You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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!
The text was updated successfully, but these errors were encountered:
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!
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!
The text was updated successfully, but these errors were encountered: