aitorzip / PyTorch-SRGAN

A modern PyTorch implementation of SRGAN
https://arxiv.org/abs/1609.04802
GNU General Public License v3.0
361 stars 92 forks source link

The question about the loss #13

Open EricKani opened 6 years ago

EricKani commented 6 years ago

Hi, I just changed you code to fit my own dataset. But I got some problem about my training loss...

[4/100][2112/2112] Discriminator_Loss: 0.9368 Generator_Loss (Content/Advers/Total): 0.0021/1.2429/0.0033 [5/100][2112/2112] Discriminator_Loss: 0.8507 Generator_Loss (Content/Advers/Total): 0.0022/1.4514/0.0036 [6/100][2112/2112] Discriminator_Loss: 0.8301 Generator_Loss (Content/Advers/Total): 0.0022/1.5216/0.0037

We can see that the Discriminator_Loss is decreasing, but the Generator_Loss got increased...I am confused by this problem and I am a new user about gannet. I hope I can get some help from you. Thank you very much!!