Keras-GAN
Collection of Keras implementations of Generative Adversarial Networks (GANs) suggested in research papers. These models are in some cases simplified versions of the ones ultimately described in the papers, but I have chosen to focus on getting the core ideas covered instead of getting every layer configuration right. Contributions and suggestions of GAN varieties to implement are very welcomed.
See also: PyTorch-GAN
Table of Contents
- Installation
- Implementations
- Auxiliary Classifier GAN
- Adversarial Autoencoder
- Bidirectional GAN
- Boundary-Seeking GAN
- Conditional GAN
- Context-Conditional GAN
- Context Encoder
- Coupled GANs
- CycleGAN
- Deep Convolutional GAN
- DiscoGAN
- DualGAN
- Generative Adversarial Network
- InfoGAN
- LSGAN
- Pix2Pix
- PixelDA
- Semi-Supervised GAN
- Super-Resolution GAN
- Wasserstein GAN
- Wasserstein GAN GP
Installation
$ git clone https://github.com/eriklindernoren/Keras-GAN
$ cd Keras-GAN/
$ sudo pip3 install -r requirements.txt
Implementations
AC-GAN
Implementation of Auxiliary Classifier Generative Adversarial Network.
Paper: https://arxiv.org/abs/1610.09585
Example
$ cd acgan/
$ python3 acgan.py
Adversarial Autoencoder
Implementation of Adversarial Autoencoder.
Paper: https://arxiv.org/abs/1511.05644
Example
$ cd aae/
$ python3 aae.py
BiGAN
Implementation of Bidirectional Generative Adversarial Network.
Paper: https://arxiv.org/abs/1605.09782
Example
$ cd bigan/
$ python3 bigan.py
BGAN
Implementation of Boundary-Seeking Generative Adversarial Networks.
Paper: https://arxiv.org/abs/1702.08431
Example
$ cd bgan/
$ python3 bgan.py
CC-GAN
Implementation of Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks.
Paper: https://arxiv.org/abs/1611.06430
Example
$ cd ccgan/
$ python3 ccgan.py
CGAN
Implementation of Conditional Generative Adversarial Nets.
Paper:https://arxiv.org/abs/1411.1784
Example
$ cd cgan/
$ python3 cgan.py
Context Encoder
Implementation of Context Encoders: Feature Learning by Inpainting.
Paper: https://arxiv.org/abs/1604.07379
Example
$ cd context_encoder/
$ python3 context_encoder.py
CoGAN
Implementation of Coupled generative adversarial networks.
Paper: https://arxiv.org/abs/1606.07536
Example
$ cd cogan/
$ python3 cogan.py
CycleGAN
Implementation of Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks.
Paper: https://arxiv.org/abs/1703.10593
Example
$ cd cyclegan/
$ bash download_dataset.sh apple2orange
$ python3 cyclegan.py
DCGAN
Implementation of Deep Convolutional Generative Adversarial Network.
Paper: https://arxiv.org/abs/1511.06434
Example
$ cd dcgan/
$ python3 dcgan.py
DiscoGAN
Implementation of Learning to Discover Cross-Domain Relations with Generative Adversarial Networks.
Paper: https://arxiv.org/abs/1703.05192
Example
$ cd discogan/
$ bash download_dataset.sh edges2shoes
$ python3 discogan.py
DualGAN
Implementation of DualGAN: Unsupervised Dual Learning for Image-to-Image Translation.
Paper: https://arxiv.org/abs/1704.02510
Example
$ cd dualgan/
$ python3 dualgan.py
GAN
Implementation of Generative Adversarial Network with a MLP generator and discriminator.
Paper: https://arxiv.org/abs/1406.2661
Example
$ cd gan/
$ python3 gan.py
InfoGAN
Implementation of InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets.
Paper: https://arxiv.org/abs/1606.03657
Example
$ cd infogan/
$ python3 infogan.py
LSGAN
Implementation of Least Squares Generative Adversarial Networks.
Paper: https://arxiv.org/abs/1611.04076
Example
$ cd lsgan/
$ python3 lsgan.py
Pix2Pix
Implementation of Image-to-Image Translation with Conditional Adversarial Networks.
Paper: https://arxiv.org/abs/1611.07004
Example
$ cd pix2pix/
$ bash download_dataset.sh facades
$ python3 pix2pix.py
PixelDA
Implementation of Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks.
Paper: https://arxiv.org/abs/1612.05424
MNIST to MNIST-M Classification
Trains a classifier on MNIST images that are translated to resemble MNIST-M (by performing unsupervised image-to-image domain adaptation). This model is compared to the naive solution of training a classifier on MNIST and evaluating it on MNIST-M. The naive model manages a 55% classification accuracy on MNIST-M while the one trained during domain adaptation gets a 95% classification accuracy.
$ cd pixelda/
$ python3 pixelda.py
```, Method, Accuracy, ------------, :---------:, Naive, 55%, PixelDA, 95%, ### SGAN
Implementation of _Semi-Supervised Generative Adversarial Network_.
[Code](sgan/sgan.py)
Paper: https://arxiv.org/abs/1606.01583
#### Example
$ cd sgan/
$ python3 sgan.py
<p align="center">
<img src="http://eriklindernoren.se/images/sgan.png" width="640"\>
</p>
### SRGAN
Implementation of _Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network_.
[Code](srgan/srgan.py)
Paper: https://arxiv.org/abs/1609.04802
<p align="center">
<img src="http://eriklindernoren.se/images/superresgan.png" width="640"\>
</p>
#### Example
$ cd srgan/
$ python3 srgan.py
<p align="center">
<img src="http://eriklindernoren.se/images/srgan.png" width="640"\>
</p>
### WGAN
Implementation of _Wasserstein GAN_ (with DCGAN generator and discriminator).
[Code](wgan/wgan.py)
Paper: https://arxiv.org/abs/1701.07875
#### Example
$ cd wgan/
$ python3 wgan.py
<p align="center">
<img src="http://eriklindernoren.se/images/wgan2.png" width="640"\>
</p>
### WGAN GP
Implementation of _Improved Training of Wasserstein GANs_.
[Code](wgan_gp/wgan_gp.py)
Paper: https://arxiv.org/abs/1704.00028
#### Example
$ cd wgan_gp/
$ python3 wgan_gp.py
<p align="center">
<img src="http://eriklindernoren.se/images/imp_wgan.gif" width="640"\>
</p>