Refine some docs (#65)

* Refine some docs
* Update docs/en_US/data_prepare.md

README.md

@@ -34,24 +34,49 @@ PaddleGAN 是一个基于飞桨的生成对抗网络开发工具包.
 
 请参考[安装文档](./docs/zh_CN/install.md)来进行PaddlePaddle和ppgan的安装
 
-## 数据准备
-请参考[数据准备](./docs/zh_CN/data_prepare.md) 来准备对应的数据.
+## 快速开始
 
+通过ppgan.app接口使用预训练模型:
 
-## 快速开始
-训练，预测，推理等请参考 [快速开始](./docs/zh_CN/get_started.md).
+ ```python
+ from ppgan.apps import RealSRPredictor
+ sr = RealSRPredictor()
+ sr.run("docs/imgs/monarch.png")
+ ```
+
+更多训练、评估教程参考:
+
+- [数据准备](./docs/zh_CN/data_prepare.md)
+- [训练/评估/推理教程](./docs/zh_CN/get_started.md)
 
 ## 模型教程
+
 * [Pixel2Pixel](./docs/zh_CN/tutorials/pix2pix_cyclegan.md)
 * [CycleGAN](./docs/zh_CN/tutorials/pix2pix_cyclegan.md)
 * [PSGAN](./docs/zh_CN/tutorials/psgan.md)
 * [First Order Motion Model](./docs/zh_CN/tutorials/motion_driving.md)
 * [视频修复](./docs/zh_CN/tutorials/video_restore.md)
 
-## 许可证书
-本项目的发布受[Apache 2.0 license](LICENSE)许可认证。
+## 在线体验
+
+通过[AI Studio实训平台](https://aistudio.baidu.com/aistudio/index)在线体验:
+
+|在线教程      |    链接   |
+|--------------|-----------|
+|老北京视频修复|[点击体验](https://aistudio.baidu.com/aistudio/projectdetail/1161285)|
+|表情动作迁移-当苏大强唱起unravel |[点击体验](https://aistudio.baidu.com/aistudio/projectdetail/1048840)|
+
+
+## 版本更新
+
+- v0.1.0 (2020.11.02)
+  - 初版发布，支持Pixel2Pixel、CycleGAN、PSGAN模型，支持视频插针、超分、老照片/视频上色、视频动作生成等应用。
+  - 模块化设计，接口简单易用。
 
 
 ## 贡献代码
 
 我们非常欢迎您可以为PaddleGAN提供任何贡献和建议。大多数贡献都需要同意参与者许可协议（CLA）。当提交拉取请求时，CLA机器人会自动检查您是否需要提供CLA。 只需要按照机器人提供的说明进行操作即可。CLA只需要同意一次，就能应用到所有的代码仓库上。关于更多的流程请参考[贡献指南](docs/zh_CN/contribute.md)。
+
+## 许可证书
+本项目的发布受[Apache 2.0 license](LICENSE)许可认证。

README_en.md

@@ -37,24 +37,41 @@ changes.
 
 Please refer to [install](./docs/en_US/install.md).
 
-## Data Prepare
-Please refer to [data prepare](./docs/en_US/data_prepare.md) for dataset preparation.
+## Quick Start
 
-## Get Start
-Please refer [get started](./docs/en_US/get_started.md) for the basic usage of PaddleGAN.
+Get started through ppgan.app interface:
+
+ ```python
+ from ppgan.apps import RealSRPredictor
+ sr = RealSRPredictor()
+ sr.run("docs/imgs/monarch.png")
+ ```
+
+More tutorials:
+
+- [Data preparation](./docs/en_US/data_prepare.md)
+- [Traning/Evaluating/Testing basic usage](./docs/zh_CN/get_started.md)
+
+## Model Tutorial
 
-## Model tutorial
 * [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)
 * [Video restore](./docs/zh_CN/tutorials/video_restore.md)
 
-## License
-PaddleGAN is released under the [Apache 2.0 license](LICENSE).
+
+## Changelog
+
+- v0.1.0 (2020.11.02)
+  - Realse 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.
 
