Extract Text and Image Latents

[mmsamiei]

Hi, in the current implementation we can only extract text and image embedding (by set return_encodings=True) which are obtained before applying latent linear layers. Isn't it better to add an option to extract latent embeddings? Another importance of this is that with the current code, it is impossible to extract the similarity matrix between a batch of images and a batch of text.

[lucidrains]

@mmsamiei Hi Mohammad! Try https://github.com/lucidrains/x-clip/commit/5eb5fcc10d574f7641e51444aa03f4e6ec8c42db#diff-3858fdc3d4b7a5fce034a5fe9f25bf300fe1431999316145c018015644e86f91R505

[mmsamiei]

Thanks a lot!