未验证 提交 a170a8ee 编写于 作者: D Daniel Yang 提交者: GitHub

Merge pull request #1270 from Evezerest/develop

Add English readme, interface and choose the model language function of PPOCRLabel
......@@ -61,7 +61,7 @@ from libs.zoomWidget import ZoomWidget
from libs.autoDialog import AutoDialog
from libs.labelDialog import LabelDialog
from libs.colorDialog import ColorDialog
from libs.labelFile import LabelFile, LabelFileError, LabelFileFormat
from libs.labelFile import LabelFile, LabelFileError
from libs.toolBar import ToolBar
from libs.ustr import ustr
from libs.hashableQListWidgetItem import HashableQListWidgetItem
......@@ -91,7 +91,7 @@ class WindowMixin(object):
class MainWindow(QMainWindow, WindowMixin):
FIT_WINDOW, FIT_WIDTH, MANUAL_ZOOM = list(range(3))
def __init__(self, defaultFilename=None, defaultPrefdefClassFile=None, defaultSaveDir=None, language="zh-CN"):
def __init__(self, lang="ch", defaultFilename=None, defaultPrefdefClassFile=None, defaultSaveDir=None):
super(MainWindow, self).__init__()
self.setWindowTitle(__appname__)
......@@ -99,15 +99,15 @@ class MainWindow(QMainWindow, WindowMixin):
self.settings = Settings()
self.settings.load()
settings = self.settings
self.lang = lang
# Load string bundle for i18n
if language not in ['zh-CN', 'en']:
language = 'zh-CN'
self.stringBundle = StringBundle.getBundle(localeStr=language) # 'en'
if lang not in ['ch', 'en']:
lang = 'en'
self.stringBundle = StringBundle.getBundle(localeStr='zh-CN' if lang=='ch' else 'en') # 'en'
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=True, lang="ch")
self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=False, lang=lang)
if os.path.exists('./data/paddle.png'):
result = self.ocr.ocr('./data/paddle.png', cls=True, det=True)
......@@ -162,7 +162,7 @@ class MainWindow(QMainWindow, WindowMixin):
self.AutoRecognition.setToolButtonStyle(Qt.ToolButtonTextBesideIcon)
self.AutoRecognition.setIcon(newIcon('Auto'))
# self.AutoRecognition.setIconSize(QSize(100,20))
self.AutoRecognition.setFixedSize(QSize(80,30))
# self.AutoRecognition.setFixedSize(QSize(80,30))
# self.AutoRecognition.setStyleSheet('text-align:center;')#border:none;font-size : 12pt;
autoRecLayout = QHBoxLayout()
autoRecLayout.setContentsMargins(0, 0, 0, 0)
......@@ -189,18 +189,18 @@ class MainWindow(QMainWindow, WindowMixin):
self.editButton = QToolButton()
self.reRecogButton = QToolButton()
self.reRecogButton.setIcon(newIcon('reRec', 30))
self.reRecogButton.setFixedSize(QSize(80,30))
# self.reRecogButton.setFixedSize(QSize(80,30))
self.reRecogButton.setToolButtonStyle(Qt.ToolButtonTextBesideIcon)
self.newButton = QToolButton()
self.newButton.setToolButtonStyle(Qt.ToolButtonTextBesideIcon)
self.newButton.setFixedSize(QSize(80, 30))
# self.newButton.setFixedSize(QSize(80, 30))
self.SaveButton = QToolButton()
self.SaveButton.setToolButtonStyle(Qt.ToolButtonTextBesideIcon)
self.SaveButton.setFixedSize(QSize(60, 30))
# self.SaveButton.setFixedSize(QSize(60, 30))
self.DelButton = QToolButton()
self.DelButton.setToolButtonStyle(Qt.ToolButtonTextBesideIcon)
self.DelButton.setFixedSize(QSize(80, 30))
# self.DelButton.setFixedSize(QSize(80, 30))
lefttoptoolbox = QHBoxLayout()
......@@ -423,10 +423,10 @@ class MainWindow(QMainWindow, WindowMixin):
'Ctrl+D', 'copy', getStr('dupBoxDetail'),
enabled=False)
hideAll = action('&Hide\nRectBox', partial(self.togglePolygons, False),
hideAll = action(getStr('hideBox'), partial(self.togglePolygons, False),
'Ctrl+H', 'hide', getStr('hideAllBoxDetail'),
enabled=False)
showAll = action('&Show\nRectBox', partial(self.togglePolygons, True),
showAll = action(getStr('showBox'), partial(self.togglePolygons, True),
'Ctrl+A', 'hide', getStr('showAllBoxDetail'),
enabled=False)
......@@ -593,7 +593,7 @@ class MainWindow(QMainWindow, WindowMixin):
zoomIn, zoomOut, zoomOrg, None,
fitWindow, fitWidth))
addActions(self.menus.autolabel, (saveRec, None, help)) # alcm,
addActions(self.menus.autolabel, (alcm, saveRec, None, help)) #
self.menus.file.aboutToShow.connect(self.updateFileMenu)
......@@ -787,7 +787,7 @@ class MainWindow(QMainWindow, WindowMixin):
QMessageBox.information(self, u'Information', msg)
def showStepsDialog(self):
msg = steps()
msg = stepsInfo(self.lang)
QMessageBox.information(self, u'Information', msg)
