fix TRT8 core bug

03bb378f · LDOUBLEV · a2a12fe4 · 2e9abcb9 · 03bb378f · 03bb378f
Commit 03bb378f authored Nov 25, 2021 by LDOUBLEV
20 changed files
--- a/.github/ISSUE_TEMPLATE/custom.md
+++ b/.github/ISSUE_TEMPLATE/custom.md
+---
+name: Issue template
+about: Issue template for code error.
+title: ''
+labels: ''
+assignees: ''
+---
+请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
+- 系统环境/System Environment：
+- 版本号/Version：Paddle：  PaddleOCR： 问题相关组件/Related components：
+- 运行指令/Command Code：
+- 完整报错/Complete Error Message：
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -5,5 +5,6 @@ recursive-include ppocr/utils *.txt utility.py logging.py network.py
 recursive-include ppocr/data *.py
 recursive-include ppocr/postprocess *.py
 recursive-include tools/infer *.py
+recursive-include tools __init__.py
 recursive-include ppocr/utils/e2e_utils *.py
 recursive-include ppstructure *.py
\ No newline at end of file
--- a/PPOCRLabel/PPOCRLabel.py
+++ b/PPOCRLabel/PPOCRLabel.py
@@ -35,6 +35,7 @@ import numpy as np
 sys.path.append(__dir__)
 sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
+sys.path.append(os.path.abspath(os.path.join(__dir__, '../PaddleOCR')))
 sys.path.append("..")
 from paddleocr import PaddleOCR
@@ -113,7 +114,7 @@ class MainWindow(QMainWindow, WindowMixin):
        getStr = lambda strId: self.stringBundle.getString(strId)
        self.defaultSaveDir = defaultSaveDir
-        self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=gpu, lang=lang)
+        self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=gpu, lang=lang, show_log=False)
        if os.path.exists('./data/paddle.png'):
            result = self.ocr.ocr('./data/paddle.png', cls=True, det=True)
@@ -390,7 +391,7 @@ class MainWindow(QMainWindow, WindowMixin):
                          'Ctrl+J', 'edit', u'Move and edit Boxs', enabled=False)
        create = action(getStr('crtBox'), self.createShape,
-                        'w', 'new', getStr('crtBoxDetail'), enabled=False)
+                        'w', 'objects', getStr('crtBoxDetail'), enabled=False)
        delete = action(getStr('delBox'), self.deleteSelectedShape,
                        'backspace', 'delete', getStr('delBoxDetail'), enabled=False)
@@ -1388,7 +1389,6 @@ class MainWindow(QMainWindow, WindowMixin):
        for box in self.PPlabel[imgidx]:
            shapes.append((box['transcription'], box['points'], None, None, box['difficult']))
-        print(shapes)
        self.loadLabels(shapes)
        self.canvas.verified = False

--- a/PPOCRLabel/README.md
+++ b/PPOCRLabel/README.md
@@ -8,7 +8,10 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w
 ### Recent Update
- 2021.8.11：
+- 2021.11.17:
+  - Support install and start PPOCRLabel through the whl package (by [d2623587501](https://github.com/d2623587501))
+  - Dataset segmentation: Divide the annotation file into training, verification and testing parts (refer to section 3.5 below, by [MrCuiHao](https://github.com/MrCuiHao))
+- 2021.8.11:
  - New functions: Open the dataset folder, image rotation (Note: Please delete the label box before rotating the image) (by [Wei-JL](https://github.com/Wei-JL))
  - Added shortcut key description (Help-Shortcut Key), repaired the direction shortcut key movement function under batch processing (by [d2623587501](https://github.com/d2623587501))
 - 2021.2.5: New batch processing and undo functions (by [Evezerest](https://github.com/Evezerest)):
@@ -21,14 +24,11 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w
  - Click to modify the recognition result.(If you can't change the result, please switch to the system default input method, or switch back to the original input method again)
 - 2020.12.18: Support re-recognition of a single label box (by [ninetailskim](https://github.com/ninetailskim) ), perfect shortcut keys.
-### TODO:
- Lock box mode: For the same scene data, the size and position of the locked detection box can be transferred between different pictures.
-## Installation
-### 1. Environment Preparation
+## 1. Installation and Run
-#### **Install PaddlePaddle 2.0**
+### 1.1 Install PaddlePaddle
 ```bash
 pip3 install --upgrade pip
@@ -42,61 +42,57 @@ python3 -m pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple
 For more software version requirements, please refer to the instructions in [Installation Document](https://www.paddlepaddle.org.cn/install/quick) for operation.
-#### **Install PaddleOCR**
+### 1.2 Install and Run PPOCRLabel
-```bash
+PPOCRLabel can be started in two ways: whl package and Python script. The whl package form is more convenient to start, and the python script to start is convenient for secondary development.
-# Recommend
-git clone https://github.com/PaddlePaddle/PaddleOCR
-# If you cannot pull successfully due to network problems, you can also choose to use the code hosting on the cloud:
-git clone https://gitee.com/paddlepaddle/PaddleOCR
-# Note: The cloud-hosting code may not be able to synchronize the update with this GitHub project in real time. There might be a delay of 3-5 days. Please give priority to the recommended method.
-```
-#### **Install Third-party Libraries**
+#### Windows
 ```bash
-cd PaddleOCR
+pip install PPOCRLabel  # install
-pip3 install -r requirements.txt
+PPOCRLabel  # run
 ```
-If you getting this error `OSError: [WinError 126] The specified module could not be found` when you install shapely on windows. Please try to download Shapely whl file using http://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely.
+> If you getting this error `OSError: [WinError 126] The specified module could not be found` when you install shapely on windows. Please try to download Shapely whl file using http://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely.
+>
-Reference: [Solve shapely installation on windows](https://stackoverflow.com/questions/44398265/install-shapely-oserror-winerror-126-the-specified-module-could-not-be-found)
+> Reference: [Solve shapely installation on windows](https://stackoverflow.com/questions/44398265/install-shapely-oserror-winerror-126-the-specified-module-could-not-be-found)
+>
-### 2. Install PPOCRLabel
+#### Ubuntu Linux
-#### Windows
+```bash
+pip3 install PPOCRLabel
+pip3 install trash-cli
+PPOCRLabel
+```
+#### MacOS
 ```bash
-pip install pyqt5
+pip3 install PPOCRLabel
-cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
+pip3 install opencv-contrib-python-headless==4.2.0.32
-python PPOCRLabel.py
+PPOCRLabel # run
 ```
-#### Ubuntu Linux
+#### 1.2.2 Build and Install the Whl Package Locally
 ```bash
-pip3 install pyqt5
+cd PaddleOCR/PPOCRLabel
-pip3 install trash-cli
+python3 setup.py bdist_wheel 
-cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
+pip3 install dist/PPOCRLabel-1.0.0-py2.py3-none-any.whl
-python3 PPOCRLabel.py
 ```
-#### MacOS
+#### 1.2.3 Run PPOCRLabel by Python Script
 ```bash
-pip3 install pyqt5
+cd ./PPOCRLabel  # Switch to the PPOCRLabel directory
-pip3 uninstall opencv-python # Uninstall opencv manually as it conflicts with pyqt
+python PPOCRLabel.py --lang ch
-pip3 install opencv-contrib-python-headless==4.2.0.32 # Install the headless version of opencv
-cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
-python3 PPOCRLabel.py
 ```
-## Usage
-### Steps
+## 2. Usage
+### 2.1 Steps
 1. Build and launch using the instructions above.
@@ -122,7 +118,7 @@ python3 PPOCRLabel.py
 10. Labeling result: the user can export the label result manually through the menu "File - Export Label", while the program will also export automatically if "File - Auto export Label Mode" is selected. The manually checked label will be stored in *Label.txt* under the opened picture folder. Click "File"-"Export Recognition Results" in the menu bar, the recognition training data of such pictures will be saved in the *crop_img* folder, and the recognition label will be saved in *rec_gt.txt*<sup>[4]</sup>.
