Yiting Qu comments

Repositories
Issues
Comments

Results 2 comments of


                                            Yiting Qu

YFCC subset taking very long to process

Same problem here

Issues while trying to reproduce the results on LLaVA-v1.5

The reason of None adv_noise.grad is that, LLaVA-1.5 by default uses @ torch.no_grad() when using the CLIP vision encoder, commenting off this line (llava/models/multimodal_encoder/clip_encoder/line39) should work.