提交 912b96d0 编写于 作者: L LielinJiang

update readme

上级 2354ab9d
English | [简体中文](./README.md)
English | [简体中文](./README_cn.md)
# PaddleGAN
still under development!!
PaddleGAN is an development kit of Generative Adversarial Network based on PaddlePaddle.
## Download Dataset
This script could download several dataset for paired images for image2image translation task.
![](./docs/imgs/color_sr_peking.gif)
```
cd PaddleGAN/script/
bash pix2pix_download.sh [cityscapes|facades|edges2handbags|edges2shoes|maps]
```
## Train
```
python -u tools/main.py --config-file configs/cyclegan-cityscapes.yaml
```
Features:
continue train from last checkpoint
```
python -u tools/main.py --config-file configs/cyclegan-cityscapes.yaml --resume your_checkpoint_path
```
- Highly Flexible:
Components are designed to be modular. Model architectures, as well as data
preprocess pipelines, can be easily customized with simple configuration
changes.
- Rich applications:
PaddleGAN provides rich of applications, such as image generation, image restore, image colorization, video interpolate, makeup shifter.
## Install
### 1. install paddlepaddle
PaddleGAN work with:
* PaddlePaddle >= 2.0.0-rc
* Python >= 3.5+
multiple gpus train:
```
CUDA_VISIBLE_DEVICES=0,1 python -m paddle.distributed.launch tools/main.py --config-file configs/pix2pix-cityscapes.yaml
pip install -U paddlepaddle-gpu
```
## Evaluate
### 2. install ppgan
```
python tools/main.py --config-file configs/cyclegan-cityscapes.yaml --evaluate-only --load your_weight_path
git clone https://github.com/PaddlePaddle/PaddleGAN
cd PaddleGAN
pip install -v -e . # or "python setup.py develop"
```
## Data Prepare
Please refer to [data prepare](./docs/data_prepare.md) for dataset preparation.
## Get Start
Please refer [get stated](./docs/get_started.md) for the basic usage of PaddleGAN.
## License
PaddleGAN is released under the [Apache 2.0 license](LICENSE).
## Contributing
Contributions are highly welcomed and we would really appreciate your feedback!!
[English](./README.md) | 简体中文
# PaddleGAN
PaddleGAN 是一个基于飞桨的生成对抗网络开发工具包.
![](./docs/imgs/color_sr_peking.gif)
特性:
- 高度的灵活性:
模块化设计,解耦各个网络组件,开发者轻松搭建、试用各种检测模型及优化策略,快速得到高性能、定制化的算法。
- 丰富的应用:
PaddleGAN 提供了非常多的应用,比如说图像生成,图像修复,图像上色,视频补帧,人脸妆容迁移等.
## 安装
### 1. 安装 paddlepaddle
PaddleGAN 所需的版本:
* PaddlePaddle >= 2.0.0-rc
* Python >= 3.5+
```
pip install -U paddlepaddle-gpu
```
### 2. 安装ppgan
```
git clone https://github.com/PaddlePaddle/PaddleGAN
cd PaddleGAN
pip install -v -e . # or "python setup.py develop"
```
## 数据准备
请参考 [数据准备](./docs/data_prepare.md) 来准备对应的数据.
## 快速开始
训练,预测,推理等请参考 [快速开始](./docs/get_started.md).
## 许可证书
本项目的发布受[Apache 2.0 license](LICENSE)许可认证。
## 贡献代码
我们非常欢迎你可以为PaddleGAN提供代码,也十分感谢你的反馈。
## data prepare
It is recommended to symlink the dataset root to `$PaddleGAN/data`.
```
PaddleGAN
|-- configs
|-- data
| |-- cityscapes
| | ├── test
| | ├── testA
| | ├── testB
| | ├── train
| | ├── trainA
| | └── trainB
| ├── horse2zebra
| | ├── testA
| | ├── testB
| | ├── trainA
| | └── trainB
| └── facades
| ├── test
| ├── train
| └── val
|-- docs
|-- ppgan
|-- tools
```
### cyclegan datasets
more dataset for cyclegan you can download from [here](https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/)
### pix2pix datasets
more dataset for pix2pix you can download from [here](hhttps://people.eecs.berkeley.edu/~tinghuiz/projects/pix2pix/datasets/)
## Train
```
python -u tools/main.py --config-file configs/cyclegan_cityscapes.yaml
```
continue train from last checkpoint
```
python -u tools/main.py --config-file configs/cyclegan_cityscapes.yaml --resume your_checkpoint_path
```
multiple gpus train:
```
CUDA_VISIBLE_DEVICES=0,1 python -m paddle.distributed.launch tools/main.py --config-file configs/pix2pix_cityscapes.yaml
```
## Evaluate
```
python tools/main.py --config-file configs/cyclegan_cityscapes.yaml --evaluate-only --load your_weight_path
```
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册