dataset)
+
+ return DataLoader(self.datasets["test"], batch_size=self.batch_size,
+ num_workers=self.num_workers, worker_init_fn=init_fn, shuffle=shuffle)
+
+ def _predict_dataloader(self, shuffle=False):
+ if isinstance(self.datasets['predict'], Txt2ImgIterableBaseDataset) or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["predict"], batch_size=self.batch_size,
+ num_workers=self.num_workers, worker_init_fn=init_fn)
+
+
+class SetupCallback(Callback):
+ def __init__(self, resume, now, logdir, ckptdir, cfgdir, config, lightning_config):
+ super().__init__()
+ self.resume = resume
+ self.now = now
+ self.logdir = logdir
+ self.ckptdir = ckptdir
+ self.cfgdir = cfgdir
+ self.config = config
+ self.lightning_config = lightning_config
+
+ def on_keyboard_interrupt(self, trainer, pl_module):
+ if trainer.global_rank == 0:
+ print("Summoning checkpoint.")
+ ckpt_path = os.path.join(self.ckptdir, "last.ckpt")
+ trainer.save_checkpoint(ckpt_path)
+
+ def on_pretrain_routine_start(self, trainer, pl_module):
+ if trainer.global_rank == 0:
+ # Create logdirs and save configs
+ os.makedirs(self.logdir, exist_ok=True)
+ os.makedirs(self.ckptdir, exist_ok=True)
+ os.makedirs(self.cfgdir, exist_ok=True)
+
+ if "callbacks" in self.lightning_config:
+ if 'metrics_over_trainsteps_checkpoint' in self.lightning_config['callbacks']:
+ os.makedirs(os.path.join(self.ckptdir, 'trainstep_checkpoints'), exist_ok=True)
+ print("Project config")
+ print(OmegaConf.to_yaml(self.config))
+ OmegaConf.save(self.config,
+ os.path.join(self.cfgdir, "{}-project.yaml".format(self.now)))
+
+ print("Lightning config")
+ print(OmegaConf.to_yaml(self.lightning_config))
+ OmegaConf.save(OmegaConf.create({"lightning": self.lightning_config}),
+ os.path.join(self.cfgdir, "{}-lightning.yaml".format(self.now)))
+
+ else:
+ # ModelCheckpoint callback created log directory --- remove it
+ if not self.resume and os.path.exists(self.logdir):
+ dst, name = os.path.split(self.logdir)
+ dst = os.path.join(dst, "child_runs", name)
+ os.makedirs(os.path.split(dst)[0], exist_ok=True)
+ try:
+ os.rename(self.logdir, dst)
+ except FileNotFoundError:
+ pass
+
+
+class ImageLogger(Callback):
+ def __init__(self, batch_frequency, max_images, clamp=True, increase_log_steps=True,
+ rescale=True, disabled=False, log_on_batch_idx=False, log_first_step=False,
+ log_images_kwargs=None):
+ super().__init__()
+ self.rescale = rescale
+ self.batch_freq = batch_frequency
+ self.max_images = max_images
+ self.logger_log_images = {
+ pl.loggers.TestTubeLogger: self._testtube,
+ }
+ self.log_steps = [2 ** n for n in range(int(np.log2(self.batch_freq)) + 1)]
+ if not increase_log_steps:
+ self.log_steps = [self.batch_freq]
+ self.clamp = clamp
+ self.disabled = disabled
+ self.log_on_batch_idx = log_on_batch_idx
+ self.log_images_kwargs = log_images_kwargs if log_images_kwargs else {}
+ self.log_first_step = log_first_step
+
+ @rank_zero_only
+ def _testtube(self, pl_module, images, batch_idx, split):
+ for k in images:
+ grid = torchvision.utils.make_grid(images[k])
+ grid = (grid + 1.0) / 2.0 # -1,1 -> 0,1; c,h,w
+
+ tag = f"{split}/{k}"
+ pl_module.logger.experiment.add_image(
+ tag, grid,
+ global_step=pl_module.global_step)
+
+ @rank_zero_only
+ def log_local(self, save_dir, split, images,
+ global_step, current_epoch, batch_idx):
+ root = os.path.join(save_dir, "images", split)
+ for k in images:
+ grid = torchvision.utils.make_grid(images[k], nrow=4)
+ if self.rescale:
+ grid = (grid + 1.0) / 2.0 # -1,1 -> 0,1; c,h,w
+ grid = grid.transpose(0, 1).transpose(1, 2).squeeze(-1)
+ grid = grid.numpy()
+ grid = (grid * 255).astype(np.uint8)
+ filename = "{}_gs-{:06}_e-{:06}_b-{:06}.png".format(
+ k,
+ global_step,
+ current_epoch,
+ batch_idx)
+ path = os.path.join(root, filename)
+ os.makedirs(os.path.split(path)[0], exist_ok=True)
+ Image.fromarray(grid).save(path)
+
+ def log_img(self, pl_module, batch, batch_idx, split="train"):
+ check_idx = batch_idx if self.log_on_batch_idx else pl_module.global_step
+ if (self.check_frequency(check_idx) and # batch_idx % self.batch_freq == 0
+ hasattr(pl_module, "log_images") and
+ callable(pl_module.log_images) and
+ self.max_images > 0):
+ logger = type(pl_module.logger)
+
+ is_train = pl_module.training
+ if is_train:
+ pl_module.eval()
+
+ with torch.no_grad():
+ images = pl_module.log_images(batch, split=split, **self.log_images_kwargs)
+
+ for k in images:
+ N = min(images[k].shape[0], self.max_images)
+ images[k] = images[k][:N]
+ if isinstance(images[k], torch.Tensor):
+ images[k] = images[k].detach().cpu()
+ if self.clamp:
+ images[k] = torch.clamp(images[k], -1., 1.)
+
+ self.log_local(pl_module.logger.save_dir, split, images,
+ pl_module.global_step, pl_module.current_epoch, batch_idx)
+
+ logger_log_images = self.logger_log_images.get(logger, lambda *args, **kwargs: None)
+ logger_log_images(pl_module, images, pl_module.global_step, split)
+
+ if is_train:
+ pl_module.train()
+
+ def check_frequency(self, check_idx):
+ if ((check_idx % self.batch_freq) == 0 or (check_idx in self.log_steps)) and (
+ check_idx > 0 or self.log_first_step):
+ try:
+ self.log_steps.pop(0)
+ except IndexError as e:
+ print(e)
+ pass
+ return True
+ return False
+
+ def on_train_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
+ if not self.disabled and (pl_module.global_step > 0 or self.log_first_step):
+ self.log_img(pl_module, batch, batch_idx, split="train")
+
+ def on_validation_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
+ if not self.disabled and pl_module.global_step > 0:
+ self.log_img(pl_module, batch, batch_idx, split="val")
+ if hasattr(pl_module, 'calibrate_grad_norm'):
+ if (pl_module.calibrate_grad_norm and batch_idx % 25 == 0) and batch_idx > 0:
+ self.log_gradients(trainer, pl_module, batch_idx=batch_idx)
+
+
+class CUDACallback(Callback):
+ # see https://github.com/SeanNaren/minGPT/blob/master/mingpt/callback.py
+ def on_train_epoch_start(self, trainer, pl_module):
+ # Reset the memory use counter
+ torch.cuda.reset_peak_memory_stats(trainer.root_gpu)
+ torch.cuda.synchronize(trainer.root_gpu)
+ self.start_time = time.time()
+
+ def on_train_epoch_end(self, trainer, pl_module, outputs):
+ torch.cuda.synchronize(trainer.root_gpu)
+ max_memory = torch.cuda.max_memory_allocated(trainer.root_gpu) / 2 ** 20
+ epoch_time = time.time() - self.start_time
+
+ try:
+ max_memory = trainer.training_type_plugin.reduce(max_memory)
+ epoch_time = trainer.training_type_plugin.reduce(epoch_time)
+
+ rank_zero_info(f"Average Epoch time: {epoch_time:.2f} seconds")
+ rank_zero_info(f"Average Peak memory {max_memory:.2f}MiB")
+ except AttributeError:
+ pass
+
+
+if __name__ == "__main__":
+ # custom parser to specify config files, train, test and debug mode,
+ # postfix, resume.
+ # `--key value` arguments are interpreted as arguments to the trainer.
+ # `nested.key=value` arguments are interpreted as config parameters.
+ # configs are merged from left-to-right followed by command line parameters.
+
+ # model:
+ # base_learning_rate: float
+ # target: path to lightning module
+ # params:
+ # key: value
+ # data:
+ # target: main.DataModuleFromConfig
+ # params:
+ # batch_size: int
+ # wrap: bool
+ # train:
+ # target: path to train dataset
+ # params:
+ # key: value
+ # validation:
+ # target: path to validation dataset
+ # params:
+ # key: value
+ # test:
+ # target: path to test dataset
+ # params:
+ # key: value
+ # lightning: (optional, has sane defaults and can be specified on cmdline)
+ # trainer:
+ # additional arguments to trainer
+ # logger:
+ # logger to instantiate
+ # modelcheckpoint:
+ # modelcheckpoint to instantiate
+ # callbacks:
+ # callback1:
+ # target: importpath
+ # params:
+ # key: value
+
+ now = datetime.datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
+
+ # add cwd for convenience and to make classes in this file available when
+ # running as `python main.py`
+ # (in particular `main.DataModuleFromConfig`)
+ sys.path.append(os.getcwd())
+
+ parser = get_parser()
+ parser = Trainer.add_argparse_args(parser)
+
+ opt, unknown = parser.parse_known_args()
+ if opt.name and opt.resume:
+ raise ValueError(
+ "-n/--name and -r/--resume cannot be specified both."
+ "If you want to resume training in a new log folder, "
+ "use -n/--name in combination with --resume_from_checkpoint"
+ )
+ if opt.resume:
+ if not os.path.exists(opt.resume):
+ raise ValueError("Cannot find {}".format(opt.resume))
+ if os.path.isfile(opt.resume):
+ paths = opt.resume.split("/")
+ # idx = len(paths)-paths[::-1].index("logs")+1
+ # logdir = "/".join(paths[:idx])
+ logdir = "/".join(paths[:-2])
+ ckpt = opt.resume
+ else:
+ assert os.path.isdir(opt.resume), opt.resume
+ logdir = opt.resume.rstrip("/")
+ ckpt = os.path.join(logdir, "checkpoints", "last.ckpt")
+
+ opt.resume_from_checkpoint = ckpt
+ base_configs = sorted(glob.glob(os.path.join(logdir, "configs/*.yaml")))
+ opt.base = base_configs + opt.base
+ _tmp = logdir.split("/")
+ nowname = _tmp[-1]
+ else:
+ if opt.name:
+ name = "_" + opt.name
+ elif opt.base:
+ cfg_fname = os.path.split(opt.base[0])[-1]
+ cfg_name = os.path.splitext(cfg_fname)[0]
+ name = "_" + cfg_name
+ else:
+ name = ""
+ nowname = now + name + opt.postfix
+ logdir = os.path.join(opt.logdir, nowname)
+
+ ckptdir = os.path.join(logdir, "checkpoints")
+ cfgdir = os.path.join(logdir, "configs")
+ seed_everything(opt.seed)
+
+ try:
+ # init and save configs
+ configs = [OmegaConf.load(cfg) for cfg in opt.base]
+ cli = OmegaConf.from_dotlist(unknown)
+ config = OmegaConf.merge(*configs, cli)
+ lightning_config = config.pop("lightning", OmegaConf.create())
+ # merge trainer cli with config
+ trainer_config = lightning_config.get("trainer", OmegaConf.create())
+ # default to ddp
+ trainer_config["accelerator"] = "ddp"
+ for k in nondefault_trainer_args(opt):
+ trainer_config[k] = getattr(opt, k)
+ if not "gpus" in trainer_config:
+ del trainer_config["accelerator"]
+ cpu = True
+ else:
+ gpuinfo = trainer_config["gpus"]
+ print(f"Running on GPUs {gpuinfo}")
+ cpu = False
+ trainer_opt = argparse.Namespace(**trainer_config)
+ lightning_config.trainer = trainer_config
+
+ # model
+ model = instantiate_from_config(config.model)
+
+ # trainer and callbacks
+ trainer_kwargs = dict()
+
+ # default logger configs
+ default_logger_cfgs = {
+ "wandb": {
+ "target": "pytorch_lightning.loggers.WandbLogger",
+ "params": {
+ "name": nowname,
+ "save_dir": logdir,
+ "offline": opt.debug,
+ "id": nowname,
+ }
+ },
+ "testtube": {
+ "target": "pytorch_lightning.loggers.TestTubeLogger",
+ "params": {
+ "name": "testtube",
+ "save_dir": logdir,
+ }
+ },
+ }
+ default_logger_cfg = default_logger_cfgs["testtube"]
+ if "logger" in lightning_config:
+ logger_cfg = lightning_config.logger
+ else:
+ logger_cfg = OmegaConf.create()
+ logger_cfg = OmegaConf.merge(default_logger_cfg, logger_cfg)
+ trainer_kwargs["logger"] = instantiate_from_config(logger_cfg)
+
+ # modelcheckpoint - use TrainResult/EvalResult(checkpoint_on=metric) to
+ # specify which metric is used to determine best models
+ default_modelckpt_cfg = {
+ "target": "pytorch_lightning.callbacks.ModelCheckpoint",
+ "params": {
+ "dirpath": ckptdir,
+ "filename": "{epoch:06}",
+ "verbose": True,
+ "save_last": True,
+ }
+ }
+ if hasattr(model, "monitor"):
+ print(f"Monitoring {model.monitor} as checkpoint metric.")
+ default_modelckpt_cfg["params"]["monitor"] = model.monitor
+ default_modelckpt_cfg["params"]["save_top_k"] = 3
+
+ if "modelcheckpoint" in lightning_config:
+ modelckpt_cfg = lightning_config.modelcheckpoint
+ else:
+ modelckpt_cfg = OmegaConf.create()
+ modelckpt_cfg = OmegaConf.merge(default_modelckpt_cfg, modelckpt_cfg)
+ print(f"Merged modelckpt-cfg: \n{modelckpt_cfg}")
+ if version.parse(pl.__version__) < version.parse('1.4.0'):
+ trainer_kwargs["checkpoint_callback"] = instantiate_from_config(modelckpt_cfg)
+
+ # add callback which sets up log directory
+ default_callbacks_cfg = {
+ "setup_callback": {
+ "target": "main.SetupCallback",
+ "params": {
+ "resume": opt.resume,
+ "now": now,
+ "logdir": logdir,
+ "ckptdir": ckptdir,
+ "cfgdir": cfgdir,
+ "config": config,
+ "lightning_config": lightning_config,
+ }
+ },
+ "image_logger": {
+ "target": "main.ImageLogger",
+ "params": {
+ "batch_frequency": 750,
+ "max_images": 4,
+ "clamp": True
+ }
+ },
+ "learning_rate_logger": {
+ "target": "main.LearningRateMonitor",
+ "params": {
+ "logging_interval": "step",
+ # "log_momentum": True
+ }
+ },
+ "cuda_callback": {
+ "target": "main.CUDACallback"
+ },
+ }
+ if version.parse(pl.__version__) >= version.parse('1.4.0'):
+ default_callbacks_cfg.update({'checkpoint_callback': modelckpt_cfg})
+
+ if "callbacks" in lightning_config:
+ callbacks_cfg = lightning_config.callbacks
+ else:
+ callbacks_cfg = OmegaConf.create()
+
+ if 'metrics_over_trainsteps_checkpoint' in callbacks_cfg:
+ print(
+ 'Caution: Saving checkpoints every n train steps without deleting. This might require some free space.')
+ default_metrics_over_trainsteps_ckpt_dict = {
+ 'metrics_over_trainsteps_checkpoint':
+ {"target": 'pytorch_lightning.callbacks.ModelCheckpoint',
+ 'params': {
+ "dirpath": os.path.join(ckptdir, 'trainstep_checkpoints'),
+ "filename": "{epoch:06}-{step:09}",
+ "verbose": True,
+ 'save_top_k': -1,
+ 'every_n_train_steps': 10000,
+ 'save_weights_only': True
+ }
+ }
+ }
+ default_callbacks_cfg.update(default_metrics_over_trainsteps_ckpt_dict)
+
+ callbacks_cfg = OmegaConf.merge(default_callbacks_cfg, callbacks_cfg)
+ if 'ignore_keys_callback' in callbacks_cfg and hasattr(trainer_opt, 'resume_from_checkpoint'):
+ callbacks_cfg.ignore_keys_callback.params['ckpt_path'] = trainer_opt.resume_from_checkpoint
+ elif 'ignore_keys_callback' in callbacks_cfg:
+ del callbacks_cfg['ignore_keys_callback']
+
+ trainer_kwargs["callbacks"] = [instantiate_from_config(callbacks_cfg[k]) for k in callbacks_cfg]
+
+ trainer = Trainer.from_argparse_args(trainer_opt, **trainer_kwargs)
+ trainer.logdir = logdir ###
+
+ # data
+ data = instantiate_from_config(config.data)
+ # NOTE according to https://pytorch-lightning.readthedocs.io/en/latest/datamodules.html
+ # calling these ourselves should not be necessary but it is.
+ # lightning still takes care of proper multiprocessing though
+ data.prepare_data()
+ data.setup()
+ print("#### Data #####")
+ for k in data.datasets:
+ print(f"{k}, {data.datasets[k].__class__.__name__}, {len(data.datasets[k])}")
+
+ # configure learning rate
+ bs, base_lr = config.data.params.batch_size, config.model.base_learning_rate
+ if not cpu:
+ ngpu = len(lightning_config.trainer.gpus.strip(",").split(','))
+ else:
+ ngpu = 1
+ if 'accumulate_grad_batches' in lightning_config.trainer:
+ accumulate_grad_batches = lightning_config.trainer.accumulate_grad_batches
+ else:
+ accumulate_grad_batches = 1
+ print(f"accumulate_grad_batches = {accumulate_grad_batches}")
+ lightning_config.trainer.accumulate_grad_batches = accumulate_grad_batches
+ if opt.scale_lr:
+ model.learning_rate = accumulate_grad_batches * ngpu * bs * base_lr
+ print(
+ "Setting learning rate to {:.2e} = {} (accumulate_grad_batches) * {} (num_gpus) * {} (batchsize) * {:.2e} (base_lr)".format(
+ model.learning_rate, accumulate_grad_batches, ngpu, bs, base_lr))
+ else:
+ model.learning_rate = base_lr
+ print("++++ NOT USING LR SCALING ++++")
+ print(f"Setting learning rate to {model.learning_rate:.2e}")
+
+
+ # allow checkpointing via USR1
+ def melk(*args, **kwargs):
+ # run all checkpoint hooks
+ if trainer.global_rank == 0:
+ print("Summoning checkpoint.")
+ ckpt_path = os.path.join(ckptdir, "last.ckpt")
+ trainer.save_checkpoint(ckpt_path)
+
+
+ def divein(*args, **kwargs):
+ if trainer.global_rank == 0:
+ import pudb;
+ pudb.set_trace()
+
+
+ import signal
+
+ signal.signal(signal.SIGUSR1, melk)
+ signal.signal(signal.SIGUSR2, divein)
+
+ # run
+ if opt.train:
+ try:
+ trainer.fit(model, data)
+ except Exception:
+ melk()
+ raise
+ if not opt.no_test and not trainer.interrupted:
+ trainer.test(model, data)
+ except Exception:
+ if opt.debug and trainer.global_rank == 0:
+ try:
+ import pudb as debugger
+ except ImportError:
+ import pdb as debugger
+ debugger.post_mortem()
+ raise
+ finally:
+ # move newly created debug project to debug_runs
+ if opt.debug and not opt.resume and trainer.global_rank == 0:
+ dst, name = os.path.split(logdir)
+ dst = os.path.join(dst, "debug_runs", name)
+ os.makedirs(os.path.split(dst)[0], exist_ok=True)
+ os.rename(logdir, dst)
+ try:
+ if trainer.global_rank == 0:
+ print(trainer.profiler.summary())
+ except:
+ pass
diff --git a/stable_diffusion/main.py b/stable_diffusion/main.py
new file mode 100644
index 0000000000000000000000000000000000000000..fb1165c81b1edf4acddd83e81c63136e043113e2
--- /dev/null
+++ b/stable_diffusion/main.py
@@ -0,0 +1,799 @@
+import argparse, os, sys, datetime, glob
+import numpy as np
+import time
+import torch
+import torchvision
+import pytorch_lightning as pl
+import json
+import pickle
+
+from packaging import version
+from omegaconf import OmegaConf
+from torch.utils.data import DataLoader, Dataset
+from functools import partial
+from PIL import Image
+
+import torch.distributed as dist
+from pytorch_lightning import seed_everything
+from pytorch_lightning.trainer import Trainer
+from pytorch_lightning.callbacks import ModelCheckpoint, Callback, LearningRateMonitor
+from pytorch_lightning.utilities.distributed import rank_zero_only
+from pytorch_lightning.utilities import rank_zero_info
+from pytorch_lightning.plugins import DDPPlugin
+
+sys.path.append("./stable_diffusion")
+
+from ldm.data.base import Txt2ImgIterableBaseDataset
+from ldm.util import instantiate_from_config
+
+
+def get_parser(**parser_kwargs):
+ def str2bool(v):
+ if isinstance(v, bool):
+ return v
+ if v.lower() in ("yes", "true", "t", "y", "1"):
+ return True
+ elif v.lower() in ("no", "false", "f", "n", "0"):
+ return False
+ else:
+ raise argparse.ArgumentTypeError("Boolean value expected.")
