Skip to content

GitLab

"tests/L1/cross_product_distributed/compare.py" did not exist on "d24c25b92ad05281f018aa489122756afdf3607d"
Commit f7081e38 authored by WenmuZhou's avatar WenmuZhou
Browse files

Merge remote-tracking branch 'origin/lite' into lite

parents 40f20c6f 3f1cb773
Show whitespace changes
Inline Side-by-side
Showing with 11131 additions and 10911 deletions
PPOCRLabel/PPOCRLabel.py
View file @ f7081e38
......@@ -206,7 +206,7 @@ class MainWindow(QMainWindow, WindowMixin):
self.labelList = EditInList()
labelListContainer = QWidget()
labelListContainer.setLayout(listLayout)
self.labelList.itemActivated.connect(self.labelSelectionChanged)
#self.labelList.itemActivated.connect(self.labelSelectionChanged)
self.labelList.itemSelectionChanged.connect(self.labelSelectionChanged)
self.labelList.clicked.connect(self.labelList.item_clicked)
# Connect to itemChanged to detect checkbox changes.
......@@ -219,7 +219,7 @@ class MainWindow(QMainWindow, WindowMixin):
################## detection box ####################
self.BoxList = QListWidget()
self.BoxList.itemActivated.connect(self.boxSelectionChanged)
#self.BoxList.itemActivated.connect(self.boxSelectionChanged)
self.BoxList.itemSelectionChanged.connect(self.boxSelectionChanged)
self.BoxList.itemDoubleClicked.connect(self.editBox)
# Connect to itemChanged to detect checkbox changes.
......@@ -435,7 +435,7 @@ class MainWindow(QMainWindow, WindowMixin):
######## New actions #######
AutoRec = action(getStr('autoRecognition'), self.autoRecognition,
'Ctrl+Shift+A', 'Auto', getStr('autoRecognition'), enabled=False)
'', 'Auto', getStr('autoRecognition'), enabled=False)
reRec = action(getStr('reRecognition'), self.reRecognition,
'Ctrl+Shift+R', 'reRec', getStr('reRecognition'), enabled=False)
......@@ -444,7 +444,7 @@ class MainWindow(QMainWindow, WindowMixin):
'Ctrl+R', 'reRec', getStr('singleRe'), enabled=False)
createpoly = action(getStr('creatPolygon'), self.createPolygon,
'q', 'new', 'Creat Polygon', enabled=True)
'q', 'new', getStr('creatPolygon'), enabled=True)
saveRec = action(getStr('saveRec'), self.saveRecResult,
'', 'save', getStr('saveRec'), enabled=False)
......@@ -452,6 +452,12 @@ class MainWindow(QMainWindow, WindowMixin):
saveLabel = action(getStr('saveLabel'), self.saveLabelFile, #
'Ctrl+S', 'save', getStr('saveLabel'), enabled=False)
undoLastPoint = action(getStr("undoLastPoint"), self.canvas.undoLastPoint,
'Ctrl+Z', "undo", getStr("undoLastPoint"), enabled=False)
undo = action(getStr("undo"), self.undoShapeEdit,
'Ctrl+Z', "undo", getStr("undo"), enabled=False)
self.editButton.setDefaultAction(edit)
self.newButton.setDefaultAction(create)
self.DelButton.setDefaultAction(deleteImg)
......@@ -512,10 +518,11 @@ class MainWindow(QMainWindow, WindowMixin):
zoom=zoom, zoomIn=zoomIn, zoomOut=zoomOut, zoomOrg=zoomOrg,
fitWindow=fitWindow, fitWidth=fitWidth,
zoomActions=zoomActions, saveLabel=saveLabel,
undo=undo, undoLastPoint=undoLastPoint,
fileMenuActions=(
opendir, saveLabel, resetAll, quit),
beginner=(), advanced=(),
editMenu=(createpoly, edit, copy, delete,singleRere,
editMenu=(createpoly, edit, copy, delete,singleRere,None, undo, undoLastPoint,
None, color1, self.drawSquaresOption),
beginnerContext=(create, edit, copy, delete, singleRere),
advancedContext=(createMode, editMode, edit, copy,
......@@ -549,8 +556,13 @@ class MainWindow(QMainWindow, WindowMixin):
self.labelDialogOption.setChecked(settings.get(SETTING_PAINT_LABEL, False))
self.labelDialogOption.triggered.connect(self.speedChoose)
self.autoSaveOption = QAction(getStr('autoSaveMode'), self)
self.autoSaveOption.setCheckable(True)
self.autoSaveOption.setChecked(settings.get(SETTING_PAINT_LABEL, False))
