README.md 6.6 KB
Newer Older
Q
qingqing01 已提交
1

L
LielinJiang 已提交
2
English | [简体中文](./README_cn.md)
3

L
LielinJiang 已提交
4 5
# PaddleGAN

L
LielinJiang 已提交
6
PaddleGAN provides developers with high-performance implementation of classic and SOTA Generative Adversarial Networks, and supports developers to quickly build, train and deploy GANs for academic, entertainment and industrial usage.
7

L
LielinJiang 已提交
8
GAN-Generative Adversarial Network, was praised by "the Father of Convolutional Networks"  **Yann LeCun (Yang Likun)**  as **[One of the most interesting ideas in the field of computer science in the past decade]**. It's the one research area in deep learning that AI researchers are most concerned about.
L
LielinJiang 已提交
9

Q
qingqing01 已提交
10
<div align='center'>
L
LaraStuStu 已提交
11
  <img src='./docs/imgs/ppgan.jpg'>
Q
qingqing01 已提交
12
</div>
L
LielinJiang 已提交
13

L
LaraStuStu 已提交
14
[![License](https://img.shields.io/badge/license-Apache%202-red.svg)](LICENSE)![python version](https://img.shields.io/badge/python-3.6+-orange.svg)
L
LielinJiang 已提交
15

L
LaraStuStu 已提交
16

L
LielinJiang 已提交
17
## Recent Contributors
L
LaraStuStu 已提交
18 19
[![](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/images/0)](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/links/0)[![](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/images/1)](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/links/1)[![](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/images/2)](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/links/2)[![](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/images/3)](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/links/3)[![](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/images/4)](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/links/4)[![](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/images/5)](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/links/5)[![](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/images/6)](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/links/6)[![](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/images/7)](https://sourcerer.io/fame/LaraStuStu/paddlepaddle/paddlegan/links/7)

L
LielinJiang 已提交
20
## Quick Start
L
LielinJiang 已提交
21

L
LielinJiang 已提交
22
* Please refer to the [installation document](./docs/en_US/install.md) to make sure you have installed PaddlePaddle and PaddleGAN correctly.
L
LaraStuStu 已提交
23

L
LielinJiang 已提交
24
* Get started through ppgan.app interface:
Q
qingqing01 已提交
25

L
LielinJiang 已提交
26 27 28 29 30 31 32 33 34
   ```python
   from ppgan.apps import RealSRPredictor
   sr = RealSRPredictor()
   sr.run("docs/imgs/monarch.png")
   ```
* More applications, please refer to [ppgan.apps apis](./docs/en_US/apis/apps.md)
* More tutorials:
  - [Data preparation](./docs/en_US/data_prepare.md)
  - [Training/Evaluating/Testing basic usage](./docs/zh_CN/get_started.md)
Q
qingqing01 已提交
35

L
LielinJiang 已提交
36
## Model Tutorial
Q
qingqing01 已提交
37

L
LielinJiang 已提交
38 39 40 41 42 43 44
* [Pixel2Pixel](./docs/en_US/tutorials/pix2pix_cyclegan.md)
* [CycleGAN](./docs/en_US/tutorials/pix2pix_cyclegan.md)
* [PSGAN](./docs/en_US/tutorials/psgan.md)
* [First Order Motion Model](./docs/en_US/tutorials/motion_driving.md)
* [FaceParsing](./docs/en_US/tutorials/face_parse.md)
* [AnimeGANv2](./docs/en_US/tutorials/animegan.md)
* [U-GAT-IT](./docs/en_US/tutorials/ugatit.md)
Q
qingqing01 已提交
45
* [Photo2Cartoon](./docs/en_US/tutorials/photo2cartoon.md)
L
lijianshe02 已提交
46
* [Wav2Lip](./docs/en_US/tutorials/wav2lip.md)
Q
qingqing01 已提交
47

L
LielinJiang 已提交
48
## Composite Application
L
LaraStuStu 已提交
49

L
LielinJiang 已提交
50
* [Video restore](./docs/zh_CN/tutorials/video_restore.md)
L
LaraStuStu 已提交
51

L
LielinJiang 已提交
52
## Examples
L
LielinJiang 已提交
53

L
LielinJiang 已提交
54
### Image Translation
L
LaraStuStu 已提交
55 56 57 58 59

<div align='center'>
  <img src='./docs/imgs/horse2zebra.gif'width='700' height='200'/>
</div>

L
LielinJiang 已提交
60
### Old video restore
L
LaraStuStu 已提交
61 62 63 64 65
<div align='center'>
  <img src='./docs/imgs/color_sr_peking.gif' width='700'/>
</div>


L
LielinJiang 已提交
66
### Motion driving
L
LaraStuStu 已提交
67
<div align='center'>
L
LielinJiang 已提交
68
  <img src='./docs/imgs/first_order.gif' width='700'>
L
LaraStuStu 已提交
69 70
</div>