+
+ parser = argparse.ArgumentParser(**parser_kwargs)
+ parser.add_argument(
+ "-n",
+ "--name",
+ type=str,
+ const=True,
+ default="",
+ nargs="?",
+ help="postfix for logdir",
+ )
+ parser.add_argument(
+ "-r",
+ "--resume",
+ type=str,
+ const=True,
+ default="",
+ nargs="?",
+ help="resume from logdir or checkpoint in logdir",
+ )
+ parser.add_argument(
+ "-b",
+ "--base",
+ nargs="*",
+ metavar="base_config.yaml",
+ help="paths to base configs. Loaded from left-to-right. "
+ "Parameters can be overwritten or added with command-line options of the form `--key value`.",
+ default=list(),
+ )
+ parser.add_argument(
+ "-t",
+ "--train",
+ type=str2bool,
+ const=True,
+ default=False,
+ nargs="?",
+ help="train",
+ )
+ parser.add_argument(
+ "--no-test",
+ type=str2bool,
+ const=True,
+ default=False,
+ nargs="?",
+ help="disable test",
+ )
+ parser.add_argument(
+ "-p",
+ "--project",
+ help="name of new or path to existing project"
+ )
+ parser.add_argument(
+ "-d",
+ "--debug",
+ type=str2bool,
+ nargs="?",
+ const=True,
+ default=False,
+ help="enable post-mortem debugging",
+ )
+ parser.add_argument(
+ "-s",
+ "--seed",
+ type=int,
+ default=23,
+ help="seed for seed_everything",
+ )
+ parser.add_argument(
+ "-f",
+ "--postfix",
+ type=str,
+ default="",
+ help="post-postfix for default name",
+ )
+ parser.add_argument(
+ "-l",
+ "--logdir",
+ type=str,
+ default="logs",
+ help="directory for logging dat shit",
+ )
+ parser.add_argument(
+ "--scale_lr",
+ action="store_true",
+ default=False,
+ help="scale base-lr by ngpu * batch_size * n_accumulate",
+ )
+ return parser
+
+
+def nondefault_trainer_args(opt):
+ parser = argparse.ArgumentParser()
+ parser = Trainer.add_argparse_args(parser)
+ args = parser.parse_args([])
+ return sorted(k for k in vars(args) if getattr(opt, k) != getattr(args, k))
+
+
+class WrappedDataset(Dataset):
+ """Wraps an arbitrary object with __len__ and __getitem__ into a pytorch dataset"""
+
+ def __init__(self, dataset):
+ self.data = dataset
+
+ def __len__(self):
+ return len(self.data)
+
+ def __getitem__(self, idx):
+ return self.data[idx]
+
+
+def worker_init_fn(_):
+ worker_info = torch.utils.data.get_worker_info()
+
+ dataset = worker_info.dataset
+ worker_id = worker_info.id
+
+ if isinstance(dataset, Txt2ImgIterableBaseDataset):
+ split_size = dataset.num_records // worker_info.num_workers
+ # reset num_records to the true number to retain reliable length information
+ dataset.sample_ids = dataset.valid_ids[worker_id * split_size:(worker_id + 1) * split_size]
+ current_id = np.random.choice(len(np.random.get_state()[1]), 1)
+ return np.random.seed(np.random.get_state()[1][current_id] + worker_id)
+ else:
+ return np.random.seed(np.random.get_state()[1][0] + worker_id)
+
+
+class DataModuleFromConfig(pl.LightningDataModule):
+ def __init__(self, batch_size, train=None, validation=None, test=None, predict=None,
+ wrap=False, num_workers=None, shuffle_test_loader=False, use_worker_init_fn=False,
+ shuffle_val_dataloader=False):
+ super().__init__()
+ self.batch_size = batch_size
+ self.dataset_configs = dict()
+ self.num_workers = num_workers if num_workers is not None else batch_size * 2
+ self.use_worker_init_fn = use_worker_init_fn
+ if train is not None:
+ self.dataset_configs["train"] = train
+ self.train_dataloader = self._train_dataloader
+ if validation is not None:
+ self.dataset_configs["validation"] = validation
+ self.val_dataloader = partial(self._val_dataloader, shuffle=shuffle_val_dataloader)
+ if test is not None:
+ self.dataset_configs["test"] = test
+ self.test_dataloader = partial(self._test_dataloader, shuffle=shuffle_test_loader)
+ if predict is not None:
+ self.dataset_configs["predict"] = predict
+ self.predict_dataloader = self._predict_dataloader
+ self.wrap = wrap
+
+ def prepare_data(self):
+ for data_cfg in self.dataset_configs.values():
+ instantiate_from_config(data_cfg)
+
+ def setup(self, stage=None):
+ self.datasets = dict(
+ (k, instantiate_from_config(self.dataset_configs[k]))
+ for k in self.dataset_configs)
+ if self.wrap:
+ for k in self.datasets:
+ self.datasets[k] = WrappedDataset(self.datasets[k])
+
+ def _train_dataloader(self):
+ is_iterable_dataset = isinstance(self.datasets['train'], Txt2ImgIterableBaseDataset)
+ if is_iterable_dataset or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["train"], batch_size=self.batch_size,
+ num_workers=self.num_workers, shuffle=False if is_iterable_dataset else True,
+ worker_init_fn=init_fn, persistent_workers=True)
+
+ def _val_dataloader(self, shuffle=False):
+ if isinstance(self.datasets['validation'], Txt2ImgIterableBaseDataset) or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["validation"],
+ batch_size=self.batch_size,
+ num_workers=self.num_workers,
+ worker_init_fn=init_fn,
+ shuffle=shuffle, persistent_workers=True)
+
+ def _test_dataloader(self, shuffle=False):
+ is_iterable_dataset = isinstance(self.datasets['train'], Txt2ImgIterableBaseDataset)
+ if is_iterable_dataset or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+
+ # do not shuffle dataloader for iterable dataset
+ shuffle = shuffle and (not is_iterable_dataset)
+
+ return DataLoader(self.datasets["test"], batch_size=self.batch_size,
+ num_workers=self.num_workers, worker_init_fn=init_fn, shuffle=shuffle, persistent_workers=True)
+
+ def _predict_dataloader(self, shuffle=False):
+ if isinstance(self.datasets['predict'], Txt2ImgIterableBaseDataset) or self.use_worker_init_fn:
+ init_fn = worker_init_fn
+ else:
+ init_fn = None
+ return DataLoader(self.datasets["predict"], batch_size=self.batch_size,
+ num_workers=self.num_workers, worker_init_fn=init_fn, persistent_workers=True)
+
+
+class SetupCallback(Callback):
+ def __init__(self, resume, now, logdir, ckptdir, cfgdir, config, lightning_config):
+ super().__init__()
+ self.resume = resume
+ self.now = now
+ self.logdir = logdir
+ self.ckptdir = ckptdir
+ self.cfgdir = cfgdir
+ self.config = config
+ self.lightning_config = lightning_config
+
+ def on_keyboard_interrupt(self, trainer, pl_module):
+ if trainer.global_rank == 0:
+ print("Summoning checkpoint.")
+ ckpt_path = os.path.join(self.ckptdir, "last.ckpt")
+ trainer.save_checkpoint(ckpt_path)
+
+ def on_pretrain_routine_start(self, trainer, pl_module):
+ if trainer.global_rank == 0:
+ # Create logdirs and save configs
+ # os.makedirs(self.logdir, exist_ok=True)
+ # os.makedirs(self.ckptdir, exist_ok=True)
+ # os.makedirs(self.cfgdir, exist_ok=True)
+
+ if "callbacks" in self.lightning_config:
+ if 'metrics_over_trainsteps_checkpoint' in self.lightning_config['callbacks']:
+ os.makedirs(os.path.join(self.ckptdir, 'trainstep_checkpoints'), exist_ok=True)
+ print("Project config")
+ print(OmegaConf.to_yaml(self.config))
+ OmegaConf.save(self.config,
+ os.path.join(self.cfgdir, "{}-project.yaml".format(self.now)))
+
+ print("Lightning config")
+ print(OmegaConf.to_yaml(self.lightning_config))
+ OmegaConf.save(OmegaConf.create({"lightning": self.lightning_config}),
+ os.path.join(self.cfgdir, "{}-lightning.yaml".format(self.now)))
+
+def get_world_size():
+ if not dist.is_available():
+ return 1
+ if not dist.is_initialized():
+ return 1
+ return dist.get_world_size()
+
+def all_gather(data):
+ """
+ Run all_gather on arbitrary picklable data (not necessarily tensors)
+ Args:
+ data: any picklable object
+ Returns:
+ list[data]: list of data gathered from each rank
+ """
+ world_size = get_world_size()
+ if world_size == 1:
+ return [data]
+
+ # serialized to a Tensor
+ origin_size = None
+ if not isinstance(data, torch.Tensor):
+ buffer = pickle.dumps(data)
+ storage = torch.ByteStorage.from_buffer(buffer)
+ tensor = torch.ByteTensor(storage).to("cuda")
+ else:
+ origin_size = data.size()
+ tensor = data.reshape(-1)
+
+ tensor_type = tensor.dtype
+
+ # obtain Tensor size of each rank
+ local_size = torch.LongTensor([tensor.numel()]).to("cuda")
+ size_list = [torch.LongTensor([0]).to("cuda") for _ in range(world_size)]
+ dist.all_gather(size_list, local_size)
+ size_list = [int(size.item()) for size in size_list]
+ max_size = max(size_list)
+
+ # receiving Tensor from all ranks
+ # we pad the tensor because torch all_gather does not support
+ # gathering tensors of different shapes
+ tensor_list = []
+ for _ in size_list:
+ tensor_list.append(torch.FloatTensor(size=(max_size,)).cuda().to(tensor_type))
+ if local_size != max_size:
+ padding = torch.FloatTensor(size=(max_size - local_size,)).cuda().to(tensor_type)
+ tensor = torch.cat((tensor, padding), dim=0)
+ dist.all_gather(tensor_list, tensor)
+
+ data_list = []
+ for size, tensor in zip(size_list, tensor_list):
+ if origin_size is None:
+ buffer = tensor.cpu().numpy().tobytes()[:size]
+ data_list.append(pickle.loads(buffer))
+ else:
+ buffer = tensor[:size]
+ data_list.append(buffer)
+
+ if origin_size is not None:
+ new_shape = [-1] + list(origin_size[1:])
+ resized_list = []
+ for data in data_list:
+ # suppose the difference of tensor size exist in first dimension
+ data = data.reshape(new_shape)
+ resized_list.append(data)
+
+ return resized_list
+ else:
+ return data_list
+
+class ImageLogger(Callback):
+ def __init__(self, batch_frequency, max_images, clamp=True, increase_log_steps=True,
+ rescale=True, disabled=False, log_on_batch_idx=False, log_first_step=False,
+ log_images_kwargs=None):
+ super().__init__()
+ self.rescale = rescale
+ self.batch_freq = batch_frequency
+ self.max_images = max_images
+ self.logger_log_images = {
+ pl.loggers.TestTubeLogger: self._testtube,
+ }
+ self.log_steps = [2 ** n for n in range(6, int(np.log2(self.batch_freq)) + 1)]
+ if not increase_log_steps:
+ self.log_steps = [self.batch_freq]
+ self.clamp = clamp
+ self.disabled = disabled
+ self.log_on_batch_idx = log_on_batch_idx
+ self.log_images_kwargs = log_images_kwargs if log_images_kwargs else {}
+ self.log_first_step = log_first_step
+
+ @rank_zero_only
+ def _testtube(self, pl_module, images, batch_idx, split):
+ for k in images:
+ grid = torchvision.utils.make_grid(images[k])
+ grid = (grid + 1.0) / 2.0 # -1,1 -> 0,1; c,h,w
+
+ tag = f"{split}/{k}"
+ pl_module.logger.experiment.add_image(
+ tag, grid,
+ global_step=pl_module.global_step)
+
+ @rank_zero_only
+ def log_local(self, save_dir, split, images, prompts,
+ global_step, current_epoch, batch_idx):
+ root = os.path.join(save_dir, "images", split)
+ names = {"reals": "before", "inputs": "after", "reconstruction": "before-vq", "samples": "after-gen"}
+ # print(root)
+ for k in images:
+ grid = torchvision.utils.make_grid(images[k], nrow=8)
+ if self.rescale:
+ grid = (grid + 1.0) / 2.0 # -1,1 -> 0,1; c,h,w
+ grid = grid.transpose(0, 1).transpose(1, 2).squeeze(-1)
+ grid = grid.numpy()
+ grid = (grid * 255).astype(np.uint8)
+ filename = "gs-{:06}_e-{:06}_b-{:06}_{}.png".format(
+ global_step,
+ current_epoch,
+ batch_idx,
+ names[k])
+ path = os.path.join(root, filename)
+ os.makedirs(os.path.split(path)[0], exist_ok=True)
+ # print(path)
+ Image.fromarray(grid).save(path)
+
+ filename = "gs-{:06}_e-{:06}_b-{:06}_prompt.json".format(
+ global_step,
+ current_epoch,
+ batch_idx)
+ path = os.path.join(root, filename)
+ with open(path, "w") as f:
+ for p in prompts:
+ f.write(f"{json.dumps(p)}\n")
+
+ def log_img(self, pl_module, batch, batch_idx, split="train"):
+ check_idx = batch_idx if self.log_on_batch_idx else pl_module.global_step
+ if (self.check_frequency(check_idx) and # batch_idx % self.batch_freq == 0
+ hasattr(pl_module, "log_images") and
+ callable(pl_module.log_images) and
+ self.max_images > 0) or (split == "val" and batch_idx == 0):
+ logger = type(pl_module.logger)
+
+ is_train = pl_module.training
+ if is_train:
+ pl_module.eval()
+
+ with torch.no_grad():
+ images = pl_module.log_images(batch, split=split, **self.log_images_kwargs)
+
+ prompts = batch["edit"]["c_crossattn"][:self.max_images]
+ prompts = [p for ps in all_gather(prompts) for p in ps]
+
+ for k in images:
+ N = min(images[k].shape[0], self.max_images)
+ images[k] = images[k][:N]
+ images[k] = torch.cat(all_gather(images[k][:N]))
+ if isinstance(images[k], torch.Tensor):
+ images[k] = images[k].detach().cpu()
+ if self.clamp:
+ images[k] = torch.clamp(images[k], -1., 1.)
+
+ self.log_local(pl_module.logger.save_dir, split, images, prompts,
+ pl_module.global_step, pl_module.current_epoch, batch_idx)
+
+ logger_log_images = self.logger_log_images.get(logger, lambda *args, **kwargs: None)
+ logger_log_images(pl_module, images, pl_module.global_step, split)
+
+ if is_train:
+ pl_module.train()
+
+ def check_frequency(self, check_idx):
+ if ((check_idx % self.batch_freq) == 0 or (check_idx in self.log_steps)) and (
+ check_idx > 0 or self.log_first_step):
+ if len(self.log_steps) > 0:
+ self.log_steps.pop(0)
+ return True
+ return False
+
+ def on_train_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
+ if not self.disabled and (pl_module.global_step > 0 or self.log_first_step):
+ self.log_img(pl_module, batch, batch_idx, split="train")
+
+ def on_validation_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
+ if not self.disabled and pl_module.global_step > 0:
+ self.log_img(pl_module, batch, batch_idx, split="val")
+ if hasattr(pl_module, 'calibrate_grad_norm'):
+ if (pl_module.calibrate_grad_norm and batch_idx % 25 == 0) and batch_idx > 0:
+ self.log_gradients(trainer, pl_module, batch_idx=batch_idx)
+
+
+class CUDACallback(Callback):
+ # see https://github.com/SeanNaren/minGPT/blob/master/mingpt/callback.py
+ def on_train_epoch_start(self, trainer, pl_module):
+ # Reset the memory use counter
+ torch.cuda.reset_peak_memory_stats(trainer.root_gpu)
+ torch.cuda.synchronize(trainer.root_gpu)
+ self.start_time = time.time()
+
+ def on_train_epoch_end(self, trainer, pl_module, outputs):
+ torch.cuda.synchronize(trainer.root_gpu)
+ max_memory = torch.cuda.max_memory_allocated(trainer.root_gpu) / 2 ** 20
+ epoch_time = time.time() - self.start_time
+
+ try:
+ max_memory = trainer.training_type_plugin.reduce(max_memory)
+ epoch_time = trainer.training_type_plugin.reduce(epoch_time)
+
+ rank_zero_info(f"Average Epoch time: {epoch_time:.2f} seconds")
+ rank_zero_info(f"Average Peak memory {max_memory:.2f}MiB")
+ except AttributeError:
+ pass
+
+
+if __name__ == "__main__":
+ # custom parser to specify config files, train, test and debug mode,
+ # postfix, resume.
+ # `--key value` arguments are interpreted as arguments to the trainer.
+ # `nested.key=value` arguments are interpreted as config parameters.
+ # configs are merged from left-to-right followed by command line parameters.
+
+ # model:
+ # base_learning_rate: float
+ # target: path to lightning module
+ # params:
+ # key: value
+ # data:
+ # target: main.DataModuleFromConfig
+ # params:
+ # batch_size: int
+ # wrap: bool
+ # train:
+ # target: path to train dataset
+ # params:
+ # key: value
+ # validation:
+ # target: path to validation dataset
+ # params:
+ # key: value
+ # test:
+ # target: path to test dataset
+ # params:
+ # key: value
+ # lightning: (optional, has sane defaults and can be specified on cmdline)
+ # trainer:
+ # additional arguments to trainer
+ # logger:
+ # logger to instantiate
+ # modelcheckpoint:
+ # modelcheckpoint to instantiate
+ # callbacks:
+ # callback1:
+ # target: importpath
+ # params:
+ # key: value
+
+ now = datetime.datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
+
+ # add cwd for convenience and to make classes in this file available when
+ # running as `python main.py`
+ # (in particular `main.DataModuleFromConfig`)
+ sys.path.append(os.getcwd())
+
+ parser = get_parser()
+ parser = Trainer.add_argparse_args(parser)
+
+ opt, unknown = parser.parse_known_args()
+
+ assert opt.name
+ cfg_fname = os.path.split(opt.base[0])[-1]
+ cfg_name = os.path.splitext(cfg_fname)[0]
+ nowname = f"{cfg_name}_{opt.name}"
+ logdir = os.path.join(opt.logdir, nowname)
+ ckpt = os.path.join(logdir, "checkpoints", "last.ckpt")
+ resume = False
+
+ if os.path.isfile(ckpt):
+ opt.resume_from_checkpoint = ckpt
+ base_configs = sorted(glob.glob(os.path.join(logdir, "configs/*.yaml")))
+ opt.base = base_configs + opt.base
+ _tmp = logdir.split("/")
+ nowname = _tmp[-1]
+ resume = True
+
+ ckptdir = os.path.join(logdir, "checkpoints")
+ cfgdir = os.path.join(logdir, "configs")
+
+ os.makedirs(logdir, exist_ok=True)
+ os.makedirs(ckptdir, exist_ok=True)
+ os.makedirs(cfgdir, exist_ok=True)
+
+ try:
+ # init and save configs
+ configs = [OmegaConf.load(cfg) for cfg in opt.base]
+ cli = OmegaConf.from_dotlist(unknown)
+ config = OmegaConf.merge(*configs, cli)
+
+ if resume:
+ # By default, when finetuning from Stable Diffusion, we load the EMA-only checkpoint to initialize all weights.
+ # If resuming InstructPix2Pix from a finetuning checkpoint, instead load both EMA and non-EMA weights.
+ config.model.params.load_ema = True
+
+ lightning_config = config.pop("lightning", OmegaConf.create())
+ # merge trainer cli with config
+ trainer_config = lightning_config.get("trainer", OmegaConf.create())
+ # default to ddp
+ trainer_config["accelerator"] = "ddp"
+ for k in nondefault_trainer_args(opt):
+ trainer_config[k] = getattr(opt, k)
+ if not "gpus" in trainer_config:
+ del trainer_config["accelerator"]
+ cpu = True
+ else:
+ gpuinfo = trainer_config["gpus"]
+ print(f"Running on GPUs {gpuinfo}")
+ cpu = False
+ trainer_opt = argparse.Namespace(**trainer_config)
+ lightning_config.trainer = trainer_config
+
+ # model
+ model = instantiate_from_config(config.model)
+
+ # trainer and callbacks
+ trainer_kwargs = dict()
+
+ # default logger configs
+ default_logger_cfgs = {
+ "wandb": {
+ "target": "pytorch_lightning.loggers.WandbLogger",
+ "params": {
+ "name": nowname,
+ "save_dir": logdir,
+ "id": nowname,
+ }
+ },
+ "testtube": {
+ "target": "pytorch_lightning.loggers.TestTubeLogger",
+ "params": {
+ "name": "testtube",
+ "save_dir": logdir,
+ }
+ },
+ }
+ default_logger_cfg = default_logger_cfgs["wandb"]
+ if "logger" in lightning_config:
+ logger_cfg = lightning_config.logger
+ else:
+ logger_cfg = OmegaConf.create()
+ logger_cfg = OmegaConf.merge(default_logger_cfg, logger_cfg)
+ trainer_kwargs["logger"] = instantiate_from_config(logger_cfg)
+
+ # modelcheckpoint - use TrainResult/EvalResult(checkpoint_on=metric) to
+ # specify which metric is used to determine best models
+ default_modelckpt_cfg = {
+ "target": "pytorch_lightning.callbacks.ModelCheckpoint",
+ "params": {
+ "dirpath": ckptdir,
+ "filename": "{epoch:06}",
+ "verbose": True,
+ "save_last": True,
+ }
+ }
+
+ if "modelcheckpoint" in lightning_config:
+ modelckpt_cfg = lightning_config.modelcheckpoint
+ else:
+ modelckpt_cfg = OmegaConf.create()
+ modelckpt_cfg = OmegaConf.merge(default_modelckpt_cfg, modelckpt_cfg)
+ print(f"Merged modelckpt-cfg: \n{modelckpt_cfg}")
+ if version.parse(pl.__version__) < version.parse('1.4.0'):
+ trainer_kwargs["checkpoint_callback"] = instantiate_from_config(modelckpt_cfg)
+
+ # add callback which sets up log directory
+ default_callbacks_cfg = {
+ "setup_callback": {
+ "target": "main.SetupCallback",
+ "params": {
+ "resume": opt.resume,
+ "now": now,
+ "logdir": logdir,
+ "ckptdir": ckptdir,
+ "cfgdir": cfgdir,
+ "config": config,
+ "lightning_config": lightning_config,
+ }
+ },
+ "image_logger": {
+ "target": "main.ImageLogger",
+ "params": {
+ "batch_frequency": 750,
+ "max_images": 4,
+ "clamp": True
+ }
+ },
+ "learning_rate_logger": {
+ "target": "main.LearningRateMonitor",
+ "params": {
+ "logging_interval": "step",
+ # "log_momentum": True
+ }
+ },
+ "cuda_callback": {
+ "target": "main.CUDACallback"
+ },
+ }
+ if version.parse(pl.__version__) >= version.parse('1.4.0'):
+ default_callbacks_cfg.update({'checkpoint_callback': modelckpt_cfg})
+
+ if "callbacks" in lightning_config:
+ callbacks_cfg = lightning_config.callbacks
+ else:
+ callbacks_cfg = OmegaConf.create()
+
+ print(
+ 'Caution: Saving checkpoints every n train steps without deleting. This might require some free space.')
