Git Product home page Git Product logo

gan_review's Introduction

GAN_Review

A Survey and Taxonomy of the Recent GANs Development. Please refer to the details in recent review paper “Generative Adversarial Networks: A Survey and Taxonomy” Wang, Zhengwei and She, Qi and Ward, Tomas E.

If you find this useful in your research, please consider citing:

@article{wang2019generative,
title={Generative Adversarial Networks: A Survey and Taxonomy},
author={Wang, Zhengwei and She, Qi and Ward, Tomas E},
journal={arXiv preprint arXiv:1906.01529},
year={2019}
}

We have classified the two GAN-variants research lines based on recent GAN developments, below we provide a summary and the demo code of these models. We have tested the codes below and tried to summary some of lightweight and easy-to-reuse module of state-of-the-art GANs.

Architecture-variant GANs

LAPGAN:
https://github.com/jimfleming/LAPGAN (TensorFlow) https://github.com/AaronYALai/Generative_Adversarial_Networks_PyTorch (PyTorch)

DCGAN:
https://github.com/carpedm20/DCGAN-tensorflow (TensorFlow)
https://github.com/last-one/DCGAN-Pytorch (PyTorch)

BEGAN:
https://github.com/carpedm20/BEGAN-tensorflow (TensorFlow)
https://github.com/anantzoid/BEGAN-pytorch (PyTorch)

PROGAN:
https://github.com/tkarras/progressive_growing_of_gans (TensorFlow)
https://github.com/nashory/pggan-pytorch (PyTorch)

SAGAN:
https://github.com/brain-research/self-attention-gan (TensorFlow)
https://github.com/heykeetae/Self-Attention-GAN (PyTorch)

BigGAN:
https://github.com/taki0112/BigGAN-Tensorflow (TensorFlow)
https://github.com/ajbrock/BigGAN-PyTorch (PyTorch)

Loss-variant GANs

WGAN:
https://github.com/ChengBinJin/WGAN-TensorFlow (TensorFlow)
https://github.com/Zeleni9/pytorch-wgan (PyTorch)

WGAN-GP:
https://github.com/changwoolee/WGAN-GP-tensorflow (TensorFlow)
https://github.com/caogang/wgan-gp (PyTorch)

LSGAN:
https://github.com/xudonmao/LSGAN (TensorFlow)
https://github.com/meliketoy/LSGAN.pytorch (PyTorch)

f-GAN:
https://github.com/LynnHo/f-GAN-Tensorflow (TensorFlow)

UGAN:
https://github.com/gokul-uf/TF-Unrolled-GAN (TensorFlow)
https://github.com/andrewliao11/unrolled-gans (PyTorch)

LS-GAN:
https://github.com/maple-research-lab/lsgan-gp-alt (TensorFlow)
https://github.com/maple-research-lab/glsgan-gp (PyTorch)

MRGAN:
https://github.com/wiseodd/generative-models/tree/master/GAN/mode_regularized_gan (TensorFlow and PyTorch)

Geometric GAN:
https://github.com/lim0606/pytorch-geometric-gan (PyTorch)

RGAN:
https://github.com/AlexiaJM/RelativisticGAN (TensorFlow and PyTorch)

SN-GAN:
https://github.com/taki0112/Spectral_Normalization-Tensorflow (TensorFlow) https://github.com/christiancosgrove/pytorch-spectral-normalization-gan (PyTorch)

gan_review's People

Contributors

sheqi avatar villawang avatar

Watchers

James Cloos avatar

Forkers

yangminsi

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.