-
at 113 line in WGAN_GP, I recommend changing the code
`alpha = tf.random_uniform(shape=self.inputs.get_shape(), minval=0.,maxval=1.)`
to
`alpha = tf.random_uniform(shape=[BATCH_SIZE,1,1,1], minva…
-
Hello everyone,
I am trying to train a WGAN-GP model on O1 and O2 opt levels, but on the gradient penalty phase, I get gradient overflow error till the division with zero exception with both O1 and O…
-
It looks that WGAN with gp improves the GAN training process a lot. Is it easy to rewrite this project with WGAN and gp?
thanks!
-
In WGAN,the task of discriminator is to predict the Wasserstein-Distance of real_data and fake_data. In the paper, the formula is maximizing Ereal[f(x)] - Efake[f(x)],in the code it should be errD = e…
-
In the original WGAN paper, there is no sigmoid function after the critic, so why the code use sigmoid in T-WGAN as the same as SGAN?
-
Hi,
I've tried to train the model with the "wgan" options turned on, and got pretty bad results.
for example (iter 240000):
![iter-000240000](https://user-images.githubusercontent.com/28001669/8940…
-
Hi, I met ConnectionRefusedError when running the command:
`python main.py --data_root datasets/CKPlus --which_model_netR resnet18 --backend_pretrain --gpu_ids 0 --gan_type wgan-gp --load_size 250 --…
-
Hello,
after running `!bash ./run_test.sh `
I get :
`Traceback (most recent call last):
File "/content/DeepFillv2_Pytorch/test.py", line 41, in
tester.WGAN_tester(opt)
File "/cont…
-
![image](https://user-images.githubusercontent.com/35527568/43630539-2f24e198-9733-11e8-98a4-94ab844573eb.png)
i find citation 13,16,30 and do not know exact principle of hinge loss.
i feel confus…
-
What is correct value of alpha coefficient to reproduce your results? You mentioned that alpha should be equal to 0.1, but in fact it equals 0.
https://github.com/harryliew/WGAN-QC/blob/3e04319243524…