Are `class transformers.CLIPModel` encoders lossy?

#18

by sinanabavi - opened Jun 11

Jun 11

I would like to decode an embedding to an image or text:
Can I do this for CLIP text and image features?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment