AdvSemiSeg icon indicating copy to clipboard operation
AdvSemiSeg copied to clipboard

loss_semi < = 0.002

Open islzf opened this issue 4 years ago • 4 comments

islzf avatar Jun 01 '20 05:06 islzf

hi ,what is the problem with my code?what should i do?

islzf avatar Jun 01 '20 05:06 islzf

I have the same problem,why?

tsrobcvai avatar Mar 28 '21 03:03 tsrobcvai

the same problems, Did you find a solution?

xiewende avatar Mar 16 '22 01:03 xiewende

I believe that Discriminator causses this problem. Model D is simple so each iter they learn too well . So after running a little time, loss will be 0. U should change training with epoch and about 5 epoch should training D !

Holmes2002 avatar Dec 22 '22 03:12 Holmes2002