Skip to content

Latest commit

 

History

History
executable file
·
113 lines (103 loc) · 7.19 KB

README.md

File metadata and controls

executable file
·
113 lines (103 loc) · 7.19 KB
Raw

Awesome-GANs with Tensorflow AwesomeBuild Status

Tensorflow implementation of GANs(Generative Adversarial Networks)

Environments

Local Environment

  • OS : Windows 10 Edu x86-64 / Linux Ubuntu 16.04 x86-64
  • CPU : i7-7700K
  • GPU : GTX 1060 6GB
  • RAM : DDR4 16GB
  • Library : TF 1.4.1 with CUDA 8.0 + cuDNN 7.0
  • Python 3.x

Minimum Environment

  • OS : Any
  • CPU : Any
  • GPU : None or Any ('compute capability of GPU' must be over 3.0)
  • RAM : 2GB ~
  • Library : TF 1.4.0 ~ with CUDA 8.0 + cuDNN 7.0 ~
  • Python 3.x

Preferred Environment

  • OS : Linux Ubuntu 14.04 x86-64 ~
  • CPU : any (quad core ~)
  • GPU : GTX 1060 6GB ~
  • RAM : DDR4 16GB ~
  • Library : TF 1.4.0 ~ with CUDA 8.0 + cuDNN 7.0 ~
  • Python 3.x

Because of the image and model size, (especially BEGAN, SGAN, SRGAN, StarGAN, ... using high resolution images as input), if you want to train them comfortably, you need a GPU which has more than 8GB.

But, of course, the most of the implementations use MNIST or CiFar-10, 100 DataSets. Meaning that we can handle it with EVEN lower spec GPU than 'The Preferred' :).

Prerequisites

  • python 3.5+
  • tensorflow-gpu or tensorflow 1.4.0
  • scipy
  • pillow
  • h5py
  • pickle
  • tqdm
  • sklearn
  • Internet :)

Usage

(before running train.py, make sure run after downloading dataset & changing dataset directory in train.py)
just download it and run train.py
$ python3 xxx_train.py

DataSets

Now supporting(?) DataSets are... (code is in /datasets.py)

  • MNIST
  • CiFar-10
  • CiFar-100
  • Celeb-A
  • pix2pix shoes
  • pix2pix bags
  • ImageNet
  • (more DataSets will be added soon!)

Repo Tree

│
├── gan_img (generated images)
│   ├── train_xxx.png
│   └── train_xxx.png
├── model (model)
│   ├── checkpoint
│   ├── ...
│   └── xxx.ckpt
├── gan_model.py (gan model)
├── gan_train.py (gan trainer)
├── dataset.py   (DataSet loader)
├── gan_tb.png   (Tensor-Board result)
└── readme.md    (results & explains)

Papers & Codes

Name Summary Paper Code
ACGAN Auxiliary Classifier Generative Adversarial Networks [arXiv] [code]
AdaGAN Boosting Generative Models [arXiv]
BEGAN Boundary Equilibrium Generative Adversarial Networks [arXiv] [code]
BGAN Boundary-Seeking Generative Adversarial Networks [arXiv] [code]
CGAN Conditional Generative Adversarial Networks [arXiv] [code]
CoGAN Coupled Generative Adversarial Networks [arXiv]
CycleGAN Unpaired img2img translation using Cycle-consistent Adversarial Networks [arXiv]
DCGAN Deep Convolutional Generative Adversarial Networks [arXiv] [code]
DiscoGAN Discover Cross-Domain Generative Adversarial Networks [arXiv]
DualGAN Unsupervised Dual Learning for Image-to-Image Translation [arXiv]
EBGAN Energy-based Generative Adversarial Networks [arXiv] [code]
f-GAN Training Generative Neural Samplers using Variational Divergence Minimization [arXiv]
GAN Generative Adversarial Networks [arXiv] [code]
Softmax GAN Generative Adversarial Networks with Softmax [arXiv] [code]
3D GAN 3D Generative Adversarial Networks [MIT]
GAP Generative Adversarial Parallelization [arXiv]
GEGAN Generalization and Equilibrium in Generative Adversarial Networks [arXiv]
InfoGAN Interpretable Representation Learning by Information Maximizing Generative Adversarial Networks [arXiv] [code]
LAPGAN Laplacian Pyramid Generative Adversarial Networks [arXiv] [code]
LSGAN Loss-Sensitive Generative Adversarial Networks [arXiv] [code]
MAGAN Margin Adaptation for Generative Adversarial Networks [arXiv] [code]
MRGAN Mode Regularized Generative Adversarial Networks [arXiv]
SalGAN Visual Saliency Prediction Generative Adversarial Networks [arXiv]
SeqGAN Sequence Generative Adversarial Networks with Policy Gradient [arXiv]
SGAN Stacked Generative Adversarial Networks [arXiv] [code]
SGAN++ Realistic Image Synthesis with Stacked Generative Adversarial Networks [arXiv]
SRGAN Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [arXiv] [code]
StarGAN Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation [arXiv] [code]
WGAN Wasserstein Generative Adversarial Networks [arXiv] [code]
ImprovedWGAN Improved Training of Wasserstein Generative Adversarial Networks [arXiv] [code]

Author

HyeongChan Kim / (@kozistr, @zer0day)