+ default_metrics_over_trainsteps_ckpt_dict = {
+ 'metrics_over_trainsteps_checkpoint': {
+ "target": 'pytorch_lightning.callbacks.ModelCheckpoint',
+ 'params': {
+ "dirpath": os.path.join(ckptdir, 'trainstep_checkpoints'),
+ "filename": "{epoch:06}-{step:09}",
+ "verbose": True,
+ 'save_top_k': -1,
+ 'every_n_train_steps': 1000,
+ 'save_weights_only': True
+ }
+ }
+ }
+ default_callbacks_cfg.update(default_metrics_over_trainsteps_ckpt_dict)
+
+ callbacks_cfg = OmegaConf.merge(default_callbacks_cfg, callbacks_cfg)
+ if 'ignore_keys_callback' in callbacks_cfg and hasattr(trainer_opt, 'resume_from_checkpoint'):
+ callbacks_cfg.ignore_keys_callback.params['ckpt_path'] = trainer_opt.resume_from_checkpoint
+ elif 'ignore_keys_callback' in callbacks_cfg:
+ del callbacks_cfg['ignore_keys_callback']
+
+ trainer_kwargs["callbacks"] = [instantiate_from_config(callbacks_cfg[k]) for k in callbacks_cfg]
+
+ trainer = Trainer.from_argparse_args(trainer_opt, plugins=DDPPlugin(find_unused_parameters=False), **trainer_kwargs)
+ trainer.logdir = logdir ###
+
+ # data
+ data = instantiate_from_config(config.data)
+ # NOTE according to https://pytorch-lightning.readthedocs.io/en/latest/datamodules.html
+ # calling these ourselves should not be necessary but it is.
+ # lightning still takes care of proper multiprocessing though
+ data.prepare_data()
+ data.setup()
+ print("#### Data #####")
+ for k in data.datasets:
+ print(f"{k}, {data.datasets[k].__class__.__name__}, {len(data.datasets[k])}")
+
+ # configure learning rate
+ bs, base_lr = config.data.params.batch_size, config.model.base_learning_rate
+ if not cpu:
+ ngpu = len(lightning_config.trainer.gpus.strip(",").split(','))
+ else:
+ ngpu = 1
+ if 'accumulate_grad_batches' in lightning_config.trainer:
+ accumulate_grad_batches = lightning_config.trainer.accumulate_grad_batches
+ else:
+ accumulate_grad_batches = 1
+ print(f"accumulate_grad_batches = {accumulate_grad_batches}")
+ lightning_config.trainer.accumulate_grad_batches = accumulate_grad_batches
+ if opt.scale_lr:
+ model.learning_rate = accumulate_grad_batches * ngpu * bs * base_lr
+ print(
+ "Setting learning rate to {:.2e} = {} (accumulate_grad_batches) * {} (num_gpus) * {} (batchsize) * {:.2e} (base_lr)".format(
+ model.learning_rate, accumulate_grad_batches, ngpu, bs, base_lr))
+ else:
+ model.learning_rate = base_lr
+ print("++++ NOT USING LR SCALING ++++")
+ print(f"Setting learning rate to {model.learning_rate:.2e}")
+
+
+ # allow checkpointing via USR1
+ def melk(*args, **kwargs):
+ # run all checkpoint hooks
+ if trainer.global_rank == 0:
+ print("Summoning checkpoint.")
+ ckpt_path = os.path.join(ckptdir, "last.ckpt")
+ trainer.save_checkpoint(ckpt_path)
+
+
+ def divein(*args, **kwargs):
+ if trainer.global_rank == 0:
+ import pudb;
+ pudb.set_trace()
+
+
+ import signal
+
+ signal.signal(signal.SIGUSR1, melk)
+ signal.signal(signal.SIGUSR2, divein)
+
+ # run
+ if opt.train:
+ try:
+ trainer.fit(model, data)
+ except Exception:
+ melk()
+ raise
+ if not opt.no_test and not trainer.interrupted:
+ trainer.test(model, data)
+ except Exception:
+ if opt.debug and trainer.global_rank == 0:
+ try:
+ import pudb as debugger
+ except ImportError:
+ import pdb as debugger
+ debugger.post_mortem()
+ raise
+ finally:
+ # move newly created debug project to debug_runs
+ if opt.debug and not opt.resume and trainer.global_rank == 0:
+ dst, name = os.path.split(logdir)
+ dst = os.path.join(dst, "debug_runs", name)
+ os.makedirs(os.path.split(dst)[0], exist_ok=True)
+ os.rename(logdir, dst)
+ if trainer.global_rank == 0:
+ print(trainer.profiler.summary())
\ No newline at end of file
diff --git a/stable_diffusion/models/first_stage_models/kl-f4/config.yaml b/stable_diffusion/models/first_stage_models/kl-f4/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..85cfb3e94e2ffa867ab49af82fcd8a4dc238e2ad
--- /dev/null
+++ b/stable_diffusion/models/first_stage_models/kl-f4/config.yaml
@@ -0,0 +1,41 @@
+model:
+ base_learning_rate: 4.5e-06
+ target: ldm.models.autoencoder.AutoencoderKL
+ params:
+ monitor: val/rec_loss
+ embed_dim: 3
+ lossconfig:
+ target: ldm.modules.losses.LPIPSWithDiscriminator
+ params:
+ disc_start: 50001
+ kl_weight: 1.0e-06
+ disc_weight: 0.5
+ ddconfig:
+ double_z: true
+ z_channels: 3
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult:
+ - 1
+ - 2
+ - 4
+ num_res_blocks: 2
+ attn_resolutions: []
+ dropout: 0.0
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 10
+ wrap: true
+ train:
+ target: ldm.data.openimages.FullOpenImagesTrain
+ params:
+ size: 384
+ crop_size: 256
+ validation:
+ target: ldm.data.openimages.FullOpenImagesValidation
+ params:
+ size: 384
+ crop_size: 256
diff --git a/stable_diffusion/models/first_stage_models/vq-f16/config.yaml b/stable_diffusion/models/first_stage_models/vq-f16/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..91c74549064bfd158424cba9c79cd2618395fc9f
--- /dev/null
+++ b/stable_diffusion/models/first_stage_models/vq-f16/config.yaml
@@ -0,0 +1,49 @@
+model:
+ base_learning_rate: 4.5e-06
+ target: ldm.models.autoencoder.VQModel
+ params:
+ embed_dim: 8
+ n_embed: 16384
+ ddconfig:
+ double_z: false
+ z_channels: 8
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult:
+ - 1
+ - 1
+ - 2
+ - 2
+ - 4
+ num_res_blocks: 2
+ attn_resolutions:
+ - 16
+ dropout: 0.0
+ lossconfig:
+ target: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
+ params:
+ disc_conditional: false
+ disc_in_channels: 3
+ disc_start: 250001
+ disc_weight: 0.75
+ disc_num_layers: 2
+ codebook_weight: 1.0
+
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 14
+ num_workers: 20
+ wrap: true
+ train:
+ target: ldm.data.openimages.FullOpenImagesTrain
+ params:
+ size: 384
+ crop_size: 256
+ validation:
+ target: ldm.data.openimages.FullOpenImagesValidation
+ params:
+ size: 384
+ crop_size: 256
diff --git a/stable_diffusion/models/first_stage_models/vq-f4-noattn/config.yaml b/stable_diffusion/models/first_stage_models/vq-f4-noattn/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..f8e499fa2aa891ea18f2cdbdd423c22bc1db6901
--- /dev/null
+++ b/stable_diffusion/models/first_stage_models/vq-f4-noattn/config.yaml
@@ -0,0 +1,46 @@
+model:
+ base_learning_rate: 4.5e-06
+ target: ldm.models.autoencoder.VQModel
+ params:
+ embed_dim: 3
+ n_embed: 8192
+ monitor: val/rec_loss
+
+ ddconfig:
+ attn_type: none
+ double_z: false
+ z_channels: 3
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult:
+ - 1
+ - 2
+ - 4
+ num_res_blocks: 2
+ attn_resolutions: []
+ dropout: 0.0
+ lossconfig:
+ target: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
+ params:
+ disc_conditional: false
+ disc_in_channels: 3
+ disc_start: 11
+ disc_weight: 0.75
+ codebook_weight: 1.0
+
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 8
+ num_workers: 12
+ wrap: true
+ train:
+ target: ldm.data.openimages.FullOpenImagesTrain
+ params:
+ crop_size: 256
+ validation:
+ target: ldm.data.openimages.FullOpenImagesValidation
+ params:
+ crop_size: 256
diff --git a/stable_diffusion/models/ldm/bsr_sr/config.yaml b/stable_diffusion/models/ldm/bsr_sr/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..861692a8d10b1764519576fd12200524faa32753
--- /dev/null
+++ b/stable_diffusion/models/ldm/bsr_sr/config.yaml
@@ -0,0 +1,80 @@
+model:
+ base_learning_rate: 1.0e-06
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
+ params:
+ linear_start: 0.0015
+ linear_end: 0.0155
+ log_every_t: 100
+ timesteps: 1000
+ loss_type: l2
+ first_stage_key: image
+ cond_stage_key: LR_image
+ image_size: 64
+ channels: 3
+ concat_mode: true
+ cond_stage_trainable: false
+ unet_config:
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+ params:
+ image_size: 64
+ in_channels: 6
+ out_channels: 3
+ model_channels: 160
+ attention_resolutions:
+ - 16
+ - 8
+ num_res_blocks: 2
+ channel_mult:
+ - 1
+ - 2
+ - 2
+ - 4
+ num_head_channels: 32
+ first_stage_config:
+ target: ldm.models.autoencoder.VQModelInterface
+ params:
+ embed_dim: 3
+ n_embed: 8192
+ monitor: val/rec_loss
+ ddconfig:
+ double_z: false
+ z_channels: 3
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult:
+ - 1
+ - 2
+ - 4
+ num_res_blocks: 2
+ attn_resolutions: []
+ dropout: 0.0
+ lossconfig:
+ target: torch.nn.Identity
+ cond_stage_config:
+ target: torch.nn.Identity
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 64
+ wrap: false
+ num_workers: 12
+ train:
+ target: ldm.data.openimages.SuperresOpenImagesAdvancedTrain
+ params:
+ size: 256
+ degradation: bsrgan_light
+ downscale_f: 4
+ min_crop_f: 0.5
+ max_crop_f: 1.0
+ random_crop: true
+ validation:
+ target: ldm.data.openimages.SuperresOpenImagesAdvancedValidation
+ params:
+ size: 256
+ degradation: bsrgan_light
+ downscale_f: 4
+ min_crop_f: 0.5
+ max_crop_f: 1.0
+ random_crop: true
diff --git a/stable_diffusion/models/ldm/layout2img-openimages256/config.yaml b/stable_diffusion/models/ldm/layout2img-openimages256/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..9e1dc15fe2732c70b918ceba4255aef895031efd
--- /dev/null
+++ b/stable_diffusion/models/ldm/layout2img-openimages256/config.yaml
@@ -0,0 +1,81 @@
+model:
+ base_learning_rate: 2.0e-06
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
+ params:
+ linear_start: 0.0015
+ linear_end: 0.0205
+ log_every_t: 100
+ timesteps: 1000
+ loss_type: l1
+ first_stage_key: image
+ cond_stage_key: coordinates_bbox
+ image_size: 64
+ channels: 3
+ conditioning_key: crossattn
+ cond_stage_trainable: true
+ unet_config:
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+ params:
+ image_size: 64
+ in_channels: 3
+ out_channels: 3
+ model_channels: 128
+ attention_resolutions:
+ - 8
+ - 4
+ - 2
+ num_res_blocks: 2
+ channel_mult:
+ - 1
+ - 2
+ - 3
+ - 4
+ num_head_channels: 32
+ use_spatial_transformer: true
+ transformer_depth: 3
+ context_dim: 512
+ first_stage_config:
+ target: ldm.models.autoencoder.VQModelInterface
+ params:
+ embed_dim: 3
+ n_embed: 8192
+ monitor: val/rec_loss
+ ddconfig:
+ double_z: false
+ z_channels: 3
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult:
+ - 1
+ - 2
+ - 4
+ num_res_blocks: 2
+ attn_resolutions: []
+ dropout: 0.0
+ lossconfig:
+ target: torch.nn.Identity
+ cond_stage_config:
+ target: ldm.modules.encoders.modules.BERTEmbedder
+ params:
+ n_embed: 512
+ n_layer: 16
+ vocab_size: 8192
+ max_seq_len: 92
+ use_tokenizer: false
+ monitor: val/loss_simple_ema
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 24
+ wrap: false
+ num_workers: 10
+ train:
+ target: ldm.data.openimages.OpenImagesBBoxTrain
+ params:
+ size: 256
+ validation:
+ target: ldm.data.openimages.OpenImagesBBoxValidation
+ params:
+ size: 256
diff --git a/stable_diffusion/models/ldm/lsun_beds256/config.yaml b/stable_diffusion/models/ldm/lsun_beds256/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..1a50c766a5e571545e4f15f897de73f9df49d85c
--- /dev/null
+++ b/stable_diffusion/models/ldm/lsun_beds256/config.yaml
@@ -0,0 +1,70 @@
+model:
+ base_learning_rate: 2.0e-06
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
+ params:
+ linear_start: 0.0015
+ linear_end: 0.0195
+ num_timesteps_cond: 1
+ log_every_t: 200
+ timesteps: 1000
+ first_stage_key: image
+ cond_stage_key: class_label
+ image_size: 64
+ channels: 3
+ cond_stage_trainable: false
+ concat_mode: false
+ monitor: val/loss
+ unet_config:
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+ params:
+ image_size: 64
+ in_channels: 3
+ out_channels: 3
+ model_channels: 224
+ attention_resolutions:
+ - 8
+ - 4
+ - 2
+ num_res_blocks: 2
+ channel_mult:
+ - 1
+ - 2
+ - 3
+ - 4
+ num_head_channels: 32
+ first_stage_config:
+ target: ldm.models.autoencoder.VQModelInterface
+ params:
+ embed_dim: 3
+ n_embed: 8192
+ ddconfig:
+ double_z: false
+ z_channels: 3
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult:
+ - 1
+ - 2
+ - 4
+ num_res_blocks: 2
+ attn_resolutions: []
+ dropout: 0.0
+ lossconfig:
+ target: torch.nn.Identity
+ cond_stage_config: __is_unconditional__
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 48
+ num_workers: 5
+ wrap: false
+ train:
+ target: ldm.data.lsun.LSUNBedroomsTrain
+ params:
+ size: 256
+ validation:
+ target: ldm.data.lsun.LSUNBedroomsValidation
+ params:
+ size: 256
diff --git a/stable_diffusion/models/ldm/lsun_churches256/config.yaml b/stable_diffusion/models/ldm/lsun_churches256/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..424d0914c9a1b9d4df3a2862ee7764404fe8adc1
--- /dev/null
+++ b/stable_diffusion/models/ldm/lsun_churches256/config.yaml
@@ -0,0 +1,92 @@
+model:
+ base_learning_rate: 5.0e-05
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
+ params:
+ linear_start: 0.0015
+ linear_end: 0.0155
+ num_timesteps_cond: 1
+ log_every_t: 200
+ timesteps: 1000
+ loss_type: l1
+ first_stage_key: image
+ cond_stage_key: image
+ image_size: 32
+ channels: 4
+ cond_stage_trainable: false
+ concat_mode: false
+ scale_by_std: true
+ monitor: val/loss_simple_ema
+ scheduler_config:
+ target: ldm.lr_scheduler.LambdaLinearScheduler
+ params:
+ warm_up_steps:
+ - 10000
+ cycle_lengths:
+ - 10000000000000
+ f_start:
+ - 1.0e-06
+ f_max:
+ - 1.0
+ f_min:
+ - 1.0
+ unet_config:
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+ params:
+ image_size: 32
+ in_channels: 4
+ out_channels: 4
+ model_channels: 192
+ attention_resolutions:
+ - 1
+ - 2
+ - 4
+ - 8
+ num_res_blocks: 2
+ channel_mult:
+ - 1
+ - 2
+ - 2
+ - 4
+ - 4
+ num_heads: 8
+ use_scale_shift_norm: true
+ resblock_updown: true
+ first_stage_config:
+ target: ldm.models.autoencoder.AutoencoderKL
+ params:
+ embed_dim: 4
+ monitor: val/rec_loss
+ ddconfig:
+ double_z: true
+ z_channels: 4
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult:
+ - 1
+ - 2
+ - 4
+ - 4
+ num_res_blocks: 2
+ attn_resolutions: []
+ dropout: 0.0
+ lossconfig:
+ target: torch.nn.Identity
+
+ cond_stage_config: '__is_unconditional__'
+
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 96
+ num_workers: 5
+ wrap: false
+ train:
+ target: ldm.data.lsun.LSUNChurchesTrain
+ params:
+ size: 256
+ validation:
+ target: ldm.data.lsun.LSUNChurchesValidation
+ params:
+ size: 256
diff --git a/stable_diffusion/models/ldm/semantic_synthesis512/config.yaml b/stable_diffusion/models/ldm/semantic_synthesis512/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..8faded2eec5899064fc464a1b543d3a1b9c0613f
--- /dev/null
+++ b/stable_diffusion/models/ldm/semantic_synthesis512/config.yaml
@@ -0,0 +1,78 @@
+model:
+ base_learning_rate: 1.0e-06
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
+ params:
+ linear_start: 0.0015
+ linear_end: 0.0205
+ log_every_t: 100
+ timesteps: 1000
+ loss_type: l1
+ first_stage_key: image
+ cond_stage_key: segmentation
+ image_size: 128
+ channels: 3
+ concat_mode: true
+ cond_stage_trainable: true
+ unet_config:
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+ params:
+ image_size: 128
+ in_channels: 6
+ out_channels: 3
+ model_channels: 128
+ attention_resolutions:
+ - 32
+ - 16
+ - 8
+ num_res_blocks: 2
+ channel_mult:
+ - 1
+ - 4
+ - 8
+ num_heads: 8
+ first_stage_config:
+ target: ldm.models.autoencoder.VQModelInterface
+ params:
+ embed_dim: 3
+ n_embed: 8192
+ monitor: val/rec_loss
+ ddconfig:
+ double_z: false
+ z_channels: 3
+ resolution: 256
+ in_channels: 3
+ out_ch: 3
+ ch: 128
+ ch_mult:
+ - 1
+ - 2
+ - 4
+ num_res_blocks: 2
+ attn_resolutions: []
+ dropout: 0.0
+ lossconfig:
+ target: torch.nn.Identity
+ cond_stage_config:
+ target: ldm.modules.encoders.modules.SpatialRescaler
+ params:
+ n_stages: 2
+ in_channels: 182
+ out_channels: 3
+data:
+ target: main.DataModuleFromConfig
+ params:
+ batch_size: 8
+ wrap: false
+ num_workers: 10
+ train:
+ target: ldm.data.landscapes.RFWTrain
+ params:
+ size: 768
+ crop_size: 512
+ segmentation_to_float32: true
+ validation:
+ target: ldm.data.landscapes.RFWValidation
+ params:
+ size: 768
+ crop_size: 512
+ segmentation_to_float32: true
diff --git a/stable_diffusion/notebook_helpers.py b/stable_diffusion/notebook_helpers.py
new file mode 100644
index 0000000000000000000000000000000000000000..5d0ebd7e1f8095053f34b1d7652b55d165097f0e
--- /dev/null
+++ b/stable_diffusion/notebook_helpers.py
@@ -0,0 +1,270 @@
+from torchvision.datasets.utils import download_url
+from ldm.util import instantiate_from_config
+import torch
+import os
+# todo ?
