Skip to content

GitLab

"...git@developer.sourcefind.cn:chenpangpang/open-webui.git" did not exist on "3b27acc77eaf112d8521ae22282c619ef9ccf394"
Unverified Commit adc62fcd authored by topduke's avatar topduke Committed by GitHub
Browse files

Merge branch 'dygraph' into dygraph

parents 8227ad1b a81b88a0
Expand all Show whitespace changes
Inline Side-by-side
Showing with 12318 additions and 10862 deletions
MANIFEST.in
View file @ adc62fcd
include LICENSE.txt include LICENSE
include README.md include README.md
recursive-include ppocr/utils *.txt utility.py logging.py recursive-include ppocr/utils *.txt utility.py logging.py network.py
recursive-include ppocr/data/ *.py recursive-include ppocr/data *.py
recursive-include ppocr/postprocess *.py recursive-include ppocr/postprocess *.py
recursive-include tools/infer *.py recursive-include tools/infer *.py
recursive-include ppocr/utils/e2e_utils/ *.py recursive-include ppocr/utils/e2e_utils *.py
\ No newline at end of file recursive-include ppstructure *.py
\ No newline at end of file
PPOCRLabel/PPOCRLabel.py
View file @ adc62fcd
...@@ -27,7 +27,12 @@ import json ...@@ -27,7 +27,12 @@ import json
import cv2 import cv2
__dir__ = os.path.dirname(os.path.abspath(__file__)) __dir__ = os.path.dirname(os.path.abspath(__file__))
import numpy as np
sys.path.append(__dir__) sys.path.append(__dir__)
sys.path.append(os.path.abspath(os.path.join(__dir__, '../..'))) sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
sys.path.append("..") sys.path.append("..")
...@@ -267,6 +272,8 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -267,6 +272,8 @@ class MainWindow(QMainWindow, WindowMixin):
self.colorDialog = ColorDialog(parent=self) self.colorDialog = ColorDialog(parent=self)
self.zoomWidgetValue = self.zoomWidget.value() self.zoomWidgetValue = self.zoomWidget.value()
self.msgBox = QMessageBox()
########## thumbnail ######### ########## thumbnail #########
hlayout = QHBoxLayout() hlayout = QHBoxLayout()
m = (0, 0, 0, 0) m = (0, 0, 0, 0)
...@@ -360,6 +367,9 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -360,6 +367,9 @@ class MainWindow(QMainWindow, WindowMixin):
opendir = action(getStr('openDir'), self.openDirDialog, opendir = action(getStr('openDir'), self.openDirDialog,
'Ctrl+u', 'open', getStr('openDir')) 'Ctrl+u', 'open', getStr('openDir'))
open_dataset_dir = action(getStr('openDatasetDir'), self.openDatasetDirDialog,
'Ctrl+p', 'open', getStr('openDatasetDir'), enabled=False)
save = action(getStr('save'), self.saveFile, save = action(getStr('save'), self.saveFile,
'Ctrl+V', 'verify', getStr('saveDetail'), enabled=False) 'Ctrl+V', 'verify', getStr('saveDetail'), enabled=False)
...@@ -398,6 +408,7 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -398,6 +408,7 @@ class MainWindow(QMainWindow, WindowMixin):
help = action(getStr('tutorial'), self.showTutorialDialog, None, 'help', getStr('tutorialDetail')) help = action(getStr('tutorial'), self.showTutorialDialog, None, 'help', getStr('tutorialDetail'))
showInfo = action(getStr('info'), self.showInfoDialog, None, 'help', getStr('info')) showInfo = action(getStr('info'), self.showInfoDialog, None, 'help', getStr('info'))
showSteps = action(getStr('steps'), self.showStepsDialog, None, 'help', getStr('steps')) showSteps = action(getStr('steps'), self.showStepsDialog, None, 'help', getStr('steps'))
showKeys = action(getStr('keys'), self.showKeysDialog, None, 'help', getStr('keys'))
zoom = QWidgetAction(self) zoom = QWidgetAction(self)
zoom.setDefaultWidget(self.zoomWidget) zoom.setDefaultWidget(self.zoomWidget)
...@@ -456,6 +467,12 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -456,6 +467,12 @@ class MainWindow(QMainWindow, WindowMixin):
undoLastPoint = action(getStr("undoLastPoint"), self.canvas.undoLastPoint, undoLastPoint = action(getStr("undoLastPoint"), self.canvas.undoLastPoint,
'Ctrl+Z', "undo", getStr("undoLastPoint"), enabled=False) 'Ctrl+Z', "undo", getStr("undoLastPoint"), enabled=False)
rotateLeft = action(getStr("rotateLeft"), partial(self.rotateImgAction,1),
'Ctrl+Alt+L', "rotateLeft", getStr("rotateLeft"), enabled=False)
rotateRight = action(getStr("rotateRight"), partial(self.rotateImgAction,-1),
'Ctrl+Alt+R', "rotateRight", getStr("rotateRight"), enabled=False)
undo = action(getStr("undo"), self.undoShapeEdit, undo = action(getStr("undo"), self.undoShapeEdit,
'Ctrl+Z', "undo", getStr("undo"), enabled=False) 'Ctrl+Z', "undo", getStr("undo"), enabled=False)
...@@ -519,13 +536,14 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -519,13 +536,14 @@ class MainWindow(QMainWindow, WindowMixin):
zoom=zoom, zoomIn=zoomIn, zoomOut=zoomOut, zoomOrg=zoomOrg, zoom=zoom, zoomIn=zoomIn, zoomOut=zoomOut, zoomOrg=zoomOrg,
fitWindow=fitWindow, fitWidth=fitWidth, fitWindow=fitWindow, fitWidth=fitWidth,
zoomActions=zoomActions, saveLabel=saveLabel, zoomActions=zoomActions, saveLabel=saveLabel,
undo=undo, undoLastPoint=undoLastPoint, undo=undo, undoLastPoint=undoLastPoint,open_dataset_dir=open_dataset_dir,
rotateLeft=rotateLeft,rotateRight=rotateRight,
fileMenuActions=( fileMenuActions=(
opendir, saveLabel, resetAll, quit), opendir, open_dataset_dir, saveLabel, resetAll, quit),
beginner=(), advanced=(), beginner=(), advanced=(),
editMenu=(createpoly, edit, copy, delete,singleRere,None, undo, undoLastPoint, editMenu=(createpoly, edit, copy, delete,singleRere,None, undo, undoLastPoint,
None, color1, self.drawSquaresOption), None, rotateLeft, rotateRight, None, color1, self.drawSquaresOption),
beginnerContext=(create, edit, copy, delete, singleRere), beginnerContext=(create, edit, copy, delete, singleRere, rotateLeft, rotateRight,),
advancedContext=(createMode, editMode, edit, copy, advancedContext=(createMode, editMode, edit, copy,