def createShape(self):
......@@ -1917,7 +1917,50 @@ class MainWindow(QMainWindow, WindowMixin):
def autolcm(self):
print('autolabelchoosemodel')
vbox = QVBoxLayout()
hbox = QHBoxLayout()
self.panel = QLabel()
self.panel.setText(self.stringBundle.getString('choseModelLg'))
self.panel.setAlignment(Qt.AlignLeft)
self.comboBox = QComboBox()
self.comboBox.setObjectName("comboBox")
self.comboBox.addItems(['Chinese & English', 'English', 'French', 'German', 'Korean', 'Japanese'])
# self.comboBox_lg = QComboBox()
# self.comboBox_lg.setObjectName("comboBox_language")
vbox.addWidget(self.panel)
vbox.addWidget(self.comboBox)
self.dialog = QDialog()
self.dialog.resize(300, 100)
self.okBtn = QPushButton(self.stringBundle.getString('ok'))
self.cancelBtn = QPushButton(self.stringBundle.getString('cancel'))
self.okBtn.clicked.connect(self.modelChoose)
self.cancelBtn.clicked.connect(self.cancel)
self.dialog.setWindowTitle(self.stringBundle.getString('choseModelLg'))
hbox.addWidget(self.okBtn)
hbox.addWidget(self.cancelBtn)
vbox.addWidget(self.panel)
vbox.addLayout(hbox)
self.dialog.setLayout(vbox)
self.dialog.setWindowModality(Qt.ApplicationModal)
self.dialog.exec_()
if self.filePath:
self.AutoRecognition.setEnabled(True)
def modelChoose(self):
print(self.comboBox.currentText())
lg_idx = {'Chinese & English': 'ch', 'English': 'en', 'French': 'french', 'German': 'german',
'Korean': 'korean', 'Japanese': 'japan'}
del self.ocr
self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=False,
lang=lg_idx[self.comboBox.currentText()])
self.dialog.close()
def cancel(self):
self.dialog.close()
def loadFilestate(self, saveDir):
self.fileStatepath = saveDir + '/fileState.txt'
......@@ -2020,18 +2063,15 @@ def get_main_app(argv=[]):
app.setWindowIcon(newIcon("app"))
# Tzutalin 201705+: Accept extra agruments to change predefined class file
argparser = argparse.ArgumentParser()
argparser.add_argument("image_dir", nargs="?")
argparser.add_argument("language", default='zh-CN',nargs="?")
argparser.add_argument("predefined_classes_file",
argparser.add_argument("--lang", default='ch', nargs="?")
argparser.add_argument("--predefined_classes_file",
default=os.path.join(os.path.dirname(__file__), "data", "predefined_classes.txt"),
nargs="?")
argparser.add_argument("save_dir", nargs="?")
args = argparser.parse_args(argv[1:])
# Usage : labelImg.py image predefClassFile saveDir
win = MainWindow(args.image_dir,
args.predefined_classes_file,
args.save_dir,
args.language)
win = MainWindow(lang=args.lang,
defaultPrefdefClassFile=args.predefined_classes_file,
)
win.show()
return app, win
......
# PPOCRLabel
PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field. It is written in python3 and pyqt5. Support rectangular frame labeling and four-point labeling mode. Annotations can be directly used for the training of PPOCR detection and recognition models.
<img src="./data/gif/steps.gif" width="100%"/>
## Installation
### 1. Install PaddleOCR
Refer to [PaddleOCR installation document](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/installation.md) to prepare PaddleOCR
### 2. Install PPOCRLabel
#### Windows + Anaconda
Download and install [Anaconda](https://www.anaconda.com/download/#download) (Python 3+)
```
conda install pyqt=5
cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
pyrcc5 -o libs/resources.py resources.qrc
python PPOCRLabel.py --lang en
```
#### Ubuntu Linux
```
sudo apt-get install pyqt5-dev-tools
sudo apt-get install trash-cli
cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
sudo pip3 install -r requirements/requirements-linux-python3.txt
make qt5py3
python3 PPOCRLabel.py --lang en
```
#### macOS
```
pip3 install pyqt5
pip3 uninstall opencv-python # Uninstall opencv manually as it conflicts with pyqt
pip3 install opencv-contrib-python-headless # Install the headless version of opencv
cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
make qt5py3
python3 PPOCRLabel.py --lang en
```
## Usage
### Steps
1. Build and launch using the instructions above.
2. Click 'Open Dir' in Menu/File to select the folder of the picture.<sup>[1]</sup>
3. Click 'Auto recognition', use PPOCR model to automatically annotate images which marked with 'X' <sup>[2]</sup>before the file name.