+from google.colab import files
+from IPython.display import Image as ipyimg
+import ipywidgets as widgets
+from PIL import Image
+from numpy import asarray
+from einops import rearrange, repeat
+import torch, torchvision
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.util import ismap
+import time
+from omegaconf import OmegaConf
+
+
+def download_models(mode):
+
+ if mode == "superresolution":
+ # this is the small bsr light model
+ url_conf = 'https://heibox.uni-heidelberg.de/f/31a76b13ea27482981b4/?dl=1'
+ url_ckpt = 'https://heibox.uni-heidelberg.de/f/578df07c8fc04ffbadf3/?dl=1'
+
+ path_conf = 'logs/diffusion/superresolution_bsr/configs/project.yaml'
+ path_ckpt = 'logs/diffusion/superresolution_bsr/checkpoints/last.ckpt'
+
+ download_url(url_conf, path_conf)
+ download_url(url_ckpt, path_ckpt)
+
+ path_conf = path_conf + '/?dl=1' # fix it
+ path_ckpt = path_ckpt + '/?dl=1' # fix it
+ return path_conf, path_ckpt
+
+ else:
+ raise NotImplementedError
+
+
+def load_model_from_config(config, ckpt):
+ print(f"Loading model from {ckpt}")
+ pl_sd = torch.load(ckpt, map_location="cpu")
+ global_step = pl_sd["global_step"]
+ sd = pl_sd["state_dict"]
+ model = instantiate_from_config(config.model)
+ m, u = model.load_state_dict(sd, strict=False)
+ model.cuda()
+ model.eval()
+ return {"model": model}, global_step
+
+
+def get_model(mode):
+ path_conf, path_ckpt = download_models(mode)
+ config = OmegaConf.load(path_conf)
+ model, step = load_model_from_config(config, path_ckpt)
+ return model
+
+
+def get_custom_cond(mode):
+ dest = "data/example_conditioning"
+
+ if mode == "superresolution":
+ uploaded_img = files.upload()
+ filename = next(iter(uploaded_img))
+ name, filetype = filename.split(".") # todo assumes just one dot in name !
+ os.rename(f"{filename}", f"{dest}/{mode}/custom_{name}.{filetype}")
+
+ elif mode == "text_conditional":
+ w = widgets.Text(value='A cake with cream!', disabled=True)
+ display(w)
+
+ with open(f"{dest}/{mode}/custom_{w.value[:20]}.txt", 'w') as f:
+ f.write(w.value)
+
+ elif mode == "class_conditional":
+ w = widgets.IntSlider(min=0, max=1000)
+ display(w)
+ with open(f"{dest}/{mode}/custom.txt", 'w') as f:
+ f.write(w.value)
+
+ else:
+ raise NotImplementedError(f"cond not implemented for mode{mode}")
+
+
+def get_cond_options(mode):
+ path = "data/example_conditioning"
+ path = os.path.join(path, mode)
+ onlyfiles = [f for f in sorted(os.listdir(path))]
+ return path, onlyfiles
+
+
+def select_cond_path(mode):
+ path = "data/example_conditioning" # todo
+ path = os.path.join(path, mode)
+ onlyfiles = [f for f in sorted(os.listdir(path))]
+
+ selected = widgets.RadioButtons(
+ options=onlyfiles,
+ description='Select conditioning:',
+ disabled=False
+ )
+ display(selected)
+ selected_path = os.path.join(path, selected.value)
+ return selected_path
+
+
+def get_cond(mode, selected_path):
+ example = dict()
+ if mode == "superresolution":
+ up_f = 4
+ visualize_cond_img(selected_path)
+
+ c = Image.open(selected_path)
+ c = torch.unsqueeze(torchvision.transforms.ToTensor()(c), 0)
+ c_up = torchvision.transforms.functional.resize(c, size=[up_f * c.shape[2], up_f * c.shape[3]], antialias=True)
+ c_up = rearrange(c_up, '1 c h w -> 1 h w c')
+ c = rearrange(c, '1 c h w -> 1 h w c')
+ c = 2. * c - 1.
+
+ c = c.to(torch.device("cuda"))
+ example["LR_image"] = c
+ example["image"] = c_up
+
+ return example
+
+
+def visualize_cond_img(path):
+ display(ipyimg(filename=path))
+
+
+def run(model, selected_path, task, custom_steps, resize_enabled=False, classifier_ckpt=None, global_step=None):
+
+ example = get_cond(task, selected_path)
+
+ save_intermediate_vid = False
+ n_runs = 1
+ masked = False
+ guider = None
+ ckwargs = None
+ mode = 'ddim'
+ ddim_use_x0_pred = False
+ temperature = 1.
+ eta = 1.
+ make_progrow = True
+ custom_shape = None
+
+ height, width = example["image"].shape[1:3]
+ split_input = height >= 128 and width >= 128
+
+ if split_input:
+ ks = 128
+ stride = 64
+ vqf = 4 #
+ model.split_input_params = {"ks": (ks, ks), "stride": (stride, stride),
+ "vqf": vqf,
+ "patch_distributed_vq": True,
+ "tie_braker": False,
+ "clip_max_weight": 0.5,
+ "clip_min_weight": 0.01,
+ "clip_max_tie_weight": 0.5,
+ "clip_min_tie_weight": 0.01}
+ else:
+ if hasattr(model, "split_input_params"):
+ delattr(model, "split_input_params")
+
+ invert_mask = False
+
+ x_T = None
+ for n in range(n_runs):
+ if custom_shape is not None:
+ x_T = torch.randn(1, custom_shape[1], custom_shape[2], custom_shape[3]).to(model.device)
+ x_T = repeat(x_T, '1 c h w -> b c h w', b=custom_shape[0])
+
+ logs = make_convolutional_sample(example, model,
+ mode=mode, custom_steps=custom_steps,
+ eta=eta, swap_mode=False , masked=masked,
+ invert_mask=invert_mask, quantize_x0=False,
+ custom_schedule=None, decode_interval=10,
+ resize_enabled=resize_enabled, custom_shape=custom_shape,
+ temperature=temperature, noise_dropout=0.,
+ corrector=guider, corrector_kwargs=ckwargs, x_T=x_T, save_intermediate_vid=save_intermediate_vid,
+ make_progrow=make_progrow,ddim_use_x0_pred=ddim_use_x0_pred
+ )
+ return logs
+
+
+@torch.no_grad()
+def convsample_ddim(model, cond, steps, shape, eta=1.0, callback=None, normals_sequence=None,
+ mask=None, x0=None, quantize_x0=False, img_callback=None,
+ temperature=1., noise_dropout=0., score_corrector=None,
+ corrector_kwargs=None, x_T=None, log_every_t=None
+ ):
+
+ ddim = DDIMSampler(model)
+ bs = shape[0] # dont know where this comes from but wayne
+ shape = shape[1:] # cut batch dim
+ print(f"Sampling with eta = {eta}; steps: {steps}")
+ samples, intermediates = ddim.sample(steps, batch_size=bs, shape=shape, conditioning=cond, callback=callback,
+ normals_sequence=normals_sequence, quantize_x0=quantize_x0, eta=eta,
+ mask=mask, x0=x0, temperature=temperature, verbose=False,
+ score_corrector=score_corrector,
+ corrector_kwargs=corrector_kwargs, x_T=x_T)
+
+ return samples, intermediates
+
+
+@torch.no_grad()
+def make_convolutional_sample(batch, model, mode="vanilla", custom_steps=None, eta=1.0, swap_mode=False, masked=False,
+ invert_mask=True, quantize_x0=False, custom_schedule=None, decode_interval=1000,
+ resize_enabled=False, custom_shape=None, temperature=1., noise_dropout=0., corrector=None,
+ corrector_kwargs=None, x_T=None, save_intermediate_vid=False, make_progrow=True,ddim_use_x0_pred=False):
+ log = dict()
+
+ z, c, x, xrec, xc = model.get_input(batch, model.first_stage_key,
+ return_first_stage_outputs=True,
+ force_c_encode=not (hasattr(model, 'split_input_params')
+ and model.cond_stage_key == 'coordinates_bbox'),
+ return_original_cond=True)
+
+ log_every_t = 1 if save_intermediate_vid else None
+
+ if custom_shape is not None:
+ z = torch.randn(custom_shape)
+ print(f"Generating {custom_shape[0]} samples of shape {custom_shape[1:]}")
+
+ z0 = None
+
+ log["input"] = x
+ log["reconstruction"] = xrec
+
+ if ismap(xc):
+ log["original_conditioning"] = model.to_rgb(xc)
+ if hasattr(model, 'cond_stage_key'):
+ log[model.cond_stage_key] = model.to_rgb(xc)
+
+ else:
+ log["original_conditioning"] = xc if xc is not None else torch.zeros_like(x)
+ if model.cond_stage_model:
+ log[model.cond_stage_key] = xc if xc is not None else torch.zeros_like(x)
+ if model.cond_stage_key =='class_label':
+ log[model.cond_stage_key] = xc[model.cond_stage_key]
+
+ with model.ema_scope("Plotting"):
+ t0 = time.time()
+ img_cb = None
+
+ sample, intermediates = convsample_ddim(model, c, steps=custom_steps, shape=z.shape,
+ eta=eta,
+ quantize_x0=quantize_x0, img_callback=img_cb, mask=None, x0=z0,
+ temperature=temperature, noise_dropout=noise_dropout,
+ score_corrector=corrector, corrector_kwargs=corrector_kwargs,
+ x_T=x_T, log_every_t=log_every_t)
+ t1 = time.time()
+
+ if ddim_use_x0_pred:
+ sample = intermediates['pred_x0'][-1]
+
+ x_sample = model.decode_first_stage(sample)
+
+ try:
+ x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True)
+ log["sample_noquant"] = x_sample_noquant
+ log["sample_diff"] = torch.abs(x_sample_noquant - x_sample)
+ except:
+ pass
+
+ log["sample"] = x_sample
+ log["time"] = t1 - t0
+
+ return log
\ No newline at end of file
diff --git a/stable_diffusion/scripts/download_models.sh b/stable_diffusion/scripts/download_models.sh
new file mode 100644
index 0000000000000000000000000000000000000000..84297d7b8b9a78d241edcd5adaf7d9aa273790de
--- /dev/null
+++ b/stable_diffusion/scripts/download_models.sh
@@ -0,0 +1,49 @@
+#!/bin/bash
+wget -O models/ldm/celeba256/celeba-256.zip https://ommer-lab.com/files/latent-diffusion/celeba.zip
+wget -O models/ldm/ffhq256/ffhq-256.zip https://ommer-lab.com/files/latent-diffusion/ffhq.zip
+wget -O models/ldm/lsun_churches256/lsun_churches-256.zip https://ommer-lab.com/files/latent-diffusion/lsun_churches.zip
+wget -O models/ldm/lsun_beds256/lsun_beds-256.zip https://ommer-lab.com/files/latent-diffusion/lsun_bedrooms.zip
+wget -O models/ldm/text2img256/model.zip https://ommer-lab.com/files/latent-diffusion/text2img.zip
+wget -O models/ldm/cin256/model.zip https://ommer-lab.com/files/latent-diffusion/cin.zip
+wget -O models/ldm/semantic_synthesis512/model.zip https://ommer-lab.com/files/latent-diffusion/semantic_synthesis.zip
+wget -O models/ldm/semantic_synthesis256/model.zip https://ommer-lab.com/files/latent-diffusion/semantic_synthesis256.zip
+wget -O models/ldm/bsr_sr/model.zip https://ommer-lab.com/files/latent-diffusion/sr_bsr.zip
+wget -O models/ldm/layout2img-openimages256/model.zip https://ommer-lab.com/files/latent-diffusion/layout2img_model.zip
+wget -O models/ldm/inpainting_big/model.zip https://ommer-lab.com/files/latent-diffusion/inpainting_big.zip
+
+
+
+cd models/ldm/celeba256
+unzip -o celeba-256.zip
+
+cd ../ffhq256
+unzip -o ffhq-256.zip
+
+cd ../lsun_churches256
+unzip -o lsun_churches-256.zip
+
+cd ../lsun_beds256
+unzip -o lsun_beds-256.zip
+
+cd ../text2img256
+unzip -o model.zip
+
+cd ../cin256
+unzip -o model.zip
+
+cd ../semantic_synthesis512
+unzip -o model.zip
+
+cd ../semantic_synthesis256
+unzip -o model.zip
+
+cd ../bsr_sr
+unzip -o model.zip
+
+cd ../layout2img-openimages256
+unzip -o model.zip
+
+cd ../inpainting_big
+unzip -o model.zip
+
+cd ../..
diff --git a/stable_diffusion/scripts/img2img.py b/stable_diffusion/scripts/img2img.py
new file mode 100644
index 0000000000000000000000000000000000000000..421e2151d9e9de75a142f5d5f532333645a36287
--- /dev/null
+++ b/stable_diffusion/scripts/img2img.py
@@ -0,0 +1,293 @@
+"""make variations of input image"""
+
+import argparse, os, sys, glob
+import PIL
+import torch
+import numpy as np
+from omegaconf import OmegaConf
+from PIL import Image
+from tqdm import tqdm, trange
+from itertools import islice
+from einops import rearrange, repeat
+from torchvision.utils import make_grid
+from torch import autocast
+from contextlib import nullcontext
+import time
+from pytorch_lightning import seed_everything
+
+from ldm.util import instantiate_from_config
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.models.diffusion.plms import PLMSSampler
+
+
+def chunk(it, size):
+ it = iter(it)
+ return iter(lambda: tuple(islice(it, size)), ())
+
+
+def load_model_from_config(config, ckpt, verbose=False):
+ print(f"Loading model from {ckpt}")
+ pl_sd = torch.load(ckpt, map_location="cpu")
+ if "global_step" in pl_sd:
+ print(f"Global Step: {pl_sd['global_step']}")
+ sd = pl_sd["state_dict"]
+ model = instantiate_from_config(config.model)
+ m, u = model.load_state_dict(sd, strict=False)
+ if len(m) > 0 and verbose:
+ print("missing keys:")
+ print(m)
+ if len(u) > 0 and verbose:
+ print("unexpected keys:")
+ print(u)
+
+ model.cuda()
+ model.eval()
+ return model
+
+
+def load_img(path):
+ image = Image.open(path).convert("RGB")
+ w, h = image.size
+ print(f"loaded input image of size ({w}, {h}) from {path}")
+ w, h = map(lambda x: x - x % 32, (w, h)) # resize to integer multiple of 32
+ image = image.resize((w, h), resample=PIL.Image.LANCZOS)
+ image = np.array(image).astype(np.float32) / 255.0
+ image = image[None].transpose(0, 3, 1, 2)
+ image = torch.from_numpy(image)
+ return 2.*image - 1.
+
+
+def main():
+ parser = argparse.ArgumentParser()
+
+ parser.add_argument(
+ "--prompt",
+ type=str,
+ nargs="?",
+ default="a painting of a virus monster playing guitar",
+ help="the prompt to render"
+ )
+
+ parser.add_argument(
+ "--init-img",
+ type=str,
+ nargs="?",
+ help="path to the input image"
+ )
+
+ parser.add_argument(
+ "--outdir",
+ type=str,
+ nargs="?",
+ help="dir to write results to",
+ default="outputs/img2img-samples"
+ )
+
+ parser.add_argument(
+ "--skip_grid",
+ action='store_true',
+ help="do not save a grid, only individual samples. Helpful when evaluating lots of samples",
+ )
+
+ parser.add_argument(
+ "--skip_save",
+ action='store_true',
+ help="do not save indiviual samples. For speed measurements.",
+ )
+
+ parser.add_argument(
+ "--ddim_steps",
+ type=int,
+ default=50,
+ help="number of ddim sampling steps",
+ )
+
+ parser.add_argument(
+ "--plms",
+ action='store_true',
+ help="use plms sampling",
+ )
+ parser.add_argument(
+ "--fixed_code",
+ action='store_true',
+ help="if enabled, uses the same starting code across all samples ",
+ )
+
+ parser.add_argument(
+ "--ddim_eta",
+ type=float,
+ default=0.0,
+ help="ddim eta (eta=0.0 corresponds to deterministic sampling",
+ )
+ parser.add_argument(
+ "--n_iter",
+ type=int,
+ default=1,
+ help="sample this often",
+ )
+ parser.add_argument(
+ "--C",
+ type=int,
+ default=4,
+ help="latent channels",
+ )
+ parser.add_argument(
+ "--f",
+ type=int,
+ default=8,
+ help="downsampling factor, most often 8 or 16",
+ )
+ parser.add_argument(
+ "--n_samples",
+ type=int,
+ default=2,
+ help="how many samples to produce for each given prompt. A.k.a batch size",
+ )
+ parser.add_argument(
+ "--n_rows",
+ type=int,
+ default=0,
+ help="rows in the grid (default: n_samples)",
+ )
+ parser.add_argument(
+ "--scale",
+ type=float,
+ default=5.0,
+ help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))",
+ )
+
+ parser.add_argument(
+ "--strength",
+ type=float,
+ default=0.75,
+ help="strength for noising/unnoising. 1.0 corresponds to full destruction of information in init image",
+ )
+ parser.add_argument(
+ "--from-file",
+ type=str,
+ help="if specified, load prompts from this file",
+ )
+ parser.add_argument(
+ "--config",
+ type=str,
+ default="configs/stable-diffusion/v1-inference.yaml",
+ help="path to config which constructs model",
+ )
+ parser.add_argument(
+ "--ckpt",
+ type=str,
+ default="models/ldm/stable-diffusion-v1/model.ckpt",
+ help="path to checkpoint of model",
+ )
+ parser.add_argument(
+ "--seed",
+ type=int,
+ default=42,
+ help="the seed (for reproducible sampling)",
+ )
+ parser.add_argument(
+ "--precision",
+ type=str,
+ help="evaluate at this precision",
+ choices=["full", "autocast"],
+ default="autocast"
+ )
+
+ opt = parser.parse_args()
+ seed_everything(opt.seed)
+
+ config = OmegaConf.load(f"{opt.config}")
+ model = load_model_from_config(config, f"{opt.ckpt}")
+
+ device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+ model = model.to(device)
+
+ if opt.plms:
+ raise NotImplementedError("PLMS sampler not (yet) supported")
+ sampler = PLMSSampler(model)
+ else:
+ sampler = DDIMSampler(model)
+
+ os.makedirs(opt.outdir, exist_ok=True)
+ outpath = opt.outdir
+
+ batch_size = opt.n_samples
+ n_rows = opt.n_rows if opt.n_rows > 0 else batch_size
+ if not opt.from_file:
+ prompt = opt.prompt
+ assert prompt is not None
+ data = [batch_size * [prompt]]
+
+ else:
+ print(f"reading prompts from {opt.from_file}")
+ with open(opt.from_file, "r") as f:
+ data = f.read().splitlines()
+ data = list(chunk(data, batch_size))
+
+ sample_path = os.path.join(outpath, "samples")
+ os.makedirs(sample_path, exist_ok=True)
+ base_count = len(os.listdir(sample_path))
+ grid_count = len(os.listdir(outpath)) - 1
+
+ assert os.path.isfile(opt.init_img)
+ init_image = load_img(opt.init_img).to(device)
+ init_image = repeat(init_image, '1 ... -> b ...', b=batch_size)
+ init_latent = model.get_first_stage_encoding(model.encode_first_stage(init_image)) # move to latent space
+
+ sampler.make_schedule(ddim_num_steps=opt.ddim_steps, ddim_eta=opt.ddim_eta, verbose=False)
+
+ assert 0. <= opt.strength <= 1., 'can only work with strength in [0.0, 1.0]'
+ t_enc = int(opt.strength * opt.ddim_steps)
+ print(f"target t_enc is {t_enc} steps")
+
+ precision_scope = autocast if opt.precision == "autocast" else nullcontext
+ with torch.no_grad():
+ with precision_scope("cuda"):
+ with model.ema_scope():
+ tic = time.time()
+ all_samples = list()
+ for n in trange(opt.n_iter, desc="Sampling"):
+ for prompts in tqdm(data, desc="data"):
+ uc = None
+ if opt.scale != 1.0:
+ uc = model.get_learned_conditioning(batch_size * [""])
+ if isinstance(prompts, tuple):
+ prompts = list(prompts)
+ c = model.get_learned_conditioning(prompts)
+
+ # encode (scaled latent)
+ z_enc = sampler.stochastic_encode(init_latent, torch.tensor([t_enc]*batch_size).to(device))
+ # decode it
+ samples = sampler.decode(z_enc, c, t_enc, unconditional_guidance_scale=opt.scale,
+ unconditional_conditioning=uc,)
+
+ x_samples = model.decode_first_stage(samples)
+ x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0)
+
+ if not opt.skip_save:
+ for x_sample in x_samples:
+ x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
+ Image.fromarray(x_sample.astype(np.uint8)).save(
+ os.path.join(sample_path, f"{base_count:05}.png"))
+ base_count += 1
+ all_samples.append(x_samples)
+
+ if not opt.skip_grid:
+ # additionally, save as grid
+ grid = torch.stack(all_samples, 0)
+ grid = rearrange(grid, 'n b c h w -> (n b) c h w')
+ grid = make_grid(grid, nrow=n_rows)
+
+ # to image
+ grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()
+ Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
+ grid_count += 1
+
+ toc = time.time()
+
+ print(f"Your samples are ready and waiting for you here: \n{outpath} \n"
+ f" \nEnjoy.")