 ## Contributing
 
 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).
+
+## License
+PaddleGAN is released under the [Apache 2.0 license](LICENSE).

docs/en_US/data_prepare.md

-## data prepare
+## Data prepare
 
 The config will suppose your data put in `$PaddleGAN/data`. You can symlink your datasets to `$PaddleGAN/data`.
 
@@ -28,8 +28,7 @@ PaddleGAN
 
 ```
 
-if you put your datasets on other place，for example ```your/data/path```,
-you can also change ```dataroot``` in config file:
+If you put your datasets on other place，for example ```your/data/path```, you can also change ```dataroot``` in config file:
 
 ```
 dataset:
@@ -41,12 +40,12 @@ dataset:
 
 ### Datasets of CycleGAN
 
-#### download existed datasets
+#### download form website
 
-##### download form website
-datasets for CycleGAN you can download from [here](https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/)
+Datasets for CycleGAN can be downloaded from [here](https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/)
+
+#### download by script
 
-##### download by script
 You can use ```download_cyclegan_data.py``` in ```PaddleGAN/data``` to download datasets you wanted. Supported datasets are: apple2orange, summer2winter_yosemite,horse2zebra, monet2photo, cezanne2photo, ukiyoe2photo, vangogh2photo, maps, cityscapes, facades, iphone2dslr_flower, ae_photos, cityscapes。
 
 run following command. Dataset will be downloaded to ```~/.cache/ppgan``` and symlink to ```PaddleGAN/data/``` .
@@ -55,7 +54,9 @@ python data/download_cyclegan_data.py --name horse2zebra
 ```
 
 #### custom dataset
+
 Data should be arranged in following way if you use custom dataset.
+
 ```
 custom_datasets
 ├── testA
@@ -66,20 +67,21 @@ custom_datasets
 
 ### Datasets of Pix2Pix
 
-#### download existed datasets
+#### Download from website
 
-##### download from website
-dataset for pix2pix you can download from [here](hhttps://people.eecs.berkeley.edu/~tinghuiz/projects/pix2pix/datasets/)
+Dataset for pix2pix can be downloaded from [here](https://people.eecs.berkeley.edu/~tinghuiz/projects/pix2pix/datasets/)
+
+#### Download by script
 
-##### download by script
 You can use ```download_pix2pix_data.py``` in ```PaddleGAN/data``` to download datasets you wanted. Supported datasets are: apple2orange, summer2winter_yosemite,horse2zebra, monet2photo, cezanne2photo, ukiyoe2photo, vangogh2photo, maps, cityscapes, facades, iphone2dslr_flower, ae_photos, cityscapes.
 
-run following command. Dataset will be downloaded to ```~/.cache/ppgan``` and symlink to ```PaddleGAN/data/``` .
+Dataset will be downloaded to ```~/.cache/ppgan``` and symlink to ```PaddleGAN/data/``` .
+
 ```
 python data/download_pix2pix_data.py --name cityscapes
 ```
 
-#### custom datasets
+#### Custom datasets
 Data should be arranged in following way if you use custom dataset. And image content shoubld be same with example image.
 
 ```

docs/en_US/install.md

@@ -25,11 +25,24 @@ Note: command above will install paddle with cuda10.2，if your installed cuda i
 </code></pre> </details> </td> </tr></tbody></table>
 
 
-### 2. Install ppgan
+### 2. Install through pip
+
+```
+# only support Python3
+python3 -m pip install --upgrade ppgan
+```
+
+Download the examples and configuration files via cloning the source code:
 
 ```
 git clone https://github.com/PaddlePaddle/PaddleGAN
 cd PaddleGAN
+```
 
+### 3. Install through source code
+
+```
+git clone https://github.com/PaddlePaddle/PaddleGAN
+cd PaddleGAN
 pip install -v -e .  # or "python setup.py develop"
 ```

docs/en_US/tutorials/motion_driving.md

@@ -13,7 +13,10 @@
 Users can upload the prepared source image and driving video, then substitute the path of source image and driving video for the `source_image` and `driving_video` parameter in the following running command. It will geneate a video file named `result.mp4` in the `output` folder, which is the animated video file.
 
