Closed YAOYI626 closed 1 year ago
@YAOYI626 Thanks for your interest.
Hey @logicwong thanks for your reply!
Just curious, is there any specific reason doing captioning without VQ, Like big gap between captioning with VQ and captioning with embeddings from ResNet?
Thanks Xiaoyi
@YAOYI626 There are two main reasons:
Thanks @logicwong for the helpful information. I'd like to close this issue.
Hi team,
Thanks for the really amazing work OFA! I want to know more about the VQ model used in OFA.
Does it share the same VQ model when doing different tasks like captioning or generation? How is the VQ model trained? @logicwong @JustinLin610
Thanks, Xiaoyi