+
+
+if __name__ == "__main__":
+ main()
diff --git a/stable_diffusion/scripts/knn2img.py b/stable_diffusion/scripts/knn2img.py
new file mode 100644
index 0000000000000000000000000000000000000000..e6eaaecab53eac9c97051c9a5cb457a240679725
--- /dev/null
+++ b/stable_diffusion/scripts/knn2img.py
@@ -0,0 +1,398 @@
+import argparse, os, sys, glob
+import clip
+import torch
+import torch.nn as nn
+import numpy as np
+from omegaconf import OmegaConf
+from PIL import Image
+from tqdm import tqdm, trange
+from itertools import islice
+from einops import rearrange, repeat
+from torchvision.utils import make_grid
+import scann
+import time
+from multiprocessing import cpu_count
+
+from ldm.util import instantiate_from_config, parallel_data_prefetch
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.models.diffusion.plms import PLMSSampler
+from ldm.modules.encoders.modules import FrozenClipImageEmbedder, FrozenCLIPTextEmbedder
+
+DATABASES = [
+ "openimages",
+ "artbench-art_nouveau",
+ "artbench-baroque",
+ "artbench-expressionism",
+ "artbench-impressionism",
+ "artbench-post_impressionism",
+ "artbench-realism",
+ "artbench-romanticism",
+ "artbench-renaissance",
+ "artbench-surrealism",
+ "artbench-ukiyo_e",
+]
+
+
+def chunk(it, size):
+ it = iter(it)
+ return iter(lambda: tuple(islice(it, size)), ())
+
+
+def load_model_from_config(config, ckpt, verbose=False):
+ print(f"Loading model from {ckpt}")
+ pl_sd = torch.load(ckpt, map_location="cpu")
+ if "global_step" in pl_sd:
+ print(f"Global Step: {pl_sd['global_step']}")
+ sd = pl_sd["state_dict"]
+ model = instantiate_from_config(config.model)
+ m, u = model.load_state_dict(sd, strict=False)
+ if len(m) > 0 and verbose:
+ print("missing keys:")
+ print(m)
+ if len(u) > 0 and verbose:
+ print("unexpected keys:")
+ print(u)
+
+ model.cuda()
+ model.eval()
+ return model
+
+
+class Searcher(object):
+ def __init__(self, database, retriever_version='ViT-L/14'):
+ assert database in DATABASES
+ # self.database = self.load_database(database)
+ self.database_name = database
+ self.searcher_savedir = f'data/rdm/searchers/{self.database_name}'
+ self.database_path = f'data/rdm/retrieval_databases/{self.database_name}'
+ self.retriever = self.load_retriever(version=retriever_version)
+ self.database = {'embedding': [],
+ 'img_id': [],
+ 'patch_coords': []}
+ self.load_database()
+ self.load_searcher()
+
+ def train_searcher(self, k,
+ metric='dot_product',
+ searcher_savedir=None):
+
+ print('Start training searcher')
+ searcher = scann.scann_ops_pybind.builder(self.database['embedding'] /
+ np.linalg.norm(self.database['embedding'], axis=1)[:, np.newaxis],
+ k, metric)
+ self.searcher = searcher.score_brute_force().build()
+ print('Finish training searcher')
+
+ if searcher_savedir is not None:
+ print(f'Save trained searcher under "{searcher_savedir}"')
+ os.makedirs(searcher_savedir, exist_ok=True)
+ self.searcher.serialize(searcher_savedir)
+
+ def load_single_file(self, saved_embeddings):
+ compressed = np.load(saved_embeddings)
+ self.database = {key: compressed[key] for key in compressed.files}
+ print('Finished loading of clip embeddings.')
+
+ def load_multi_files(self, data_archive):
+ out_data = {key: [] for key in self.database}
+ for d in tqdm(data_archive, desc=f'Loading datapool from {len(data_archive)} individual files.'):
+ for key in d.files:
+ out_data[key].append(d[key])
+
+ return out_data
+
+ def load_database(self):
+
+ print(f'Load saved patch embedding from "{self.database_path}"')
+ file_content = glob.glob(os.path.join(self.database_path, '*.npz'))
+
+ if len(file_content) == 1:
+ self.load_single_file(file_content[0])
+ elif len(file_content) > 1:
+ data = [np.load(f) for f in file_content]
+ prefetched_data = parallel_data_prefetch(self.load_multi_files, data,
+ n_proc=min(len(data), cpu_count()), target_data_type='dict')
+
+ self.database = {key: np.concatenate([od[key] for od in prefetched_data], axis=1)[0] for key in
+ self.database}
+ else:
+ raise ValueError(f'No npz-files in specified path "{self.database_path}" is this directory existing?')
+
+ print(f'Finished loading of retrieval database of length {self.database["embedding"].shape[0]}.')
+
+ def load_retriever(self, version='ViT-L/14', ):
+ model = FrozenClipImageEmbedder(model=version)
+ if torch.cuda.is_available():
+ model.cuda()
+ model.eval()
+ return model
+
+ def load_searcher(self):
+ print(f'load searcher for database {self.database_name} from {self.searcher_savedir}')
+ self.searcher = scann.scann_ops_pybind.load_searcher(self.searcher_savedir)
+ print('Finished loading searcher.')
+
+ def search(self, x, k):
+ if self.searcher is None and self.database['embedding'].shape[0] < 2e4:
+ self.train_searcher(k) # quickly fit searcher on the fly for small databases
+ assert self.searcher is not None, 'Cannot search with uninitialized searcher'
+ if isinstance(x, torch.Tensor):
+ x = x.detach().cpu().numpy()
+ if len(x.shape) == 3:
+ x = x[:, 0]
+ query_embeddings = x / np.linalg.norm(x, axis=1)[:, np.newaxis]
+
+ start = time.time()
+ nns, distances = self.searcher.search_batched(query_embeddings, final_num_neighbors=k)
+ end = time.time()
+
+ out_embeddings = self.database['embedding'][nns]
+ out_img_ids = self.database['img_id'][nns]
+ out_pc = self.database['patch_coords'][nns]
+
+ out = {'nn_embeddings': out_embeddings / np.linalg.norm(out_embeddings, axis=-1)[..., np.newaxis],
+ 'img_ids': out_img_ids,
+ 'patch_coords': out_pc,
+ 'queries': x,
+ 'exec_time': end - start,
+ 'nns': nns,
+ 'q_embeddings': query_embeddings}
+
+ return out
+
+ def __call__(self, x, n):
+ return self.search(x, n)
+
+
+if __name__ == "__main__":
+ parser = argparse.ArgumentParser()
+ # TODO: add n_neighbors and modes (text-only, text-image-retrieval, image-image retrieval etc)
+ # TODO: add 'image variation' mode when knn=0 but a single image is given instead of a text prompt?
+ parser.add_argument(
+ "--prompt",
+ type=str,
+ nargs="?",
+ default="a painting of a virus monster playing guitar",
+ help="the prompt to render"
+ )
+
+ parser.add_argument(
+ "--outdir",
+ type=str,
+ nargs="?",
+ help="dir to write results to",
+ default="outputs/txt2img-samples"
+ )
+
+ parser.add_argument(
+ "--skip_grid",
+ action='store_true',
+ help="do not save a grid, only individual samples. Helpful when evaluating lots of samples",
+ )
+
+ parser.add_argument(
+ "--ddim_steps",
+ type=int,
+ default=50,
+ help="number of ddim sampling steps",
+ )
+
+ parser.add_argument(
+ "--n_repeat",
+ type=int,
+ default=1,
+ help="number of repeats in CLIP latent space",
+ )
+
+ parser.add_argument(
+ "--plms",
+ action='store_true',
+ help="use plms sampling",
+ )
+
+ parser.add_argument(
+ "--ddim_eta",
+ type=float,
+ default=0.0,
+ help="ddim eta (eta=0.0 corresponds to deterministic sampling",
+ )
+ parser.add_argument(
+ "--n_iter",
+ type=int,
+ default=1,
+ help="sample this often",
+ )
+
+ parser.add_argument(
+ "--H",
+ type=int,
+ default=768,
+ help="image height, in pixel space",
+ )
+
+ parser.add_argument(
+ "--W",
+ type=int,
+ default=768,
+ help="image width, in pixel space",
+ )
+
+ parser.add_argument(
+ "--n_samples",
+ type=int,
+ default=3,
+ help="how many samples to produce for each given prompt. A.k.a batch size",
+ )
+
+ parser.add_argument(
+ "--n_rows",
+ type=int,
+ default=0,
+ help="rows in the grid (default: n_samples)",
+ )
+
+ parser.add_argument(
+ "--scale",
+ type=float,
+ default=5.0,
+ help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))",
+ )
+
+ parser.add_argument(
+ "--from-file",
+ type=str,
+ help="if specified, load prompts from this file",
+ )
+
+ parser.add_argument(
+ "--config",
+ type=str,
+ default="configs/retrieval-augmented-diffusion/768x768.yaml",
+ help="path to config which constructs model",
+ )
+
+ parser.add_argument(
+ "--ckpt",
+ type=str,
+ default="models/rdm/rdm768x768/model.ckpt",
+ help="path to checkpoint of model",
+ )
+
+ parser.add_argument(
+ "--clip_type",
+ type=str,
+ default="ViT-L/14",
+ help="which CLIP model to use for retrieval and NN encoding",
+ )
+ parser.add_argument(
+ "--database",
+ type=str,
+ default='artbench-surrealism',
+ choices=DATABASES,
+ help="The database used for the search, only applied when --use_neighbors=True",
+ )
+ parser.add_argument(
+ "--use_neighbors",
+ default=False,
+ action='store_true',
+ help="Include neighbors in addition to text prompt for conditioning",
+ )
+ parser.add_argument(
+ "--knn",
+ default=10,
+ type=int,
+ help="The number of included neighbors, only applied when --use_neighbors=True",
+ )
+
+ opt = parser.parse_args()
+
+ config = OmegaConf.load(f"{opt.config}")
+ model = load_model_from_config(config, f"{opt.ckpt}")
+
+ device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+ model = model.to(device)
+
+ clip_text_encoder = FrozenCLIPTextEmbedder(opt.clip_type).to(device)
+
+ if opt.plms:
+ sampler = PLMSSampler(model)
+ else:
+ sampler = DDIMSampler(model)
+
+ os.makedirs(opt.outdir, exist_ok=True)
+ outpath = opt.outdir
+
+ batch_size = opt.n_samples
+ n_rows = opt.n_rows if opt.n_rows > 0 else batch_size
+ if not opt.from_file:
+ prompt = opt.prompt
+ assert prompt is not None
+ data = [batch_size * [prompt]]
+
+ else:
+ print(f"reading prompts from {opt.from_file}")
+ with open(opt.from_file, "r") as f:
+ data = f.read().splitlines()
+ data = list(chunk(data, batch_size))
+
+ sample_path = os.path.join(outpath, "samples")
+ os.makedirs(sample_path, exist_ok=True)
+ base_count = len(os.listdir(sample_path))
+ grid_count = len(os.listdir(outpath)) - 1
+
+ print(f"sampling scale for cfg is {opt.scale:.2f}")
+
+ searcher = None
+ if opt.use_neighbors:
+ searcher = Searcher(opt.database)
+
+ with torch.no_grad():
+ with model.ema_scope():
+ for n in trange(opt.n_iter, desc="Sampling"):
+ all_samples = list()
+ for prompts in tqdm(data, desc="data"):
+ print("sampling prompts:", prompts)
+ if isinstance(prompts, tuple):
+ prompts = list(prompts)
+ c = clip_text_encoder.encode(prompts)
+ uc = None
+ if searcher is not None:
+ nn_dict = searcher(c, opt.knn)
+ c = torch.cat([c, torch.from_numpy(nn_dict['nn_embeddings']).cuda()], dim=1)
+ if opt.scale != 1.0:
+ uc = torch.zeros_like(c)
+ if isinstance(prompts, tuple):
+ prompts = list(prompts)
+ shape = [16, opt.H // 16, opt.W // 16] # note: currently hardcoded for f16 model
+ samples_ddim, _ = sampler.sample(S=opt.ddim_steps,
+ conditioning=c,
+ batch_size=c.shape[0],
+ shape=shape,
+ verbose=False,
+ unconditional_guidance_scale=opt.scale,
+ unconditional_conditioning=uc,
+ eta=opt.ddim_eta,
+ )
+
+ x_samples_ddim = model.decode_first_stage(samples_ddim)
+ x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
+
+ for x_sample in x_samples_ddim:
+ x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
+ Image.fromarray(x_sample.astype(np.uint8)).save(
+ os.path.join(sample_path, f"{base_count:05}.png"))
+ base_count += 1
+ all_samples.append(x_samples_ddim)
+
+ if not opt.skip_grid:
+ # additionally, save as grid
+ grid = torch.stack(all_samples, 0)
+ grid = rearrange(grid, 'n b c h w -> (n b) c h w')
+ grid = make_grid(grid, nrow=n_rows)
+
+ # to image
+ grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()
+ Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
+ grid_count += 1
+
+ print(f"Your samples are ready and waiting for you here: \n{outpath} \nEnjoy.")
diff --git a/stable_diffusion/scripts/sample_diffusion.py b/stable_diffusion/scripts/sample_diffusion.py
new file mode 100644
index 0000000000000000000000000000000000000000..876fe3c3642fcc8c7209e4f763c0134166615f78
--- /dev/null
+++ b/stable_diffusion/scripts/sample_diffusion.py
@@ -0,0 +1,313 @@
+import argparse, os, sys, glob, datetime, yaml
+import torch
+import time
+import numpy as np
+from tqdm import trange
+
+from omegaconf import OmegaConf
+from PIL import Image
+
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.util import instantiate_from_config
+
+rescale = lambda x: (x + 1.) / 2.
+
+def custom_to_pil(x):
+ x = x.detach().cpu()
+ x = torch.clamp(x, -1., 1.)
+ x = (x + 1.) / 2.
+ x = x.permute(1, 2, 0).numpy()
+ x = (255 * x).astype(np.uint8)
+ x = Image.fromarray(x)
+ if not x.mode == "RGB":
+ x = x.convert("RGB")
+ return x
+
+
+def custom_to_np(x):
+ # saves the batch in adm style as in https://github.com/openai/guided-diffusion/blob/main/scripts/image_sample.py
+ sample = x.detach().cpu()
+ sample = ((sample + 1) * 127.5).clamp(0, 255).to(torch.uint8)
+ sample = sample.permute(0, 2, 3, 1)
+ sample = sample.contiguous()
+ return sample
+
+
+def logs2pil(logs, keys=["sample"]):
+ imgs = dict()
+ for k in logs:
+ try:
+ if len(logs[k].shape) == 4:
+ img = custom_to_pil(logs[k][0, ...])
+ elif len(logs[k].shape) == 3:
+ img = custom_to_pil(logs[k])
+ else:
+ print(f"Unknown format for key {k}. ")
+ img = None
+ except:
+ img = None
+ imgs[k] = img
+ return imgs
+
+
+@torch.no_grad()
+def convsample(model, shape, return_intermediates=True,
+ verbose=True,
+ make_prog_row=False):
+
+
+ if not make_prog_row:
+ return model.p_sample_loop(None, shape,
+ return_intermediates=return_intermediates, verbose=verbose)
+ else:
+ return model.progressive_denoising(
+ None, shape, verbose=True
+ )
+
+
+@torch.no_grad()
+def convsample_ddim(model, steps, shape, eta=1.0
+ ):
+ ddim = DDIMSampler(model)
+ bs = shape[0]
+ shape = shape[1:]
+ samples, intermediates = ddim.sample(steps, batch_size=bs, shape=shape, eta=eta, verbose=False,)
+ return samples, intermediates
+
+
+@torch.no_grad()
+def make_convolutional_sample(model, batch_size, vanilla=False, custom_steps=None, eta=1.0,):
+
+
+ log = dict()
+
+ shape = [batch_size,
+ model.model.diffusion_model.in_channels,
+ model.model.diffusion_model.image_size,
+ model.model.diffusion_model.image_size]
+
+ with model.ema_scope("Plotting"):
+ t0 = time.time()
+ if vanilla:
+ sample, progrow = convsample(model, shape,
+ make_prog_row=True)
+ else:
+ sample, intermediates = convsample_ddim(model, steps=custom_steps, shape=shape,
+ eta=eta)
+
+ t1 = time.time()
+
+ x_sample = model.decode_first_stage(sample)
+
+ log["sample"] = x_sample
+ log["time"] = t1 - t0
+ log['throughput'] = sample.shape[0] / (t1 - t0)
+ print(f'Throughput for this batch: {log["throughput"]}')
+ return log
+
+def run(model, logdir, batch_size=50, vanilla=False, custom_steps=None, eta=None, n_samples=50000, nplog=None):
+ if vanilla:
+ print(f'Using Vanilla DDPM sampling with {model.num_timesteps} sampling steps.')
+ else:
+ print(f'Using DDIM sampling with {custom_steps} sampling steps and eta={eta}')
+
+
+ tstart = time.time()
+ n_saved = len(glob.glob(os.path.join(logdir,'*.png')))-1
+ # path = logdir
+ if model.cond_stage_model is None:
+ all_images = []
+
+ print(f"Running unconditional sampling for {n_samples} samples")
+ for _ in trange(n_samples // batch_size, desc="Sampling Batches (unconditional)"):
+ logs = make_convolutional_sample(model, batch_size=batch_size,
+ vanilla=vanilla, custom_steps=custom_steps,
+ eta=eta)
+ n_saved = save_logs(logs, logdir, n_saved=n_saved, key="sample")
+ all_images.extend([custom_to_np(logs["sample"])])
+ if n_saved >= n_samples:
+ print(f'Finish after generating {n_saved} samples')
+ break
+ all_img = np.concatenate(all_images, axis=0)
+ all_img = all_img[:n_samples]
+ shape_str = "x".join([str(x) for x in all_img.shape])
+ nppath = os.path.join(nplog, f"{shape_str}-samples.npz")
+ np.savez(nppath, all_img)
+
+ else:
+ raise NotImplementedError('Currently only sampling for unconditional models supported.')
+
+ print(f"sampling of {n_saved} images finished in {(time.time() - tstart) / 60.:.2f} minutes.")
+
+
+def save_logs(logs, path, n_saved=0, key="sample", np_path=None):
+ for k in logs:
+ if k == key:
+ batch = logs[key]
+ if np_path is None:
+ for x in batch:
+ img = custom_to_pil(x)
+ imgpath = os.path.join(path, f"{key}_{n_saved:06}.png")
+ img.save(imgpath)
+ n_saved += 1
+ else:
+ npbatch = custom_to_np(batch)
+ shape_str = "x".join([str(x) for x in npbatch.shape])
+ nppath = os.path.join(np_path, f"{n_saved}-{shape_str}-samples.npz")
+ np.savez(nppath, npbatch)
+ n_saved += npbatch.shape[0]
+ return n_saved
+
+
+def get_parser():
+ parser = argparse.ArgumentParser()
+ parser.add_argument(
+ "-r",
+ "--resume",
+ type=str,
+ nargs="?",
+ help="load from logdir or checkpoint in logdir",
+ )
+ parser.add_argument(
+ "-n",
+ "--n_samples",
+ type=int,
+ nargs="?",
+ help="number of samples to draw",
+ default=50000
+ )
+ parser.add_argument(
+ "-e",
+ "--eta",
+ type=float,
+ nargs="?",
+ help="eta for ddim sampling (0.0 yields deterministic sampling)",
+ default=1.0
+ )
+ parser.add_argument(
+ "-v",
+ "--vanilla_sample",
+ default=False,
+ action='store_true',
+ help="vanilla sampling (default option is DDIM sampling)?",
+ )
+ parser.add_argument(
+ "-l",
+ "--logdir",
+ type=str,
+ nargs="?",
+ help="extra logdir",
+ default="none"
+ )
+ parser.add_argument(
+ "-c",
+ "--custom_steps",
+ type=int,
+ nargs="?",
+ help="number of steps for ddim and fastdpm sampling",
+ default=50
+ )
+ parser.add_argument(
+ "--batch_size",
+ type=int,
+ nargs="?",
+ help="the bs",
+ default=10
+ )
+ return parser
+
+
+def load_model_from_config(config, sd):
+ model = instantiate_from_config(config)
+ model.load_state_dict(sd,strict=False)
+ model.cuda()
+ model.eval()
+ return model
+
+
+def load_model(config, ckpt, gpu, eval_mode):
+ if ckpt:
+ print(f"Loading model from {ckpt}")
+ pl_sd = torch.load(ckpt, map_location="cpu")
+ global_step = pl_sd["global_step"]
+ else:
+ pl_sd = {"state_dict": None}
+ global_step = None
+ model = load_model_from_config(config.model,
+ pl_sd["state_dict"])
+
+ return model, global_step
+
+
+if __name__ == "__main__":
+ now = datetime.datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
+ sys.path.append(os.getcwd())
+ command = " ".join(sys.argv)
+
+ parser = get_parser()
+ opt, unknown = parser.parse_known_args()
+ ckpt = None
+
+ if not os.path.exists(opt.resume):
+ raise ValueError("Cannot find {}".format(opt.resume))
+ if os.path.isfile(opt.resume):
+ # paths = opt.resume.split("/")
+ try:
+ logdir = '/'.join(opt.resume.split('/')[:-1])
+ # idx = len(paths)-paths[::-1].index("logs")+1
+ print(f'Logdir is {logdir}')
+ except ValueError:
+ paths = opt.resume.split("/")
+ idx = -2 # take a guess: path/to/logdir/checkpoints/model.ckpt
+ logdir = "/".join(paths[:idx])
+ ckpt = opt.resume
+ else:
+ assert os.path.isdir(opt.resume), f"{opt.resume} is not a directory"
+ logdir = opt.resume.rstrip("/")
+ ckpt = os.path.join(logdir, "model.ckpt")
+
+ base_configs = sorted(glob.glob(os.path.join(logdir, "config.yaml")))
+ opt.base = base_configs
+
+ configs = [OmegaConf.load(cfg) for cfg in opt.base]
+ cli = OmegaConf.from_dotlist(unknown)
+ config = OmegaConf.merge(*configs, cli)
+
+ gpu = True
+ eval_mode = True
+
+ if opt.logdir != "none":
+ locallog = logdir.split(os.sep)[-1]
+ if locallog == "": locallog = logdir.split(os.sep)[-2]
+ print(f"Switching logdir from '{logdir}' to '{os.path.join(opt.logdir, locallog)}'")
+ logdir = os.path.join(opt.logdir, locallog)
+
+ print(config)
+
+ model, global_step = load_model(config, ckpt, gpu, eval_mode)
+ print(f"global step: {global_step}")
+ print(75 * "=")
+ print("logging to:")
+ logdir = os.path.join(logdir, "samples", f"{global_step:08}", now)
+ imglogdir = os.path.join(logdir, "img")
+ numpylogdir = os.path.join(logdir, "numpy")
+
+ os.makedirs(imglogdir)
+ os.makedirs(numpylogdir)
+ print(logdir)
+ print(75 * "=")
+
+ # write config out
+ sampling_file = os.path.join(logdir, "sampling_config.yaml")
+ sampling_conf = vars(opt)
+
+ with open(sampling_file, 'w') as f:
+ yaml.dump(sampling_conf, f, default_flow_style=False)
+ print(sampling_conf)
+
+
+ run(model, imglogdir, eta=opt.eta,
+ vanilla=opt.vanilla_sample, n_samples=opt.n_samples, custom_steps=opt.custom_steps,
+ batch_size=opt.batch_size, nplog=numpylogdir)
+
+ print("done.")