delete, shapeLineColor, shapeFillColor), delete, shapeLineColor, shapeFillColor),
onLoadActive=( onLoadActive=(
...@@ -563,9 +581,9 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -563,9 +581,9 @@ class MainWindow(QMainWindow, WindowMixin):
self.autoSaveOption.triggered.connect(self.autoSaveFunc) self.autoSaveOption.triggered.connect(self.autoSaveFunc)
addActions(self.menus.file, addActions(self.menus.file,
(opendir, None, saveLabel, saveRec, self.autoSaveOption, None, resetAll, deleteImg, quit)) (opendir, open_dataset_dir, None, saveLabel, saveRec, self.autoSaveOption, None, resetAll, deleteImg, quit))
addActions(self.menus.help, (showSteps, showInfo)) addActions(self.menus.help, (showKeys,showSteps, showInfo))
addActions(self.menus.view, ( addActions(self.menus.view, (
self.displayLabelOption, self.labelDialogOption, self.displayLabelOption, self.labelDialogOption,
None, None,
...@@ -760,6 +778,10 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -760,6 +778,10 @@ class MainWindow(QMainWindow, WindowMixin):
msg = stepsInfo(self.lang) msg = stepsInfo(self.lang)
QMessageBox.information(self, u'Information', msg) QMessageBox.information(self, u'Information', msg)
def showKeysDialog(self):
msg = keysInfo(self.lang)
QMessageBox.information(self, u'Information', msg)
def createShape(self): def createShape(self):
assert self.beginner() assert self.beginner()
self.canvas.setEditing(False) self.canvas.setEditing(False)
...@@ -773,6 +795,38 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -773,6 +795,38 @@ class MainWindow(QMainWindow, WindowMixin):
self.actions.create.setEnabled(False) self.actions.create.setEnabled(False)
self.actions.undoLastPoint.setEnabled(True) self.actions.undoLastPoint.setEnabled(True)
def rotateImg(self, filename, k, _value):
self.actions.rotateRight.setEnabled(_value)
pix = cv2.imread(filename)
pix = np.rot90(pix, k)
cv2.imwrite(filename, pix)
self.canvas.update()
self.loadFile(filename)
def rotateImgWarn(self):
if self.lang == 'ch':
self.msgBox.warning (self, "提示", "\n 该图片已经有标注框,旋转操作会打乱标注,建议清除标注框后旋转。")
else:
self.msgBox.warning (self, "Warn", "\n The picture already has a label box, and rotation will disrupt the label.\
It is recommended to clear the label box and rotate it.")
def rotateImgAction(self, k=1, _value=False):
filename = self.mImgList[self.currIndex]
if os.path.exists(filename):
if self.itemsToShapesbox:
self.rotateImgWarn()
else:
self.saveFile()
self.dirty = False
self.rotateImg(filename=filename, k=k, _value=True)
else:
self.rotateImgWarn()
self.actions.rotateRight.setEnabled(False)
self.actions.rotateLeft.setEnabled(False)
def toggleDrawingSensitive(self, drawing=True): def toggleDrawingSensitive(self, drawing=True):
"""In the middle of drawing, toggling between modes should be disabled.""" """In the middle of drawing, toggling between modes should be disabled."""
self.actions.editMode.setEnabled(not drawing) self.actions.editMode.setEnabled(not drawing)
...@@ -880,7 +934,12 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -880,7 +934,12 @@ class MainWindow(QMainWindow, WindowMixin):
self.updateComboBox() self.updateComboBox()
def updateBoxlist(self): def updateBoxlist(self):
for shape in self.canvas.selectedShapes+[self.canvas.hShape]: self.canvas.selectedShapes_hShape = []
if self.canvas.hShape != None:
self.canvas.selectedShapes_hShape = self.canvas.selectedShapes + [self.canvas.hShape]
else:
self.canvas.selectedShapes_hShape = self.canvas.selectedShapes
for shape in self.canvas.selectedShapes_hShape:
item = self.shapesToItemsbox[shape] # listitem item = self.shapesToItemsbox[shape] # listitem
text = [(int(p.x()), int(p.y())) for p in shape.points] text = [(int(p.x()), int(p.y())) for p in shape.points]
item.setText(str(text)) item.setText(str(text))
...@@ -1413,6 +1472,7 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -1413,6 +1472,7 @@ class MainWindow(QMainWindow, WindowMixin):
def loadRecent(self, filename): def loadRecent(self, filename):
if self.mayContinue(): if self.mayContinue():
print(filename,"======")
self.loadFile(filename) self.loadFile(filename)
def scanAllImages(self, folderPath): def scanAllImages(self, folderPath):
...@@ -1448,6 +1508,23 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -1448,6 +1508,23 @@ class MainWindow(QMainWindow, WindowMixin):
self.lastOpenDir = targetDirPath self.lastOpenDir = targetDirPath
self.importDirImages(targetDirPath) self.importDirImages(targetDirPath)
def openDatasetDirDialog(self,):
if self.lastOpenDir and os.path.exists(self.lastOpenDir):
if platform.system() == 'Windows':
os.startfile(self.lastOpenDir)
else:
os.system('open ' + os.path.normpath(self.lastOpenDir))
defaultOpenDirPath = self.lastOpenDir
else:
if self.lang == 'ch':
self.msgBox.warning(self, "提示", "\n 原文件夹已不存在,请从新选择数据集路径!")
else:
self.msgBox.warning(self, "Warn", "\n The original folder no longer exists, please choose the data set path again!")
self.actions.open_dataset_dir.setEnabled(False)
defaultOpenDirPath = os.path.dirname(self.filePath) if self.filePath else '.'
def importDirImages(self, dirpath, isDelete = False): def importDirImages(self, dirpath, isDelete = False):
if not self.mayContinue() or not dirpath: if not self.mayContinue() or not dirpath:
return return
...@@ -1495,6 +1572,10 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -1495,6 +1572,10 @@ class MainWindow(QMainWindow, WindowMixin):
self.reRecogButton.setEnabled(True) self.reRecogButton.setEnabled(True)
self.actions.AutoRec.setEnabled(True) self.actions.AutoRec.setEnabled(True)
self.actions.reRec.setEnabled(True) self.actions.reRec.setEnabled(True)
self.actions.open_dataset_dir.setEnabled(True)
self.actions.rotateLeft.setEnabled(True)
self.actions.rotateRight.setEnabled(True)
def openPrevImg(self, _value=False): def openPrevImg(self, _value=False):
......
