Happsky

I also meet the same problem, @ahmedsalaheldin did you solve it?

@junyanz Cuda 8.0 and torch version is commit 0219027e6c4644a0ba5c5bf137c989a0a8c9e01b. @ahmedsalaheldin did you find any pretrained pytorch model for style tranfer?

@taesung89 what's you Lua version, 5.1 or 5.2?

@ahmedsalaheldin may you share the pytorch pre-trained models?

Thanks for your quick reply @phillipi and I have another question that when I training on pix2pix, the loss_D_fake, loss_D_real and loss_G_GAN are equal to 0, is this a normal...

@d0t1q I'm having this issue as well, were you able to resolve this?

I meet the same problem.

I think you should train 200 epochs instead of 200K iterations.

1 1841 86.55 20.67 18.13 16.67 16.57 16.30 15.53 30.11 1 1842 86.55 17.14 13.90 12.61 14.12 15.32 15.14 29.37 1 1843 86.56 20.29 15.57 13.95 14.83 15.16 15.28 35.23...

My version is 0.3.0.post4, should I update to 0.4?