fix conflict

bupt906 · Dec 16, 2021 · 721c76b · 721c76b
2 parents 98162be + b77f9ec
commit 721c76b
Show file tree

Hide file tree

Showing 294 changed files with 18,399 additions and 12,321 deletions.
diff --git a/.github/ISSUE_TEMPLATE/custom.md b/.github/ISSUE_TEMPLATE/custom.md
@@ -0,0 +1,15 @@
+---
+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：
diff --git 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
diff --git a/PPOCRLabel/PPOCRLabel.py b/PPOCRLabel/PPOCRLabel.py
@@ -35,6 +35,7 @@
 
 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 @@ def __init__(self, lang="ch", gpu=False, defaultFilename=None, defaultPrefdefCla
         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 @@ def __init__(self, lang="ch", gpu=False, defaultFilename=None, defaultPrefdefCla
                           '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 @@ def showBoundingBoxFromPPlabel(self, filePath):
         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
 

diff --git 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
-# 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.
-```
+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.
 
-#### **Install Third-party Libraries**
+#### Windows
 
 ```bash
-cd PaddleOCR
-pip3 install -r requirements.txt
+pip install PPOCRLabel  # install
+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.
-
-Reference: [Solve shapely installation on windows](https://stackoverflow.com/questions/44398265/install-shapely-oserror-winerror-126-the-specified-module-could-not-be-found)
+> 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)
+>
 
-### 2. Install PPOCRLabel
+#### Ubuntu Linux
 
-#### Windows
+```bash
+pip3 install PPOCRLabel
+pip3 install trash-cli
+PPOCRLabel
+```
 
+#### MacOS
 ```bash
-pip install pyqt5
-cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
-python PPOCRLabel.py
+pip3 install PPOCRLabel
+pip3 install opencv-contrib-python-headless==4.2.0.32
+PPOCRLabel # run
 ```
 
-#### Ubuntu Linux
+#### 1.2.2 Build and Install the Whl Package Locally
 
 ```bash
-pip3 install pyqt5
-pip3 install trash-cli
-cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
-python3 PPOCRLabel.py
+cd PaddleOCR/PPOCRLabel
+python3 setup.py bdist_wheel 
+pip3 install dist/PPOCRLabel-1.0.0-py2.py3-none-any.whl
 ```
 
-#### MacOS
+#### 1.2.3 Run PPOCRLabel by Python Script
+
 ```bash
-pip3 install pyqt5
-pip3 uninstall opencv-python # Uninstall opencv manually as it conflicts with pyqt
-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
+cd ./PPOCRLabel  # Switch to the PPOCRLabel directory
+python PPOCRLabel.py --lang ch
 ```
 
-## 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) :
 
-### Export Label Result
+  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) `
+
+### 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.*
 
-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.
+### 3.5 Dataset division
 
-*Note: The status of the checkboxes in the recognition results still needs to be saved manually by clicking Save Button.*
+- Enter the following command in the terminal to execute the dataset division script:
 
-### Error message
+  ```
+  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`
+
+  - `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)