PPOCRLabel/README.md
View file @ adc62fcd
...@@ -8,9 +8,12 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w ...@@ -8,9 +8,12 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w
### Recent Update ### Recent Update
- 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)): - 2021.2.5: New batch processing and undo functions (by [Evezerest](https://github.com/Evezerest)):
- Batch processing function: Press and hold the Ctrl key to select the box, you can move, copy, and delete in batches. - **Batch processing function**: Press and hold the Ctrl key to select the box, you can move, copy, and delete in batches.
- Undo function: In the process of drawing a four-point label box or after editing the box, press Ctrl+Z to undo the previous operation. - **Undo function**: In the process of drawing a four-point label box or after editing the box, press Ctrl+Z to undo the previous operation.
- Fix image rotation and size problems, optimize the process of editing the mark frame (by [ninetailskim](https://github.com/ninetailskim)、 [edencfc](https://github.com/edencfc)). - Fix image rotation and size problems, optimize the process of editing the mark frame (by [ninetailskim](https://github.com/ninetailskim)、 [edencfc](https://github.com/edencfc)).
- 2021.1.11: Optimize the labeling experience (by [edencfc](https://github.com/edencfc)), - 2021.1.11: Optimize the labeling experience (by [edencfc](https://github.com/edencfc)),
- Users can choose whether to pop up the label input dialog after drawing the detection box in "View - Pop-up Label Input Dialog". - Users can choose whether to pop up the label input dialog after drawing the detection box in "View - Pop-up Label Input Dialog".
...@@ -23,15 +26,51 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w ...@@ -23,15 +26,51 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w
## Installation ## Installation
### 1. Install PaddleOCR ### 1. Environment Preparation
PaddleOCR models has been built in PPOCRLabel, please refer to [PaddleOCR installation document](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/installation.md) to prepare PaddleOCR and make sure it works. #### **Install PaddlePaddle 2.0**
```bash
pip3 install --upgrade pip
# If you have cuda9 or cuda10 installed on your machine, please run the following command to install
python3 -m pip install paddlepaddle-gpu==2.0.0 -i https://mirror.baidu.com/pypi/simple
# If you only have cpu on your machine, please run the following command to install
python3 -m pip install paddlepaddle==2.0.0 -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**
```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.
```
#### **Install Third-party Libraries**
```bash
cd PaddleOCR
pip3 install -r requirements.txt
```
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 ### 2. Install PPOCRLabel
#### Windows #### Windows
``` ```bash
pip install pyqt5 pip install pyqt5
cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
python PPOCRLabel.py python PPOCRLabel.py
...@@ -39,15 +78,15 @@ python PPOCRLabel.py ...@@ -39,15 +78,15 @@ python PPOCRLabel.py
#### Ubuntu Linux #### Ubuntu Linux
``` ```bash
pip3 install pyqt5 pip3 install pyqt5
pip3 install trash-cli pip3 install trash-cli
cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
python3 PPOCRLabel.py python3 PPOCRLabel.py
``` ```
#### macOS #### MacOS
``` ```bash
pip3 install pyqt5 pip3 install pyqt5
pip3 uninstall opencv-python # Uninstall opencv manually as it conflicts with pyqt 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 pip3 install opencv-contrib-python-headless==4.2.0.32 # Install the headless version of opencv
...@@ -77,11 +116,11 @@ python3 PPOCRLabel.py ...@@ -77,11 +116,11 @@ python3 PPOCRLabel.py
7. Double click the result in 'recognition result' list to manually change inaccurate recognition results. 7. Double click the result in 'recognition result' list to manually change inaccurate recognition results.
8. Click "Check", the image status will switch to "√",then the program automatically jump to the next. 8. **Click "Check", the image status will switch to "√",then the program automatically jump to the next.**
9. Click "Delete Image" and the image will be deleted to the recycle bin. 9. Click "Delete Image" and the image will be deleted to the recycle bin.
10. Labeling result: the user can save manually through the menu "File - Save Label", while the program will also save automatically if "File - Auto Save Label Mode" is selected. The manually checked label will be stored in *Label.txt* under the opened picture folder. Click "PaddleOCR"-"Save 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>. 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 ### Note
...@@ -95,10 +134,10 @@ python3 PPOCRLabel.py ...@@ -95,10 +134,10 @@ python3 PPOCRLabel.py
| File name | Description | | File name | Description |
| :-----------: | :----------------------------------------------------------: | | :-----------: | :----------------------------------------------------------: |
| Label.txt | The detection label file can be directly used for PPOCR detection model training. After the user saves 5 label results, the file will be automatically saved. It will also be written when the user closes the application or changes the file folder. | | Label.txt | The detection label file can be directly used for PPOCR detection model training. After the user saves 5 label results, the file will be automatically exported. It will also be written when the user closes the application or changes the file folder. |
| fileState.txt | The picture status file save the image in the current folder that has been manually confirmed by the user. | | fileState.txt | The picture status file save the image in the current folder that has been manually confirmed by the user. |
| Cache.cach | Cache files to save the results of model recognition. | | Cache.cach | Cache files to save the results of model recognition. |
| 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"-"Save recognition result". | | 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* | | crop_img | The recognition data, generated at the same time with *rec_gt.txt* |
## Explanation ## Explanation
...@@ -132,16 +171,16 @@ python3 PPOCRLabel.py ...@@ -132,16 +171,16 @@ python3 PPOCRLabel.py
- 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: 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)
### Save ### Export Label Result
PPOCRLabel supports three ways to save Label.txt PPOCRLabel supports three ways to export Label.txt
- Automatically save: After selecting "File - Auto Save 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 saved after detecting that the user has manually checked 5 images. - 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.
- Manual save: Click "File-Save Marking Results" to manually save the label. - Manual export: Click "File-Export Marking Results" to manually export the label.
