# pytorch-generative-model-collections
**Repository Path**: wengo/pytorch-generative-model-collections
## Basic Information
- **Project Name**: pytorch-generative-model-collections
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-12-18
- **Last Updated**: 2020-12-19
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# pytorch-generative-model-collections
Original : [[Tensorflow version]](https://github.com/hwalsuklee/tensorflow-generative-model-collections)
Pytorch implementation of various GANs.
This repository was re-implemented with reference to [tensorflow-generative-model-collections](https://github.com/hwalsuklee/tensorflow-generative-model-collections) by [Hwalsuk Lee](https://github.com/hwalsuklee)
I tried to implement this repository as much as possible with [tensorflow-generative-model-collections](https://github.com/hwalsuklee/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)
### Lists (Table is borrowed from [tensorflow-generative-model-collections](https://github.com/hwalsuklee/tensorflow-generative-model-collections))
*Name* | *Paper Link* | *Value Function*
:---: | :---: | :--- |
**GAN** | [Arxiv](https://arxiv.org/abs/1406.2661) | 
**LSGAN**| [Arxiv](https://arxiv.org/abs/1611.04076) | 
**WGAN**| [Arxiv](https://arxiv.org/abs/1701.07875) | 
**WGAN_GP**| [Arxiv](https://arxiv.org/abs/1704.00028) | 
**DRAGAN**| [Arxiv](https://arxiv.org/abs/1705.07215) | 
**CGAN**| [Arxiv](https://arxiv.org/abs/1411.1784) | 
**infoGAN**| [Arxiv](https://arxiv.org/abs/1606.03657) | 
**ACGAN**| [Arxiv](https://arxiv.org/abs/1610.09585) | 
**EBGAN**| [Arxiv](https://arxiv.org/abs/1609.03126) | 
**BEGAN**| [Arxiv](https://arxiv.org/abs/1703.10717) | 
#### Variants of GAN structure (Figures are borrowed from [tensorflow-generative-model-collections](https://github.com/hwalsuklee/tensorflow-generative-model-collections))
### Results for mnist
Network architecture of generator and discriminator is the exaclty sames as in [infoGAN paper](https://arxiv.org/abs/1606.03657).
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](https://github.com/zalandoresearch/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](https://github.com/hwalsuklee/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](https://github.com/hwalsuklee/tensorflow-generative-model-collections) and tested with Pytorch 0.4.0 on Ubuntu 16.04 using GPU.