-### Note
+### 2.2 Note
 [1] PPOCRLabel uses the opened folder as the project. After opening the image folder, the picture will not be displayed in the dialog. Instead, the pictures under the folder will be directly imported into the program after clicking "Open Dir".
@@ -140,9 +136,11 @@ python3 PPOCRLabel.py
 |  rec_gt.txt   | The recognition label file, which can be directly used for PPOCR identification model training, is generated after the user clicks on the menu bar "File"-"Export recognition result". |
 |   crop_img    | The recognition data, generated at the same time with *rec_gt.txt* |
-## Explanation
-### Shortcut keys
+## 3. Explanation
+### 3.1 Shortcut keys
 | Shortcut keys            | Description                                      |
 | ------------------------ | ------------------------------------------------ |
@@ -162,31 +160,56 @@ python3 PPOCRLabel.py
 | Ctrl--                   | Zoom out                                         |
 | ↑→↓←                     | Move selected box                                |
-### Built-in Model
+### 3.2 Built-in Model
 - Default model: PPOCRLabel uses the Chinese and English ultra-lightweight OCR model in PaddleOCR by default, supports Chinese, English and number recognition, and multiple language detection.
 - Model language switching: Changing the built-in model language is supportable by clicking "PaddleOCR"-"Choose OCR Model" in the menu bar. Currently supported languagesinclude French, German, Korean, and Japanese.
  For specific model download links, please refer to [PaddleOCR Model List](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/models_list_en.md#multilingual-recognition-modelupdating)
- Custom model: The model trained by users can be replaced by modifying PPOCRLabel.py in [PaddleOCR class instantiation](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/PPOCRLabel/PPOCRLabel.py#L110) referring [Custom Model Code](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/whl_en.md#use-custom-model)
+- **Custom Model**: If users want to replace the built-in model with their own inference model, they can follow the [Custom Model Code Usage](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_en/whl_en.md#31-use-by-code) by modifying PPOCRLabel.py for [Instantiation of PaddleOCR class](https://github.com/PaddlePaddle/PaddleOCR/blob/release/ 2.3/PPOCRLabel/PPOCRLabel.py#L116) :
+  add parameter `det_model_dir`  in `self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=gpu, lang=lang) `
-### Export Label Result
+### 3.3 Export Label Result
 PPOCRLabel supports three ways to export Label.txt
 - Automatically export: After selecting "File - Auto Export Label Mode", the program will automatically write the annotations into Label.txt every time the user confirms an image. If this option is not turned on, it will be automatically exported after detecting that the user has manually checked 5 images.
+  > The automatically export mode is turned off by default
 - Manual export: Click "File-Export Marking Results" to manually export the label.
 - Close application export
-### Export Partial Recognition Results
+### 3.4 Export Partial Recognition Results
+For some data that are difficult to recognize, the recognition results will not be exported by **unchecking** the corresponding tags in the recognition results checkbox. The unchecked recognition result is saved as `True` in the `difficult` variable in the label file `label.txt`.
+> *Note: The status of the checkboxes in the recognition results still needs to be saved manually by clicking Save Button.*
+### 3.5 Dataset division
-For some data that are difficult to recognize, the recognition results will not be exported by **unchecking** the corresponding tags in the recognition results checkbox.
+- Enter the following command in the terminal to execute the dataset division script:
-*Note: The status of the checkboxes in the recognition results still needs to be saved manually by clicking Save Button.*
+  ```
+  cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
+  python gen_ocr_train_val_test.py --trainValTestRatio 6:2:2 --labelRootPath ../train_data/label --detRootPath ../train_data/det --recRootPath ../train_data/rec
+  ```
+  Parameter Description:
+  - `trainValTestRatio` is the division ratio of the number of images in the training set, validation set, and test set, set according to your actual situation, the default is `6:2:2`
+  - `labelRootPath` is the storage path of the dataset labeled by PPOCRLabel, the default is `../train_data/label`
-### Error message
+  - `detRootPath` is the path where the text detection dataset is divided according to the dataset marked by PPOCRLabel. The default is `../train_data/det`
+  - `recRootPath` is the path where the character recognition dataset is divided according to the dataset marked by PPOCRLabel. The default is `../train_data/rec`
+### 3.6 Error message
 - If paddleocr is installed with whl, it has a higher priority than calling PaddleOCR class with paddleocr.py, which may cause an exception if whl package is not updated.
@@ -204,6 +227,8 @@ For some data that are difficult to recognize, the recognition results will not
    pip install opencv-contrib-python-headless==4.2.0.32
    ```
-### Related
