Zero-Shot Image Classification
OpenCLIP
English
clip
biology
CV
images
animals
species
taxonomy
rare species
endangered species
evolutionary biology
multimodal
knowledge-guided
Instructions to use imageomics/bioclip-vit-b-16-inat-only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use imageomics/bioclip-vit-b-16-inat-only with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:imageomics/bioclip-vit-b-16-inat-only') tokenizer = open_clip.get_tokenizer('hf-hub:imageomics/bioclip-vit-b-16-inat-only') - Notebooks
- Google Colab
- Kaggle
Update README.md
#1
by balajiRRK - opened
add model_description
Let's actually just use the short description (slightly modified):
BioCLIP is a foundation model for the tree of life, built using CLIP architecture as a vision model for general organismal biology. This model is trained on iNat21 following the same procedure, however, iNat21 is a subset of the TreeOfLife-10M dataset on which BioCLIP was trained. More information can be found in the BioCLIP repository.
Updated the model_description to fit the short description that you provided.
egrace479 changed pull request status to merged