diff --git a/stable_diffusion/scripts/tests/test_watermark.py b/stable_diffusion/scripts/tests/test_watermark.py
new file mode 100644
index 0000000000000000000000000000000000000000..f93f8a6e70763c0e284157bc8225827520b2f5ef
--- /dev/null
+++ b/stable_diffusion/scripts/tests/test_watermark.py
@@ -0,0 +1,18 @@
+import cv2
+import fire
+from imwatermark import WatermarkDecoder
+
+
+def testit(img_path):
+ bgr = cv2.imread(img_path)
+ decoder = WatermarkDecoder('bytes', 136)
+ watermark = decoder.decode(bgr, 'dwtDct')
+ try:
+ dec = watermark.decode('utf-8')
+ except:
+ dec = "null"
+ print(dec)
+
+
+if __name__ == "__main__":
+ fire.Fire(testit)
\ No newline at end of file
diff --git a/stable_diffusion/setup.py b/stable_diffusion/setup.py
new file mode 100644
index 0000000000000000000000000000000000000000..a24d541676407eee1bea271179ffd1d80c6a8e79
--- /dev/null
+++ b/stable_diffusion/setup.py
@@ -0,0 +1,13 @@
+from setuptools import setup, find_packages
+
+setup(
+ name='latent-diffusion',
+ version='0.0.1',
+ description='',
+ packages=find_packages(),
+ install_requires=[
+ 'torch',
+ 'numpy',
+ 'tqdm',
+ ],
+)
\ No newline at end of file
diff --git a/test.json b/test.json
new file mode 100644
index 0000000000000000000000000000000000000000..9be0fa0e60cff9a89a81e4c2c4e92529d3cbc9ff
--- /dev/null
+++ b/test.json
@@ -0,0 +1,2452 @@
+[
+ {
+ "input": "data/magicbrush/images/242679/242679-input.png",
+ "output": "data/magicbrush/images/242679/242679-output1.png",
+ "instruction": "Put a cat on the seat.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/368667/368667-input.png",
+ "output": "data/magicbrush/images/368667/368667-output1.png",
+ "instruction": "Have there be a stream running through the field",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/368667/368667-output1.png",
+ "output": "data/magicbrush/images/368667/368667-output2.png",
+ "instruction": "Add a giraffe in the field",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/368667/368667-output2.png",
+ "output": "data/magicbrush/images/368667/368667-output3.png",
+ "instruction": "Add a supernova explosion in the sky",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/385042/385042-input.png",
+ "output": "data/magicbrush/images/385042/385042-output1.png",
+ "instruction": "Make the hydrant all white.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/385042/385042-output1.png",
+ "output": "data/magicbrush/images/385042/385042-output2.png",
+ "instruction": "Put the hydrant on asphalt.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/385042/385042-output2.png",
+ "output": "data/magicbrush/images/385042/385042-output3.png",
+ "instruction": "Add a leashed dog to the hydrant.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/483348/483348-input.png",
+ "output": "data/magicbrush/images/483348/483348-output1.png",
+ "instruction": "Put down the seat.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/483348/483348-output1.png",
+ "output": "data/magicbrush/images/483348/483348-output2.png",
+ "instruction": "Put a frog in the toilet.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/483348/483348-output2.png",
+ "output": "data/magicbrush/images/483348/483348-output3.png",
+ "instruction": "Repair the floor.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/141946/141946-input.png",
+ "output": "data/magicbrush/images/141946/141946-output1.png",
+ "instruction": "let the laptop screen be blank",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/141946/141946-output1.png",
+ "output": "data/magicbrush/images/141946/141946-output2.png",
+ "instruction": "let the chair be red",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/141946/141946-output2.png",
+ "output": "data/magicbrush/images/141946/141946-output3.png",
+ "instruction": "let the desktop be black",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/408425/408425-input.png",
+ "output": "data/magicbrush/images/408425/408425-output1.png",
+ "instruction": "change the bright lime green curtains to white curtains",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/408425/408425-output1.png",
+ "output": "data/magicbrush/images/408425/408425-output2.png",
+ "instruction": "change the bed to a bean bag",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/408425/408425-output2.png",
+ "output": "data/magicbrush/images/408425/408425-output3.png",
+ "instruction": "let the table be wooden",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/352290/352290-input.png",
+ "output": "data/magicbrush/images/352290/352290-output1.png",
+ "instruction": "What if the horse was using a hat?",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/352290/352290-output1.png",
+ "output": "data/magicbrush/images/352290/352290-output2.png",
+ "instruction": "Let's add birds to the sky",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/385037/385037-input.png",
+ "output": "data/magicbrush/images/385037/385037-output1.png",
+ "instruction": "Remove the man.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/385037/385037-output1.png",
+ "output": "data/magicbrush/images/385037/385037-output2.png",
+ "instruction": "Make the woman obese.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/385037/385037-output2.png",
+ "output": "data/magicbrush/images/385037/385037-output3.png",
+ "instruction": "Give the woman a helmet.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/464144/464144-input.png",
+ "output": "data/magicbrush/images/464144/464144-output1.png",
+ "instruction": "Let a boy ski.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/578213/578213-input.png",
+ "output": "data/magicbrush/images/578213/578213-output1.png",
+ "instruction": "put banana shaped candles in the candle holder",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/127515/127515-input.png",
+ "output": "data/magicbrush/images/127515/127515-output1.png",
+ "instruction": "let the player catch a ball",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/308332/308332-input.png",
+ "output": "data/magicbrush/images/308332/308332-output1.png",
+ "instruction": "Have there be a mermaid in the picture on the wall",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/308332/308332-output1.png",
+ "output": "data/magicbrush/images/308332/308332-output2.png",
+ "instruction": "Have the mermaid be reading a book",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/308332/308332-output2.png",
+ "output": "data/magicbrush/images/308332/308332-output3.png",
+ "instruction": "Have there be a lobster on the bed",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/284725/284725-input.png",
+ "output": "data/magicbrush/images/284725/284725-output1.png",
+ "instruction": "Remove the car in front of the bus.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/284725/284725-output1.png",
+ "output": "data/magicbrush/images/284725/284725-output2.png",
+ "instruction": "Put a small cat on top of the bus.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/560472/560472-input.png",
+ "output": "data/magicbrush/images/560472/560472-output1.png",
+ "instruction": "let there be patties in the pan",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/560472/560472-output1.png",
+ "output": "data/magicbrush/images/560472/560472-output2.png",
+ "instruction": "let there be pancakes on the pan",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/560472/560472-output2.png",
+ "output": "data/magicbrush/images/560472/560472-output3.png",
+ "instruction": "let there be a bottle of wine",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/441483/441483-input.png",
+ "output": "data/magicbrush/images/441483/441483-output1.png",
+ "instruction": "Let the toilet bowl have a lid.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/116518/116518-input.png",
+ "output": "data/magicbrush/images/116518/116518-output1.png",
+ "instruction": "Make the teddy bear black.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/116518/116518-output1.png",
+ "output": "data/magicbrush/images/116518/116518-output2.png",
+ "instruction": "Have the dog lick the teddy bear.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/116518/116518-output2.png",
+ "output": "data/magicbrush/images/116518/116518-output3.png",
+ "instruction": "Put a dragonfly on the dog's ear.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/103966/103966-input.png",
+ "output": "data/magicbrush/images/103966/103966-output1.png",
+ "instruction": "replace the tennis rackets with a shovel",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/103966/103966-output1.png",
+ "output": "data/magicbrush/images/103966/103966-output2.png",
+ "instruction": "change the bench into a wooden pew",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/103966/103966-output2.png",
+ "output": "data/magicbrush/images/103966/103966-output3.png",
+ "instruction": "let there be a bucket of the dirt",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/258155/258155-input.png",
+ "output": "data/magicbrush/images/258155/258155-output1.png",
+ "instruction": "Let the blanket be longer and hang over the bed.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/495146/495146-input.png",
+ "output": "data/magicbrush/images/495146/495146-output1.png",
+ "instruction": "Add a helicopter.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/70491/70491-input.png",
+ "output": "data/magicbrush/images/70491/70491-output1.png",
+ "instruction": "let the remote turn into a VR headset",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/70491/70491-output1.png",
+ "output": "data/magicbrush/images/70491/70491-output2.png",
+ "instruction": "let there be a movie poster on the wall",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/70491/70491-output2.png",
+ "output": "data/magicbrush/images/70491/70491-output3.png",
+ "instruction": "let there be a credit card on the table",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/296012/296012-input.png",
+ "output": "data/magicbrush/images/296012/296012-output1.png",
+ "instruction": "transform the car into a red sports car",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/221187/221187-input.png",
+ "output": "data/magicbrush/images/221187/221187-output1.png",
+ "instruction": "Change the banana to a microphone.",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/160864/160864-input.png",
+ "output": "data/magicbrush/images/160864/160864-output1.png",
+ "instruction": "make the baseball players hold swords",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/160864/160864-output1.png",
+ "output": "data/magicbrush/images/160864/160864-output2.png",
+ "instruction": "make the catcher laugh",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/160864/160864-output2.png",
+ "output": "data/magicbrush/images/160864/160864-output3.png",
+ "instruction": "let the catcher wear a clown costume",
+ "task": "magicbrush"
+ },
+ {
+ "input": "data/magicbrush/images/51746/51746-input.png",
+ "output": "data/magicbrush/images/51746/51746-output1.png",
+ "instruction": "change the white couch to a brown couch",
+ "task": "magicbrush"
+ },
+ {
+ "instruction": "Make her close the door",
+ "input": "data/ag/images/ZY2B1.mp4_27_left.png",
+ "output": "data/ag/images/ZY2B1.mp4_27_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her pick up the glass",
+ "input": "data/ag/images/W4MEA.mp4_0_left.png",
+ "output": "data/ag/images/W4MEA.mp4_0_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her close her jacket fully",
+ "input": "data/ag/images/6ALEL.mp4_3_left.png",
+ "output": "data/ag/images/6ALEL.mp4_3_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him stand up",
+ "input": "data/ag/images/V2MHO.mp4_18_left.png",
+ "output": "data/ag/images/V2MHO.mp4_18_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her turn to the left",
+ "input": "data/ag/images/F5UVQ.mp4_6_left.png",
+ "output": "data/ag/images/F5UVQ.mp4_6_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her stand up",
+ "input": "data/ag/images/5RET1.mp4_0_left.png",
+ "output": "data/ag/images/5RET1.mp4_0_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him lift up the plastic bag",
+ "input": "data/ag/images/8D4ZT.mp4_245_left.png",
+ "output": "data/ag/images/8D4ZT.mp4_245_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the person stand up fully upright",
+ "input": "data/ag/images/W1SRN.mp4_0_left.png",
+ "output": "data/ag/images/W1SRN.mp4_0_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Move his hands towards his face",
+ "input": "data/ag/images/4KOBZ.mp4_12_left.png",
+ "output": "data/ag/images/4KOBZ.mp4_12_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Drop the bags onto the floor",
+ "input": "data/ag/images/I75CL.mp4_4_left.png",
+ "output": "data/ag/images/I75CL.mp4_4_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him stand up",
+ "input": "data/ag/images/R2KI4.mp4_15_left.png",
+ "output": "data/ag/images/R2KI4.mp4_15_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Open the door",
+ "input": "data/ag/images/HIJBX.mp4_16_left.png",
+ "output": "data/ag/images/HIJBX.mp4_16_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the woman lean forward towards the stick",
+ "input": "data/ag/images/QIBAJ.mp4_37_left.png",
+ "output": "data/ag/images/QIBAJ.mp4_37_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her face fully visible looking at the camera",
+ "input": "data/ag/images/LU82W.mp4_4_left.png",
+ "output": "data/ag/images/LU82W.mp4_4_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Show his hands on the plate to arrange the food",
+ "input": "data/ag/images/35ZZP.mp4_138_left.png",
+ "output": "data/ag/images/35ZZP.mp4_138_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Move both hands towards the cup",
+ "input": "data/ag/images/N4SA2.mp4_27_left.png",
+ "output": "data/ag/images/N4SA2.mp4_27_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her stand up",
+ "input": "data/ag/images/WJEVU.mp4_2_left.png",
+ "output": "data/ag/images/WJEVU.mp4_2_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him fully close the drawer",
+ "input": "data/ag/images/JJ47B.mp4_3_left.png",
+ "output": "data/ag/images/JJ47B.mp4_3_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Move the cloth up towards his face",
+ "input": "data/ag/images/7614L.mp4_45_left.png",
+ "output": "data/ag/images/7614L.mp4_45_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the person lean back further in their chair",
+ "input": "data/ag/images/JJZ1X.mp4_4_left.png",
+ "output": "data/ag/images/JJZ1X.mp4_4_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him lower both arms",
+ "input": "data/ag/images/9VZOY.mp4_39_left.png",
+ "output": "data/ag/images/9VZOY.mp4_39_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him face towards the left",
+ "input": "data/ag/images/1FX8Q.mp4_20_left.png",
+ "output": "data/ag/images/1FX8Q.mp4_20_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him close the door half way",
+ "input": "data/ag/images/6JLD4.mp4_12_left.png",
+ "output": "data/ag/images/6JLD4.mp4_12_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her put the laptop down",
+ "input": "data/ag/images/XVI3M.mp4_9_left.png",
+ "output": "data/ag/images/XVI3M.mp4_9_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her walk away from the table",
+ "input": "data/ag/images/S2S7I.mp4_14_left.png",
+ "output": "data/ag/images/S2S7I.mp4_14_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him turn facing towards the camera",
+ "input": "data/ag/images/VF3Y0.mp4_18_left.png",
+ "output": "data/ag/images/VF3Y0.mp4_18_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him type on the laptop",
+ "input": "data/ag/images/X28IF.mp4_14_left.png",
+ "output": "data/ag/images/X28IF.mp4_14_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the person step forward and close the door",
+ "input": "data/ag/images/3Q3YY.mp4_14_left.png",
+ "output": "data/ag/images/3Q3YY.mp4_14_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him turn forward while keeping the orange cup on the surface",
+ "input": "data/ag/images/AUYOZ.mp4_44_left.png",
+ "output": "data/ag/images/AUYOZ.mp4_44_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him put the plate down on the table",
+ "input": "data/ag/images/THW67.mp4_89_left.png",
+ "output": "data/ag/images/THW67.mp4_89_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him walk further towards the right",
+ "input": "data/ag/images/1VMZM.mp4_1_left.png",
+ "output": "data/ag/images/1VMZM.mp4_1_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the person walk down the stairs",
+ "input": "data/ag/images/14XKK.mp4_184_left.png",
+ "output": "data/ag/images/14XKK.mp4_184_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her grab the book from the shelf",
+ "input": "data/ag/images/RH44U.mp4_92_left.png",
+ "output": "data/ag/images/RH44U.mp4_92_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the man take a bite from the snack in his hand",
+ "input": "data/ag/images/J7TT5.mp4_9_left.png",
+ "output": "data/ag/images/J7TT5.mp4_9_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Move her hands with the bread down towards the table",
+ "input": "data/ag/images/KNN3G.mp4_97_left.png",
+ "output": "data/ag/images/KNN3G.mp4_97_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make him put down the red shovel",
+ "input": "data/ag/images/7614L.mp4_56_left.png",
+ "output": "data/ag/images/7614L.mp4_56_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Close the laundry machine door",
+ "input": "data/ag/images/RRDAM.mp4_9_left.png",
+ "output": "data/ag/images/RRDAM.mp4_9_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the man partially stand up",
+ "input": "data/ag/images/ZVMAY.mp4_40_left.png",
+ "output": "data/ag/images/ZVMAY.mp4_40_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the man turn around",
+ "input": "data/ag/images/FVPMC.mp4_113_left.png",
+ "output": "data/ag/images/FVPMC.mp4_113_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the man put down the book on the sofa",
+ "input": "data/ag/images/2KGV3.mp4_126_left.png",
+ "output": "data/ag/images/2KGV3.mp4_126_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the person lift their left leg up",
+ "input": "data/ag/images/WXC7V.mp4_13_left.png",
+ "output": "data/ag/images/WXC7V.mp4_13_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make the person spread their arms wide to both sides",
+ "input": "data/ag/images/9PAQ4.mp4_8_left.png",
+ "output": "data/ag/images/9PAQ4.mp4_8_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make them look at the shelf behind them",
+ "input": "data/ag/images/BWZL2.mp4_26_left.png",
+ "output": "data/ag/images/BWZL2.mp4_26_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Open the door fully",
+ "input": "data/ag/images/YK49T.mp4_41_left.png",
+ "output": "data/ag/images/YK49T.mp4_41_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Open the door",
+ "input": "data/ag/images/KWQKH.mp4_8_left.png",
+ "output": "data/ag/images/KWQKH.mp4_8_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make them stand up",
+ "input": "data/ag/images/YIK5I.mp4_92_left.png",
+ "output": "data/ag/images/YIK5I.mp4_92_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Put down the black piece of clothing onto the floor",
+ "input": "data/ag/images/VIN5T.mp4_5_left.png",
+ "output": "data/ag/images/VIN5T.mp4_5_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make her sit down fully cross-legged reading the book",
+ "input": "data/ag/images/O1LOW.mp4_41_left.png",
+ "output": "data/ag/images/O1LOW.mp4_41_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make them close the curtains",
+ "input": "data/ag/images/MFGLZ.mp4_30_left.png",
+ "output": "data/ag/images/MFGLZ.mp4_30_right.png",
+ "task": "ag"
+ },
+ {
+ "instruction": "Make them stand up fully upright looking at their hands",
+ "input": "data/ag/images/MZ3I3.mp4_67_left.png",
+ "output": "data/ag/images/MZ3I3.mp4_67_right.png",
+ "task": "ag"
+ },
+ {
+ "id": "36",
+ "instruction": "Make remote fall down",
+ "input": "data/something/images/36/first.jpg",
+ "output": "data/something/images/36/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "106",
+ "instruction": "Open waste basket",
+ "input": "data/something/images/106/first.jpg",
+ "output": "data/something/images/106/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "206",
+ "instruction": "Unfold cloth",
+ "input": "data/something/images/206/first.jpg",
+ "output": "data/something/images/206/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "220",
+ "instruction": "Drop a peg next to the wallet",
+ "input": "data/something/images/220/first.jpg",
+ "output": "data/something/images/220/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "219962",
+ "instruction": "Move hand away from container",
+ "input": "data/something/images/219962/first.jpg",
+ "output": "data/something/images/219962/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "219925",
+ "instruction": "Move medicine bottle closer to the edge",
+ "input": "data/something/images/219925/first.jpg",
+ "output": "data/something/images/219925/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "219866",
+ "instruction": "Add an orange",
+ "input": "data/something/images/219866/first.jpg",
+ "output": "data/something/images/219866/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "219411",
+ "instruction": "Lift the surface up on the left side",
+ "input": "data/something/images/219411/first.jpg",
+ "output": "data/something/images/219411/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "219259",
+ "instruction": "Make the shampoo bottle fall down and land horizontally",
+ "input": "data/something/images/219259/first.jpg",
+ "output": "data/something/images/219259/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "218705",
+ "instruction": "Flip the bottle upside down",
+ "input": "data/something/images/218705/first.jpg",
+ "output": "data/something/images/218705/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "218699",
+ "instruction": "Put keys into bowl",
+ "input": "data/something/images/218699/first.jpg",
+ "output": "data/something/images/218699/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "218363",
+ "instruction": "Add lid onto jar",
+ "input": "data/something/images/218363/first.jpg",
+ "output": "data/something/images/218363/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "218016",
+ "instruction": "Lift phone up",
+ "input": "data/something/images/218016/first.jpg",
+ "output": "data/something/images/218016/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "217555",
+ "instruction": "Flip the bottle upside down",
+ "input": "data/something/images/217555/first.jpg",
+ "output": "data/something/images/217555/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "217432",
+ "instruction": "Put wallet next to remote",
+ "input": "data/something/images/217432/first.jpg",
+ "output": "data/something/images/217432/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "217421",
+ "instruction": "Tear paper apart",
+ "input": "data/something/images/217421/first.jpg",
+ "output": "data/something/images/217421/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "217177",
+ "instruction": "Tear the paper into two pieces",
+ "input": "data/something/images/217177/first.jpg",
+ "output": "data/something/images/217177/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "217129",
+ "instruction": "Twist the cloth",
+ "input": "data/something/images/217129/first.jpg",
+ "output": "data/something/images/217129/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "217077",
+ "instruction": "Move the cutting board in front of the clock",
+ "input": "data/something/images/217077/first.jpg",
+ "output": "data/something/images/217077/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "217013",
+ "instruction": "Drop the glass on top of the pills",
+ "input": "data/something/images/217013/first.jpg",
+ "output": "data/something/images/217013/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "216998",
+ "instruction": "Put the book down on the table and remove the hand",
+ "input": "data/something/images/216998/first.jpg",
+ "output": "data/something/images/216998/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "216970",
+ "instruction": "Put a comb into the box",
+ "input": "data/something/images/216970/first.jpg",
+ "output": "data/something/images/216970/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "216852",
+ "instruction": "Tear the paper apart into two pieces",
+ "input": "data/something/images/216852/first.jpg",
+ "output": "data/something/images/216852/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "216236",
+ "instruction": "Stuffing the paper into the cup",
+ "input": "data/something/images/216236/first.jpg",
