Generative Adversarial Networks
This repository contains implementation of various architectures of Generative Models.
Papers to read (Prerequisites)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Generative Adversarial Networks by Ian Goodfellow et al.
- Wasserstein GAN by Soumith et al.
- Improved training of Wasserstein GANs by Arjovsky et al.
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks by Zhu et al.
- Wasserstein GANs
- WGAN with gradient penalty
- CycleGANs (soon)
Usage of GPU is highly recommended.
Cloning the Repository
$ git clone https://github.com/prajjwal1/gans
To train the model:
$ cd WGAN $ python wgan_gp.py
This repository is under constant development. Will be updated regularly.