Merge pull request #1270 from Evezerest/develop
Add English readme, interface and choose the model language function of PPOCRLabel
This commit is contained in:
Daniel Yang
GitHub
commit
a170a8ee37
|
|
@ -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
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,97 @@
|
|||
# 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)
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -150,18 +150,33 @@ def get_rotate_crop_image(img, points):
|
|||
except Exception as e:
|
||||
print(e)
|
||||
|
||||
def steps():
|
||||
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" \
|
||||
"4. 手动标注：点击 “矩形标注”（推荐直接在英文模式下点击键盘中的 “W”)，用户可对当前图片中模型未检出的部分进行手动" \
|
||||
"绘制标记框。点击键盘P，则使用四点标注模式（或点击“编辑” - “四点标注”），用户依次点击4个点后，双击左键表示标注完成。\n" \
|
||||
"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。\n" \
|
||||
"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。\n" \
|
||||
"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。\n" \
|
||||
"8. 保存：点击 “保存”，图片状态切换为 “√”，跳转至下一张。\n" \
|
||||
"9. 删除：点击 “删除图像”，图片将会被删除至回收站。\n" \
|
||||
"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"
|
||||
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" \
|
||||
"4. 手动标注：点击 “矩形标注”（推荐直接在英文模式下点击键盘中的 “W”)，用户可对当前图片中模型未检出的部分进行手动" \
|
||||
"绘制标记框。点击键盘P，则使用四点标注模式（或点击“编辑” - “四点标注”），用户依次点击4个点后，双击左键表示标注完成。\n" \
|
||||
"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。\n" \
|
||||
"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。\n" \
|
||||
"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。\n" \
|
||||
"8. 保存：点击 “保存”，图片状态切换为 “√”，跳转至下一张。\n" \
|
||||
"9. 删除：点击 “删除图像”，图片将会被删除至回收站。\n" \
|
||||
"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
|
||||
|
|
@ -87,4 +87,10 @@ creatPolygon=四点标注
|
|||
drawSquares=正方形标注
|
||||
saveRec=保存识别结果
|
||||
tempLabel=待识别
|
||||
steps=操作步骤
|
||||
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
|
||||
|
|
@ -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
|
||||
steps=Steps
|
||||
choseModelLg=Choose Model Language
|
||||
cancel=Cancel
|
||||
ok=OK
|
||||
autolabeling=Automatic Labeling
|
||||
hideBox=Hide All Box
|
||||
showBox=Show All Box
|
||||
Loading…
Reference in New Issue