+ "output": "data/something/images/216236/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "216153",
+ "instruction": "Push the chair closer to the desk",
+ "input": "data/something/images/216153/first.jpg",
+ "output": "data/something/images/216153/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "216106",
+ "instruction": "Move the candles close to each other",
+ "input": "data/something/images/216106/first.jpg",
+ "output": "data/something/images/216106/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "216074",
+ "instruction": "moving nail clipper and sponge closer to each other",
+ "input": "data/something/images/216074/first.jpg",
+ "output": "data/something/images/216074/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "216042",
+ "instruction": "Flip the bottle upside down",
+ "input": "data/something/images/216042/first.jpg",
+ "output": "data/something/images/216042/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "215962",
+ "instruction": "Tear the paper into two pieces",
+ "input": "data/something/images/215962/first.jpg",
+ "output": "data/something/images/215962/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "215692",
+ "instruction": "Tipping sign over",
+ "input": "data/something/images/215692/first.jpg",
+ "output": "data/something/images/215692/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "215668",
+ "instruction": "Moving cup away from pen",
+ "input": "data/something/images/215668/first.jpg",
+ "output": "data/something/images/215668/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "215405",
+ "instruction": "Dropping the battery next to the mug",
+ "input": "data/something/images/215405/first.jpg",
+ "output": "data/something/images/215405/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "215371",
+ "instruction": "Tear the paper apart into two pieces",
+ "input": "data/something/images/215371/first.jpg",
+ "output": "data/something/images/215371/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "215270",
+ "instruction": "Flip the cup upside down",
+ "input": "data/something/images/215270/first.jpg",
+ "output": "data/something/images/215270/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "215221",
+ "instruction": "Take one match box away",
+ "input": "data/something/images/215221/first.jpg",
+ "output": "data/something/images/215221/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "214831",
+ "instruction": "Putting the bottle upright",
+ "input": "data/something/images/214831/first.jpg",
+ "output": "data/something/images/214831/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "214816",
+ "instruction": "Making the marker fall down to lie horizontally",
+ "input": "data/something/images/214816/first.jpg",
+ "output": "data/something/images/214816/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "214773",
+ "instruction": "Tear paper apart",
+ "input": "data/something/images/214773/first.jpg",
+ "output": "data/something/images/214773/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "214723",
+ "instruction": "Remove the black marker",
+ "input": "data/something/images/214723/first.jpg",
+ "output": "data/something/images/214723/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "214198",
+ "instruction": "Putting egg into the bowl",
+ "input": "data/something/images/214198/first.jpg",
+ "output": "data/something/images/214198/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "214157",
+ "instruction": "Adding another coaster of the same type",
+ "input": "data/something/images/214157/first.jpg",
+ "output": "data/something/images/214157/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "214021",
+ "instruction": "Lifting up the purse with a hand",
+ "input": "data/something/images/214021/first.jpg",
+ "output": "data/something/images/214021/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "213978",
+ "instruction": "Plugging USB into the port fully",
+ "input": "data/something/images/213978/first.jpg",
+ "output": "data/something/images/213978/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "213751",
+ "instruction": "Opening the book with the hands",
+ "input": "data/something/images/213751/first.jpg",
+ "output": "data/something/images/213751/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "213743",
+ "instruction": "Putting a bottle and card on the table",
+ "input": "data/something/images/213743/first.jpg",
+ "output": "data/something/images/213743/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "213518",
+ "instruction": "Lift her hands up to show a piece of paper",
+ "input": "data/something/images/213518/first.jpg",
+ "output": "data/something/images/213518/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "213403",
+ "instruction": "Wiping further towards the left with the cloth",
+ "input": "data/something/images/213403/first.jpg",
+ "output": "data/something/images/213403/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "213316",
+ "instruction": "Remove the lid of the left bottle with the hand",
+ "input": "data/something/images/213316/first.jpg",
+ "output": "data/something/images/213316/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "213259",
+ "instruction": "Rip paper apart into two pieces",
+ "input": "data/something/images/213259/first.jpg",
+ "output": "data/something/images/213259/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "213068",
+ "instruction": "Add a hand that pushes the hat further to the right",
+ "input": "data/something/images/213068/first.jpg",
+ "output": "data/something/images/213068/last.jpg",
+ "task": "something"
+ },
+ {
+ "id": "005422",
+ "instruction": "the tiny yellow cylinder turns brown",
+ "input": "data/clevr/images/CLEVR_default_005422.png",
+ "task": "clevr"
+ },
+ {
+ "id": "000031",
+ "instruction": "change the large green matte ball behind the large shiny cylinder to red",
+ "input": "data/clevr/images/CLEVR_default_000031.png",
+ "task": "clevr"
+ },
+ {
+ "id": "033588",
+ "instruction": "move the large purple metal ball to the left of the yellow cube",
+ "input": "data/clevr/images/CLEVR_default_033588.png",
+ "task": "clevr"
+ },
+ {
+ "id": "035238",
+ "instruction": "move the green ball to the right of the brown cylinder",
+ "input": "data/clevr/images/CLEVR_default_035238.png",
+ "task": "clevr"
+ },
+ {
+ "id": "003468",
+ "instruction": "the large red rubber ball that is to the right of the green matte object becomes gray",
+ "input": "data/clevr/images/CLEVR_default_003468.png",
+ "task": "clevr"
+ },
+ {
+ "id": "000831",
+ "instruction": "the cyan shiny cylinder turns purple",
+ "input": "data/clevr/images/CLEVR_default_000831.png",
+ "task": "clevr"
+ },
+ {
+ "id": "007896",
+ "instruction": "the tiny blue thing changes to red",
+ "input": "data/clevr/images/CLEVR_default_007896.png",
+ "task": "clevr"
+ },
+ {
+ "id": "027232",
+ "instruction": "remove the small green block",
+ "input": "data/clevr/images/CLEVR_default_027232.png",
+ "task": "clevr"
+ },
+ {
+ "id": "001220",
+ "instruction": "turn the small gray metallic cylinder behind the purple metallic thing brown",
+ "input": "data/clevr/images/CLEVR_default_001220.png",
+ "task": "clevr"
+ },
+ {
+ "id": "004473",
+ "instruction": "the red cylinder becomes green",
+ "input": "data/clevr/images/CLEVR_default_004473.png",
+ "task": "clevr"
+ },
+ {
+ "id": "012381",
+ "instruction": "make the surface of red cylinder matte",
+ "input": "data/clevr/images/CLEVR_default_012381.png",
+ "task": "clevr"
+ },
+ {
+ "id": "031028",
+ "instruction": "remove the large brown cube left of the large blue matte cylinder",
+ "input": "data/clevr/images/CLEVR_default_031028.png",
+ "task": "clevr"
+ },
+ {
+ "id": "014155",
+ "instruction": "make the gray rubber object shiny",
+ "input": "data/clevr/images/CLEVR_default_014155.png",
+ "task": "clevr"
+ },
+ {
+ "id": "001827",
+ "instruction": "the cylinder becomes gray",
+ "input": "data/clevr/images/CLEVR_default_001827.png",
+ "task": "clevr"
+ },
+ {
+ "id": "005025",
+ "instruction": "Turn the blue cube gray",
+ "input": "data/clevr/images/CLEVR_default_005025.png",
+ "task": "clevr"
+ },
+ {
+ "id": "004838",
+ "instruction": "the tiny yellow object turns purple",
+ "input": "data/clevr/images/CLEVR_default_004838.png",
+ "task": "clevr"
+ },
+ {
+ "id": "019598",
+ "instruction": "add a red large sphere",
+ "input": "data/clevr/images/CLEVR_default_019598.png",
+ "task": "clevr"
+ },
+ {
+ "id": "037672",
+ "instruction": "move the green sphere in front of the red small sphere",
+ "input": "data/clevr/images/CLEVR_default_037672.png",
+ "task": "clevr"
+ },
+ {
+ "id": "029712",
+ "instruction": "remove the green shiny block",
+ "input": "data/clevr/images/CLEVR_default_029712.png",
+ "task": "clevr"
+ },
+ {
+ "id": "038145",
+ "instruction": "move the large blue sphere to the right of the red cube",
+ "input": "data/clevr/images/CLEVR_default_038145.png",
+ "task": "clevr"
+ },
+ {
+ "id": "015982",
+ "instruction": "the gray metal block becomes matte",
+ "input": "data/clevr/images/CLEVR_default_015982.png",
+ "task": "clevr"
+ },
+ {
+ "id": "038036",
+ "instruction": "move the brown sphere to the right of the purple block",
+ "input": "data/clevr/images/CLEVR_default_038036.png",
+ "task": "clevr"
+ },
+ {
+ "id": "025311",
+ "instruction": "the big yellow rubber cylinder behind the cyan rubber cylinder is now no longer there",
+ "input": "data/clevr/images/CLEVR_default_025311.png",
+ "task": "clevr"
+ },
+ {
+ "id": "008461",
+ "instruction": "the metallic block changes to a matte surface",
+ "input": "data/clevr/images/CLEVR_default_008461.png",
+ "task": "clevr"
+ },
+ {
+ "id": "022978",
+ "instruction": "add a small red cube",
+ "input": "data/clevr/images/CLEVR_default_022978.png",
+ "task": "clevr"
+ },
+ {
+ "id": "000711",
+ "instruction": "the large blue rubber cube on the left side of the gray matte cylinder is now cyan",
+ "input": "data/clevr/images/CLEVR_default_000711.png",
+ "task": "clevr"
+ },
+ {
+ "id": "005585",
+ "instruction": "make the tiny rubber ball a gray color",
+ "input": "data/clevr/images/CLEVR_default_005585.png",
+ "task": "clevr"
+ },
+ {
+ "id": "030422",
+ "instruction": "remove the tiny blue metallic cylinder",
+ "input": "data/clevr/images/CLEVR_default_030422.png",
+ "task": "clevr"
+ },
+ {
+ "id": "010651",
+ "instruction": "make all purple objects disappear",
+ "input": "data/clevr/images/CLEVR_default_010651.png",
+ "task": "clevr"
+ },
+ {
+ "id": "011377",
+ "instruction": "make the red cube larger",
+ "input": "data/clevr/images/CLEVR_default_011377.png",
+ "task": "clevr"
+ },
+ {
+ "id": "007141",
+ "instruction": "make the big green rubber cylinder turn purple",
+ "input": "data/clevr/images/CLEVR_default_007141.png",
+ "task": "clevr"
+ },
+ {
+ "id": "006137",
+ "instruction": "the yellow object changes color to green",
+ "input": "data/clevr/images/CLEVR_default_006137.png",
+ "task": "clevr"
+ },
+ {
+ "id": "031913",
+ "instruction": "remove the tiny blue matte ball",
+ "input": "data/clevr/images/CLEVR_default_031913.png",
+ "task": "clevr"
+ },
+ {
+ "id": "008307",
+ "instruction": "make the purple sphere smaller",
+ "input": "data/clevr/images/CLEVR_default_008307.png",
+ "task": "clevr"
+ },
+ {
+ "id": "007889",
+ "instruction": "the large gray metal cylinder to the right of the cyan thing turns brown",
+ "input": "data/clevr/images/CLEVR_default_007889.png",
+ "task": "clevr"
+ },
+ {
+ "id": "020926",
+ "instruction": "add a small gray rubber ball on the right side",
+ "input": "data/clevr/images/CLEVR_default_020926.png",
+ "task": "clevr"
+ },
+ {
+ "id": "019092",
+ "instruction": "remove all red objects",
+ "input": "data/clevr/images/CLEVR_default_019092.png",
+ "task": "clevr"
+ },
+ {
+ "id": "012697",
+ "instruction": "the yellow matte rubber block now gets metallic surface",
+ "input": "data/clevr/images/CLEVR_default_012697.png",
+ "task": "clevr"
+ },
+ {
+ "id": "029795",
+ "instruction": "remove the the big gray shiny ball",
+ "input": "data/clevr/images/CLEVR_default_029795.png",
+ "task": "clevr"
+ },
+ {
+ "id": "000125",
+ "instruction": "the big metal sphere becomes gray",
+ "input": "data/clevr/images/CLEVR_default_000125.png",
+ "task": "clevr"
+ },
+ {
+ "id": "032084",
+ "instruction": "move the purple cube in front of the red ball",
+ "input": "data/clevr/images/CLEVR_default_032084.png",
+ "task": "clevr"
+ },
+ {
+ "id": "006040",
+ "instruction": "the small gray rubber cylinder becomes brown",
+ "input": "data/clevr/images/CLEVR_default_006040.png",
+ "task": "clevr"
+ },
+ {
+ "id": "018004",
+ "instruction": "remove all red objects",
+ "input": "data/clevr/images/CLEVR_default_018004.png",
+ "task": "clevr"
+ },
+ {
+ "id": "013680",
+ "instruction": "the cyan object turns shiny",
+ "input": "data/clevr/images/CLEVR_default_013680.png",
+ "task": "clevr"
+ },
+ {
+ "id": "007014",
+ "instruction": "the yellow object changes to purple",
+ "input": "data/clevr/images/CLEVR_default_007014.png",
+ "task": "clevr"
+ },
+ {
+ "id": "032614",
+ "instruction": "move the red cylinder to the right of the gray block",
+ "input": "data/clevr/images/CLEVR_default_032614.png",
+ "task": "clevr"
+ },
+ {
+ "id": "027258",
+ "instruction": "remove the brown matte sphere",
+ "input": "data/clevr/images/CLEVR_default_027258.png",
+ "task": "clevr"
+ },
+ {
+ "id": "021346",
+ "instruction": "add a tiny yellow metal ball on the left side of the yellow cylinder",
+ "input": "data/clevr/images/CLEVR_default_021346.png",
+ "task": "clevr"
+ },
+ {
+ "id": "027358",
+ "instruction": "remove the small gray metallic cylinder",
+ "input": "data/clevr/images/CLEVR_default_027358.png",
+ "task": "clevr"
+ },
+ {
+ "id": "025070",
+ "instruction": "remove the tiny blue shiny object",
+ "input": "data/clevr/images/CLEVR_default_025070.png",
+ "task": "clevr"
+ },
+ {
+ "input": "data/whatsup/images/dragonfruit_on_table.jpeg",
+ "output": "data/whatsup/images/dragonfruit_under_table.jpeg",
+ "caption": "A dragonfruit under a table",
+ "instruction": "Move the dragonfruit under the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/cup_in-front_of_remote.jpeg",
+ "output": "data/whatsup/images/cup_left_of_remote.jpeg",
+ "caption": "A cup to the left of a remote",
+ "instruction": "Move the cup to the left of the remote",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_on_chair.jpeg",
+ "output": "data/whatsup/images/book_left_of_chair.jpeg",
+ "caption": "A book to the left of a chair",
+ "instruction": "Move the book to the left of the chair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/helmet_on_table.jpeg",
+ "output": "data/whatsup/images/helmet_under_table.jpeg",
+ "caption": "A helmet under a table",
+ "instruction": "Move the helmet under the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/pot_on_chair.jpeg",
+ "output": "data/whatsup/images/pot_right_of_chair.jpeg",
+ "caption": "A pot to the right of a chair",
+ "instruction": "Move the pot to the right of the chair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/sunglasses_on_chair.jpeg",
+ "output": "data/whatsup/images/sunglasses_under_chair.jpeg",
+ "caption": "A sunglasses under a chair",
+ "instruction": "Move the sunglasses under the chair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/bowl_behind_headphones.jpeg",
+ "output": "data/whatsup/images/bowl_right_of_headphones.jpeg",
+ "caption": "A bowl to the right of a headphones",
+ "instruction": "Move the bowl to the right of the headphones",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/remote_in-front_of_headphones.jpeg",
+ "output": "data/whatsup/images/remote_right_of_headphones.jpeg",
+ "caption": "A remote to the right of a headphones",
+ "instruction": "Move the remote to the right of the headphones",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/remote_in-front_of_tape.jpeg",
+ "output": "data/whatsup/images/remote_left_of_tape.jpeg",
+ "caption": "A remote to the left of a tape",
+ "instruction": "Move the remote to the left of the tape",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/bowl_left_of_armchair.jpeg",
+ "output": "data/whatsup/images/bowl_on_armchair.jpeg",
+ "caption": "A bowl on a armchair",
+ "instruction": "Move the bowl on the armchair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_left_of_flower.jpeg",
+ "output": "data/whatsup/images/book_behind_flower.jpeg",
+ "caption": "A book behind a flower",
+ "instruction": "Move the book behind the flower",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_left_of_table.jpeg",
+ "output": "data/whatsup/images/book_under_table.jpeg",
+ "caption": "A book under a table",
+ "instruction": "Move the book under the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_in-front_of_knife.jpeg",
+ "output": "data/whatsup/images/book_behind_knife.jpeg",
+ "caption": "A book behind a knife",
+ "instruction": "Move the book behind the knife",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/kettle_on_chair.jpeg",
+ "output": "data/whatsup/images/kettle_right_of_chair.jpeg",
+ "caption": "A kettle to the right of a chair",
+ "instruction": "Move the kettle to the right of the chair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/plate_right_of_candle.jpeg",
+ "output": "data/whatsup/images/plate_left_of_candle.jpeg",
+ "caption": "A plate to the left of a candle",
+ "instruction": "Move the plate to the left of the candle",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/yarn_under_armchair.jpeg",
+ "output": "data/whatsup/images/yarn_right_of_armchair.jpeg",
+ "caption": "A yarn to the right of a armchair",
+ "instruction": "Move the yarn to the right of the armchair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/remote_right_of_candle.jpeg",
+ "output": "data/whatsup/images/remote_left_of_candle.jpeg",
+ "caption": "A remote to the left of a candle",
+ "instruction": "Move the remote to the left of the candle",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/mug_left_of_headphones.jpeg",
+ "output": "data/whatsup/images/mug_right_of_headphones.jpeg",
+ "caption": "A mug to the right of a headphones",
+ "instruction": "Move the mug to the right of the headphones",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/cap_in-front_of_candle.jpeg",
+ "output": "data/whatsup/images/cap_right_of_candle.jpeg",
+ "caption": "A cap to the right of a candle",
+ "instruction": "Move the cap to the right of the candle",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_behind_headphones.jpeg",
+ "output": "data/whatsup/images/book_left_of_headphones.jpeg",
+ "caption": "A book to the left of a headphones",
+ "instruction": "Move the book to the left of the headphones",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/can_behind_knife.jpeg",
+ "output": "data/whatsup/images/can_right_of_knife.jpeg",
+ "caption": "A can to the right of a knife",
+ "instruction": "Move the can to the right of the knife",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/mug_behind_plate.jpeg",
+ "output": "data/whatsup/images/mug_right_of_plate.jpeg",
+ "caption": "A mug to the right of a plate",
+ "instruction": "Move the mug to the right of the plate",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/lemon_on_table.jpeg",
+ "output": "data/whatsup/images/lemon_right_of_table.jpeg",
+ "caption": "A lemon to the right of a table",
+ "instruction": "Move the lemon to the right of the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/mug_in-front_of_bowl.jpeg",
+ "output": "data/whatsup/images/mug_left_of_bowl.jpeg",
+ "caption": "A mug to the left of a bowl",
+ "instruction": "Move the mug to the left of the bowl",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_left_of_cap.jpeg",
+ "output": "data/whatsup/images/book_right_of_cap.jpeg",
+ "caption": "A book to the right of a cap",
+ "instruction": "Move the book to the right of the cap",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/bowl_right_of_spoon.jpeg",
+ "output": "data/whatsup/images/bowl_behind_spoon.jpeg",
+ "caption": "A bowl behind a spoon",
+ "instruction": "Move the bowl behind the spoon",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/can_in-front_of_tape.jpeg",
+ "output": "data/whatsup/images/can_left_of_tape.jpeg",
+ "caption": "A can to the left of a tape",
+ "instruction": "Move the can to the left of the tape",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/mug_in-front_of_knife.jpeg",
+ "output": "data/whatsup/images/mug_right_of_knife.jpeg",
+ "caption": "A mug to the right of a knife",
+ "instruction": "Move the mug to the right of the knife",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/pillow_right_of_armchair.jpeg",
+ "output": "data/whatsup/images/pillow_under_armchair.jpeg",
+ "caption": "A pillow under a armchair",
+ "instruction": "Move the pillow under the armchair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/laptop_under_chair.jpeg",
+ "output": "data/whatsup/images/laptop_on_chair.jpeg",
+ "caption": "A laptop on a chair",
+ "instruction": "Move the laptop on the chair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/bowl_left_of_table.jpeg",
+ "output": "data/whatsup/images/bowl_under_table.jpeg",
+ "caption": "A bowl under a table",
+ "instruction": "Move the bowl under the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/plate_in-front_of_phone.jpeg",
+ "output": "data/whatsup/images/plate_left_of_phone.jpeg",
+ "caption": "A plate to the left of a phone",
+ "instruction": "Move the plate to the left of the phone",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_right_of_cup.jpeg",
+ "output": "data/whatsup/images/book_left_of_cup.jpeg",
+ "caption": "A book to the left of a cup",
+ "instruction": "Move the book to the left of the cup",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/oven-mitt_right_of_chair.jpeg",
+ "output": "data/whatsup/images/oven-mitt_under_chair.jpeg",
+ "caption": "A oven mitt under a chair",
+ "instruction": "Move the oven mitt under the chair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_behind_headphones.jpeg",
+ "output": "data/whatsup/images/book_right_of_headphones.jpeg",
+ "caption": "A book to the right of a headphones",
+ "instruction": "Move the book to the right of the headphones",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/can_right_of_knife.jpeg",
+ "output": "data/whatsup/images/can_left_of_knife.jpeg",
+ "caption": "A can to the left of a knife",
+ "instruction": "Move the can to the left of the knife",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/bowl_left_of_spoon.jpeg",
+ "output": "data/whatsup/images/bowl_behind_spoon.jpeg",
+ "caption": "A bowl behind a spoon",
+ "instruction": "Move the bowl behind the spoon",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/lamp_under_table.jpeg",
+ "output": "data/whatsup/images/lamp_right_of_table.jpeg",
+ "caption": "A lamp to the right of a table",
+ "instruction": "Move the lamp to the right of the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/bowl_behind_remote.jpeg",
+ "output": "data/whatsup/images/bowl_left_of_remote.jpeg",
+ "caption": "A bowl to the left of a remote",
+ "instruction": "Move the bowl to the left of the remote",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/dog_on_table.jpeg",
+ "output": "data/whatsup/images/dog_right_of_table.jpeg",
+ "caption": "A dog to the right of a table",
+ "instruction": "Move the dog to the right of the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/mug_on_table.jpeg",
+ "output": "data/whatsup/images/mug_right_of_table.jpeg",
+ "caption": "A mug to the right of a table",
+ "instruction": "Move the mug to the right of the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/plate_left_of_bowl.jpeg",
+ "output": "data/whatsup/images/plate_behind_bowl.jpeg",
+ "caption": "A plate behind a bowl",
+ "instruction": "Move the plate behind the bowl",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/painting_right_of_chair.jpeg",
+ "output": "data/whatsup/images/painting_under_chair.jpeg",
+ "caption": "A painting under a chair",
+ "instruction": "Move the painting under the chair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/scarf_under_armchair.jpeg",
+ "output": "data/whatsup/images/scarf_left_of_armchair.jpeg",
+ "caption": "A scarf to the left of a armchair",
+ "instruction": "Move the scarf to the left of the armchair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/dog_on_table.jpeg",
+ "output": "data/whatsup/images/dog_under_table.jpeg",
+ "caption": "A dog under a table",
+ "instruction": "Move the dog under the table",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/book_right_of_tape.jpeg",
+ "output": "data/whatsup/images/book_behind_tape.jpeg",
+ "caption": "A book behind a tape",
+ "instruction": "Move the book behind the tape",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/bowl_in-front_of_flower.jpeg",
