LAVIS - A One-stop Library for Language-Vision Intelligence
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
Fym68 opened this issue 7 months ago · comments
I want to use the instructblip model to evaluate okvqa and textvqa, but my output has no content, making me wonder if my operation is correct. Could someone provide evaluation script or implementation guideline for okVQA or textvqa?