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

How do I reproduce the results of the rvos report? #73

Open
xinbaiw opened this issue Mar 24, 2024 · 10 comments
Open

How do I reproduce the results of the rvos report? #73

xinbaiw opened this issue Mar 24, 2024 · 10 comments

Comments

@xinbaiw
Copy link

xinbaiw commented Mar 24, 2024

The inference is that the model being called is DEVA-propagation.pth? I used this model to infer the J&F on the rvos task, which is 64.8. The one reported in the paper is 66.0. Can you help me find out where I went wrong?

image

@xinbaiw
Copy link
Author

xinbaiw commented Mar 24, 2024

The inference is that the model being called is DEVA-propagation.pth? I used this model to infer the J&F on the rvos task, which is 64.8. The one reported in the paper is 66.0. Can you help me find out where I went wrong?

image

image

@hkchengrex
Copy link
Owner

Can you compare your output with our pre-computed one and see if there is any discrepancy? It should reproduce exactly. There is too little information here for me to look into it.

@xinbaiw
Copy link
Author

xinbaiw commented Mar 25, 2024

Can you compare your output with our pre-computed one and see if there is any discrepancy? It should reproduce exactly. There is too little information here for me to look into it.

Can you find anything wrong with these details?

parser.add_argument('--mask_path', default='/home/data2/Ref-YouTubeVOS-ReferFormer-SwinL-detections')
parser.add_argument('--model', default='./saves/DEVA-propagation.pth')
parser.add_argument('--img_path', default='/home/data2/rvos/valid/JPEGImages')

image
image

@xinbaiw
Copy link
Author

xinbaiw commented Mar 26, 2024

Hi, can you help me?

@hkchengrex
Copy link
Owner

I cannot peek into your file system and know what is in each folder. One potential reason is that you are not using all the frames in YouTubeVOS (i.e., https://drive.google.com/drive/folders/16uw2j3o8Pi2xhvgGopYMKyjKtzV9RQ6c)

@xinbaiw
Copy link
Author

xinbaiw commented Mar 27, 2024

I cannot peek into your file system and know what is in each folder. One potential reason is that you are not using all the frames in YouTubeVOS (i.e., https://drive.google.com/drive/folders/16uw2j3o8Pi2xhvgGopYMKyjKtzV9RQ6c)

Thank you for your reply. When I used all frames of youtube-vos to test, out of memory, single card 4090 (24g), do you have a solution?

@xinbaiw
Copy link
Author

xinbaiw commented Mar 27, 2024

How to reduce memory usage when testing?

@hkchengrex
Copy link
Owner

@longmalongma
Copy link

See here https://github.com/hkchengrex/Tracking-Anything-with-DEVA/blob/main/docs/EVALUATION.md#general-arguments

Use --amp

After using amp, the memory is still not enough. Is there any other way?

@longmalongma
Copy link

See here https://github.com/hkchengrex/Tracking-Anything-with-DEVA/blob/main/docs/EVALUATION.md#general-arguments
Use --amp

After using amp, the memory is still not enough. Is there any other way?

Why does the test go out or memory at a later stage?

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

3 participants