self.autoSaveOption.triggered.connect(self.autoSaveFunc)
addActions(self.menus.file,
(opendir, None, saveLabel, saveRec, None, resetAll, deleteImg, quit))
(opendir, None, saveLabel, saveRec, self.autoSaveOption, None, resetAll, deleteImg, quit))
addActions(self.menus.help, (showSteps, showInfo))
addActions(self.menus.view, (
......@@ -566,9 +578,9 @@ class MainWindow(QMainWindow, WindowMixin):
# Custom context menu for the canvas widget:
addActions(self.canvas.menus[0], self.actions.beginnerContext)
addActions(self.canvas.menus[1], (
action('&Copy here', self.copyShape),
action('&Move here', self.moveShape)))
#addActions(self.canvas.menus[1], (
# action('&Copy here', self.copyShape),
# action('&Move here', self.moveShape)))
self.statusBar().showMessage('%s started.' % __appname__)
......@@ -758,6 +770,7 @@ class MainWindow(QMainWindow, WindowMixin):
self.canvas.setEditing(False)
self.canvas.fourpoint = True
self.actions.create.setEnabled(False)
self.actions.undoLastPoint.setEnabled(True)
def toggleDrawingSensitive(self, drawing=True):
"""In the middle of drawing, toggling between modes should be disabled."""
......@@ -866,10 +879,11 @@ class MainWindow(QMainWindow, WindowMixin):
self.updateComboBox()
def updateBoxlist(self):
shape = self.canvas.selectedShape
for shape in self.canvas.selectedShapes+[self.canvas.hShape]:
item = self.shapesToItemsbox[shape] # listitem
text = [(int(p.x()), int(p.y())) for p in shape.points]
item.setText(str(text))
self.actions.undo.setEnabled(True)
self.setDirty()
def indexTo5Files(self, currIndex):
......@@ -902,23 +916,27 @@ class MainWindow(QMainWindow, WindowMixin):
if len(self.mImgList) > 0:
self.zoomWidget.setValue(self.zoomWidgetValue + self.imgsplider.value())
# React to canvas signals.
def shapeSelectionChanged(self, selected=False):
if self._noSelectionSlot:
self._noSelectionSlot = False
else:
shape = self.canvas.selectedShape
if shape:
self.shapesToItems[shape].setSelected(True)
self.shapesToItemsbox[shape].setSelected(True) # ADD
else:
def shapeSelectionChanged(self, selected_shapes):
self._noSelectionSlot = True
for shape in self.canvas.selectedShapes:
shape.selected = False
self.labelList.clearSelection()
self.actions.delete.setEnabled(selected)
self.actions.copy.setEnabled(selected)
self.actions.edit.setEnabled(selected)
self.actions.shapeLineColor.setEnabled(selected)
self.actions.shapeFillColor.setEnabled(selected)
self.actions.singleRere.setEnabled(selected)
self.canvas.selectedShapes = selected_shapes
for shape in self.canvas.selectedShapes:
shape.selected = True
self.shapesToItems[shape].setSelected(True)
self.shapesToItemsbox[shape].setSelected(True)
self.labelList.scrollToItem(self.currentItem()) # QAbstractItemView.EnsureVisible
self.BoxList.scrollToItem(self.currentBox())
self._noSelectionSlot = False
n_selected = len(selected_shapes)
self.actions.singleRere.setEnabled(n_selected)
self.actions.delete.setEnabled(n_selected)
self.actions.copy.setEnabled(n_selected)
self.actions.edit.setEnabled(n_selected == 1)
def addLabel(self, shape):
shape.paintLabel = self.displayLabelOption.isChecked()
......@@ -941,10 +959,11 @@ class MainWindow(QMainWindow, WindowMixin):
action.setEnabled(True)
self.updateComboBox()
def remLabel(self, shape):
if shape is None:
def remLabels(self, shapes):
if shapes is None:
# print('rm empty label')
return
for shape in shapes:
item = self.shapesToItems[shape]
self.labelList.takeItem(self.labelList.row(item))
del self.shapesToItems[shape]
......@@ -1001,7 +1020,7 @@ class MainWindow(QMainWindow, WindowMixin):
item.setText(str([(int(p.x()), int(p.y())) for p in shape.points]))
self.updateComboBox()
def updateComboBox(self):