+### 4. Related
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)
\ No newline at end of file
--- a/PPOCRLabel/README_ch.md
+++ b/PPOCRLabel/README_ch.md
@@ -2,14 +2,17 @@
 # PPOCRLabel
-PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置PPOCR模型对数据自动标注和重新识别。使用python3和pyqt5编写，支持矩形框标注和四点标注模式，导出格式可直接用于PPOCR检测和识别模型的训练。
+PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置PP-OCR模型对数据自动标注和重新识别。使用Python3和PyQT5编写，支持矩形框标注和四点标注模式，导出格式可直接用于PaddleOCR检测和识别模型的训练。
 <img src="./data/gif/steps.gif" width="100%"/>
 #### 近期更新
+- 2021.11.17：
+  - 新增支持通过whl包安装和启动PPOCRLabel（by [d2623587501](https://github.com/d2623587501)）
+  - 标注数据集切分：对标注数据进行训练、验证与测试集划分（参考下方3.5节，by [MrCuiHao](https://github.com/MrCuiHao)）
 - 2021.8.11：
-  - 新增功能：打开数据所在文件夹、图像旋转（注意：旋转前的图片上不能存在标记框）（by [Wei-JL](https://github.com/Wei-JL)）
+  - 新增功能：打开数据所在文件夹、右键图像旋转90度（注意：旋转前的图片上不能存在标记框，by [Wei-JL](https://github.com/Wei-JL)）
  - 新增快捷键说明（帮助-快捷键）、修复批处理下的方向快捷键移动功能（by [d2623587501](https://github.com/d2623587501)）
 - 2021.2.5：新增批处理与撤销功能（by [Evezerest](https://github.com/Evezerest))
  - **批处理功能**：按住Ctrl键选择标记框后可批量移动、复制、删除、重新识别。
@@ -21,85 +24,75 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置P
  - 识别结果更改为单击修改。（如果无法修改，请切换为系统自带输入法，或再次切回原输入法）
 - 2020.12.18： 支持对单个标记框进行重新识别（by [ninetailskim](https://github.com/ninetailskim)），完善快捷键。
-#### 尽请期待
- 锁定框模式：针对同一场景数据，被锁定的检测框的大小与位置能在不同图片之间传递。
 如果您对以上内容感兴趣或对完善工具有不一样的想法，欢迎加入我们的SIG队伍与我们共同开发。可以在[此处](https://github.com/PaddlePaddle/PaddleOCR/issues/1728)完成问卷和前置任务，经过我们确认相关内容后即可正式加入，享受SIG福利，共同为OCR开源事业贡献（特别说明：针对PPOCRLabel的改进也属于PaddleOCR前置任务）
-## 安装
-### 1. 环境搭建
+## 1. 安装与运行
-#### 安装PaddlePaddle
+### 1.1 安装PaddlePaddle
 ```bash
 pip3 install --upgrade pip
-如果您的机器安装的是CUDA9或CUDA10，请运行以下命令安装
+# 如果您的机器安装的是CUDA9或CUDA10，请运行以下命令安装
 python3 -m pip install paddlepaddle-gpu -i https://mirror.baidu.com/pypi/simple
-如果您的机器是CPU，请运行以下命令安装
+# 如果您的机器是CPU，请运行以下命令安装
 python3 -m pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple
 ```
 更多的版本需求，请参照[安装文档](https://www.paddlepaddle.org.cn/install/quick)中的说明进行操作。
-#### **安装PaddleOCR**
+### 1.2 安装与运行PPOCRLabel
-```bash
+PPOCRLabel可通过whl包与Python脚本两种方式启动，whl包形式启动更加方便，python脚本启动便于二次开发
-【推荐】git clone https://github.com/PaddlePaddle/PaddleOCR
-如果因为网络问题无法pull成功，也可选择使用码云上的托管：
+#### 1.2.1 通过whl包安装与运行
-git clone https://gitee.com/paddlepaddle/PaddleOCR
+##### Windows
-注：码云托管代码可能无法实时同步本github项目更新，存在3~5天延时，请优先使用推荐方式。
+```bash
+pip install PPOCRLabel  # 安装
+PPOCRLabel --lang ch  # 运行
 ```
+> 注意：通过whl包安装PPOCRLabel会自动下载 `paddleocr` whl包，其中shapely依赖可能会出现 `[winRrror 126] 找不到指定模块的问题。` 的错误，建议从[这里](https://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely)下载并安装
-#### 安装第三方库
+##### Ubuntu Linux
 ```bash
-cd PaddleOCR
+pip3 install PPOCRLabel
-pip3 install -r requirements.txt
+pip3 install trash-cli
+PPOCRLabel --lang ch
 ```
-注意，windows环境下，建议从[这里](https://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely)下载shapely安装包完成安装， 直接通过pip安装的shapely库可能出现`[winRrror 126] 找不到指定模块的问题`。
+##### MacOS
-### 2. 安装PPOCRLabel
-#### Windows
 ```bash
-pip install pyqt5
+pip3 install PPOCRLabel
-cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
+pip3 install opencv-contrib-python-headless==4.2.0.32 # 如果下载过慢请添加"-i https://mirror.baidu.com/pypi/simple"
-python PPOCRLabel.py --lang ch
+PPOCRLabel --lang ch # 启动
 ```
-#### Ubuntu Linux
+#### 1.2.2 本地构建whl包并安装
 ```bash
-pip3 install pyqt5
+cd PaddleOCR/PPOCRLabel
-pip3 install trash-cli
+python3 setup.py bdist_wheel 
-cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
+pip3 install dist/PPOCRLabel-1.0.0-py2.py3-none-any.whl -i https://mirror.baidu.com/pypi/simple
-python3 PPOCRLabel.py --lang ch
 ```
-#### MacOS
+#### 1.2.3 通过Python脚本运行PPOCRLabel
+如果您对PPOCRLabel文件有所更改，通过Python脚本运行会更加方面的看到更改的结果
 ```bash
-pip3 install pyqt5
+cd ./PPOCRLabel  # 切换到PPOCRLabel目录
-pip3 uninstall opencv-python # 由于mac版本的opencv与pyqt有冲突，需先手动卸载opencv
+python PPOCRLabel.py --lang ch
-pip3 install opencv-contrib-python-headless==4.2.0.32 # 安装headless版本的open-cv
-cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
-python3 PPOCRLabel.py --lang ch
 ```
-## 使用
+## 2. 使用
-### 操作步骤
+### 2.1 操作步骤
 1. 安装与运行：使用上述命令安装与运行程序。
 2. 打开文件夹：在菜单栏点击 “文件” - "打开目录" 选择待标记图片的文件夹<sup>[1]</sup>.
@@ -112,7 +105,7 @@ python3 PPOCRLabel.py --lang ch
 9. 删除：点击 “删除图像”，图片将会被删除至回收站。
 10. 导出结果：用户可以通过菜单中“文件-导出标记结果”手动导出，同时也可以点击“文件 - 自动导出标记结果”开启自动导出。手动确认过的标记将会被存放在所打开图片文件夹下的*Label.txt*中。在菜单栏点击 “文件” - "导出识别结果"后，会将此类图片的识别训练数据保存在*crop_img*文件夹下，识别标签保存在*rec_gt.txt*中<sup>[4]</sup>。
-### 注意
+### 2.2 注意
 [1] PPOCRLabel以文件夹为基本标记单位，打开待标记的图片文件夹后，不会在窗口栏中显示图片，而是在点击 "选择文件夹" 之后直接将文件夹下的图片导入到程序中。
@@ -130,9 +123,11 @@ python3 PPOCRLabel.py --lang ch
 |  rec_gt.txt   | 识别标签。可直接用于PPOCR识别模型训练。需用户手动点击菜单栏“文件” - "导出识别结果"后产生。 |
 |   crop_img    |   识别数据。按照检测框切割后的图片。与rec_gt.txt同时产生。   |
-## 说明
-### 快捷键
+## 3. 说明
+### 3.1 快捷键
 | 快捷键           | 说明                         |
 | ---------------- | ---------------------------- |
@@ -152,29 +147,53 @@ python3 PPOCRLabel.py --lang ch
 | Ctrl--           | 放大                         |
 | ↑→↓←             | 移动标记框                   |
-### 内置模型
+### 3.2 内置模型
 - 默认模型：PPOCRLabel默认使用PaddleOCR中的中英文超轻量OCR模型，支持中英文与数字识别，多种语言检测。
 - 模型语言切换：用户可通过菜单栏中 "PaddleOCR" - "选择模型" 切换内置模型语言，目前支持的语言包括法文、德文、韩文、日文。具体模型下载链接可参考[PaddleOCR模型列表](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/models_list.md).