- Close application save - Close application export
### Export partial recognition results ### 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. 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.
......
PPOCRLabel/README_ch.md
View file @ adc62fcd
...@@ -8,9 +8,12 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置P ...@@ -8,9 +8,12 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置P
#### 近期更新 #### 近期更新
- 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)) - 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。 - **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。
- 撤销功能：在绘制四点标注框过程中或对框进行编辑操作后，按下Ctrl+Z可撤销上一部操作。 - **撤销功能**：在绘制四点标注框过程中或对框进行编辑操作后，按下Ctrl+Z可撤销上一部操作。
- 修复图像旋转和尺寸问题、优化编辑标记框过程（by [ninetailskim](https://github.com/ninetailskim)、 [edencfc](https://github.com/edencfc)） - 修复图像旋转和尺寸问题、优化编辑标记框过程（by [ninetailskim](https://github.com/ninetailskim)、 [edencfc](https://github.com/edencfc)）
- 2021.1.11：优化标注体验（by [edencfc](https://github.com/edencfc)）： - 2021.1.11：优化标注体验（by [edencfc](https://github.com/edencfc)）：
- 用户可在“视图 - 弹出标记输入框”选择在画完检测框后标记输入框是否弹出。 - 用户可在“视图 - 弹出标记输入框”选择在画完检测框后标记输入框是否弹出。
...@@ -27,13 +30,48 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置P ...@@ -27,13 +30,48 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置P
## 安装 ## 安装
### 1. 安装PaddleOCR ### 1. 环境搭建
PPOCRLabel内置PaddleOCR模型，故请参考[PaddleOCR安装文档](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/installation.md)准备好PaddleOCR，并确保PaddleOCR安装成功。 #### 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
python3 -m pip install paddlepaddle-gpu==2.0.0 -i https://mirror.baidu.com/pypi/simple
如果您的机器是CPU，请运行以下命令安装
python3 -m pip install paddlepaddle==2.0.0 -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**
```bash
【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：
git clone https://gitee.com/paddlepaddle/PaddleOCR
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。
```
#### 安装第三方库
```bash
cd PaddleOCR
pip3 install -r requirements.txt
```
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`。
### 2. 安装PPOCRLabel ### 2. 安装PPOCRLabel
#### Windows #### Windows
``` ```bash
pip install pyqt5 pip install pyqt5
cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下 cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
python PPOCRLabel.py --lang ch python PPOCRLabel.py --lang ch
...@@ -41,15 +79,15 @@ python PPOCRLabel.py --lang ch ...@@ -41,15 +79,15 @@ python PPOCRLabel.py --lang ch
#### Ubuntu Linux #### Ubuntu Linux
``` ```bash
pip3 install pyqt5 pip3 install pyqt5
pip3 install trash-cli pip3 install trash-cli
cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下 cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
python3 PPOCRLabel.py --lang ch python3 PPOCRLabel.py --lang ch
``` ```
#### macOS #### MacOS
``` ```bash
pip3 install pyqt5 pip3 install pyqt5
pip3 uninstall opencv-python # 由于mac版本的opencv与pyqt有冲突，需先手动卸载opencv pip3 uninstall opencv-python # 由于mac版本的opencv与pyqt有冲突，需先手动卸载opencv
pip3 install opencv-contrib-python-headless==4.2.0.32 # 安装headless版本的open-cv pip3 install opencv-contrib-python-headless==4.2.0.32 # 安装headless版本的open-cv
...@@ -57,6 +95,8 @@ cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下 ...@@ -57,6 +95,8 @@ cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
python3 PPOCRLabel.py --lang ch python3 PPOCRLabel.py --lang ch
``` ```
## 使用 ## 使用
### 操作步骤 ### 操作步骤
...@@ -68,9 +108,9 @@ python3 PPOCRLabel.py --lang ch ...@@ -68,9 +108,9 @@ python3 PPOCRLabel.py --lang ch
5. 标记框绘制完成后，用户点击 “确认”，检测框会先被预分配一个 “待识别” 标签。 5. 标记框绘制完成后，用户点击 “确认”，检测框会先被预分配一个 “待识别” 标签。
6. 重新识别：将图片中的所有检测画绘制/调整完成后，点击 “重新识别”，PPOCR模型会对当前图片中的**所有检测框**重新识别<sup>[3]</sup>。 6. 重新识别：将图片中的所有检测画绘制/调整完成后，点击 “重新识别”，PPOCR模型会对当前图片中的**所有检测框**重新识别<sup>[3]</sup>。
7. 内容更改：双击识别结果，对不准确的识别结果进行手动更改。 7. 内容更改：双击识别结果，对不准确的识别结果进行手动更改。
8. **确认标记**：点击 “确认”，图片状态切换为 “√”，跳转至下一张。 8. **确认标记：点击 “确认”，图片状态切换为 “√”，跳转至下一张。**
9. 删除：点击 “删除图像”，图片将会被删除至回收站。 9. 删除：点击 “删除图像”，图片将会被删除至回收站。
10. 保存结果：用户可以通过菜单中“文件-保存标记结果”手动保存，同时也可以点击“文件 - 自动保存标记结果”开启自动保存。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” - "保存识别结果"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>。 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 ### 注意
...@@ -84,10 +124,10 @@ python3 PPOCRLabel.py --lang ch ...@@ -84,10 +124,10 @@ python3 PPOCRLabel.py --lang ch
| 文件名 | 说明 | | 文件名 | 说明 |
| :-----------: | :----------------------------------------------------------: | | :-----------: | :----------------------------------------------------------: |
| Label.txt | 检测标签，可直接用于PPOCR检测模型训练。用户每保存5张检测结果后，程序会进行自动写入。当用户关闭应用程序或切换文件路径后同样会进行写入。 | | Label.txt | 检测标签，可直接用于PPOCR检测模型训练。用户每确认5张检测结果后，程序会进行自动写入。当用户关闭应用程序或切换文件路径后同样会进行写入。 |
| fileState.txt | 图片状态标记文件，保存当前文件夹下已经被用户手动确认过的图片名称。 | | fileState.txt | 图片状态标记文件，保存当前文件夹下已经被用户手动确认过的图片名称。 |
| Cache.cach | 缓存文件，保存模型自动识别的结果。 | | Cache.cach | 缓存文件，保存模型自动识别的结果。 |
