Generative Model Papers with Implementation in Keras

This Repository contains a collection of Keras implementations of Generative Adversarial Networks (GANs) suggested in research papers. All of these implementations are originally inspired by https://github.com/eriklindernoren/Keras-GAN. The Notebooks are the simplest version of the real code by Erik Linder-Norén and can be directly tested at Google Colab Notebooks.

New models are continously being added at daily basis.

Feel free to contact me at zshnnisar@gmail.com for any query or any other implementation.

Table of Contents

• GAN-Generative Adversarial Network
• DCGAN-Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• WGAN-Wasserstein GAN
• WGAN_GP-Improved Training of Wasserstein GANs
• CGAN-Conditional Generative Adversarial Nets
• BiGAN-Bidirectional Generative Adversarial Network
• Pix2PixGAN-Image-to-Image Translation with Conditional Adversarial Networks
• CycleGAN-Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

Code Implementations and Results

GAN-Generative Adversarial Network

Code: Google Colab Notebook

Generated Results

DCGAN-Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Code: Google Colab Notebook

Generated Results

WGAN-Wasserstein GAN

Code: Google Colab Notebook

Generated Results

WGAN_GP-Improved Training of Wasserstein GANs

Code: Google Colab Notebook

Generated Results

CGAN-Conditional Generative Adversarial Nets

Code: Google Colab Notebook

Generated Results

BiGAN-Bidirectional Generative Adversarial Network

Code: Google Colab Notebook

Generated Results

Pix2PixGAN-Image-to-Image Translation with Conditional Adversarial Networks

Code: Google Colab Notebook

Generated Results

CycleGAN-Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

This Network is implemented for two different datasets including MNIST and BRATS-2017.

Code: Google Colab Notebook for MNIST

Generated Results for MNIST

Code: Google Colab Notebook for BRATS-2017

Generated Results for BRATS-2017