- - 自定义模型：用户可根据[自定义模型代码使用](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/whl.md#%E8%87%AA%E5%AE%9A%E4%B9%89%E6%A8%A1%E5%9E%8B)，通过修改PPOCRLabel.py中针对[PaddleOCR类的实例化](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/PPOCRLabel/PPOCRLabel.py#L110)替换成自己训练的模型。
+ - **自定义模型**：如果用户想将内置模型更换为自己的推理模型，可根据[自定义模型代码使用](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/whl.md#%E8%87%AA%E5%AE%9A%E4%B9%89%E6%A8%A1%E5%9E%8B)，通过修改PPOCRLabel.py中针对[PaddleOCR类的实例化](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/PPOCRLabel/PPOCRLabel.py#L116) 实现，例如指定检测模型：`self.ocr = PaddleOCR(det=True, cls=True, use_gpu=gpu, lang=lang) `，在 `det_model_dir` 中传入  自己的模型即可。 
-### 导出标记结果
+### 3.3 导出标记结果
 PPOCRLabel支持三种导出方式：
 - 自动导出：点击“文件 - 自动导出标记结果”后，用户每确认过一张图片，程序自动将标记结果写入Label.txt中。若未开启此选项，则检测到用户手动确认过5张图片后进行自动导出。
+  > 默认情况下自动导出功能为关闭状态
 - 手动导出：点击“文件 - 导出标记结果”手动导出标记。
 - 关闭应用程序导出
-### 导出部分识别结果
+### 3.4 导出部分识别结果
+针对部分难以识别的数据，通过在识别结果的复选框中**取消勾选**相应的标记，其识别结果不会被导出。被取消勾选的识别结果在标记文件 `label.txt` 中的 `difficult` 变量保存为 `True` 。
+> *注意：识别结果中的复选框状态仍需用户手动点击确认后才能保留*
+### 3.5 数据集划分
+在终端中输入以下命令执行数据集划分脚本：
+```
+cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
+python gen_ocr_train_val_test.py --trainValTestRatio 6:2:2 --labelRootPath ../train_data/label --detRootPath ../train_data/det --recRootPath ../train_data/rec
+```
+参数说明：
+- `trainValTestRatio` 是训练集、验证集、测试集的图像数量划分比例，根据实际情况设定，默认是`6:2:2`
-针对部分难以识别的数据，通过在识别结果的复选框中**取消勾选**相应的标记，其识别结果不会被导出。
+- `labelRootPath` 是PPOCRLabel标注的数据集存放路径，默认是`../train_data/label`
-*注意：识别结果中的复选框状态仍需用户手动点击确认后才能保留*
+- `detRootPath` 是根据PPOCRLabel标注的数据集划分后的文本检测数据集存放的路径，默认是`../train_data/det `
+- `recRootPath` 是根据PPOCRLabel标注的数据集划分后的字符识别数据集存放的路径，默认是`../train_data/rec`
+### 3.6 错误提示
-### 错误提示
 - 如果同时使用whl包安装了paddleocr，其优先级大于通过paddleocr.py调用PaddleOCR类，whl包未更新时会导致程序异常。
 - PPOCRLabel**不支持对中文文件名**的图片进行自动标注。
@@ -194,6 +213,8 @@ PPOCRLabel支持三种导出方式：
    pip install opencv-contrib-python-headless==4.2.0.32
    ```
-### 参考资料
+### 4. 参考资料
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)
--- a/PPOCRLabel/gen_ocr_train_val_test.py
+++ b/PPOCRLabel/gen_ocr_train_val_test.py
+# coding:utf8
+import os
+import shutil
+import random
+import argparse
+# 删除划分的训练集、验证集、测试集文件夹，重新创建一个空的文件夹
+def isCreateOrDeleteFolder(path, flag):
+    flagPath = os.path.join(path, flag)
+    if os.path.exists(flagPath):
+        shutil.rmtree(flagPath)
+    os.makedirs(flagPath)
+    flagAbsPath = os.path.abspath(flagPath)
+    return flagAbsPath
+def splitTrainVal(root, dir, absTrainRootPath, absValRootPath, absTestRootPath, trainTxt, valTxt, testTxt, flag):
+    # 按照指定的比例划分训练集、验证集、测试集
+    labelPath = os.path.join(root, dir)
+    labelAbsPath = os.path.abspath(labelPath)
+    if flag == "det":
+        labelFilePath = os.path.join(labelAbsPath, args.detLabelFileName)
+    elif flag == "rec":
+        labelFilePath = os.path.join(labelAbsPath, args.recLabelFileName)
+    labelFileRead = open(labelFilePath, "r", encoding="UTF-8")
+    labelFileContent = labelFileRead.readlines()
+    random.shuffle(labelFileContent)
+    labelRecordLen = len(labelFileContent)
+    for index, labelRecordInfo in enumerate(labelFileContent):
+        imageRelativePath = labelRecordInfo.split('\t')[0]
+        imageLabel = labelRecordInfo.split('\t')[1]
+        imageName = os.path.basename(imageRelativePath)
+        if flag == "det":
+            imagePath = os.path.join(labelAbsPath, imageName)
+        elif flag == "rec":
+            imagePath = os.path.join(labelAbsPath, "{}\\{}".format(args.recImageDirName, imageName))
+        # 按预设的比例划分训练集、验证集、测试集
+        trainValTestRatio = args.trainValTestRatio.split(":")
+        trainRatio = eval(trainValTestRatio[0]) / 10
+        valRatio = trainRatio + eval(trainValTestRatio[1]) / 10
+        curRatio = index / labelRecordLen
+        if curRatio < trainRatio:
+            imageCopyPath = os.path.join(absTrainRootPath, imageName)
+            shutil.copy(imagePath, imageCopyPath)
+            trainTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
+        elif curRatio >= trainRatio and curRatio < valRatio:
+            imageCopyPath = os.path.join(absValRootPath, imageName)
+            shutil.copy(imagePath, imageCopyPath)
+            valTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
+        else:
+            imageCopyPath = os.path.join(absTestRootPath, imageName)
+            shutil.copy(imagePath, imageCopyPath)
+            testTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
+# 删掉存在的文件
+def removeFile(path):
+    if os.path.exists(path):
+        os.remove(path)
+def genDetRecTrainVal(args):
+    detAbsTrainRootPath = isCreateOrDeleteFolder(args.detRootPath, "train")
+    detAbsValRootPath = isCreateOrDeleteFolder(args.detRootPath, "val")
+    detAbsTestRootPath = isCreateOrDeleteFolder(args.detRootPath, "test")
+    recAbsTrainRootPath = isCreateOrDeleteFolder(args.recRootPath, "train")
+    recAbsValRootPath = isCreateOrDeleteFolder(args.recRootPath, "val")
+    recAbsTestRootPath = isCreateOrDeleteFolder(args.recRootPath, "test")
+    removeFile(os.path.join(args.detRootPath, "train.txt"))
+    removeFile(os.path.join(args.detRootPath, "val.txt"))
+    removeFile(os.path.join(args.detRootPath, "test.txt"))
+    removeFile(os.path.join(args.recRootPath, "train.txt"))
+    removeFile(os.path.join(args.recRootPath, "val.txt"))
+    removeFile(os.path.join(args.recRootPath, "test.txt"))
+    detTrainTxt = open(os.path.join(args.detRootPath, "train.txt"), "a", encoding="UTF-8")
+    detValTxt = open(os.path.join(args.detRootPath, "val.txt"), "a", encoding="UTF-8")
+    detTestTxt = open(os.path.join(args.detRootPath, "test.txt"), "a", encoding="UTF-8")
+    recTrainTxt = open(os.path.join(args.recRootPath, "train.txt"), "a", encoding="UTF-8")
+    recValTxt = open(os.path.join(args.recRootPath, "val.txt"), "a", encoding="UTF-8")
+    recTestTxt = open(os.path.join(args.recRootPath, "test.txt"), "a", encoding="UTF-8")
+    for root, dirs, files in os.walk(args.labelRootPath):
+        for dir in dirs:
+            splitTrainVal(root, dir, detAbsTrainRootPath, detAbsValRootPath, detAbsTestRootPath, detTrainTxt, detValTxt,
+                          detTestTxt, "det")
+            splitTrainVal(root, dir, recAbsTrainRootPath, recAbsValRootPath, recAbsTestRootPath, recTrainTxt, recValTxt,
+                          recTestTxt, "rec")
+        break
+if __name__ == "__main__":
+    # 功能描述：分别划分检测和识别的训练集、验证集、测试集
+    # 说明：可以根据自己的路径和需求调整参数，图像数据往往多人合作分批标注，每一批图像数据放在一个文件夹内用PPOCRLabel进行标注，
+    # 如此会有多个标注好的图像文件夹汇总并划分训练集、验证集、测试集的需求
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--trainValTestRatio",
+        type=str,
+        default="6:2:2",
+        help="ratio of trainset:valset:testset")
+    parser.add_argument(
+        "--labelRootPath",
+        type=str,
+        default="../train_data/label",
+        help="path to the dataset marked by ppocrlabel, E.g, dataset folder named 1,2,3..."
