about the results you provided

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

5.91k stars 1.05k forks source link

about the results you provided #46

Closed cyforsr closed 5 years ago

cyforsr commented 5 years ago

When I compute the psnr between the HR images and the SR images you provided in Google Drive. The psnr of your SR baboon image in Google drive is 18.57dB, but in your paper the value is 20.35dB. Can you provide the psnr.py? or tell me what happened about my code? and I use skimage.measure.compare_psnr( )

xinntao commented 5 years ago

We have tested on the Y channel. I think you may evaluate on RGB channels. It is described in Sec4.3 in the ESRGAN paper.

cyforsr commented 5 years ago

The psnr value is 20.35dB. You are right.