pytorch-generative-model-collections
Pytorch implementation of various GANs.
This repository was re-implemented with reference to tensorflow-generative-model-collections by Hwalsuk Lee
I tried to implement this repository as much as possible with tensorflow-generative-model-collections, But some models are a little different.
This repository is included code for CPU mode Pytorch, but i did not test. I tested only in GPU mode Pytorch.
Dataset
MNIST
Fashion-MNIST
CIFAR10
SVHN
STL10
LSUN-bed
I only tested the code on MNIST and Fashion-MNIST.
Generative Adversarial Networks (GANs)
Name
Paper Link
Value Function
LSGAN
WGAN_GP
DRAGAN
infoGAN
ACGAN
EBGAN
BEGAN
Variants of GAN structure (Figures are borrowed from tensorflow-generative-model-collections)
Results for mnist
Network architecture of generator and discriminator is the exaclty sames as in infoGAN paper.
For fair comparison of core ideas in all gan variants, all implementations for network architecture are kept same except EBGAN and BEGAN. Small modification is made for EBGAN/BEGAN, since those adopt auto-encoder strucutre for discriminator. But I tried to keep the capacity of discirminator.
The following results can be reproduced with command:
python main.py --dataset mnist --gan_type --epoch 50 --batch_size 64
Fixed generation
All results are generated from the fixed noise vector.
Name
Epoch 1
Epoch 25
Epoch 50
GIF
GAN
LSGAN
WGAN
WGAN_GP
DRAGAN
EBGAN
BEGAN
Conditional generation
Each row has the same noise vector and each column has the same label condition.
Name
Epoch 1
Epoch 25
Epoch 50
GIF
CGAN
ACGAN
infoGAN
InfoGAN : Manipulating two continous codes
All results have the same noise vector and label condition, but have different continous vector.
Name
Epoch 1
Epoch 25
Epoch 50
GIF
infoGAN
Loss plot
Name
Loss
GAN
LSGAN
WGAN
WGAN_GP
DRAGAN
EBGAN
BEGAN
CGAN
ACGAN
infoGAN
Results for fashion-mnist
Comments on network architecture in mnist are also applied to here.
Fashion-mnist is a recently proposed dataset consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. (T-shirt/top, Trouser, Pullover, Dress, Coat, Sandal, Shirt, Sneaker, Bag, Ankle boot)
The following results can be reproduced with command:
python main.py --dataset fashion-mnist --gan_type --epoch 50 --batch_size 64
Fixed generation
All results are generated from the fixed noise vector.
Name
Epoch 1
Epoch 25
Epoch 50
GIF
GAN
LSGAN
WGAN
WGAN_GP
DRAGAN
EBGAN
BEGAN
Conditional generation
Each row has the same noise vector and each column has the same label condition.
Name
Epoch 1
Epoch 25
Epoch 50
GIF
CGAN
ACGAN
infoGAN
ACGAN tends to fall into mode-collapse in tensorflow-generative-model-collections, but Pytorch ACGAN does not fall into mode-collapse.
InfoGAN : Manipulating two continous codes
All results have the same noise vector and label condition, but have different continous vector.
Name
Epoch 1
Epoch 25
Epoch 50
GIF
infoGAN
Loss plot
Name
Loss
GAN
LSGAN
WGAN
WGAN_GP
DRAGAN
EBGAN
BEGAN
CGAN
ACGAN
infoGAN
Folder structure
The following shows basic folder structure.
├── main.py # gateway
├── data
│ ├── mnist # mnist data (not included in this repo)
│ ├── ...
│ ├── ...
│ └── fashion-mnist # fashion-mnist data (not included in this repo)
│
├── GAN.py # vainilla GAN
├── utils.py # utils
├── dataloader.py # dataloader
├── models # model files to be saved here
└── results # generation results to be saved here
Development Environment
Ubuntu 16.04 LTS
NVIDIA GTX 1080 ti
cuda 9.0
Python 3.5.2
pytorch 0.4.0
torchvision 0.2.1
numpy 1.14.3
matplotlib 2.2.2
imageio 2.3.0
scipy 1.1.0
Acknowledgements
This implementation has been based on tensorflow-generative-model-collections and tested with Pytorch 0.4.0 on Ubuntu 16.04 using GPU.