+    )
+    parser.add_argument(
+        "--detRootPath",
+        type=str,
+        default="../train_data/det",
+        help="the path where the divided detection dataset is placed")
+    parser.add_argument(
+        "--recRootPath",
+        type=str,
+        default="../train_data/rec",
+        help="the path where the divided recognition dataset is placed"
+    )
+    parser.add_argument(
+        "--detLabelFileName",
+        type=str,
+        default="Label.txt",
+        help="the name of the detection annotation file")
+    parser.add_argument(
+        "--recLabelFileName",
+        type=str,
+        default="rec_gt.txt",
+        help="the name of the recognition annotation file"
+    )
+    parser.add_argument(
+        "--recImageDirName",
+        type=str,
+        default="crop_img",
+        help="the name of the folder where the cropped recognition dataset is located"
+    )
+    args = parser.parse_args()
+    genDetRecTrainVal(args)
--- a/PPOCRLabel/libs/resources.py
+++ b/PPOCRLabel/libs/resources.py
--- a/PPOCRLabel/libs/stringBundle.py
+++ b/PPOCRLabel/libs/stringBundle.py
@@ -19,6 +19,9 @@ import sys
 import locale
 from libs.ustr import ustr
+__dir__ = os.path.dirname(os.path.abspath(__file__)) # 获取本程序文件路径
+__dirpath__ = os.path.abspath(os.path.join(__dir__, '../resources/strings'))
 try:
    from PyQt5.QtCore import *
 except ImportError:
@@ -57,7 +60,7 @@ class StringBundle:
    def __createLookupFallbackList(self, localeStr):
        resultPaths = []
-        basePath = ":/strings"
+        basePath = "\strings" if os.name == 'nt' else ":/strings"
        resultPaths.append(basePath)
        if localeStr is not None:
            # Don't follow standard BCP47. Simple fallback
@@ -65,6 +68,7 @@ class StringBundle:
            for tag in tags:
                lastPath = resultPaths[-1]
                resultPaths.append(lastPath + '-' + tag)
+            resultPaths[-1] = __dirpath__ + resultPaths[-1] + ".properties"
        return resultPaths

--- a/PPOCRLabel/libs/utils.py
+++ b/PPOCRLabel/libs/utils.py
@@ -17,6 +17,10 @@ import re
 import sys
 import cv2
 import numpy as np
+import os
+__dir__ = os.path.dirname(os.path.abspath(__file__)) # 获取本程序文件路径
+__iconpath__ = os.path.abspath(os.path.join(__dir__, '../resources/icons'))
 try:
    from PyQt5.QtGui import *
@@ -29,9 +33,9 @@ except ImportError:
 def newIcon(icon, iconSize=None):
    if iconSize is not None:
-        return QIcon(QIcon(':/' + icon).pixmap(iconSize,iconSize))
+        return QIcon(QIcon(__iconpath__ + "/" + icon + ".png").pixmap(iconSize,iconSize))
    else:
-        return QIcon(':/' + icon)
+        return QIcon(__iconpath__ + "/" + icon + ".png")
 def newButton(text, icon=None, slot=None):

--- a/PPOCRLabel/requirements.txt
+++ b/PPOCRLabel/requirements.txt
+pyqt5
+paddleocr
\ No newline at end of file
--- a/PPOCRLabel/resources.qrc
+++ b/PPOCRLabel/resources.qrc
@@ -35,7 +35,7 @@
 <file alias="prev">resources/icons/prev.png</file>
 <file alias="resetall">resources/icons/resetall.png</file>
 <file alias="verify">resources/icons/verify.png</file>
-<file alias="strings">resources/strings/strings.properties</file>
+<file alias="strings">resources/strings/strings-en.properties</file>
 <file alias="strings-zh-CN">resources/strings/strings-zh-CN.properties</file>
 </qresource>
 </RCC>
--- a/PPOCRLabel/resources/strings/strings.properties
+++ b/PPOCRLabel/resources/strings/strings.properties
--- a/PPOCRLabel/setup.py
+++ b/PPOCRLabel/setup.py
-# Copyright (c) <2015-Present> Tzutalin
+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
-# Copyright (C) 2013  MIT, Computer Science and Artificial Intelligence Laboratory. Bryan Russell, Antonio Torralba,
+#
-# William T. Freeman. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
+# Licensed under the Apache License, Version 2.0 (the "License");
-# associated documentation files (the "Software"), to deal in the Software without restriction, including without
+# you may not use this file except in compliance with the License.
-# limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the
+# You may obtain a copy of the License at
-# Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+#
-# The above copyright notice and this permission notice shall be included in all copies or substantial portions of
+#     http://www.apache.org/licenses/LICENSE-2.0
-# the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT
+#
-# NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
+# Unless required by applicable law or agreed to in writing, software
-# SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
+# distributed under the License is distributed on an "AS IS" BASIS,
-# CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# THE SOFTWARE.
+# See the License for the specific language governing permissions and
+# limitations under the License.
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
+from setuptools import setup
+from io import open
-from setuptools import setup, find_packages, Command
-from sys import platform as _platform
+with open('requirements.txt', encoding="utf-8-sig") as f:
-from shutil import rmtree
+    requirements = f.readlines()
-import sys
+    requirements.append('tqdm')
-import os
-here = os.path.abspath(os.path.dirname(__file__))
+def readme():
-NAME = 'labelImg'
+    with open('README.md', encoding="utf-8-sig") as f:
-REQUIRES_PYTHON = '>=3.0.0'
+        README = f.read()
-REQUIRED_DEP = ['pyqt5', 'lxml']
+    return README
-about = {}
-with open(os.path.join(here, 'libs', '__init__.py')) as f:
-    exec(f.read(), about)
-with open('README.rst') as readme_file:
-    readme = readme_file.read()
-with open('HISTORY.rst') as history_file:
-    history = history_file.read()
-# OS specific settings
-SET_REQUIRES = []
-if _platform == "linux" or _platform == "linux2":
-   # linux
-   print('linux')
-elif _platform == "darwin":
-   # MAC OS X
-   SET_REQUIRES.append('py2app')
-required_packages = find_packages()
-required_packages.append('labelImg')
-APP = [NAME + '.py']
-OPTIONS = {
-    'argv_emulation': True,
-    'iconfile': 'resources/icons/app.icns'
-}
-class UploadCommand(Command):
-    """Support setup.py upload."""
-    description=readme + '\n\n' + history,
-    user_options = []
-    @staticmethod
-    def status(s):
-        """Prints things in bold."""
-        print('\033[1m{0}\033[0m'.format(s))
-    def initialize_options(self):
-        pass
-    def finalize_options(self):
-        pass
-    def run(self):
-        try:
-            self.status('Removing previous builds…')
-            rmtree(os.path.join(here, 'dist'))
-        except OSError:
-            self.status('Fail to remove previous builds..')
