Code and hyperparameters for the paper "Generative Adversarial Networks"
-
Updated
Jun 26, 2014 - Python
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.
Code and hyperparameters for the paper "Generative Adversarial Networks"
Code and hyperparameters for the paper "Generative Adversarial Networks"
Add colors to black and white images with neural networks (GANs).
Reversing GAN image generation for similarity search and error/artifact fixing
Tensorflow implementation of Energy Based Generative Adversarial Networks (EBGAN)
A generative adversarial network for text generation, written in TensorFlow.
An implementation of context encoders by Deepak Pathak with a remodeled discriminator.
Text to image synthesis using thought vectors
Chainer implementation of Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
InfoGAN inspired neural network trained on zap50k images (using Tensorflow + tf-slim). Intermediate layers of the discriminator network are used to do image similarity.
A Tensorflow Implementation of Generative Adversarial Networks as presented in the original paper by Goodfellow et. al. (https://arxiv.org/abs/1406.2661)
Implementation of a Deep Convolutional Generative Adversarial Network to generate realistic MNIST digits at 64x64 resolution in Tensorflow.
Generative Adversarial Networks implementation in Chainer
Released June 10, 2014