lazyslide.models.multimodal.CONCH#
- class CONCH(model_path=None, token=None)#
Bases:
ImageTextModelGitHub 🤗 Hugging Face Paper | Multimodal foundation model
- encode_image(image)#
This should return the image feature before normalize.
Bases: ImageTextModel
GitHub 🤗 Hugging Face Paper | Multimodal foundation model
This should return the image feature before normalize.