-            pass
-        self.status('Building Source and Wheel (universal) distribution…')
-        os.system(
-            '{0} setup.py sdist bdist_wheel --universal'.format(sys.executable))
-        self.status('Uploading the package to PyPI via Twine…')
-        os.system('twine upload dist/*')
-        self.status('Pushing git tags…')
-        os.system('git tag -d v{0}'.format(about['__version__']))
-        os.system('git tag v{0}'.format(about['__version__']))
-        # os.system('git push --tags')
-        sys.exit()
 setup(
-    app=APP,
+    name='PPOCRLabel',
-    name=NAME,
+    packages=['PPOCRLabel'],
-    version=about['__version__'],
+    package_data = {'PPOCRLabel': ['libs/*','resources/strings/*','resources/icons/*']},
-    description="LabelImg is a graphical image annotation tool and label object bounding boxes in images",
+    package_dir={'PPOCRLabel': ''},
-    long_description=readme + '\n\n' + history,
-    author="TzuTa Lin",
-    author_email='tzu.ta.lin@gmail.com',
-    url='https://github.com/tzutalin/labelImg',
-    python_requires=REQUIRES_PYTHON,
-    package_dir={'labelImg': '.'},
-    packages=required_packages,
-    entry_points={
-        'console_scripts': [
-            'labelImg=labelImg.labelImg:main'
-        ]
-    },
    include_package_data=True,
-    install_requires=REQUIRED_DEP,
+    entry_points={"console_scripts": ["PPOCRLabel= PPOCRLabel.PPOCRLabel:main"]},
-    license="MIT license",
+    version='1.0.0',
-    zip_safe=False,
+    install_requires=requirements,
-    keywords='labelImg labelTool development annotation deeplearning',
+    license='Apache License 2.0',
+    description='PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, with built-in PPOCR model to automatically detect and re-recognize data. It is written in python3 and pyqt5, supporting rectangular box annotation and four-point annotation modes. Annotations can be directly used for the training of PPOCR detection and recognition models',
+    long_description=readme(),
+    long_description_content_type='text/markdown',
+    url='https://github.com/PaddlePaddle/PaddleOCR',
+    download_url='https://github.com/PaddlePaddle/PaddleOCR.git',
+    keywords=[
+        'ocr textdetection textrecognition paddleocr crnn east star-net rosetta ocrlite db chineseocr chinesetextdetection chinesetextrecognition'
+    ],
    classifiers=[
-        'Development Status :: 5 - Production/Stable',
+        'Intended Audience :: Developers', 'Operating System :: OS Independent',
-        'Intended Audience :: Developers',
-        'License :: OSI Approved :: MIT License',
        'Natural Language :: English',
-        'Programming Language :: Python :: 3',
-        'Programming Language :: Python :: 3.3',
-        'Programming Language :: Python :: 3.4',
-        'Programming Language :: Python :: 3.5',
        'Programming Language :: Python :: 3.6',
-        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.7', 'Topic :: Utilities'
-    ],
+    ], )
-    package_data={'data/predefined_classes.txt': ['data/predefined_classes.txt']},
\ No newline at end of file
-    options={'py2app': OPTIONS},
-    setup_requires=SET_REQUIRES,
-    # $ setup.py publish support.
-    cmdclass={
-        'upload': UploadCommand,
-    }
-)
--- a/PTDN/configs/ppocr_rec_mobile_params.txt
+++ b/PTDN/configs/ppocr_rec_mobile_params.txt
-===========================train_params===========================
-model_name:ocr_rec
-python:python3.7
-gpu_list:0|0,1
-Global.use_gpu:True|True
-Global.auto_cast:null
-Global.epoch_num:lite_train_infer=2|whole_train_infer=300
-Global.save_model_dir:./output/
-Train.loader.batch_size_per_card:lite_train_infer=128|whole_train_infer=128
-Global.pretrained_model:null
-train_model_name:latest
-train_infer_img_dir:./inference/rec_inference
-null:null
-##
-trainer:norm_train|pact_train
-norm_train:tools/train.py -c configs/rec/rec_icdar15_train.yml -o
-pact_train:deploy/slim/quantization/quant.py -c configs/rec/rec_icdar15_train.yml -o
-fpgm_train:null
-distill_train:null
-null:null
-null:null
-##
-===========================eval_params===========================
-eval:tools/eval.py -c configs/rec/rec_icdar15_train.yml -o
-null:null
-##
-===========================infer_params===========================
-Global.save_inference_dir:./output/
-Global.pretrained_model:
-norm_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
-quant_export:deploy/slim/quantization/export_model.py -c configs/rec/rec_icdar15_train.yml -o
-fpgm_export:null
-distill_export:null
-export1:null
-export2:null
-##
-infer_model:./inference/ch_ppocr_mobile_v2.0_rec_infer/
-infer_export:null
-infer_quant:False
-inference:tools/infer/predict_rec.py
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
-null:null
-===========================cpp_infer_params===========================
-use_opencv:True
-infer_model:./inference/ch_ppocr_mobile_v2.0_rec_infer/
-infer_quant:False
-inference:./deploy/cpp_infer/build/ppocr rec
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1
--use_tensorrt:False|True
--precision:fp32|fp16
--rec_model_dir:
--image_dir:./inference/rec_inference/
-null:null
--benchmark:True
-===========================serving_params===========================
-model_name:ocr_rec
-python:python3.7
-trans_model:-m paddle_serving_client.convert
--dirname:./inference/ch_ppocr_mobile_v2.0_rec_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/pdserving/ppocr_rec_mobile_2.0_serving/
--serving_client:./deploy/pdserving/ppocr_rec_mobile_2.0_client/
-serving_dir:./deploy/pdserving
-web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency=1
-op.rec.local_service_conf.devices:null|0
-op.rec.local_service_conf.use_mkldnn:True|False
-op.rec.local_service_conf.thread_num:1|6
-op.rec.local_service_conf.use_trt:False|True
-op.rec.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_http_client.py --image_dir=../../doc/imgs_words_en
--- a/PTDN/configs/ppocr_rec_server_params.txt
+++ b/PTDN/configs/ppocr_rec_server_params.txt
-===========================train_params===========================
-model_name:ocr_server_rec
-python:python3.7
-gpu_list:0|0,1
-Global.use_gpu:True|True
-Global.auto_cast:null
-Global.epoch_num:lite_train_infer=2|whole_train_infer=300
-Global.save_model_dir:./output/
-Train.loader.batch_size_per_card:lite_train_infer=128|whole_train_infer=128
-Global.pretrained_model:null
-train_model_name:latest
-train_infer_img_dir:./inference/rec_inference
-null:null
-##
-trainer:norm_train|pact_train
-norm_train:tools/train.py -c tests/configs/rec_icdar15_r34_train.yml -o
-pact_train:deploy/slim/quantization/quant.py -c tests/configs/rec_icdar15_r34_train.yml -o
-fpgm_train:null
-distill_train:null
-null:null
-null:null
-##
-===========================eval_params===========================
-eval:tools/eval.py -c tests/configs/rec_icdar15_r34_train.yml -o
-null:null
-##
-===========================infer_params===========================
-Global.save_inference_dir:./output/
-Global.pretrained_model:
-norm_export:tools/export_model.py -c tests/configs/rec_icdar15_r34_train.yml -o
-quant_export:deploy/slim/quantization/export_model.py -c tests/configs/rec_icdar15_r34_train.yml -o
-fpgm_export:null
-distill_export:null
-export1:null
-export2:null
-##
-infer_model:./inference/ch_ppocr_server_v2.0_rec_infer/
-infer_export:null
-infer_quant:False
-inference:tools/infer/predict_rec.py
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
-null:null
-===========================cpp_infer_params===========================
-use_opencv:True
-infer_model:./inference/ch_ppocr_server_v2.0_rec_infer/
-infer_quant:False
-inference:./deploy/cpp_infer/build/ppocr rec
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1
--use_tensorrt:False|True
--precision:fp32|fp16
--rec_model_dir:
--image_dir:./inference/rec_inference/
-null:null
--benchmark:True
-===========================serving_params===========================
-model_name:ocr_server_rec
-python:python3.7
-trans_model:-m paddle_serving_client.convert
--dirname:./inference/ch_ppocr_server_v2.0_rec_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/pdserving/ppocr_rec_mobile_2.0_serving/
--serving_client:./deploy/pdserving/ppocr_rec_mobile_2.0_client/
-serving_dir:./deploy/pdserving
-web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency=1
-op.rec.local_service_conf.devices:null|0
-op.rec.local_service_conf.use_mkldnn:True|False
-op.rec.local_service_conf.thread_num:1|6
-op.rec.local_service_conf.use_trt:False|True
-op.rec.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_http_client.py --image_dir=../../doc/imgs_words_en
--- a/PTDN/docs/install.md
+++ b/PTDN/docs/install.md
-## 环境配置
-本教程适用于PTDN目录下基础功能测试的运行环境搭建。
-推荐环境：
- CUDA 10.1
- CUDNN 7.6
- TensorRT 6.1.0.5 / 7.1
-推荐docker镜像安装，按照如下命令创建镜像，当前目录映射到镜像中的`/paddle`目录下
-```
-nvidia-docker run --name paddle -it -v $PWD:/paddle paddlepaddle/paddle:latest-dev-cuda10.1-cudnn7-gcc82 /bin/bash
-cd /paddle
-# 安装带TRT的paddle
-pip3.7 install https://paddle-wheel.bj.bcebos.com/with-trt/2.1.3/linux-gpu-cuda10.1-cudnn7-mkl-gcc8.2-trt6-avx/paddlepaddle_gpu-2.1.3.post101-cp37-cp37m-linux_x86_64.whl
-# 安装AutoLog
-git clone https://github.com/LDOUBLEV/AutoLog
-cd AutoLog
-pip3.7 install -r requirements.txt
-python3.7 setup.py bdist_wheel
-pip3.7 install ./dist/auto_log-1.0.0-py3-none-any.whl
-# 下载OCR代码
-cd ../
-git clone https://github.com/PaddlePaddle/PaddleOCR
-```
-安装PaddleOCR依赖：
-```
-cd PaddleOCR
-pip3.7 install -r requirements.txt
-```
-## FAQ :
-Q. You are using Paddle compiled with TensorRT, but TensorRT dynamic library is not found. Ignore this if TensorRT is not needed.
