search

lucidrains / CoCa-pytorch

Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch
MIT License
1.04k stars 88 forks source link

Do you plan to give the code for fine-tuning？ #7

Closed yang178908 closed 9 months ago

yang178908 commented 2 years ago

Hello, I want to reproduce the VQA task, so do you have any plans to give code about fine-tuning? Thank you!

yoon28 commented 1 year ago

+1, one more person also waiting the code :)

yuzexing commented 9 months ago

+1, one more person also waiting the code :)

rom1504 commented 9 months ago

what about using this https://github.com/mlfoundations/open_clip#fine-tuning-coca ? openclip implementation is based on this repo and has pretrained models + doc on how to fine tune

lucidrains commented 9 months ago

@yuzexing @rom1504 what Romain said