Displaying 1 to 10 from 10 results

iGAN - Interactive Image Generation via Generative Adversarial Networks

  •    Python

[Project] [Youtube] [Paper] A research prototype developed by UC Berkeley and Adobe CTL. Latest development: [pix2pix]: Torch implementation for learning a mapping from input images to output images. [CycleGAN]: Torch implementation for learning an image-to-image translation (i.e. pix2pix) without input-output pairs. [pytorch-CycleGAN-and-pix2pix]: PyTorch implementation for both unpaired and paired image-to-image translation.

DCGAN-tensorflow - A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

  •    Javascript

Tensorflow implementation of Deep Convolutional Generative Adversarial Networks which is a stabilize Generative Adversarial Networks. The referenced torch code can be found here.

chainer-gan-lib - Chainer implementation of recent GAN variants

  •    Python

This repository collects chainer implementation of state-of-the-art GAN algorithms. These codes are evaluated with the inception score on Cifar-10 dataset. Note that our codes are not faithful re-implementation of the original paper. This implementation has been tested with the following versions.




tf-dcgan - DCGAN implementation by TensorFlow

  •    Python

DCGAN implementation by TensorFlow

DCGAN-LSGAN-WGAN-WGAN-GP-Tensorflow - DCGAN LSGAN WGAN WGAN-GP Tensorflow

  •    Python

Tensorflow implementation of DCGAN, LSGAN, WGAN and WGAN-GP, and we use DCGAN as the network architecture in all experiments.


psgan - Periodic Spatial Generative Adversarial Networks

  •    Jupyter

This code implements Periodic Spatial Generative Adversarial Networks (PSGANs) on top of Lasagne/Theano. The code was tested on top of Lasagne (version 0.2.dev1) and Theano (0.9.0dev2). PSGANs can generate sample textures of arbitrary size that look strikingly similar - but not exactly the same - compared to a single (or several) source image(s).

spatial_gan - Spatial Generative Adversarial Networks

  •    Python

The code was tested on top of Lasagne (version 0.2.dev1) and Theano (0.9.0dev2). SGANs can generate sample textures of arbitrary size that look strikingly similar - but not exactly the same - compared to a single (or several) source image(s).