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.

Sign up for GitHub

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

Jump to bottom

Incorrect normalization of W and H in inference for non-square input images #12

Open

TakuyaNarihira opened this issue Oct 22, 2024 · 0 comments

Assignees

Labels

bug

TakuyaNarihira commented Oct 22, 2024 •

edited

Loading

I found a bug in the GenWarp code when I tried inference on a non-square input image.

https://github.com/sony/genwarp/blob/main/genwarp/GenWarp.py#L396

        coords = torch.stack((grid[..., 0]/H, grid[..., 1]/W), dim=-1)

The normalization of H and W is flipped, and should be corrected. I’ll probably make a PR sometime soon.

kaz-sony added the bug label

kaz-sony self-assigned this

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment