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

why test psnr is nan #6

Open
lfliu opened this issue Sep 23, 2021 · 5 comments
Open

why test psnr is nan #6

lfliu opened this issue Sep 23, 2021 · 5 comments

Comments

@lfliu
Copy link

lfliu commented Sep 23, 2021

image

@Sumching
Copy link
Collaborator

Please provide more information, such as which dataset for testing and which version of MegEngine. In my case, this test script worked well and the result was 39.765.

@lfliu
Copy link
Author

lfliu commented Sep 23, 2021

thanks for your answer.my MegEngine is 1.5 and the test data is the val set of sidd.

@Sumching
Copy link
Collaborator

After installing MegEngine=1.5, your results still cannot be reproduced. Please check whether the image pair to be calculated is correct, and check whether nan appears in each image pair or only a few pairs.

@lfliu
Copy link
Author

lfliu commented Sep 24, 2021

At first,I meet the error in this script dataset.py ,"no module named nori2",so I just delete this row of the original code because nori2 cannot be installed by pip. May be this reason?

@Sumching
Copy link
Collaborator

Sumching commented Sep 24, 2021

Thanks for pointing out this error, I have deleted these external packages. But I don't think this is the reason why the output is nan and please clone this project again and test again. I provide my numerical packages for reference:
MegEnginee == 1.5.0
numpy. == 1.19.5
opencv-python == 4.5.3.56
scikit-image == 0.17.2
scipy == 1.5.4
six == 1.16.0

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