Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error when evaluating on GQA dataset #6

Open
qncsn2016 opened this issue Apr 16, 2024 · 1 comment
Open

Error when evaluating on GQA dataset #6

qncsn2016 opened this issue Apr 16, 2024 · 1 comment

Comments

@qncsn2016
Copy link

Hello,

I was attempting to evaluate the model on the GQA dataset by following the instructions provided in the Getting Started guide. However, I encountered an error when running the evaluation script. The error message was:
model_vqa_loader.py: error: unrecognized arguments: --seg-image-folder ./playground/data/eval/gqa/data/seg_images --use_seg

Upon inspecting the model_vqa_loader.py, I noticed that it does not include the parameters --seg-image-folder and --use_seg. I found these parameters in the model_seg_loader.py, but this file does not support the question-file and answer-file parameters required for GQA evaluation.

Could you please advise on how to correctly set up the evaluation for the GQA dataset using the necessary segmentation images and files?

Thank you!

@praeclarumjj3
Copy link
Member

praeclarumjj3 commented Apr 17, 2024

Hi @qncsn2016, thanks for your interest in our work. You do not need to pass the segmentation maps for the GQA dataset. I have pushed a fix for the evaluation script here. Thanks for pointing this out!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants