gabehamilton/HyperGAN

Generative Adversarial Network framework with API and command line tool.

HyperGAN 0.10.0-alpha1

A composable GAN API and CLI. Built for developers, researchers, and artists.

HyperGAN is currently in open beta.

Logos generated with examples/colorizer

See more on the hypergan youtube

Table of contents

• About
• Showcase
• Documentation
• Changelog
• Quick start
  • Requirements
  • Install
  • Train
  • Development Mode
  • Running on CPU
• The pip package hypergan
• Training
• Sampling
• API
  • Examples
• Datasets
  • Creating a Dataset
  • Downloadable Datasets
  • Cleaning up data
• Contributing
• Versioning
• Sources
• Papers
• Citation

About

Generative Adversarial Networks consist of 2 learning systems that learn together. HyperGAN implements these learning systems in Tensorflow with deep learning.

For an introduction to GANs, see http://blog.aylien.com/introduction-generative-adversarial-networks-code-tensorflow/

HyperGAN is a community project. GANs are a very new and active field of research. Join the community discord.

Features

• Community project
• Transfer learning
• Online learning
• Dataset agnostic
• Reproducible architectures using json configurations
• Domain Specific Language to define custom architectures
• API

Showcase

See the

Documentation

• Model author JSON reference
• Model author tutorial 1
• 0.10.0
• 0.9.x
• Test coverage

Changelog

See the full changelog here: Changelog.md

Quick start

Requirements

Recommended: GTX 1080+

Install

Install hypergan:

  pip3 install hypergan --upgrade

Optional virtualenv:

If you use virtualenv:

  virtualenv --system-site-packages -p python3 hypergan
  source hypergan/bin/activate

Dependencies:

If installation fails try this.

  pip3 install numpy tensorflow-gpu hyperchamber pillow pygame

Dependency help

If the above step fails see the dependency documentation:

• tensorflow - https://www.tensorflow.org/install/
• pygame - http://www.pygame.org/wiki/GettingStarted

Create a new model

  hypergan new mymodel

This will create a mymodel.json based off the default configuration. You can change configuration templates with the -c flag.

List configuration templates

  hypergan new mymodel -l

See all configuration templates with --list-templates or -l.

Train

  # Train a 32x32 gan with batch size 32 on a folder of folders of pngs, resizing images as necessary
  hypergan train folder/ -s 32x32x3 -f png -c mymodel --resize

Development mode

If you wish to modify hypergan

git clone https://github.com/255BITS/hypergan
cd hypergan
python3 setup.py develop

Running on CPU

Make sure to include the following 2 arguments:

CUDA_VISIBLE_DEVICES= hypergan --device '/cpu:0'

Don't train on CPU! It's too slow.

The pip package hypergan

 hypergan -h

Training

  # Train a 32x32 gan with batch size 32 on a folder of pngs
  hypergan train [folder] -s 32x32x3 -f png -b 32 --config [name]

Sampling

  # Train a 256x256 gan with batch size 32 on a folder of pngs
  hypergan train [folder] -s 32x32x3 -f png -b 32 --config [name] --sampler static_batch --sample_every 5 --save_samples

By default hypergan will not save samples to disk. To change this, use --save_samples.

One way a network learns:

To create videos:

  ffmpeg -i samples/%06d.png -vcodec libx264 -crf 22 -threads 0 gan.mp4

Arguments

To see a detailed list, run

  hypergan -h

Examples

See the example documentation https://github.com/255BITS/HyperGAN/tree/master/examples

Datasets

To build a new network you need a dataset. Your data should be structured like:

  [folder]/[directory]/*.png

Creating a Dataset

Datasets in HyperGAN are meant to be simple to create. Just use a folder of images.

 [folder]/*.png

For jpg(pass -f jpg)

Downloadable datasets

• Loose images of any kind can be used
• CelebA aligned faces http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
• MS Coco http://mscoco.org/
• ImageNet http://image-net.org/
• youtube-dl (see examples/Readme.md)

Cleaning up data

To convert and resize your data for processing, you can use imagemagick

for i in *.jpg; do; convert $i  -resize "300x256" -gravity north   -extent 256x256 -format png -crop 256x256+0+0 +repage $i-256x256.png;done

Contributing

Contributions are welcome and appreciated! We have many open issues in the Issues tab.

See how to contribute.

Versioning

HyperGAN uses semantic versioning. http://semver.org/

TLDR: x.y.z

• x is incremented on stable public releases.
• y is incremented on API breaking changes. This includes configuration file changes and graph construction changes.
• z is incremented on non-API breaking changes. z changes will be able to reload a saved graph.

Papers

• GAN - https://arxiv.org/abs/1406.2661
• DCGAN - https://arxiv.org/abs/1511.06434
• InfoGAN - https://arxiv.org/abs/1606.03657
• Improved GAN - https://arxiv.org/abs/1606.03498
• Adversarial Inference - https://arxiv.org/abs/1606.00704
• Energy-based Generative Adversarial Network - https://arxiv.org/abs/1609.03126
• Wasserstein GAN - https://arxiv.org/abs/1701.07875
• Least Squares GAN - https://arxiv.org/pdf/1611.04076v2.pdf
• Boundary Equilibrium GAN - https://arxiv.org/abs/1703.10717
• Self-Normalizing Neural Networks - https://arxiv.org/abs/1706.02515
• Variational Approaches for Auto-Encoding Generative Adversarial Networks - https://arxiv.org/pdf/1706.04987.pdf
• CycleGAN - https://junyanz.github.io/CycleGAN/
• DiscoGAN - https://arxiv.org/pdf/1703.05192.pdf
• Softmax GAN - https://arxiv.org/abs/1704.06191
• The Cramer Distance as a Solution to Biased Wasserstein Gradients - https://arxiv.org/abs/1705.10743
• Improved Training of Wasserstein GANs - https://arxiv.org/abs/1704.00028
• More...

Sources

• DCGAN - https://github.com/carpedm20/DCGAN-tensorflow
• InfoGAN - https://github.com/openai/InfoGAN
• Improved GAN - https://github.com/openai/improved-gan
• Hyperchamber - https://github.com/255bits/hyperchamber

Citation

  HyperGAN Community
  HyperGAN, (2016-2019+), 
  GitHub repository, 
  https://github.com/HyperGAN/HyperGAN

HyperGAN comes with no warranty or support.