Open jorie-peng opened 1 year ago
Hi @jorie-peng,
Do you have any update on this? Have you been able to reproduce the results for VizWiz?
Hi @jorie-peng and @lavoiems . Have you guys figured out how to reproduce the results for VizWiz yet? Thanks!
Hi @jorie-peng and @lavoiems . Have you guys figured out how to reproduce the results for VizWiz yet? Thanks!
haven't, maybe @LiJunnan1992 knows.
hello, I also want to test the instructblip model with coco dataset ,but I don't know how to do ? I have the A100 GPU with centos, could you tell me how to config the according file?
Thanks for your released model, But when I used instructBLIP vicuna7B model to eval VizWiz, the acc result is 26%, while the result in paper is 34.5%, is there any special setting? such as for "unanswerable" answer.
With same experiment setting, I can get right result in okvqa、gqa, except VizWiz.
Here is my setting:
eval setting