def updateComboBox(self): # TODO：貌似没用
# Get the unique labels and add them to the Combobox.
itemsTextList = [str(self.labelList.item(i).text()) for i in range(self.labelList.count())]
......@@ -1031,7 +1050,7 @@ class MainWindow(QMainWindow, WindowMixin):
for box in self.result_dic:
trans_dic = {"label": box[1][0], "points": box[0], 'difficult': False}
if trans_dic["label"] is "" and mode == 'Auto':
if trans_dic["label"] == "" and mode == 'Auto':
continue
shapes.append(trans_dic)
......@@ -1054,26 +1073,38 @@ class MainWindow(QMainWindow, WindowMixin):
return False
def copySelectedShape(self):
self.addLabel(self.canvas.copySelectedShape())
for shape in self.canvas.copySelectedShape():
self.addLabel(shape)
# fix copy and delete
self.shapeSelectionChanged(True)
#self.shapeSelectionChanged(True)
def labelSelectionChanged(self):
item = self.currentItem()
self.labelList.scrollToItem(item, QAbstractItemView.EnsureVisible)
if item and self.canvas.editing():
self._noSelectionSlot = True
self.canvas.selectShape(self.itemsToShapes[item])
shape = self.itemsToShapes[item]
if self._noSelectionSlot:
return
if self.canvas.editing():
selected_shapes = []
for item in self.labelList.selectedItems():
selected_shapes.append(self.itemsToShapes[item])
if selected_shapes:
self.canvas.selectShapes(selected_shapes)
else:
self.canvas.deSelectShape()
def boxSelectionChanged(self):
item = self.currentBox()
self.BoxList.scrollToItem(item, QAbstractItemView.EnsureVisible)
if item and self.canvas.editing():
self._noSelectionSlot = True
self.canvas.selectShape(self.itemsToShapesbox[item])
shape = self.itemsToShapesbox[item]
if self._noSelectionSlot:
#self.BoxList.scrollToItem(self.currentBox(), QAbstractItemView.PositionAtCenter)
return
if self.canvas.editing():
selected_shapes = []
for item in self.BoxList.selectedItems():
selected_shapes.append(self.itemsToShapesbox[item])
if selected_shapes:
self.canvas.selectShapes(selected_shapes)
else:
self.canvas.deSelectShape()
def labelItemChanged(self, item):
shape = self.itemsToShapes[item]
......@@ -1113,6 +1144,8 @@ class MainWindow(QMainWindow, WindowMixin):
if self.beginner(): # Switch to edit mode.