4. Create Box:
4.1 Click 'Create RectBox' or press 'W' in English keyboard mode to draw a new rectangle detection box. Click and release left mouse to select a region to annotate the text area.
4.2 Press 'P' to enter four-point labeling mode which enables you to create any four-point shape by clicking four points with the left mouse button in succession and DOUBLE CLICK the left mouse as the signal of labeling completion.
5. After the marking frame is drawn, the user clicks "OK", and the detection frame will be pre-assigned a "TEMPORARY" label.
6. Click 're-Recognition', model will rewrite ALL recognition results in ALL detection box<sup>[3]</sup>.
7. Double click the result in 'recognition result' list to manually change inaccurate recognition results.
8. Click "Save", 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.
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.
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>.
### 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".
[2] The image status indicates whether the user has saved the image manually. If it has not been saved manually it is "X", otherwise it is "√", PPOCRLabel will not relabel pictures with a status of "√".
[3] After clicking "Re-recognize", the model will overwrite ALL recognition results in the picture.
Therefore, if the recognition result has been manually changed before, it may change after re-recognition.
[4] The files produced by PPOCRLabel include the following, please do not manually change the contents, otherwise it will cause the program to be abnormal.
| File name | Description |
| :-----------: | :----------------------------------------------------------: |
| Label.txt | The detection label file can be directly used for PPOCR detection model training. After the user saves 10 label results, the file will be automatically saved. 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. |
| 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 "PaddleOCR"-"Save recognition result". |
| crop_img | The recognition data, generated at the same time with *rec_gt.txt* |
## Related
1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)
因为 它太大了无法显示 source diff 。你可以改为 查看blob
......@@ -150,7 +150,8 @@ def get_rotate_crop_image(img, points):
except Exception as e:
print(e)
def steps():
def stepsInfo(lang='en'):
if lang == 'ch':
msg = "1. 安装与运行:使用上述命令安装与运行程序。\n" \
"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.\n"\
"3. 自动标注:点击 ”自动标注“,使用PPOCR超轻量模型对图片文件名前图片状态为 “X” 的图片进行自动标注。\n" \
......@@ -164,4 +165,18 @@ def steps():
"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," \
"识别标签保存在*rec_gt.txt*中。\n"
else:
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"\
"3. Click 'Auto recognition', use PPOCR model to automatically annotate images which marked with 'X' before the file name."\
"4. Create Box:\n"\
"4.1 Click 'Create RectBox' or press 'W' in English keyboard mode to draw a new rectangle detection box. Click and release left mouse to select a region to annotate the text area.\n"\
"4.2 Press 'P' to enter four-point labeling mode which enables you to create any four-point shape by clicking four points with the left mouse button in succession and DOUBLE CLICK the left mouse as the signal of labeling completion.\n"\
"5. After the marking frame is drawn, the user clicks 'OK', and the detection frame will be pre-assigned a TEMPORARY label.\n"\
"6. Click re-Recognition, model will rewrite ALL recognition results in ALL detection box.\n"\
"7. Double click the result in 'recognition result' list to manually change inaccurate recognition results.\n"\
"8. Click 'Save', the image status will switch to '√',then the program automatically jump to the next.\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"\
" 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
\ No newline at end of file
......@@ -88,3 +88,9 @@ drawSquares=正方形标注
saveRec=保存识别结果
tempLabel=待识别
steps=操作步骤
choseModelLg=选择模型语言
cancel=取消
ok=确认
autolabeling=自动标注中
hideBox=隐藏所有标注
showBox=显示所有标注
\ No newline at end of file
......@@ -76,10 +76,10 @@ ImageResize=Image Resize
IR=Image Resize
autoRecognition=Auto Recognition
reRecognition=Re-recognition
mfile=file
medit=eidt
mview=view
mhelp=help
mfile=File
medit=Eidt
mview=View
mhelp=Help
iconList=Icon List
detectionBoxposition=Detection box position
recognitionResult=Recognition result
......@@ -87,4 +87,10 @@ creatPolygon=Create Quadrilateral
drawSquares=Draw Squares
saveRec=Save Recognition Result
tempLabel=TEMPORARY
setps=Steps
\ No newline at end of file
steps=Steps
choseModelLg=Choose Model Language
cancel=Cancel
ok=OK
autolabeling=Automatic Labeling
hideBox=Hide All Box
showBox=Show All Box
\ No newline at end of file
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册