+ "output": "data/whatsup/images/bowl_left_of_flower.jpeg",
+ "caption": "A bowl to the left of a flower",
+ "instruction": "Move the bowl to the left of the flower",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/remote_in-front_of_scissors.jpeg",
+ "output": "data/whatsup/images/remote_right_of_scissors.jpeg",
+ "caption": "A remote to the right of a scissors",
+ "instruction": "Move the remote to the right of the scissors",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/pot_left_of_chair.jpeg",
+ "output": "data/whatsup/images/pot_on_chair.jpeg",
+ "caption": "A pot on a chair",
+ "instruction": "Move the pot on the chair",
+ "task": "whatsup"
+ },
+ {
+ "input": "data/whatsup/images/can_in-front_of_spoon.jpeg",
+ "output": "data/whatsup/images/can_right_of_spoon.jpeg",
+ "caption": "A can to the right of a spoon",
+ "instruction": "Move the can to the right of the spoon",
+ "task": "whatsup"
+ },
+ {
+ "instruction": "Make the photo seem like it was taken at a picnic at a park.",
+ "input": "data/emu/images/2660.png",
+ "type": "global",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make it into Conceptual Art.",
+ "input": "data/emu/images/2398.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background to a busy Street filled with cars.",
+ "input": "data/emu/images/1070.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make it into contemporary art style. ",
+ "input": "data/emu/images/2412.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background into a basketball court.",
+ "input": "data/emu/images/982.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change this image into a 1980s Dungeons & Dragons cartoon background art.",
+ "input": "data/emu/images/1901.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the image into pencil drawing.",
+ "input": "data/emu/images/1606.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "turn this photo into a picasso painting",
+ "input": "data/emu/images/3588.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Fill the bathroom with water",
+ "input": "data/emu/images/2111.png",
+ "type": "global",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the image into a cubist style art work.",
+ "input": "data/emu/images/1599.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background in oil painting.",
+ "input": "data/emu/images/980.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background so it is in a cafe.",
+ "input": "data/emu/images/996.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "give this image a salvador dali impression",
+ "input": "data/emu/images/3485.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make this image look like the Simpsons Cartoon.",
+ "input": "data/emu/images/2793.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make the photo seem like it was taken during summer.",
+ "input": "data/emu/images/2687.png",
+ "type": "global",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make it look like Andy Warhol painted it. ",
+ "input": "data/emu/images/2418.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make the image look like a cartoon",
+ "input": "data/emu/images/2603.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background to yellowstone national park",
+ "input": "data/emu/images/1262.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the image to a Matisse.",
+ "input": "data/emu/images/1642.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make it anime.",
+ "input": "data/emu/images/2389.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Recreate this image in the style of a doodle drawing.",
+ "input": "data/emu/images/2905.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make it look like Gustav Klimt painted the image.",
+ "input": "data/emu/images/2422.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the style to a 1940\u2019s era.",
+ "input": "data/emu/images/1812.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Depict this as if it were a comic book picture.",
+ "input": "data/emu/images/2103.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "I want this done as a pop art piece.",
+ "input": "data/emu/images/2273.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background to Snoopy dog wallpaper.",
+ "input": "data/emu/images/1034.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change this image into a watercolor art.",
+ "input": "data/emu/images/1915.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Turn the image into a drawing made from chalk.",
+ "input": "data/emu/images/3404.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make the background a severe lightning storm. . ",
+ "input": "data/emu/images/2524.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background to a buffet restaurant.",
+ "input": "data/emu/images/1069.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make it look like a renaissance painting. ",
+ "input": "data/emu/images/2442.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background to a Vincent Van Gogh painting.",
+ "input": "data/emu/images/1051.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change this into a child's finger painting.",
+ "input": "data/emu/images/1935.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background to a field of wildflowers.",
+ "input": "data/emu/images/1112.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make the background a huge petting zoo. ",
+ "input": "data/emu/images/2509.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make this look like a comic book photo",
+ "input": "data/emu/images/2808.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Recreate this in the painting style of Thomas Kincaid.",
+ "input": "data/emu/images/2907.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the field into a platform in outer space.",
+ "input": "data/emu/images/1525.png",
+ "type": "global",
+ "task": "emu"
+ },
+ {
+ "instruction": "I want this as a watercolor.",
+ "input": "data/emu/images/2272.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the image to be taking at night.",
+ "input": "data/emu/images/1658.png",
+ "type": "global",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the image to a drawing by Kehinde Wiley",
+ "input": "data/emu/images/1652.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the style to Cubism.",
+ "input": "data/emu/images/1807.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Turn it into Art Deco. ",
+ "input": "data/emu/images/3383.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make this image look inspired by a Piet Mondrian painting.",
+ "input": "data/emu/images/2788.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make it look like it was drawn with crayons. ",
+ "input": "data/emu/images/2453.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Give this image a look inspired by Michelangelo's \"David\".",
+ "input": "data/emu/images/2241.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background into a terrarium full of ants and other bugs.",
+ "input": "data/emu/images/990.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Change the background to a swamp.",
+ "input": "data/emu/images/1191.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Make the background a pet store",
+ "input": "data/emu/images/2516.png",
+ "type": "background",
+ "task": "emu"
+ },
+ {
+ "instruction": "Remake this image in the style of a cave wall pictograph.",
+ "input": "data/emu/images/2915.png",
+ "type": "style",
+ "task": "emu"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000008494.jpg",
+ "instruction": "Move the hand slightly up so that the sponge also cleans the wooden board",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000014164.jpg",
+ "instruction": "Turn on the water tab with the left hand",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000005172.jpg",
+ "instruction": "Open the left drawer as well",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000000838.jpg",
+ "instruction": "Open the orange bag further with both hands",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000014791.jpg",
+ "instruction": "Turn the carrot strips horizontally 90 degrees",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000000422.jpg",
+ "instruction": "Pick up the egg with the right hand",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000010225.jpg",
+ "instruction": "Pour the contents from the blue bowl into the pot",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000005658.jpg",
+ "instruction": "Grab the egg with the right hand",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000000946.jpg",
+ "instruction": "Move the orange bag with rice closer to the oven and start pouring it into the pot",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000004055.jpg",
+ "instruction": "Move their left hand away from holding the pot",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000009459.jpg",
+ "instruction": "Drop the sponge to their feet",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P34_rgb_frames_frame_0000016120.jpg",
+ "instruction": "Use the sponge in the right hand to clean the plate",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000012640.jpg",
+ "instruction": "Grab the wooden laddle with the left hand",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000001878.jpg",
+ "instruction": "Grab the soap bottle on the right with the hand",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000002194.jpg",
+ "instruction": "Take the white cup out of the cupboard",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000000796.jpg",
+ "instruction": "Move the hand towards the oven knob",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000000422.jpg",
+ "instruction": "Push the chair away from the table",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000004769.jpg",
+ "instruction": "Grab the yellow cup with the hand and move it towards the pot",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000002133.jpg",
+ "instruction": "Open the drawer a little more",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000017118.jpg",
+ "instruction": "Lift the frying pan up",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000007533.jpg",
+ "instruction": "Move hand with the spoon further to the right to drop the coffee powder down",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P35_rgb_frames_frame_0000002910.jpg",
+ "instruction": "Pour more milk so that it overflows",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P36_rgb_frames_frame_0000000838.jpg",
+ "instruction": "Put the potato down on the white cutting board",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P36_rgb_frames_frame_0000002682.jpg",
+ "instruction": "Let the paper towel fall down",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P36_rgb_frames_frame_0000002194.jpg",
+ "instruction": "Let the hand pull out some meaty contents out of the container",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P36_rgb_frames_frame_0000010391.jpg",
+ "instruction": "Use the hand to move all the potato pieces towards the pan",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P36_rgb_frames_frame_0000000796.jpg",
+ "instruction": "The hand lifts the plastic container up",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P36_rgb_frames_frame_0000001428.jpg",
+ "instruction": "Move the peeler onto the potato to attempt another peel",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P36_rgb_frames_frame_0000007162.jpg",
+ "instruction": "Move the knife over to start chopping the left bigger piece of potato too",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P36_rgb_frames_frame_0000003467.jpg",
+ "instruction": "Put the bowl down on the left side",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000005172.jpg",
+ "instruction": "Move the right hand to one of the oven knobs",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000002703.jpg",
+ "instruction": "Put both hands around the plate",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000000796.jpg",
+ "instruction": "Open the sandwich maker and place the sandwich inside",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000001428.jpg",
+ "instruction": "Close the sandwich maker with the left hand",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000002133.jpg",
+ "instruction": "Move the hand towards the handle of the drawer",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000022806.jpg",
+ "instruction": "Rub both hands against each other under the water tab",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000016070.jpg",
+ "instruction": "Move the left hand with the metal thing under the running water",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000003473.jpg",
+ "instruction": "The fork pulls one piece of fish out of the can",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000031297.jpg",
+ "instruction": "Put the pan down next to the plate",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P32_rgb_frames_frame_0000026186.jpg",
+ "instruction": "Pull one noodle out of the pot with the fork",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000002682.jpg",
+ "instruction": "Move all the dishes into sink right under the water tab",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000002133.jpg",
+ "instruction": "Move the laddle to the left side inside the pot",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000017273.jpg",
+ "instruction": "Move the wooden laddle towards the pan",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000062516.jpg",
+ "instruction": "The hand lets go off the white can and it drops into the pan",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000011532.jpg",
+ "instruction": "Grab the soap bottle on the bottom left with the hand",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000006710.jpg",
+ "instruction": "Drop the transparent large bowl onto the floor",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000008298.jpg",
+ "instruction": "Grab the gray cloth with the hand",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000007205.jpg",
+ "instruction": "Pour all the orange content from the bag into the big bowl",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000014488.jpg",
+ "instruction": "Poke the food in the pan with the fork",
+ "task": "epic"
+ },
+ {
+ "input": "data/epic/images/EPIC-KITCHENS_P33_rgb_frames_frame_0000006220.jpg",
+ "instruction": "Move the spoon with rice up towards the bowl",
+ "task": "epic"
+ },
+ {
+ "input": "data/kubric/images/further_location/2720/image0.jpg",
+ "output": "data/kubric/images/further_location/2720/image1.jpg",
+ "instruction": "move the green-purple pencil case further left",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/closer/6566/image0.jpg",
+ "output": "data/kubric/images/closer/6566/image1.jpg",
+ "instruction": "Move the Nintendo gaming console and the turquoise bowl closer to each other.",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/further_location/12310/image1.jpg",
+ "output": "data/kubric/images/further_location/12310/image0.jpg",
+ "instruction": "put the white-yellow mug further right",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/10350/image1.jpg",
+ "output": "data/kubric/images/counting/10350/image0.jpg",
+ "instruction": "remove 4 green hat with feather from the image",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/20895/image0.jpg",
+ "output": "data/kubric/images/rotate/20895/image1.jpg",
+ "instruction": "push the green turtle toy down",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/19565/image0.jpg",
+ "output": "data/kubric/images/rotate/19565/image1.jpg",
+ "instruction": "turn the colorful xylophone around",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/22201/image0.jpg",
+ "output": "data/kubric/images/rotate/22201/image1.jpg",
+ "instruction": "Turn the round bowl upside down",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/further_location/11674/image0.jpg",
+ "output": "data/kubric/images/further_location/11674/image1.jpg",
+ "instruction": "shift the black flip-flop sandal further right",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/attribute/4010/image0.jpg",
+ "output": "data/kubric/images/attribute/4010/image1.jpg",
+ "instruction": "make the light-gray tape smaller",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/further_location/7123/image0.jpg",
+ "output": "data/kubric/images/further_location/7123/image1.jpg",
+ "instruction": "put the white-black shoes further right",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/closer/7006/image0.jpg",
+ "output": "data/kubric/images/closer/7006/image1.jpg",
+ "instruction": "Move the white soccer cleats and the white-pink shoes closer to each other.",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/13161/image0.jpg",
+ "output": "data/kubric/images/rotate/13161/image1.jpg",
+ "instruction": "turn the unicorn 90 degrees",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/attribute/6444/image1.jpg",
+ "output": "data/kubric/images/attribute/6444/image0.jpg",
+ "instruction": "make the brown straw hat small",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/11627/image0.jpg",
+ "output": "data/kubric/images/location/11627/image1.jpg",
+ "instruction": "place the black hat on the right hand of the yellow nesquik chocolate powder canister",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/9480/image1.jpg",
+ "output": "data/kubric/images/location/9480/image0.jpg",
+ "instruction": "place the yellow ballet shoe behind the red scissors",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/945/image0.jpg",
+ "output": "data/kubric/images/location/945/image1.jpg",
+ "instruction": "place the CARSII on the right of the green-purple pencil case",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/7357/image1.jpg",
+ "output": "data/kubric/images/counting/7357/image0.jpg",
+ "instruction": "remove 4 yellow medicine bottle from the scene",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/5002/image0.jpg",
+ "output": "data/kubric/images/location/5002/image1.jpg",
+ "instruction": "put the yellow nesquik chocolate powder canister on the right hand of the red towel",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/6027/image0.jpg",
+ "output": "data/kubric/images/counting/6027/image1.jpg",
+ "instruction": "add 1 white porcelain ramekin to the platform",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/3794/image0.jpg",
+ "output": "data/kubric/images/counting/3794/image1.jpg",
+ "instruction": "add 1 toy sheep to the platform",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/1752/image1.jpg",
+ "output": "data/kubric/images/location/1752/image0.jpg",
+ "instruction": "shift the position of the vintage metal alarm clock above the toy squirrel",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/18611/image0.jpg",
+ "output": "data/kubric/images/rotate/18611/image1.jpg",
+ "instruction": "the white drug bottle is flipped upside down",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/attribute/8159/image1.jpg",
+ "output": "data/kubric/images/attribute/8159/image0.jpg",
+ "instruction": "transform the black DVD into a white DVD",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/1353/image0.jpg",
+ "output": "data/kubric/images/rotate/1353/image1.jpg",
+ "instruction": "let the teenage mutant ninja turtle figure drop",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/808/image0.jpg",
+ "output": "data/kubric/images/rotate/808/image1.jpg",
+ "instruction": "flip the black-white bowl upside down",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/attribute/6882/image1.jpg",
+ "output": "data/kubric/images/attribute/6882/image0.jpg",
+ "instruction": "turn the green-purple pencil case into a colorful pencil case",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/11848/image0.jpg",
+ "output": "data/kubric/images/counting/11848/image1.jpg",
+ "instruction": "add 1 red towel to the image",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/closer/4815/image0.jpg",
+ "output": "data/kubric/images/closer/4815/image1.jpg",
+ "instruction": "Swap positions of both items.",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/159/image0.jpg",
+ "output": "data/kubric/images/location/159/image1.jpg",
+ "instruction": "put the white-red plate behind the white-blue basket",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/closer/5767/image1.jpg",
+ "output": "data/kubric/images/closer/5767/image0.jpg",
+ "instruction": "Swap the positions of the two objects.",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/8969/image0.jpg",
+ "output": "data/kubric/images/counting/8969/image1.jpg",
+ "instruction": "add 1 white keyboard to the platform",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/4707/image0.jpg",
+ "output": "data/kubric/images/counting/4707/image1.jpg",
+ "instruction": "add 2 white square saucer to the scene",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/further_location/8412/image0.jpg",
+ "output": "data/kubric/images/further_location/8412/image1.jpg",
+ "instruction": "move the black and yellow hammer further right",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/further_location/1443/image0.jpg",
+ "output": "data/kubric/images/further_location/1443/image1.jpg",
+ "instruction": "shift the red flower pot further right",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/4004/image0.jpg",
+ "output": "data/kubric/images/location/4004/image1.jpg",
+ "instruction": "shift the position of the toy dicynodont dinosaur on the right hand of the red toy airplane",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/12306/image1.jpg",
+ "output": "data/kubric/images/location/12306/image0.jpg",
+ "instruction": "put the unicorn behind the CARSII",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/further_location/7442/image1.jpg",
+ "output": "data/kubric/images/further_location/7442/image0.jpg",
+ "instruction": "shift the teenage mutant ninja turtle figure further left",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/5556/image1.jpg",
+ "output": "data/kubric/images/location/5556/image0.jpg",
+ "instruction": "put the white porcelain ramekin on the right hand of the brown shoe",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/10529/image0.jpg",
+ "output": "data/kubric/images/counting/10529/image1.jpg",
+ "instruction": "add 1 brown leather boot to the image",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/attribute/2093/image1.jpg",
+ "output": "data/kubric/images/attribute/2093/image0.jpg",
+ "instruction": "convert the white keyboard into a black keyboard",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/location/6867/image1.jpg",
+ "output": "data/kubric/images/location/6867/image0.jpg",
+ "instruction": "shift the position of the yellow soccer cleats above the white bowl",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/closer/9735/image0.jpg",
+ "output": "data/kubric/images/closer/9735/image1.jpg",
+ "instruction": "Swap the positions of the teenage mutant ninja turtle figure and the white DVD.",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/attribute/11535/image0.jpg",
+ "output": "data/kubric/images/attribute/11535/image1.jpg",
+ "instruction": "turn the blue-white shoes big",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/9808/image1.jpg",
+ "output": "data/kubric/images/counting/9808/image0.jpg",
+ "instruction": "remove 2 shark from the image",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/15466/image0.jpg",
+ "output": "data/kubric/images/rotate/15466/image1.jpg",
+ "instruction": "flip the yellow-orange shoes upside down",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/attribute/3737/image1.jpg",
+ "output": "data/kubric/images/attribute/3737/image0.jpg",
+ "instruction": "turn the blue shoe into a white running shoe",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/rotate/12794/image0.jpg",
+ "output": "data/kubric/images/rotate/12794/image1.jpg",
+ "instruction": "turn the green-purple pencil case 90 degrees",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/counting/2015/image1.jpg",
+ "output": "data/kubric/images/counting/2015/image0.jpg",
+ "instruction": "remove 1 green-orange magnifying glass from the scene",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/attribute/9885/image0.jpg",
+ "output": "data/kubric/images/attribute/9885/image1.jpg",
+ "instruction": "convert the golden-black high heel into a red high heel",
+ "task": "kubric"
+ },
+ {
+ "input": "data/kubric/images/further_location/6435/image0.jpg",
+ "output": "data/kubric/images/further_location/6435/image1.jpg",
+ "instruction": "move the red scissors further right",
+ "task": "kubric"
+ }
+]
\ No newline at end of file