 ```
-python -u tools/first-order-demo.py  --driving_video ./ravel_10.mp4  --source_image ./sudaqiang.png --relative --adapt_scale
+python -u tools/first-order-demo.py \
+     --driving_video ./ravel_10.mp4  \
+     --source_image ./sudaqiang.png \
+     --relative --adapt_scale
 ```
 
 **params:**
@@ -29,6 +32,7 @@ python -u tools/first-order-demo.py  --driving_video ./ravel_10.mp4  --source_im
 
 ## Reference
 
+```
 @InProceedings{Siarohin_2019_NeurIPS,
   author={Siarohin, Aliaksandr and Lathuilière, Stéphane and Tulyakov, Sergey and Ricci, Elisa and Sebe, Nicu},
   title={First Order Motion Model for Image Animation},
@@ -36,3 +40,4 @@ python -u tools/first-order-demo.py  --driving_video ./ravel_10.mp4  --source_im
   month = {December},
   year = {2019}
 }
+```

docs/zh_CN/data_prepare.md

@@ -41,19 +41,21 @@ dataset:
 
 ### CycleGAN模型相关的数据集下载
 
-#### 已有的数据集下载
+#### 从网页下载
 
-##### 从网页下载
 cyclgan模型相关的数据集可以在[这里](https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/)下载
 
-##### 使用脚本下载
+#### 使用脚本下载
+
 我们在 ```PaddleGAN/data``` 文件夹下提供了一个脚本 ```download_cyclegan_data.py``` 方便下载CycleGAN相关的
 数据集。执行如下命令可以下载相关的数据集，目前支持的数据集名称有：apple2orange, summer2winter_yosemite,horse2zebra, monet2photo, cezanne2photo, ukiyoe2photo, vangogh2photo, maps, cityscapes, facades, iphone2dslr_flower, ae_photos, cityscapes。
 
 执行如下命令，可以下载对应的数据集到 ```~/.cache/ppgan``` 并软连接到 ```PaddleGAN/data/``` 下。
+
 ```
 python data/download_cyclegan_data.py --name horse2zebra
 ```
+
 #### 使用自己的数据集
 如果你使用自己的数据集，需要构造成如下目录的格式。注意 ```xxxA```，```xxxB```文件数量，文件内容无需一一对应。
 ```
@@ -66,20 +68,22 @@ custom_datasets
 
 ### Pix2Pix相关的数据集下载
 
-#### 已有的数据集下载
+#### 从网页下载
 
-##### 从网页下载
 pixel2pixel模型相关的数据集可以在[这里](hhttps://people.eecs.berkeley.edu/~tinghuiz/projects/pix2pix/datasets/)下载
 
-##### 使用脚本下载
+#### 使用脚本下载
+
 我们在 ```PaddleGAN/data``` 文件夹下提供了一个脚本 ```download_pix2pix_data.py``` 方便下载pix2pix模型相关的数据集。执行如下命令可以下载相关的数据集，目前支持的数据集名称有：apple2orange, summer2winter_yosemite,horse2zebra, monet2photo, cezanne2photo, ukiyoe2photo, vangogh2photo, maps, cityscapes, facades, iphone2dslr_flower, ae_photos, cityscapes。
 
 执行如下命令，可以下载对应的数据集到 ```~/.cache/ppgan``` 并软连接到 ```PaddleGAN/data/``` 下。
+
 ```
 python data/download_pix2pix_data.py --name cityscapes
 ```
 
