-
Why the value of G_loss is increasing？
thank U.
-
Have you tried WGAN with GAN-CLS? I am trying to use use Wasserstein distance, in GAN CLS and I modified the cost and clipped the weights, but it GAN doesn't learn anything. If I don't clip the weight…
-
Add alpha-WGAN from https://arxiv.org/abs/1908.02498
-
Have you tried WGAN-GP loss? I am having trouble while fading in a new layer using WGAN-GP loss, it causes the loss to go grazy and results in mode collapse.
-
i rewrite caogang/wgangp code to generate 512*512 images , i add 2-3 conv2d layers in Dnet and Gnet, but when i run that code ,the loss explode to 30000000, and after i train the model 50k epochs with…
-
Hi,
when I train the code, I set up the opt.gan_type = "wgan-gp"
but there goes error, the full text is:
------------ Options -------------
batchSize: 1
beta1: 0.5
checkpoints_dir: ./checkpoint…
-
Hello, I have some questions to ask you.I want to use GaN to generate data from other data sets. How to use my own data set?
I encountered many problems in the process of revision. I am a beginner.
-
I have a GPU with a 32GB memory ram. I can not train the WGAN even with the batchsize=1. OOM error will occur. I was wondering which module needs the most memory and is there any modification for mak…
-
Hello!
When I use formula for loss of WGAN I get negative value for such loss, how did you you avoid this?
Thanks!
-
[Wasserstein GANs](https://arxiv.org/abs/1701.07875) are supposed to fix some of the challenges of GANs.
- No more vanishing gradients!
- No more mode collapse!
- Loss function is more meaningful.
…