-A. 问题一般是当前安装paddle版本带TRT，但是本地环境找不到TensorRT的预测库，需要下载TensorRT库，解压后设置环境变量LD_LIBRARY_PATH;
-如：
-```
-export LD_LIBRARY_PATH=/usr/local/python3.7.0/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/paddle/package/TensorRT-6.0.1.5/lib
-```
-或者问题是下载的TensorRT版本和当前paddle中编译的TRT版本不匹配，需要下载版本相符的TRT。
--- a/README.md
+++ b/README.md
@@ -25,7 +25,7 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools
 **Recent updates**
- PaddleOCR R&D team would like to share the key points of PP-OCRv2, at 20:15 pm on September 8th, [Live Address](https://live.bilibili.com/21689802).
+- PaddleOCR R&D team would like to share the key points of PP-OCRv2, at 20:15 pm on September 8th, [Course Address](https://aistudio.baidu.com/aistudio/education/group/info/6758).
 - 2021.9.7 release PaddleOCR v2.3, [PP-OCRv2](#PP-OCRv2) is proposed. The inference speed of PP-OCRv2 is 220% higher than that of PP-OCR server in CPU device. The F-score of PP-OCRv2 is 7% higher than that of PP-OCR mobile.
 - 2021.8.3 released PaddleOCR v2.2, add a new structured documents analysis toolkit, i.e., [PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README.md), support layout analysis and table recognition (One-key to export chart images to Excel files).
 - 2021.4.8 release end-to-end text recognition algorithm [PGNet](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf) which is published in AAAI 2021. Find tutorial [here](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/pgnet_en.md)；release multi language recognition [models](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md), support more than 80 languages recognition; especically, the performance of [English recognition model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/models_list_en.md#English) is Optimized.
@@ -86,9 +86,9 @@ Mobile DEMO experience (based on EasyEdge and Paddle-Lite, supports iOS and Andr
 | Model introduction                                           | Model name                   | Recommended scene | Detection model                                              | Direction classifier                                         | Recognition model                                            |
 | ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
-| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） |  ch_PP-OCRv2_xx |Mobile&Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/ch/ch_PP-OCRv2_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
+| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） |  ch_PP-OCRv2_xx |Mobile & Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/ch/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
-| Chinese and English ultra-lightweight PP-OCR model (9.4M)       | ch_ppocr_mobile_v2.0_xx      | Mobile & server   |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar)      |
+| Chinese and English ultra-lightweight PP-OCR model (9.4M)       | ch_ppocr_mobile_v2.0_xx      | Mobile & server   |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar)      |
-| Chinese and English general PP-OCR model (143.4M)               | ch_ppocr_server_v2.0_xx      | Server            |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_traingit.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar)  |  
+| Chinese and English general PP-OCR model (143.4M)               | ch_ppocr_server_v2.0_xx      | Server            |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_traingit.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar)  |
 For more model downloads (including multiple languages), please refer to [PP-OCR series model downloads](./doc/doc_en/models_list_en.md).
@@ -102,7 +102,6 @@ For a new language request, please refer to [Guideline for new language_requests
 - PP-OCR Industry Landing: from Training to Deployment
    - [PP-OCR Model and Configuration](./doc/doc_en/models_and_config_en.md)
        - [PP-OCR Model Download](./doc/doc_en/models_list_en.md)
-        - [Yml Configuration](./doc/doc_en/config_en.md)
        - [Python Inference for PP-OCR Model Library](./doc/doc_en/inference_ppocr_en.md)
    - [PP-OCR Training](./doc/doc_en/training_en.md)
        - [Text Detection](./doc/doc_en/detection_en.md)
@@ -119,7 +118,7 @@ For a new language request, please refer to [Guideline for new language_requests
    - [Table Recognition](./ppstructure/table/README.md)
 - Academic Circles
    - [Two-stage Algorithm](./doc/doc_en/algorithm_overview_en.md)
-    - [PGNet Algorithm](./doc/doc_en/algorithm_overview_en.md)
+    - [PGNet Algorithm](./doc/doc_en/pgnet_en.md)
    - [Python Inference](./doc/doc_en/inference_en.md)
 - Data Annotation and Synthesis
    - [Semi-automatic Annotation Tool: PPOCRLabel](./PPOCRLabel/README.md)

--- a/README_ch.md
+++ b/README_ch.md
@@ -24,7 +24,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 **近期更新**
- PaddleOCR研发团队对最新发版内容技术深入解读，9月8日晚上20:15，[直播地址](https://live.bilibili.com/21689802)。
+- PaddleOCR研发团队对最新发版内容技术深入解读，9月8日晚上20:15，[课程回放](https://aistudio.baidu.com/aistudio/education/group/info/6758)。
 - 2021.9.7 发布PaddleOCR v2.3，发布[PP-OCRv2](#PP-OCRv2)，CPU推理速度相比于PP-OCR server提升220%；效果相比于PP-OCR mobile 提升7%。
 - 2021.8.3 发布PaddleOCR v2.2，新增文档结构分析[PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README_ch.md)工具包，支持版面分析与表格识别（含Excel导出）。
 - 2021.6.29 [FAQ](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/FAQ.md)新增5个高频问题，总数248个，每周一都会更新，欢迎大家持续关注。
@@ -81,9 +81,9 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 | 模型简介     | 模型名称     |推荐场景          | 检测模型 | 方向分类器 | 识别模型 |
 | ------------ | --------------- | ----------------|---- | ---------- | -------- |
-| 中英文超轻量PP-OCRv2模型（13.0M） |  ch_PP-OCRv2_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