self.canvas.setEditing(True)
self.actions.create.setEnabled(True)
self.actions.undoLastPoint.setEnabled(False)
self.actions.undo.setEnabled(True)
else:
self.actions.editMode.setEnabled(True)
self.setDirty()
......@@ -1450,7 +1483,7 @@ class MainWindow(QMainWindow, WindowMixin):
item = QListWidgetItem(closeicon, filename)
self.fileListWidget.addItem(item)
print('dirPath in importDirImages is', dirpath)
print('DirPath in importDirImages is', dirpath)
self.iconlist.clear()
self.additems5(dirpath)
self.changeFileFolder = True
......@@ -1459,7 +1492,6 @@ class MainWindow(QMainWindow, WindowMixin):
self.reRecogButton.setEnabled(True)
self.actions.AutoRec.setEnabled(True)
self.actions.reRec.setEnabled(True)
self.actions.saveLabel.setEnabled(True)
def openPrevImg(self, _value=False):
......@@ -1549,6 +1581,7 @@ class MainWindow(QMainWindow, WindowMixin):
self.fileListWidget.insertItem(int(currIndex), item)
self.openNextImg()
self.actions.saveRec.setEnabled(True)
self.actions.saveLabel.setEnabled(True)
elif mode == 'Auto':
if annotationFilePath and self.saveLabels(annotationFilePath, mode=mode):
......@@ -1644,7 +1677,8 @@ class MainWindow(QMainWindow, WindowMixin):
self.setDirty()
def deleteSelectedShape(self):
self.remLabel(self.canvas.deleteSelected())
self.remLabels(self.canvas.deleteSelected())
self.actions.undo.setEnabled(True)
self.setDirty()
if self.noShapes():
for action in self.actions.onShapesPresent:
......@@ -1654,7 +1688,7 @@ class MainWindow(QMainWindow, WindowMixin):
color = self.colorDialog.getColor(self.lineColor, u'Choose line color',
default=DEFAULT_LINE_COLOR)
if color:
self.canvas.selectedShape.line_color = color
for shape in self.canvas.selectedShapes: shape.line_color = color
self.canvas.update()
self.setDirty()
......@@ -1662,7 +1696,7 @@ class MainWindow(QMainWindow, WindowMixin):
color = self.colorDialog.getColor(self.fillColor, u'Choose fill color',
default=DEFAULT_FILL_COLOR)
if color:
self.canvas.selectedShape.fill_color = color
for shape in self.canvas.selectedShapes: shape.fill_color = color
self.canvas.update()
self.setDirty()
......@@ -1764,7 +1798,7 @@ class MainWindow(QMainWindow, WindowMixin):
QMessageBox.information(self, "Information", msg)
return
result = self.ocr.ocr(img_crop, cls=True, det=False)
if result[0][0] is not '':
if result[0][0] != '':
result.insert(0, box)
print('result in reRec is ', result)
self.result_dic.append(result)
......@@ -1786,7 +1820,7 @@ class MainWindow(QMainWindow, WindowMixin):
def singleRerecognition(self):
img = cv2.imread(self.filePath)
shape = self.canvas.selectedShape
for shape in self.canvas.selectedShapes:
box = [[int(p.x()), int(p.y())] for p in shape.points]
assert len(box) == 4
img_crop = get_rotate_crop_image(img, np.array(box, np.float32))
......@@ -1795,7 +1829,7 @@ class MainWindow(QMainWindow, WindowMixin):
QMessageBox.information(self, "Information", msg)
return
result = self.ocr.ocr(img_crop, cls=True, det=False)
if result[0][0] is not '':
if result[0][0] != '':
result.insert(0, box)
print('result in reRec is ', result)
if result[1][0] == shape.label:
......@@ -1862,6 +1896,8 @@ class MainWindow(QMainWindow, WindowMixin):
for each in states:
file, state = each.split('\t')
self.fileStatedict[file] = 1
self.actions.saveLabel.setEnabled(True)
self.actions.saveRec.setEnabled(True)
def saveFilestate(self):
......@@ -1913,28 +1949,35 @@ class MainWindow(QMainWindow, WindowMixin):
self.savePPlabel()
def saveRecResult(self):
if None in [self.PPlabelpath, self.PPlabel, self.fileStatedict]:
QMessageBox.information(self, "Information", "Save file first")
if {} in [self.PPlabelpath, self.PPlabel, self.fileStatedict]:
QMessageBox.information(self, "Information", "Check the image first")
return
rec_gt_dir = os.path.dirname(self.PPlabelpath) + '/rec_gt.txt'
crop_img_dir = os.path.dirname(self.PPlabelpath) + '/crop_img/'
ques_img = []
if not os.path.exists(crop_img_dir):
os.mkdir(crop_img_dir)
with open(rec_gt_dir, 'w', encoding='utf-8') as f:
for key in self.fileStatedict:
idx = self.getImglabelidx(key)
try:
img = cv2.imread(key)
for i, label in enumerate(self.PPlabel[idx]):
if label['difficult']: continue
img = cv2.imread(key)
