Instructions to use keras/deit_base_distilled_patch16_224_imagenet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/deit_base_distilled_patch16_224_imagenet with KerasHub:
import keras_hub import keras # Load ImageClassifier model image_classifier = keras_hub.models.ImageClassifier.from_preset( "hf://keras/deit_base_distilled_patch16_224_imagenet", num_classes=2, ) # Fine-tune image_classifier.fit( x=keras.random.randint((32, 64, 64, 3), 0, 256), y=keras.random.randint((32, 1), 0, 2), ) # Classify image image_classifier.predict(keras.random.randint((1, 64, 64, 3), 0, 256))import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/deit_base_distilled_patch16_224_imagenet") - Keras
How to use keras/deit_base_distilled_patch16_224_imagenet with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://keras/deit_base_distilled_patch16_224_imagenet") - Notebooks
- Google Colab
- Kaggle
Download metadata.json from keras/deit_base_distilled_patch16_224_imagenet: direct link, hf CLI and curl.
- Browser
- Download file 194 Bytes
-
https://huggingface.co/keras/deit_base_distilled_patch16_224_imagenet/resolve/main/metadata.json
- Command line
-
hf download hf://keras/deit_base_distilled_patch16_224_imagenet/metadata.json
-
curl -L -o metadata.json https://huggingface.co/keras/deit_base_distilled_patch16_224_imagenet/resolve/main/metadata.json
194 Bytes
| { | |
| "keras_version": "3.8.0", | |
| "keras_hub_version": "0.22.0.dev0", | |
| "parameter_count": 85800192, | |
| "date_saved": "2025-07-28@20:36:17", | |
| "tasks": [ | |
| "ImageClassifier" | |
| ] | |
| } |