rr191211

How to handle multiple images with Blip2 models ?

1

How to handle multiple images with Blip2 models? I have a large number of questions which require more than one image to answer for VQA task, like 1 questions vs...

Pre-training code of UDOP

2

Thanks for your awesome work in UDOP, I was trying out Finetune on VQA. Do you plan to release the code to pre-train such a model? Thank you!

Dear authors, Thank you for such seminal work! I am wondering about the training time and the required hardware resource. If I could be wrong, I didn't find related statements...