| 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” - "保存识别结果"后产生。 | | 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。 | | 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 ## 说明
...@@ -120,19 +160,19 @@ python3 PPOCRLabel.py --lang ch ...@@ -120,19 +160,19 @@ python3 PPOCRLabel.py --lang ch
- 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：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。
### 保存方式 ### 导出标记结果
PPOCRLabel支持三种保存方式： PPOCRLabel支持三种导出方式：
- 自动保存：点击“文件 - 自动保存标记结果”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张图片后进行自动保存。 - 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。
- 手动保存：点击“文件 - 保存标记结果”手动保存标记。 - 手动导出：点击“文件 - 导出标记结果”手动导出标记。
- 关闭应用程序保存 - 关闭应用程序导出
### 导出部分识别结果 ### 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。 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。
*注意：识别结果中的复选框状态仍需用户手动点击保存后才能保留* *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*
### 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。 - 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/libs/canvas.py
View file @ adc62fcd
...@@ -23,6 +23,7 @@ except ImportError: ...@@ -23,6 +23,7 @@ except ImportError:
from libs.shape import Shape from libs.shape import Shape
from libs.utils import distance from libs.utils import distance
import copy
CURSOR_DEFAULT = Qt.ArrowCursor CURSOR_DEFAULT = Qt.ArrowCursor
CURSOR_POINT = Qt.PointingHandCursor CURSOR_POINT = Qt.PointingHandCursor
...@@ -81,6 +82,7 @@ class Canvas(QWidget): ...@@ -81,6 +82,7 @@ class Canvas(QWidget):
self.fourpoint = True # ADD self.fourpoint = True # ADD
self.pointnum = 0 self.pointnum = 0
self.movingShape = False self.movingShape = False
self.selectCountShape = False
#initialisation for panning #initialisation for panning
self.pan_initial_pos = QPoint() self.pan_initial_pos = QPoint()
...@@ -702,6 +704,10 @@ class Canvas(QWidget): ...@@ -702,6 +704,10 @@ class Canvas(QWidget):
def keyPressEvent(self, ev): def keyPressEvent(self, ev):
key = ev.key() key = ev.key()
shapesBackup = []
shapesBackup = copy.deepcopy(self.shapes)
self.shapesBackups.pop()
self.shapesBackups.append(shapesBackup)
if key == Qt.Key_Escape and self.current: if key == Qt.Key_Escape and self.current:
print('ESC press') print('ESC press')
self.current = None self.current = None
...@@ -709,17 +715,21 @@ class Canvas(QWidget): ...@@ -709,17 +715,21 @@ class Canvas(QWidget):
self.update() self.update()
elif key == Qt.Key_Return and self.canCloseShape(): elif key == Qt.Key_Return and self.canCloseShape():
self.finalise() self.finalise()
elif key == Qt.Key_Left and self.selectedShape: elif key == Qt.Key_Left and self.selectedShapes:
self.moveOnePixel('Left') self.moveOnePixel('Left')
elif key == Qt.Key_Right and self.selectedShape: elif key == Qt.Key_Right and self.selectedShapes:
self.moveOnePixel('Right') self.moveOnePixel('Right')
elif key == Qt.Key_Up and self.selectedShape: elif key == Qt.Key_Up and self.selectedShapes:
self.moveOnePixel('Up') self.moveOnePixel('Up')
elif key == Qt.Key_Down and self.selectedShape: elif key == Qt.Key_Down and self.selectedShapes:
self.moveOnePixel('Down') self.moveOnePixel('Down')
def moveOnePixel(self, direction): def moveOnePixel(self, direction):
# print(self.selectedShape.points) # print(self.selectedShape.points)
self.selectCount = len(self.selectedShapes)
self.selectCountShape = True
for i in range(len(self.selectedShapes)):
self.selectedShape = self.selectedShapes[i]
if direction == 'Left' and not self.moveOutOfBound(QPointF(-1.0, 0)): if direction == 'Left' and not self.moveOutOfBound(QPointF(-1.0, 0)):
# print("move Left one pixel") # print("move Left one pixel")
self.selectedShape.points[0] += QPointF(-1.0, 0) self.selectedShape.points[0] += QPointF(-1.0, 0)
...@@ -744,6 +754,9 @@ class Canvas(QWidget): ...@@ -744,6 +754,9 @@ class Canvas(QWidget):
self.selectedShape.points[1] += QPointF(0, 1.0) self.selectedShape.points[1] += QPointF(0, 1.0)
self.selectedShape.points[2] += QPointF(0, 1.0) self.selectedShape.points[2] += QPointF(0, 1.0)
self.selectedShape.points[3] += QPointF(0, 1.0) self.selectedShape.points[3] += QPointF(0, 1.0)
shapesBackup = []
shapesBackup = copy.deepcopy(self.shapes)
self.shapesBackups.append(shapesBackup)
self.shapeMoved.emit() self.shapeMoved.emit()
self.repaint() self.repaint()
...@@ -840,6 +853,7 @@ class Canvas(QWidget): ...@@ -840,6 +853,7 @@ class Canvas(QWidget):
def restoreShape(self): def restoreShape(self):
if not self.isShapeRestorable: if not self.isShapeRestorable:
return return
self.shapesBackups.pop() # latest self.shapesBackups.pop() # latest
shapesBackup = self.shapesBackups.pop() shapesBackup = self.shapesBackups.pop()
self.shapes = shapesBackup self.shapes = shapesBackup
......
PPOCRLabel/libs/resources.py
View file @ adc62fcd
This diff is collapsed.