img_crop = get_rotate_crop_image(img, np.array(label['points'], np.float32))
img_name = os.path.splitext(os.path.basename(idx))[0] + '_crop_'+str(i)+'.jpg'
cv2.imwrite(crop_img_dir+img_name, img_crop)
f.write('crop_img/'+ img_name + '\t')
f.write(label['transcription'] + '\n')
QMessageBox.information(self, "Information", "Cropped images has been saved in "+str(crop_img_dir))
except Exception as e:
ques_img.append(key)
print("Can not read image ",e)
if ques_img:
QMessageBox.information(self, "Information", "The following images can not be saved, "
"please check the image path and labels.\n" + "".join(str(i)+'\n' for i in ques_img))
QMessageBox.information(self, "Information", "Cropped images have been saved in "+str(crop_img_dir))
def speedChoose(self):
if self.labelDialogOption.isChecked():
......@@ -1945,6 +1988,33 @@ class MainWindow(QMainWindow, WindowMixin):
self.canvas.newShape.disconnect()
self.canvas.newShape.connect(partial(self.newShape, False))
def autoSaveFunc(self):
if self.autoSaveOption.isChecked():
self.autoSaveNum = 1 # Real auto_Save
try:
self.saveLabelFile()
except:
pass
print('The program will automatically save once after confirming an image')
else:
self.autoSaveNum = 5 # Used for backup
print('The program will automatically save once after confirming 5 images (default)')
def undoShapeEdit(self):
self.canvas.restoreShape()
self.labelList.clear()
self.BoxList.clear()
self.loadShapes(self.canvas.shapes)
self.actions.undo.setEnabled(self.canvas.isShapeRestorable)
def loadShapes(self, shapes, replace=True):
self._noSelectionSlot = True
for shape in shapes:
self.addLabel(shape)
self.labelList.clearSelection()
self._noSelectionSlot = False
self.canvas.loadShapes(shapes, replace=replace)
def inverted(color):
return QColor(*[255 - v for v in color.getRgb()])
......@@ -1991,7 +2061,7 @@ if __name__ == '__main__':
resource_file = './libs/resources.py'
if not os.path.exists(resource_file):
output = os.system('pyrcc5 -o libs/resources.py resources.qrc')
assert output is 0, "operate the cmd have some problems ,please check whether there is a in the lib " \
assert output == 0, "operate the cmd have some problems ,please check whether there is a in the lib " \
"directory resources.py "
import libs.resources
sys.exit(main())
PPOCRLabel/README.md
View file @ f7081e38
......@@ -8,6 +8,10 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w
### Recent Update
- 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.
- 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)).
- 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".
- The recognition result scrolls synchronously when users click related detection box.
......@@ -16,7 +20,6 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w
### TODO:
- Lock box mode: For the same scene data, the size and position of the locked detection box can be transferred between different pictures.
- Experience optimization: Add undo, batch operation include move, copy, delete and so on, optimize the annotation process.
## Installation
......@@ -49,7 +52,7 @@ python3 PPOCRLabel.py
```
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
pip3 install opencv-contrib-python-headless==4.2.0.32 # Install the headless version of opencv
cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
python3 PPOCRLabel.py
```
......@@ -76,12 +79,11 @@ python3 PPOCRLabel.py
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(The results will not be written directly to the file at this time).
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.
10. Labeling result: the user can save manually through the menu "File - Save Label", while the program will also save automatically after every 5 images confirmed by the user.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 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>.
### Note
......@@ -89,8 +91,7 @@ python3 PPOCRLabel.py
[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.
[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 can be found under the opened picture folder including the following, please do not manually change the contents, otherwise it will cause the program to be abnormal.
