Keras implementations of Generative Adversarial Networks (GANs) suggested in research papers. If dense layers gets the job done for a given model I will often prefer them over convolutional layers. The reason is that I would like to enable people without GPUs to test these implementations out. 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. However, because of this the results will not always be as nice as in the papers.
Table of Contents
- Table of Contents
$ git clone https://github.com/eriklindernoren/Keras-GAN $ cd Keras-GAN $ sudo pip3 install -r requirements.txt
Implementation of Auxiliary Classifier Generative Adversarial Network.
Implementation of Adversarial Autoencoder.
Implementation of Bidirectional Generative Adversarial Network.
Implementation of Boundary-Seeking Generative Adversarial Networks.
Implementation of Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks.
Implementation of Context Encoders: Feature Learning by Inpainting.
Implementation of Coupled generative adversarial networks.
Implementation of Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks.
$ cd cyclegan $ bash download_dataset.sh apple2orange $ python3 cyclegan.py
Implementation of Deep Convolutional Generative Adversarial Network.
Implementation of DualGAN: Unsupervised Dual Learning for Image-to-Image Translation.
Implementation of Generative Adversarial Network with a MLP generator and discriminator.
Implementation of InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets.
Implementation of Least Squares Generative Adversarial Networks.
Implementation of Semi-Supervised Generative Adversarial Network.
Implementation of Wasserstein GAN (with DCGAN generator and discriminator).