Generative Adversarial Networks (GAN)


The generative network generates candidates while the discriminative network evaluates them. Typically, the generative network learns to map from a latent space to a data distribution of interest, while the discriminative network distinguishes candidates produced by the generator from the true data distribution. The generative network's training objective is to increase the error rate of the discriminative network.

Overview

6 GAN Architectures You Really Should Know
Some of the most popular GAN architectures, particularly 6 architectures that you should know to have a diverse coverage on GANs.
generative-adversarial-networks survey tutorial article

Tutorials

PyTorch - GAN
PyTorch implementations of Generative Adversarial Networks.
generative-adversarial-networks pytorch began cyclegan
GAN Lab
An Interactive, Visual Experimentation Tool for Generative Adversarial Networks
interactive generative-adversarial-networks neural-networks code
How to Detect Data-Copying in Generative Models
I propose some new definitions and test statistics for conceptualizing and measuring overfitting by generative models.
generative-modeling data-copying generative-adversarial-networks variational-autoencoders

Libraries

General
SimpleGAN
A Tensorflow-based framework to ease the training of generative models
computer-vision generative-adversarial-networks tensorflow deep-learning
Mimicry
A PyTorch library for the reproducibility of GAN research.
generative-adversarial-networks pytorch benchmarks reproducability
Table of Contents
Share a project
Share something you or the community has made with ML.
Topic experts
Share