+| 中英文超轻量PP-OCRv2模型（13.0M） |  ch_PP-OCRv2_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
-| 中英文超轻量PP-OCR mobile模型（9.4M） | ch_ppocr_mobile_v2.0_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar)      |
+| 中英文超轻量PP-OCR mobile模型（9.4M） | ch_ppocr_mobile_v2.0_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar)      |
-| 中英文通用PP-OCR server模型（143.4M）   |ch_ppocr_server_v2.0_xx|服务器端 |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar)    |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar)  |  
+| 中英文通用PP-OCR server模型（143.4M）   |ch_ppocr_server_v2.0_xx|服务器端 |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar)    |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar)  |
 更多模型下载（包括多语言），可以参考[PP-OCR 系列模型下载](./doc/doc_ch/models_list.md)
@@ -94,7 +94,6 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 - PP-OCR产业落地：从训练到部署
    - [PP-OCR模型与配置文件](./doc/doc_ch/models_and_config.md)
        - [PP-OCR模型下载](./doc/doc_ch/models_list.md)
-        - [配置文件内容与生成](./doc/doc_ch/config.md)
        - [PP-OCR模型库快速推理](./doc/doc_ch/inference_ppocr.md)
    - [PP-OCR模型训练](./doc/doc_ch/training.md)
        - [文本检测](./doc/doc_ch/detection.md)
@@ -109,15 +108,16 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 - [PP-Structure信息提取](./ppstructure/README_ch.md)
    - [版面分析](./ppstructure/layout/README_ch.md)
    - [表格识别](./ppstructure/table/README_ch.md)
+- OCR学术圈
+    - [两阶段模型介绍与下载](./doc/doc_ch/algorithm_overview.md)
+    - [端到端PGNet算法](./doc/doc_ch/pgnet.md)
+    - [基于Python脚本预测引擎推理](./doc/doc_ch/inference.md)
+    - [使用PaddleOCR架构添加新算法](./doc/doc_ch/add_new_algorithm.md)
 - 数据标注与合成
    - [半自动标注工具PPOCRLabel](./PPOCRLabel/README_ch.md)
    - [数据合成工具Style-Text](./StyleText/README_ch.md)
    - [其它数据标注工具](./doc/doc_ch/data_annotation.md)
    - [其它数据合成工具](./doc/doc_ch/data_synthesis.md)
- OCR学术圈
-    - [两阶段模型介绍与下载](./doc/doc_ch/algorithm_overview.md)
-    - [端到端PGNet算法](./doc/doc_ch/pgnet.md)
-    - [基于Python脚本预测引擎推理](./doc/doc_ch/inference.md)
 - 数据集
    - [通用中英文OCR数据集](./doc/doc_ch/datasets.md)
    - [手写中文OCR数据集](./doc/doc_ch/handwritten_datasets.md)

--- a/benchmark/readme.md
+++ b/benchmark/readme.md
-# PaddleOCR DB/EAST 算法训练benchmark测试
+# PaddleOCR DB/EAST/PSE 算法训练benchmark测试
 PaddleOCR/benchmark目录下的文件用于获取并分析训练日志。
 训练采用icdar2015数据集，包括1000张训练图像和500张测试图像。模型配置采用resnet18_vd作为backbone，分别训练batch_size=8和batch_size=16的情况。
@@ -28,7 +28,3 @@ det_res18_db_v2.0_sp_bs8_fp32_1
 det_res18_db_v2.0_mp_bs16_fp32_1
 det_res18_db_v2.0_mp_bs8_fp32_1
 ```
--- a/benchmark/run_benchmark_det.sh
+++ b/benchmark/run_benchmark_det.sh
@@ -6,27 +6,35 @@ function _set_params(){
    run_mode=${1:-"sp"}          # 单卡sp|多卡mp
    batch_size=${2:-"64"}
    fp_item=${3:-"fp32"}         # fp32|fp16
-    max_iter=${4:-"500"}       # 可选，如果需要修改代码提前中断
+    max_epoch=${4:-"10"}         # 可选，如果需要修改代码提前中断
-    model_name=${5:-"model_name"}
+    model_item=${5:-"model_item"}
    run_log_path=${TRAIN_LOG_DIR:-$(pwd)}  # TRAIN_LOG_DIR 后续QA设置该参数
+#   日志解析所需参数
+    base_batch_size=${batch_size}
+    mission_name="OCR"
+    direction_id="0"
+    ips_unit="images/sec"
+    skip_steps=2                 # 解析日志，有些模型前几个step耗时长，需要跳过                                    (必填)
+    keyword="ips:"               # 解析日志，筛选出数据所在行的关键字                                             (必填)
+    index="1"
+    model_name=${model_item}_${run_mode}_bs${batch_size}_${fp_item}        # model_item 用于yml文件名匹配，model_name 用于数据入库前端展示
 #   以下不用修改   
    device=${CUDA_VISIBLE_DEVICES//,/ }
    arr=(${device})
    num_gpu_devices=${#arr[*]}
-    log_file=${run_log_path}/${model_name}_${run_mode}_bs${batch_size}_${fp_item}_${num_gpu_devices}
+    log_file=${run_log_path}/${model_item}_${run_mode}_bs${batch_size}_${fp_item}_${num_gpu_devices}
 }
 function _train(){
    echo "Train on ${num_gpu_devices} GPUs"
    echo "current CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES, gpus=$num_gpu_devices, batch_size=$batch_size"
-    train_cmd="-c configs/det/${model_name}.yml -o Train.loader.batch_size_per_card=${batch_size} Global.epoch_num=${max_iter} "   
+    train_cmd="-c configs/det/${model_item}.yml -o Train.loader.batch_size_per_card=${batch_size} Global.epoch_num=${max_epoch} Global.eval_batch_step=[0,20000] Global.print_batch_step=2"
    case ${run_mode} in
      sp) 
-        train_cmd="python3.7 tools/train.py "${train_cmd}""
+        train_cmd="python tools/train.py "${train_cmd}""
        ;;
      mp)
-        train_cmd="python3.7 -m paddle.distributed.launch --log_dir=./mylog --gpus=$CUDA_VISIBLE_DEVICES tools/train.py ${train_cmd}"
+        train_cmd="python -m paddle.distributed.launch --log_dir=./mylog --gpus=$CUDA_VISIBLE_DEVICES tools/train.py ${train_cmd}"
        ;;
      *) echo "choose run_mode(sp or mp)"; exit 1;
    esac
@@ -39,18 +47,14 @@ function _train(){
        echo -e "${model_name}, SUCCESS"
        export job_fail_flag=0
    fi
-    kill -9 `ps -ef|grep 'python3.7'|awk '{print $2}'`
    if [ $run_mode = "mp" -a -d mylog ]; then
        rm ${log_file}
        cp mylog/workerlog.0 ${log_file}
    fi
-    # run log analysis
-    analysis_cmd="python3.7 benchmark/analysis.py --filename ${log_file}  --mission_name ${model_name} --run_mode ${mode} --direction_id 0 --keyword 'ips:' --base_batch_size ${batch_szie} --skip_steps 1 --gpu_num ${num_gpu_devices}  --index 1  --model_mode=-1  --ips_unit=samples/sec"
-    eval $analysis_cmd
 }
+source ${BENCHMARK_ROOT}/scripts/run_model.sh      # 在该脚本中会对符合benchmark规范的log使用analysis.py 脚本进行性能数据解析;该脚本在连调时可从benchmark repo中下载https://github.com/PaddlePaddle/benchmark/blob/master/scripts/run_model.sh;如果不联调只想要产出训练log可以注掉本行,提交时需打开
 _set_params $@
-_train
+#_train      # 如果只想产出训练log,不解析,可取消注释
+_run         # 该函数在run_model.sh中,执行时会调用_train; 如果不联调只想要产出训练log可以注掉本行,提交时需打开