https://github.com/rahulbhalley/turing-gan

Source code for "Training Generative Adversarial Networks Via Turing Test".
https://github.com/rahulbhalley/turing-gan

cifar10 fashion-mnist gan generative-adversarial-network lipschitz-functions mnist optimal-transport pytorch turing-gans turing-test wasserstein wasserstein-gan

Last synced: 23 days ago
JSON representation

Source code for "Training Generative Adversarial Networks Via Turing Test".

• Host: GitHub
• URL: https://github.com/rahulbhalley/turing-gan
• Owner: RahulBhalley
• Created: 2018-11-21T17:42:04.000Z (over 6 years ago)
• Default Branch: pytorch
• Last Pushed: 2020-05-29T13:42:39.000Z (about 5 years ago)
• Last Synced: 2025-03-31T04:51:30.253Z (about 2 months ago)
• Topics: cifar10, fashion-mnist, gan, generative-adversarial-network, lipschitz-functions, mnist, optimal-transport, pytorch, turing-gans, turing-test, wasserstein, wasserstein-gan
• Homepage: https://arxiv.org/abs/1810.10948
• Size: 372 MB
• Stars: 13
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Turing Generative Adversarial Network

I found Turing GAN a way to train GANs quickly! This excited me to write my own versions in [PyTorch](https://pytorch.org) refering the original Keras [code](https://github.com/bojone/T-GANs).

## Experiments

So, following are my experiments' resulting image data.

### Note

- For all the experiments the images shown below are sampled after 100K iterations of training the Turing GAN on various datasets. 

- All the experiments used spectral normalization for 1-Lipschitz contraint enforcement. 

- I trained all of the Turing GANs with both Jensen-Shannon and Wasserstein divergences.

### CIFAR-10

#### Turing Standard GAN with Spectral Normalization

![](https://raw.githubusercontent.com/rahulbhalley/turing-gan.pytorch/pytorch/sgan/samples/cifar-10/latest_100000.png)

#### Turing Wasserstein GAN with Spectral Normalization

![](https://raw.githubusercontent.com/rahulbhalley/turing-gan.pytorch/pytorch/wgan/samples/cifar-10/latest_100000.png)

### MNIST

#### Turing Standard GAN with Spectral Normalization

![](https://raw.githubusercontent.com/rahulbhalley/turing-gan.pytorch/pytorch/sgan/samples/mnist/latest_100000.png)

#### Turing Wasserstein GAN with Spectral Normalization

![](https://raw.githubusercontent.com/rahulbhalley/turing-gan.pytorch/pytorch/wgan/samples/mnist/latest_100000.png)

### Fashion MNIST

#### Turing Standard GAN with Spectral Normalization

![](https://raw.githubusercontent.com/rahulbhalley/turing-gan.pytorch/pytorch/sgan/samples/fashion-mnist/latest_100000.png)

#### Turing Wasserstein GAN with Spectral Normalization

![](https://raw.githubusercontent.com/rahulbhalley/turing-gan.pytorch/pytorch/wgan/samples/fashion-mnist/latest_100000.png)

## References

- Training Generative Adversarial Networks Via Turing Test [[arXiv](https://arxiv.org/abs/1810.10948)]

- Original [T-GANs](https://github.com/bojone/T-GANs) implementation

- Spectral Normalization for Generative Adversarial Networks [[arXiv](https://arxiv.org/abs/1802.05957)]

- Spectral Normalization [implementation](https://github.com/christiancosgrove/pytorch-spectral-normalization-gan/blob/master/spectral_normalization.py) in [PyTorch](https://pytorch.org)