-
please ref:
https://github.com/eriklindernoren/PyTorch-GAN/blob/master/implementations/wgan_gp/wgan_gp.py
if choose 'wgan-gp'in d_loss and GP are not update differently in train()
d_loss =…
-
Hi, @oyxhust
I have met this error when train time.
-------------------------------------------
model [WGAN_GP_Model] was created
create web directory ./checkpoints/mnist/web...
Traceback (mos…
-
@JamesMBartlett @JamesMBartlett
Test WGAN with Style classification network
-
Thank you for sharing the implementations of the GAN based models on popular datasets like CelebA.
I have implemented the WGAN-GP model (in PyTorch), the samples are looking closer the reported work …
-
In this line of the code you are calling the discrimnator with a single input which is the interpolated image but it also requires another parameter which is the z
https://github.com/lkhphuc/Anomaly-…
-
I want to train the `lapsrn_wgan`, can you give me some reference material?
-
In the WGAN_GP paper [ArXiv](https://arxiv.org/abs/1701.07875), alpha is sampled for each example. However, it's sampled element-wise referred to [WGAN_GP](https://github.com/znxlwm/pytorch-generative…
-
There are examples in the book of what the WGAN should generate after 25 epochs of training.
But when I train the model, these are the generated samples at the 25th epoch of training.
I …
-
Hi, I want to report a bug and corresponding fix to your team.
I believe this fix could help others who use WGAN-gp algorithm to train GANs.
## Bug and Reason
It appears in the "code example" …
-
Thank for your work! I'm confused about the batch normalization layer used in the discriminator of wgan_gp. I think there shouldn't be any batch normalization layer in the discriminator.
I think the …