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

the iterations between two stage #78

Open Jimzhou82sub opened 4 years ago

Jimzhou82sub commented 4 years ago

Hi, In your paper,first, you train a PSNR-oriented model with the L1 loss, and then train the RAGAN, I want to knew, before you train the RAGAN,how much iterations do you train the PSNR-oriented model.