PPOCRLabel/libs/utils.py
View file @ adc62fcd
...@@ -174,6 +174,7 @@ def stepsInfo(lang='en'): ...@@ -174,6 +174,7 @@ def stepsInfo(lang='en'):
"10. 标注结果：关闭应用程序或切换文件路径后，手动保存过的标签将会被存放在所打开图片文件夹下的" \ "10. 标注结果：关闭应用程序或切换文件路径后，手动保存过的标签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 “PaddleOCR” - 保存识别结果后，会将此类图片的识别训练数据保存在*crop_img*文件夹下，" \ "*Label.txt*中。在菜单栏点击 “PaddleOCR” - 保存识别结果后，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。\n" "识别标签保存在*rec_gt.txt*中。\n"
else: else:
msg = "1. Build and launch using the instructions above.\n" \ msg = "1. Build and launch using the instructions above.\n" \
"2. Click 'Open Dir' in Menu/File to select the folder of the picture.\n"\ "2. Click 'Open Dir' in Menu/File to select the folder of the picture.\n"\
...@@ -188,4 +189,56 @@ def stepsInfo(lang='en'): ...@@ -188,4 +189,56 @@ def stepsInfo(lang='en'):
"9. Click 'Delete Image' and the image will be deleted to the recycle bin.\n"\ "9. Click 'Delete Image' and the image will be deleted to the recycle bin.\n"\
"10. Labeling result: After closing the application or switching the file path, the manually saved label will be stored in *Label.txt* under the opened picture folder.\n"\ "10. Labeling result: After closing the application or switching the file path, the manually saved label will be stored in *Label.txt* under the opened picture folder.\n"\
" Click PaddleOCR-Save 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*.\n" " Click PaddleOCR-Save 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*.\n"
return msg
def keysInfo(lang='en'):
if lang == 'ch':
msg = "快捷键\t\t\t说明\n" \
"———————————————————————\n"\
"Ctrl + shift + R\t\t对当前图片的所有标记重新识别\n" \
"W\t\t\t新建矩形框\n" \
"Q\t\t\t新建四点框\n" \
"Ctrl + E\t\t编辑所选框标签\n" \
"Ctrl + R\t\t重新识别所选标记\n" \
"Ctrl + C\t\t复制并粘贴选中的标记框\n" \
"Ctrl + 鼠标左键\t\t多选标记框\n" \
"Backspace\t\t删除所选框\n" \
"Ctrl + V\t\t确认本张图片标记\n" \
"Ctrl + Shift + d\t删除本张图片\n" \
"D\t\t\t下一张图片\n" \
"A\t\t\t上一张图片\n" \
"Ctrl++\t\t\t缩小\n" \
"Ctrl--\t\t\t放大\n" \
"↑→↓←\t\t\t移动标记框\n" \
"———————————————————————\n" \
"注：Mac用户Command键替换上述Ctrl键"
else:
msg = "Shortcut Keys\t\tDescription\n" \
"———————————————————————\n" \
"Ctrl + shift + R\t\tRe-recognize all the labels\n" \
"\t\t\tof the current image\n" \
"\n"\
"W\t\t\tCreate a rect box\n" \
"Q\t\t\tCreate a four-points box\n" \
"Ctrl + E\t\tEdit label of the selected box\n" \
"Ctrl + R\t\tRe-recognize the selected box\n" \
"Ctrl + C\t\tCopy and paste the selected\n" \
"\t\t\tbox\n" \
"\n"\
"Ctrl + Left Mouse\tMulti select the label\n" \
"Button\t\t\tbox\n" \
"\n"\
"Backspace\t\tDelete the selected box\n" \
"Ctrl + V\t\tCheck image\n" \
"Ctrl + Shift + d\tDelete image\n" \
"D\t\t\tNext image\n" \
"A\t\t\tPrevious image\n" \
"Ctrl++\t\t\tZoom in\n" \
"Ctrl--\t\t\tZoom out\n" \
"↑→↓←\t\t\tMove selected box" \
"———————————————————————\n" \
"Notice:For Mac users, use the 'Command' key instead of the 'Ctrl' key"
return msg return msg
\ No newline at end of file
PPOCRLabel/resources.qrc
View file @ adc62fcd
...@@ -18,6 +18,8 @@ ...@@ -18,6 +18,8 @@
<file alias="quit">resources/icons/quit.png</file> <file alias="quit">resources/icons/quit.png</file>
<file alias="copy">resources/icons/copy.png</file> <file alias="copy">resources/icons/copy.png</file>
<file alias="edit">resources/icons/edit.png</file> <file alias="edit">resources/icons/edit.png</file>
<file alias="rotateLeft">resources/icons/rotateLeft.png</file>
<file alias="rotateRight">resources/icons/rotateRight.png</file>
<file alias="open">resources/icons/open.png</file> <file alias="open">resources/icons/open.png</file>
<file alias="save">resources/icons/save.png</file> <file alias="save">resources/icons/save.png</file>
<file alias="format_voc">resources/icons/format_voc.png</file> <file alias="format_voc">resources/icons/format_voc.png</file>
......
PPOCRLabel/resources/strings/strings-zh-CN.properties
View file @ adc62fcd
...@@ -31,6 +31,7 @@ save=确认 ...@@ -31,6 +31,7 @@ save=确认
saveAs=另存为 saveAs=另存为
fitWinDetail=缩放到当前窗口大小 fitWinDetail=缩放到当前窗口大小
openDir=打开目录 openDir=打开目录
openDatasetDir=打开数据集路径
copyPrevBounding=复制当前图像中的上一个边界框 copyPrevBounding=复制当前图像中的上一个边界框
showHide=显示/隐藏标签 showHide=显示/隐藏标签
changeSaveFormat=更改存储格式 changeSaveFormat=更改存储格式
...@@ -85,19 +86,22 @@ detectionBoxposition=检测框位置 ...@@ -85,19 +86,22 @@ detectionBoxposition=检测框位置
recognitionResult=识别结果 recognitionResult=识别结果
creatPolygon=四点标注 creatPolygon=四点标注
drawSquares=正方形标注 drawSquares=正方形标注
saveRec=保存识别结果 rotateLeft=图片左旋转90度
rotateRight=图片右旋转90度
saveRec=导出识别结果
tempLabel=待识别 tempLabel=待识别
nullLabel=无法识别 nullLabel=无法识别
steps=操作步骤 steps=操作步骤
keys=快捷键
choseModelLg=选择模型语言 choseModelLg=选择模型语言
cancel=取消 cancel=取消
ok=确认 ok=确认
autolabeling=自动标注中 autolabeling=自动标注中
hideBox=隐藏所有标注 hideBox=隐藏所有标注
showBox=显示所有标注 showBox=显示所有标注
saveLabel=保存标记结果 saveLabel=导出标记结果
singleRe=重识别此区块 singleRe=重识别此区块
labelDialogOption=弹出标记输入框 labelDialogOption=弹出标记输入框
undo=撤销 undo=撤销
undoLastPoint=撤销上个点 undoLastPoint=撤销上个点
autoSaveMode=自动保存标记结果 autoSaveMode=自动导出标记结果
\ No newline at end of file \ No newline at end of file
PPOCRLabel/resources/strings/strings.properties
View file @ adc62fcd
...@@ -3,6 +3,7 @@ openFileDetail=Open image or label file ...@@ -3,6 +3,7 @@ openFileDetail=Open image or label file
quit=Quit quit=Quit
quitApp=Quit application quitApp=Quit application
openDir=Open Dir openDir=Open Dir
openDatasetDir=Open DatasetDir
copyPrevBounding=Copy previous Bounding Boxes in the current image copyPrevBounding=Copy previous Bounding Boxes in the current image
changeSavedAnnotationDir=Change default saved Annotation dir changeSavedAnnotationDir=Change default saved Annotation dir
openAnnotation=Open Annotation openAnnotation=Open Annotation
...@@ -84,20 +85,23 @@ iconList=Icon List ...@@ -84,20 +85,23 @@ iconList=Icon List
detectionBoxposition=Detection box position detectionBoxposition=Detection box position
recognitionResult=Recognition result recognitionResult=Recognition result
creatPolygon=Create Quadrilateral creatPolygon=Create Quadrilateral