 #### 使用自己的数据集
+
 如果你使用自己的数据集，需要构造成如下目录的格式。同时图片应该制作成下图的样式，即左边为一种风格，另一边为相应转换的风格。
 
 ```

docs/zh_CN/install.md

@@ -23,8 +23,21 @@ pip install -U paddlepaddle-gpu==2.0.0rc0
 </code></pre> </details> </td> <td align="left"><details><summary> install </summary><pre><code>python -m pip install https://paddle-wheel.bj.bcebos.com/2.0.0-rc0-gpu-cuda9-cudnn7-mkl%2Fpaddlepaddle_gpu-2.0.0rc0.post90-cp36-cp36m-linux_x86_64.whl
 </code></pre> </details> </td> </tr></tbody></table>
 
+### 2. 通过Pip安装
 
-### 2. 安装ppgan
+```
+# only support Python3
+python3 -m pip install --upgrade ppgan
+```
+
+下载示例和配置文件:
+
+```
+git clone https://github.com/PaddlePaddle/PaddleGAN
+cd PaddleGAN
+```
+
+### 3. 通过源码安装PaddleGAN
 
 ```
 git clone https://github.com/PaddlePaddle/PaddleGAN

docs/zh_CN/tutorials/motion_driving.md

@@ -17,7 +17,10 @@ First order motion model的任务是image animation，给定一张源图片，
 用户可以上传自己准备的视频和图片，并在如下命令中的source_image参数和driving_video参数分别换成自己的图片和视频路径，然后运行如下命令，就可以完成动作表情迁移，程序运行成功后，会在ouput文件夹生成名为result.mp4的视频文件，该文件即为动作迁移后的视频。本项目中提供了原始图片和驱动视频供展示使用。运行的命令如下所示：
 
 ```
-python -u tools/first-order-demo.py  --driving_video ./ravel_10.mp4  --source_image ./sudaqiang.png --relative --adapt_scale
+python -u tools/first-order-demo.py  \
+     --driving_video ./ravel_10.mp4 \
+     --source_image ./sudaqiang.png \
+     --relative --adapt_scale
 ```
 
 **参数说明:**
@@ -34,6 +37,7 @@ python -u tools/first-order-demo.py  --driving_video ./ravel_10.mp4  --source_im
 
 ## 参考文献
 
+```
 @InProceedings{Siarohin_2019_NeurIPS,
   author={Siarohin, Aliaksandr and Lathuilière, Stéphane and Tulyakov, Sergey and Ricci, Elisa and Sebe, Nicu},
   title={First Order Motion Model for Image Animation},
@@ -41,3 +45,5 @@ python -u tools/first-order-demo.py  --driving_video ./ravel_10.mp4  --source_im
   month = {December},
   year = {2019}
 }
+
+```

ppgan/modules/init.py

@@ -17,6 +17,10 @@ import numpy as np
 
 import paddle
 
+from ..utils.logger import get_logger
+
+logger = get_logger('init')
+
 
 def _calculate_fan_in_and_fan_out(tensor):
     dimensions = len(tensor.shape)
@@ -65,7 +69,6 @@ def calculate_gain(nonlinearity, param=None):
     Args:
         nonlinearity: the non-linear function (`nn.functional` name)
         param: optional parameter for the non-linear function
-
     """
     linear_fns = [
         'linear', 'conv1d', 'conv2d', 'conv3d', 'conv_transpose1d',
@@ -310,5 +313,5 @@ def init_weights(net, init_type='normal', init_gain=0.02):
             normal_(m.weight, 1.0, init_gain)
             constant_(m.bias, 0.0)
 
-    print('initialize network with %s' % init_type)
+    logger.debug('initialize network with %s' % init_type)
     net.apply(init_func)  # apply the initialization function <init_func>

ppgan/utils/logger.py

@@ -35,7 +35,7 @@ def setup_logger(output=None, name="ppgan"):
         logging.Logger: a logger
     """
     logger = logging.getLogger(name)
-    logger.setLevel(logging.DEBUG)
+    logger.setLevel(logging.INFO)
     logger.propagate = False
 
     plain_formatter = logging.Formatter(