PyTorch-StudioGAN

PyTorch-StudioGAN copied to clipboard

ReACGAN + ADC has lower performance than plain ReACGAN

4

Hi, first of all I would like to thank you tremendously for your work. I'm certain that this repository alone has saved countless hours for researchers and developers all across...

Adversarian

Backbone networks for GAN evaluation

1

Hi & Good day! In the section "4.3 Backbone networks for GAN evaluation" of your article, you have mentioned that you have used DINO as a metric. Does that mean...

davidHemf

[CVPR 2023] Adding NoisyTwins Regularization to StyleGAN2

2

Hi MingKug and team, Thanks for your great work in maintaining the repository. We just released our new work NoisyTwins [CVPR 2023], a regularizer for the latent space of GAN....

rangwani-harsh

TSNE Analysis, K-Nearest Neighbor Analysis, Frequency Analysis and Semantic Factorization

2

Hi & good day! Thanks for the paper, the repo and codes. I was searching through folders to find out the source code for image analysis, but didn't see anything...

davidHemf

set d_cond_mtd to "PD" in stylegan2, there is a bug: 'Discriminator' object has no attribute 'embedding'

1

set d_cond_mtd to "PD" in stylegan2, there is a bug: 'Discriminator' object has no attribute 'embedding'

cs911

import utils.misc as misc: error solution

1

My system is linux, and when I use main.py, it calls config.py. When “import utils.misc as misc“ and so on, it will report an error. However, if you add an...

shizuguilai

Gradient penalty "interpolates" term

1

Hi, This is **'cal_grad_penalty'** function in `/src/utils/losses.py` ``` def cal_grad_penalty(real_images, real_labels, fake_images, discriminator, device): batch_size, c, h, w = real_images.shape alpha = torch.rand(batch_size, 1) alpha = alpha.expand(batch_size, real_images.nelement() // batch_size).contiguous().view(batch_size,...

rl-max

Fix CAS computation

1

- missing optimizer.zero_grad() - validation accuracy was computed on the training set instead of the validation set - fix log Also, I believe would be better to generate a fake...

sup3rgiu

Hello, I have found the code for 2c loss. Where is ContraGAN's model in the paper "Contrastive Learning for Conditional Image Generation"

zhihangzhang

Hello, I wanted to run experiments with the “historical” DCGAN architecture on CIFAR10, noting that, unlike the original paper by Radfort et al. (2015), the discrimination is not bounded to...

ben-schindler