Zero-Shot Image Classification
Transformers
PyTorch
English
clip
geolocalization
geolocation
geographic
street
climate
urban
rural
multi-modal
geoguessr
Instructions to use geolocal/StreetCLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use geolocal/StreetCLIP with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="geolocal/StreetCLIP") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("geolocal/StreetCLIP") model = AutoModelForZeroShotImageClassification.from_pretrained("geolocal/StreetCLIP") - Notebooks
- Google Colab
- Kaggle
Pre-defined "class names" list ?
#3
by shodanx2 - opened
Hi,
The documentation for this models specified the end user must supply the model with a series of names locations for the model to choose from, given example.
"San Jose", "San Diego", "Los Angeles", "Las Vegas", "San Francisco"
I would like to know, are city names the only valid class names and
Has anyone already made a better list that includes all cities on Earth ?
And lastly, what would be an efficient manner to have this output be globe coordinates, of a globe heat map of likely locations ?
thanks