Taxabind
Collection
Collection of models in the TaxaBind Framework
•
6 items
•
Updated
TaxaBind is a multimodal embedding space consisting of six modalities. This model contains image and text modalities in open_clip
format. The model is used for zero-shot classification of species images using taxonomic text classes.
import open_clip
model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:MVRL/taxabind-vit-b-16')
tokenizer = open_clip.get_tokenizer('hf-hub:MVRL/taxabind-vit-b-16')