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

Reproducing the Video Denoiser #25

Open
gauenk opened this issue Aug 18, 2023 · 7 comments
Open

Reproducing the Video Denoiser #25

gauenk opened this issue Aug 18, 2023 · 7 comments

Comments

@gauenk
Copy link

gauenk commented Aug 18, 2023

Hello RVRT Team 👋 Thank you again for your great code.

I have followed your paper's instructions to train my own RVRT model. However, my network's quality does not match the network you share online, nor the numbers you report.

Maybe I have missed something on my end, but I want to know if you have a training script so I can inspect all the details myself?

Thank you.

@gauenk
Copy link
Author

gauenk commented Aug 29, 2023

I am gently following up on the previous comment.

@Dawson0813
Copy link

Dawson0813 commented Aug 31, 2023

I caught the same problem with you, even though the iterator number more than 20000 times, the loss almost stay the same(8e-2). Thus the infference results of the new-trained model is still far from the pre-trained one.

@gauenk
Copy link
Author

gauenk commented Sep 6, 2023

As a researcher with limited GPUs, your comment means more to me than you know.

@Dawson0813
Copy link

Dawson0813 commented Sep 7, 2023

As a researcher with limited GPUs, your comment means more to me than you know.

Thank you for your kindly reply too. I wonder whether you have solved above issues. Last week I used a small trainning-sets to verify the RVRT network, but both the training loss and the test PSNR still stay the same.

@Dawson0813
Copy link

Dawson0813 commented Sep 7, 2023

The test results of author's pre-trained model is realy good, thanks again for their great work. I am sure that I have missed some key procedures in my training too, and I am also eagerly looking forward to get some more details from the RVRT team.

@gauenk
Copy link
Author

gauenk commented Sep 9, 2023

My issue is still unresolved.

@zjuzhk
Copy link

zjuzhk commented Dec 11, 2024

The test results of author's pre-trained model is realy good, thanks again for their great work. I am sure that I have missed some key procedures in my training too, and I am also eagerly looking forward to get some more details from the RVRT team.

Have you solved the problem? I am also facing the same issue where the training loss remains at nearly 8e-2 and does not converge.

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