SimonYang

Results 3 comments of SimonYang

Nope Acturally in the end of training, the loss of discriminator was almost converged to 0.5, and it looked like normal. All facts show that the camera pose and generator...

Sorry to bother you again, I found that I cannot train this model successfully unless using the `hotdog` data. Do I need to change these params blow, when I use...

I found that the dim of pixels is wrong. So I changed: `pixels.cuda()` But nothing changed, still this bug exists.