rotateLeft=Left turn 90 degrees
rotateRight=Right turn 90 degrees
drawSquares=Draw Squares drawSquares=Draw Squares
saveRec=Save Recognition Result saveRec=Export Recognition Result
tempLabel=TEMPORARY tempLabel=TEMPORARY
nullLabel=NULL nullLabel=NULL
steps=Steps steps=Steps
keys=Shortcut Keys
choseModelLg=Choose Model Language choseModelLg=Choose Model Language
cancel=Cancel cancel=Cancel
ok=OK ok=OK
autolabeling=Automatic Labeling autolabeling=Automatic Labeling
hideBox=Hide All Box hideBox=Hide All Box
showBox=Show All Box showBox=Show All Box
saveLabel=Save Label saveLabel=Export Label
singleRe=Re-recognition RectBox singleRe=Re-recognition RectBox
labelDialogOption=Pop-up Label Input Dialog labelDialogOption=Pop-up Label Input Dialog
undo=Undo undo=Undo
undoLastPoint=Undo Last Point undoLastPoint=Undo Last Point
autoSaveMode=Auto Save Label Mode autoSaveMode=Auto Export Label Mode
\ No newline at end of file \ No newline at end of file
StyleText/engine/text_drawers.py
View file @ adc62fcd
...@@ -66,6 +66,7 @@ class StdTextDrawer(object): ...@@ -66,6 +66,7 @@ class StdTextDrawer(object):
corpus_list.append(corpus[0:i]) corpus_list.append(corpus[0:i])
text_input_list.append(text_input) text_input_list.append(text_input)
corpus = corpus[i:] corpus = corpus[i:]
i = 0
break break
draw.text((char_x, 2), char_i, fill=(0, 0, 0), font=font) draw.text((char_x, 2), char_i, fill=(0, 0, 0), font=font)
char_x += char_size char_x += char_size
...@@ -78,7 +79,6 @@ class StdTextDrawer(object): ...@@ -78,7 +79,6 @@ class StdTextDrawer(object):
corpus_list.append(corpus[0:i]) corpus_list.append(corpus[0:i])
text_input_list.append(text_input) text_input_list.append(text_input)
corpus = corpus[i:]
break break
return corpus_list, text_input_list return corpus_list, text_input_list
__init__.py
View file @ adc62fcd
...@@ -11,7 +11,8 @@ ...@@ -11,7 +11,8 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and # See the License for the specific language governing permissions and
# limitations under the License. # limitations under the License.
import paddleocr
from .paddleocr import *
__all__ = ['PaddleOCR', 'draw_ocr'] __version__ = paddleocr.VERSION
from .paddleocr import PaddleOCR __all__ = ['PaddleOCR', 'PPStructure', 'draw_ocr', 'draw_structure_result', 'save_structure_res','download_with_progressbar']
from .tools.infer.utility import draw_ocr
configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml 0 → 100644
View file @ adc62fcd
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/ch_db_mv3/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
name: DistillationModel
algorithm: Distillation
Models:
Student:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Student2:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Teacher:
pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
freeze_params: true
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: ResNet
layers: 18
Neck:
name: DBFPN
out_channels: 256
Head:
name: DBHead
k: 50
Loss:
name: CombinedLoss
loss_config_list:
- DistillationDilaDBLoss:
weight: 1.0
model_name_pairs:
- ["Student", "Teacher"]
- ["Student2", "Teacher"]
key: maps
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
- DistillationDMLLoss:
model_name_pairs:
- ["Student", "Student2"]
maps_name: "thrink_maps"
weight: 1.0
# act: None
model_name_pairs: ["Student", "Student2"]
key: maps
- DistillationDBLoss:
weight: 1.0
model_name_list: ["Student", "Student2"]
# key: maps
# name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DistillationDBPostProcess
model_name: ["Student", "Student2", "Teacher"]
# key: maps
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
Metric:
name: DistillationMetric
base_metric_name: DetMetric
main_indicator: hmean
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
ratio_list: [1.0]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [960, 960]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
# image_shape: [736, 1280]
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 2
configs/det/ch_ppocr_v2.1/ch_det_lite_train_distill_v2.1.yml 0 → 100644
View file @ adc62fcd
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/ch_db_mv3/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
name: DistillationModel
algorithm: Distillation
Models:
Student:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Teacher:
pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
freeze_params: true
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: ResNet
layers: 18
Neck:
name: DBFPN
out_channels: 256
Head:
name: DBHead
k: 50
Loss:
name: CombinedLoss
loss_config_list:
- DistillationDilaDBLoss:
weight: 1.0
model_name_pairs:
- ["Student", "Teacher"]
key: maps
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
- DistillationDBLoss:
weight: 1.0
model_name_list: ["Student", "Teacher"]
# key: maps
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DistillationDBPostProcess
model_name: ["Student", "Student2"]
key: head_out
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
Metric:
name: DistillationMetric
base_metric_name: DetMetric
main_indicator: hmean
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
ratio_list: [1.0]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [960, 960]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
# image_shape: [736, 1280]
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 2
configs/det/ch_ppocr_v2.1/ch_det_lite_train_dml_v2.1.yml 0 → 100644
View file @ adc62fcd
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/ch_db_mv3/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
name: DistillationModel
algorithm: Distillation
Models:
Student:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Student2:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Loss:
name: CombinedLoss
loss_config_list:
- DistillationDMLLoss:
model_name_pairs:
- ["Student", "Student2"]
maps_name: "thrink_maps"
weight: 1.0
act: "softmax"
model_name_pairs: ["Student", "Student2"]
key: maps
- DistillationDBLoss:
