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.

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

Same error, solution didn't work: RuntimeError expected input... to have 28 channels, but got 27 channels instead #24

Closed
dkoslicki opened this issue Mar 3, 2022 · 4 comments · May be fixed by #61
Closed

Same error, solution didn't work: RuntimeError expected input... to have 28 channels, but got 27 channels instead #24

dkoslicki opened this issue Mar 3, 2022 · 4 comments · May be fixed by #61

Comments

@dkoslicki
Copy link

I ran into the same error as #14 , and verified that self.nonblind_denoising was set to True here, but still receive the error:

line 585, in _conv_forward
    return F.conv3d(
RuntimeError: Given groups=1, weight of size [96, 28, 1, 3, 3], expected input[1, 27, 40, 128, 128] to have 28 channels, but got 27 channels instead

This is using the dataset VRT/testsets/REDS4/sharp_bicubic via the call python main_test_vrt.py --task 008_VRT_videodenoising_DAVIS --folder_lq testsets/REDS4/sharp_bicubic --tile 40 128 128 --tile_overlap 2 20 20. I ultimately want to run this on my own folder of PNGs from a video.
@JingyunLiang
Copy link
Owner

JingyunLiang commented Mar 3, 2022 •
edited

It's a bug. Try to add --sigma 1 for quick fix. It should output similar results as no added noise. We will fix it later.

Also note that we train it as a non-blind denoising model. You may need to try different sigmas (e.g., larger sigma if the video is heavily corrupted by Gaussian noise).

@dkoslicki
Copy link
Author

I see; but unfortunately --sigma 1 did not fix the issue: I got the exact same error message.

@JingyunLiang
Copy link
Owner

JingyunLiang commented Mar 3, 2022 •
edited

I see. It's because you didn't specify --folder_gt, so it uses another dataloader. We did not provide an interface for lq-only-input in denoising.

@JingyunLiang JingyunLiang mentioned this issue Mar 30, 2022
Open
@haikunzhang95
Copy link

It's a bug. Try to add --sigma 1 for quick fix. It should output similar results as no added noise. We will fix it later.

Also note that we train it as a non-blind denoising model. You may need to try different sigmas (e.g., larger sigma if the video is heavily corrupted by Gaussian noise).

Have you fixed the bug?

@Stelath Stelath mentioned this issue Jun 18, 2023
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Fixed Evaluation Denoising Sigma Error Stelath/VRT
3 participants
@dkoslicki @JingyunLiang @haikunzhang95