L
LielinJiang 已提交
71
### Super resolution
L
LaraStuStu 已提交
72 73 74 75 76 77

<div align='center'>
  <img src='./docs/imgs/sr_demo.png'width='700' height='250'/>
</div>


L
LielinJiang 已提交
78
### Makeup shifter
L
LaraStuStu 已提交
79 80 81

<div align='center'>
  <img src='./docs/imgs/makeup_shifter.png'width='700' height='250'/>
L
LielinJiang 已提交
82 83 84
</div>


L
LielinJiang 已提交
85
### Face cartoonization
L
LielinJiang 已提交
86 87 88

<div align='center'>
  <img src='./docs/imgs/ugatit.png'width='700' height='250'/>
L
LaraStuStu 已提交
89 90
</div>

H
haoqiang 已提交
91 92 93 94 95 96 97 98

### Realistic face cartoonization

<div align='center'>
  <img src='./docs/imgs/photo2cartoon.png'width='700' height='250'/>
</div>


L
LielinJiang 已提交
99
### Photo animation
Q
qingqing01 已提交
100 101 102 103

<div align='center'>
  <img src='./docs/imgs/animeganv2.png'width='700' height='250'/>
</div>
Q
qingqing01 已提交
104

L
lijianshe02 已提交
105 106 107 108 109 110 111 112

### Lip-syncing

<div align='center'>
  <img src='./docs/imgs/mona.gif'width='700'>
</div>


L
LielinJiang 已提交
113
## Changelog
Q
qingqing01 已提交
114 115

- v0.1.0 (2020.11.02)
L
LielinJiang 已提交
116 117
  - Release first version, supported models include Pixel2Pixel, CycleGAN, PSGAN. Supported applications include video frame interpolation, super resolution, colorize images and videos, image animation.
  - Modular design and friendly interface.
L
LielinJiang 已提交
118

L
LielinJiang 已提交
119
## Community
L
LaraStuStu 已提交
120

L
LielinJiang 已提交
121
Scan OR Code below to join [PaddleGAN QQ Group:1058398620], you can get offical technical support  here and communicate with other developers/friends. Look forward to your participation!
L
LaraStuStu 已提交
122 123 124 125

<div align='center'>
  <img src='./docs/imgs/qq.png'width='250' height='300'/>
</div>
L
LielinJiang 已提交
126

L
LielinJiang 已提交
127
### PaddleGAN Special Interest Group(SIG)
L
LielinJiang 已提交
128

L
LielinJiang 已提交
129
It was first proposed and used by [ACM(Association for Computing Machinery)](https://en.wikipedia.org/wiki/Association_for_Computing_Machinery) in 1961. Top International open source organizations including [Kubernates](https://kubernetes.io/) all adopt the form of SIGs, so that members with the same specific interests can share, learn knowledge and develop projects. These members do not need to be in the same country/region or the same organization, as long as they are like-minded, they can all study, work, and play together with the same goals~
L
LielinJiang 已提交
130

L
LielinJiang 已提交
131
PaddleGAN SIG is such a developer organization that brings together people who interested in GAN. There are frontline developers of PaddlePaddle, senior engineers from the world's top 500, and students from top universities at home and abroad.
L
LielinJiang 已提交
132

L
LielinJiang 已提交
133
We are continuing to recruit developers interested and capable to join us building this project and explore more useful and interesting applications together.
Q
qingqing01 已提交
134

L
LielinJiang 已提交
135
SIG contributions:
Q
qingqing01 已提交
136

L
LielinJiang 已提交
137 138 139
- [zhen8838](https://github.com/zhen8838): contributed to AnimeGANv2.
- [Jay9z](https://github.com/Jay9z): contributed to DCGAN and updated install docs, etc.
- [HighCWu](https://github.com/HighCWu): contributed to c-DCGAN and WGAN. Support to use `paddle.vision.datasets`.
Q
qingqing01 已提交
140
- [hao-qiang](https://github.com/hao-qiang) & [ minivision-ai ](https://github.com/minivision-ai): contributed to the photo2cartoon project.
Q
qingqing01 已提交
141

L
LielinJiang 已提交
142

L
LielinJiang 已提交
143
## Contributing
Q
qingqing01 已提交
144

L
LielinJiang 已提交
145 146 147
Contributions and suggestions are highly welcomed. Most contributions require you to agree to a [Contributor License Agreement (CLA)](https://cla-assistant.io/PaddlePaddle/PaddleGAN) declaring.
When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA. Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
For more, please reference [contribution guidelines](docs/en_US/contribute.md).
L
LaraStuStu 已提交
148

L
LielinJiang 已提交
149 150
## License
PaddleGAN is released under the [Apache 2.0 license](LICENSE).