why not subtract the mean of the image.?

xinntao / ESRGAN

ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

https://github.com/xinntao/BasicSR

Apache License 2.0

5.95k stars 1.06k forks source link

why not subtract the mean of the image.? #37

Open Rainyfish opened 5 years ago

Rainyfish commented 5 years ago

@xinntao Hi, I didn't find the operation about subtracting the mean of the image. I am confused that if the image should be normalized or not. I think it may be useful and easy to train the network with the zero mean of the input images. Looking forward to your reply. best wishes.

xinntao commented 5 years ago

I have tried this before. Subtracting the mean does not improve much.

So I directly use the [0,1] range for simplicity.