Generative Adversarial Network topic

Generative adversarial networks (GAN) are a class of generative machine learning frameworks. A GAN consists of two competing neural networks, often termed the Discriminator network and the Generator network. GANs have been shown to be powerful generative models and are able to successfully generate new data given a large enough training dataset.

List Generative Adversarial Network repositories

DeepNetworks

23
Stars
4
Forks
Watchers

My implementations of deep neural networks for practice.

Improved Wasserstein GAN (WGAN-GP) application on medical (MRI) images

video_prediction

302
Stars
65
Forks
Watchers

Stochastic Adversarial Video Prediction

CS231n

50
Stars
9
Forks
Watchers

PyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Recognition"

StyleGAN-pytorch

26
Stars
6
Forks
Watchers

PyTorch implementation of A Style-Based Generator Architecture for Generative Adversarial Network

ChemGAN-challenge

113
Stars
54
Forks
Watchers

Code for the paper: ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity? arXiv preprint arXiv:1708.08227.

DeepNAG

39
Stars
4
Forks
Watchers

Deep Non-Adversarial Gesture Generation

GANimation

1.9k
Stars
411
Forks
Watchers

GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]