-
Currently, we can not implement formula (3) easily in paper _[Improved Training of Wasserstein GANs](https://arxiv.org/abs/1704.00028)_, because we need the gradient of a gradient. Maybe this will be …
-
HI,
I run your code of CT_gan_cifar.py,I evaluate the Inception Score of CT-GAN with 1000 generated images, the best score is 5.65 within the running 10000 iterations. To compare CT-GAN with origin…
-
I found your code used by training the LSUN bedrooms128*128 in your paper, but cannot reproduce the results. The data link in your issue #30 is a "ILSVRC2012_128.tar" one but not the bedrooms images.…
biuyq updated
6 years ago
-
I wrote an wgan with gradient penalty on the cifar dataset.
https://github.com/robotcator/wgan-gp/tree/wgan-cifar10
it would be useful to integrate wgan-gp to this repo.
The reference:
[pytorch…
-
I see when calculating D_loss, you use the fake images generated by this [https://github.com/igul222/improved_wgan_training/blob/master/gan_cifar_resnet.py#L192](https://github.com/igul222/improved_wg…
-
Hey, I appreciate your work! You make my life better.
I found (maybe) a small bug in your WGAN_GP code. When calculating gradient penalty, you write:
```
D_inter,_,_=self.discriminator(interpol…
-
I would like to know what hardware you used and its approximate training time.
edwhu updated
6 years ago
-
https://github.com/wiseodd/generative-models/blob/566ac2e95971ab55d65169e565b9d53023ccc113/GAN/improved_wasserstein_gan/wgan_gp_tensorflow.py#L89
Hi,
Thanks for the code, but I found that the grad…
-
I want to implement the improved WGAN with mxnet. However, the gradient penalty is a great headache. It is a complex loss function, which contains the data gradient. For simple loss functions, we can …
-
I am trying using your improved wgan code to generate LSUN bedroom picture. However the quality of my generated pictures is not that good like yours and I think the reason may lie in the network archi…