[StarGAN V2](https://arxiv.org/pdf/1912.01865.pdf)is an image-to-image translation model published on CVPR2020.
A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains. Existing methods address either of the issues, having limited diversity or multiple models for all domains. StarGAN v2 is a single framework that tackles both and shows significantly improved results over the baselines. Experiments on CelebA-HQ and a new animal faces dataset (AFHQ) validate superiority of StarGAN v2 in terms of visual quality, diversity, and scalability.
## 2 How to use
### 2.1 Prepare dataset
The CelebAHQ dataset used by StarGAN V2 can be downloaded from [here](https://www.dropbox.com/s/f7pvjij2xlpff59/celeba_hq.zip?dl=0), and the AFHQ dataset can be downloaded from [here](https://www.dropbox.com/s/t9l9o3vsx2jai3z/afhq.zip?dl=0). Then unzip dataset to the ``PaddleGAN/data`` directory.
The structure of dataset is as following:
```
├── data
├── afhq
| ├── train
| | ├── cat
| | ├── dog
| | └── wild
| └── val
| ├── cat
| ├── dog
| └── wild
└── celeba_hq
├── train
| ├── female
| └── male
└── val
├── female
└── male
```
### 2.2 Train/Test
The example uses the AFHQ dataset as an example. If you want to use the CelebAHQ dataset, you can change the config file.
