confused about the training input range

[zxcvads]

hi ,i have a question about the input dataset range ,i have see your paper released model input range is(0,256),if i change the input range to(-1,1) or (0,1)，i am confused about the PSNR change ,can you have a try in different training data range ?

[bigeagle]

It's not substantial. Some hyper parameters (such as learning rate) may need to be tuned according to data range.

[bigeagle]

No specific reason. Some legacy code use (0, 256). Using (0, 1) is OK and can reach the comparable PSNR.