DCGAN-tensorflow icon indicating copy to clipboard operation
DCGAN-tensorflow copied to clipboard

Questions about g_loss

Open qiangqiangzhu opened this issue 5 years ago • 2 comments

The G loss is close to zero in the begging of the iteration. But the G loss is growing with the increase of iteration. After one epoch. Is it right?

I use their own data sets, similar mnist data sets

qiangqiangzhu avatar Apr 09 '19 02:04 qiangqiangzhu

I am having the same situation. I am also using my own dataset. Can anyone explain if this is normal or if this is incorrect?

matak07 avatar Jul 21 '19 00:07 matak07

Hi! I have the same issue with u, have you solved it?

PS: I using the MNIST data set

chqwer2 avatar Jan 18 '21 07:01 chqwer2