zealscott / sgdl Goto Github PK

Should we get the opposite conclusion? i.e., MP_t >= MP_{t+1}

I am new to denoise. Thank you very much!

When the code runs to Phase II, an error occurs as follows.
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [100, 1]], which is output 0 of TBackward, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
Thank you very much!

Do you implement the code of SGCN yourself, Could you please offer the code about SGCN?

https://github.com/ZJU-DAILY/SGDL/blob/main/code/main.py

I am new to denoise. Thank you very much!

This question is based on https://github.com/ZJU-DAILY/SGDL/issues/3.
Thank you very much!