weight: 1.0
model_name_list: ["Student", "Student2"]
# key: maps
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DistillationDBPostProcess
model_name: ["Student", "Student2"]
key: head_out
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
Metric:
name: DistillationMetric
base_metric_name: DetMetric
main_indicator: hmean
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
ratio_list: [1.0]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [960, 960]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
# image_shape: [736, 1280]
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 2
configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml
View file @ adc62fcd
...@@ -17,7 +17,7 @@ Global: ...@@ -17,7 +17,7 @@ Global:
character_type: ch character_type: ch
max_text_length: 25 max_text_length: 25
infer_mode: false infer_mode: false
use_space_char: false use_space_char: true
distributed: true distributed: true
save_res_path: ./output/rec/predicts_chinese_lite_distillation_v2.1.txt save_res_path: ./output/rec/predicts_chinese_lite_distillation_v2.1.txt
...@@ -27,54 +27,55 @@ Optimizer: ...@@ -27,54 +27,55 @@ Optimizer:
beta1: 0.9 beta1: 0.9
beta2: 0.999 beta2: 0.999
lr: lr:
name: Cosine name: Piecewise
learning_rate: 0.0005 decay_epochs : [700, 800]
values : [0.001, 0.0001]
warmup_epoch: 5 warmup_epoch: 5
regularizer: regularizer:
name: L2 name: L2
factor: 1.0e-05 factor: 2.0e-05
Architecture: Architecture:
model_type: &model_type "rec"
name: DistillationModel name: DistillationModel
algorithm: Distillation algorithm: Distillation
Models: Models:
Student: Teacher:
pretrained: pretrained:
freeze_params: false freeze_params: false
return_all_feats: true return_all_feats: true
model_type: rec model_type: *model_type
algorithm: CRNN algorithm: CRNN
Transform: Transform:
Backbone: Backbone:
name: MobileNetV3 name: MobileNetV1Enhance
scale: 0.5 scale: 0.5
model_name: small
small_stride: [1, 2, 2, 2]
Neck: Neck:
name: SequenceEncoder name: SequenceEncoder
encoder_type: rnn encoder_type: rnn
hidden_size: 48 hidden_size: 64
Head: Head:
name: CTCHead name: CTCHead
fc_decay: 0.00001 mid_channels: 96
Teacher: fc_decay: 0.00002
Student:
pretrained: pretrained:
freeze_params: false freeze_params: false
return_all_feats: true return_all_feats: true
model_type: rec model_type: *model_type
algorithm: CRNN algorithm: CRNN
Transform: Transform:
Backbone: Backbone:
name: MobileNetV3 name: MobileNetV1Enhance
scale: 0.5 scale: 0.5
model_name: small
small_stride: [1, 2, 2, 2]
Neck: Neck:
name: SequenceEncoder name: SequenceEncoder
encoder_type: rnn encoder_type: rnn
hidden_size: 48 hidden_size: 64
Head: Head:
name: CTCHead name: CTCHead
fc_decay: 0.00001 mid_channels: 96
fc_decay: 0.00002
Loss: Loss:
......
configs/rec/rec_icdar15_train.yml
View file @ adc62fcd
...@@ -10,7 +10,7 @@ Global: ...@@ -10,7 +10,7 @@ Global:
cal_metric_during_train: True cal_metric_during_train: True
pretrained_model: pretrained_model:
checkpoints: checkpoints:
save_inference_dir: save_inference_dir: ./
use_visualdl: False use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png infer_img: doc/imgs_words_en/word_10.png
# for data or label process # for data or label process
...@@ -60,8 +60,8 @@ Metric: ...@@ -60,8 +60,8 @@ Metric:
Train: Train:
dataset: dataset:
name: SimpleDataSet name: SimpleDataSet
data_dir: ./train_data/ data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/train_list.txt"] label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms: transforms:
- DecodeImage: # load image - DecodeImage: # load image
img_mode: BGR img_mode: BGR
...@@ -81,8 +81,8 @@ Train: ...@@ -81,8 +81,8 @@ Train:
Eval: Eval:
dataset: dataset:
name: SimpleDataSet name: SimpleDataSet
data_dir: ./train_data/ data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/val_list.txt"] label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms: transforms:
- DecodeImage: # load image - DecodeImage: # load image
img_mode: BGR img_mode: BGR
......
configs/table/table_mv3.yml 0 → 100755
View file @ adc62fcd
Global:
use_gpu: true
epoch_num: 50
log_smooth_window: 20
print_batch_step: 5
save_model_dir: ./output/table_mv3/
save_epoch_step: 5
# evaluation is run every 400 iterations after the 0th iteration
eval_batch_step: [0, 400]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words/ch/word_1.jpg
# for data or label process
character_dict_path: ppocr/utils/dict/table_structure_dict.txt
character_type: en
max_text_length: 100
max_elem_length: 500
max_cell_num: 500
infer_mode: False
process_total_num: 0
process_cut_num: 0
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
clip_norm: 5.0
lr:
learning_rate: 0.001
regularizer:
name: 'L2'
factor: 0.00000
Architecture:
model_type: table
algorithm: TableAttn
Backbone:
name: MobileNetV3
scale: 1.0
model_name: small
disable_se: True
Head:
name: TableAttentionHead
hidden_size: 256
l2_decay: 0.00001
loc_type: 2
Loss:
name: TableAttentionLoss
structure_weight: 100.0
loc_weight: 10000.0
PostProcess:
name: TableLabelDecode
Metric:
name: TableMetric
main_indicator: acc
Train:
dataset:
name: PubTabDataSet
data_dir: train_data/table/pubtabnet/train/
label_file_path: train_data/table/pubtabnet/PubTabNet_2.0.0_train.jsonl
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- ResizeTableImage:
max_len: 488
- TableLabelEncode:
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- PaddingTableImage:
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
loader:
shuffle: True
batch_size_per_card: 32
drop_last: True
num_workers: 1
Eval:
dataset:
name: PubTabDataSet
data_dir: train_data/table/pubtabnet/val/
label_file_path: train_data/table/pubtabnet/PubTabNet_2.0.0_val.jsonl
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- ResizeTableImage:
max_len: 488
- TableLabelEncode:
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- PaddingTableImage:
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 16
num_workers: 1
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment