Didn't see multiple functions

[rakesh-reddy95]

Hi @INVOKERer

I don't see the initialisation for this function. from basicsr.models.archs.discriminator import MultiscaleDiscriminator

[INVOKERer]

Sorry, it is unnecessary. I forgot to delete it.

[rakesh-reddy95]

But I see it's been used in multiple places in image_restoration2_model.py

[INVOKERer]

image_restoration2_model.py is just useful for Learning Degradation Representations for Image Deblurring (another paper).

[rakesh-reddy95]

Okay after fixing I see this grid over the output. And is random everytime I generate the output.

[rakesh-reddy95]

I have commented out state_dict_pth_classifier and loading 'ckpts/RevD-B/net_g_GoPro.pth'

[INVOKERer]

It may be the problem like https://github.com/megvii-research/NAFNet/issues/25 , could you test the model trained on RealBlur? The images from GoPro dataset are almost token by day.

[rakesh-reddy95]

This is indeed giving complete grid by running using RealBlur model.

[INVOKERer]

Alright, I will try to provide a version that cancel the TLSC in the encoder tomorrow.

[rakesh-reddy95]

Thank you.

[INVOKERer]

Hi, PatchAdaRevIDSlideV2 in basicsr.arch.AdaRevID_arch is the version cancel the TLSC, while I am not sure it can solve the problem.

[rakesh-reddy95]

I see that the issue is with the model. I have used RevD-L then the issue is not there.

[INVOKERer]

Thank you very much. I will check the model when I am free.

[Brandon-git-hub]

Hello, Thanks for your work! I have used PatchAdaRevIDSlideV2 with weights of RevD-S, and still some results are broken in Gopro dataset. This scene have much more broken images.

[INVOKERer]

Sorry. I see the results are not broken in my public results 百度网盘(提取码:27ex). Probably something went wrong while I was sorting through the code. I will check it next week.

[INVOKERer]

Hi @Brandon-git-hub @rakesh-reddy95 , I found that I accidentally deleted AdaRevIDSlideV2 for testing in basicsr.arch.AdaRevID_arch. I have re-uploaded it. The broken results on GoPro do not appear when I test with AdaRevIDSlideV2. Maybe it is the reason cause the grid over your image @rakesh-reddy95 .

[Brandon-git-hub]

@INVOKERer Thanks for your help! I think my issue might be related to the classifier. I noticed that even I didn't load the classifier weights into model, the classifier is still being used (each time I run, the number of decoders is different). How can I run RevD-L without the adaptive function?

[INVOKERer]

You can turn the hyper-param pretrain from false to true for RevD.

[Brandon-git-hub]

I run validation.py on the Gopro dataset and get a PSNR of 34.656160. This is better than the result reported in the paper. I'm not sure why, but it's a good result!

[luciferincc]

When I tested on AdaRevD-B, I also encountered the above problem. How should I solve it?And The results show that the number of num_decoders is 0.

[INVOKERer]

Hi @Brandon-git-hub @rakesh-reddy95 @luciferincc , the reason for this error was found to be that I set up the AdaRevD-L network by default in yml, and the model in val.py is the pth of AdaRevD-B. This issue has been fixed.

[luciferincc]

Hi @Brandon-git-hub @rakesh-reddy95 @luciferincc , the reason for this error was found to be that I set up the AdaRevD-L network by default in yml, and the model in val.py is the pth of AdaRevD-B. This issue has been fixed.

Thanks, I have downloaded the new yml file and it works.