Aaron Han

Hi,thanks for open source your code. I run the code on my server with 62G memory.After running for a while, the training was interrupted. I found a similar phenomenon in...

impressive work! could you please release BriVL w/ RoBERTa-large pre-trained on the 650M data? Thanks a lot!

about DISFA F1score

1

Hello! I followed the image example you provided for pre-processing and got the same image database. However after completing the training for stage2 using resnet50, the three folds average is...

Question about two stages training?

1

Hi,I wonder the second stage fintuning is based on finetuned first stage T5 model or initial T5 model?

Is the linear layer initialized by the linear layer of llava? I found that the pretrain_mm_mlp_adapter parameter is not set in the script. Does it mean that the linear layer...