......@@ -107,13 +108,14 @@ Therefore, if the recognition result has been manually changed before, it may ch
### Shortcut keys
| Shortcut keys | Description |
| ---------------- | ------------------------------------------------ |
| Ctrl + shift + A | Automatically label all unchecked images |
| Ctrl + shift + R | Re-recognize all the labels of the current image |
| ------------------------ | ------------------------------------------------ |
| Ctrl + Shift + R | Re-recognize all the labels of the current image |
| W | Create a rect box |
| Q | Create a four-points box |
| Ctrl + E | Edit label of the selected box |
| Ctrl + R | Re-recognize the selected box |
| Ctrl + C | Copy and paste the selected box |
| Ctrl + Left Mouse Button | Multi select the label box |
| Backspace | Delete the selected box |
| Ctrl + V | Check image |
| Ctrl + Shift + d | Delete image |
......@@ -136,7 +138,7 @@ Therefore, if the recognition result has been manually changed before, it may ch
PPOCRLabel supports three ways to save Label.txt
- Automatically save: When it detects that the user has manually checked 5 pictures, the program automatically writes the annotations into Label.txt. The user can change the value of ``self.autoSaveNum`` in ``PPOCRLabel.py`` to set the number of images to be automatically saved after confirmation.
- 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.
- Manual save: Click "File-Save Marking Results" to manually save the label.
- Close application save
......@@ -160,9 +162,9 @@ For some data that are difficult to recognize, the recognition results will not
```
pyrcc5 -o libs/resources.py resources.qrc
```
- If you get an error ``` module 'cv2' has no attribute 'INTER_NEAREST'```, you need to delete all opencv related packages first, and then reinstall the headless version of opencv
- If you get an error ``` module 'cv2' has no attribute 'INTER_NEAREST'```, you need to delete all opencv related packages first, and then reinstall the 4.2.0.32 version of headless opencv
```
pip install opencv-contrib-python-headless
pip install opencv-contrib-python-headless==4.2.0.32
```
### Related
......
PPOCRLabel/README_ch.md
View file @ f7081e38
......@@ -8,6 +8,10 @@ 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
- 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。
- 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)）
- 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。
- 识别结果与检测框同步滚动。
......@@ -17,9 +21,8 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置P
#### 尽请期待
- 锁定框模式：针对同一场景数据，被锁定的检测框的大小与位置能在不同图片之间传递。
- 体验优化：增加撤销操作，批量移动、复制、删除等功能。优化标注流程。
如果您对以上内容感兴趣或对完善工具有不一样的想法，欢迎加入我们的队伍与我们共同开发
如果您对以上内容感兴趣或对完善工具有不一样的想法，欢迎加入我们的SIG队伍与我们共同开发。可以在[此处](https://github.com/PaddlePaddle/PaddleOCR/issues/1728)完成问卷和前置任务，经过我们确认相关内容后即可正式加入，享受SIG福利，共同为OCR开源事业贡献（特别说明：针对PPOCRLabel的改进也属于PaddleOCR前置任务）
## 安装
......@@ -49,7 +52,7 @@ python3 PPOCRLabel.py --lang ch
```
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 install opencv-contrib-python-headless # 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
cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
python3 PPOCRLabel.py --lang ch
```
......@@ -65,9 +68,9 @@ 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。
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。
8. 确认标记：点击 “确认”，图片状态切换为 “√”，跳转至下一张（此时不会直接将结果写入文件）。
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。
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，同时程序也会在用户每确认5张图片后自动保存一次。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. 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>。
### 注意
......@@ -93,12 +96,13 @@ python3 PPOCRLabel.py --lang ch
| 快捷键 | 说明 |
| ---------------- | ---------------------------- |
| Ctrl + shift + A | 自动标注所有未确认过的图片 |
| Ctrl + shift + R | 对当前图片的所有标记重新识别 |
| W | 新建矩形框 |
| Q | 新建四点框 |
| Ctrl + E | 编辑所选框标签 |
| Ctrl + R | 重新识别所选标记 |
| Ctrl + C | 复制并粘贴选中的标记框 |
| Ctrl + 鼠标左键 | 多选标记框 |
| Backspace | 删除所选框 |
| Ctrl + V | 确认本张图片标记 |
| Ctrl + Shift + d | 删除本张图片 |
......@@ -120,7 +124,7 @@ python3 PPOCRLabel.py --lang ch
PPOCRLabel支持三种保存方式：
- 程序自动保存：当检测到用户手动确认过5张图片后，程序自动将标记结果写入Label.txt中。其中用户可通过更改```PPOCRLabel.py```中的```self.autoSaveNum```的数值设置确认几张图片后进行自动保存。
- 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。
- 手动保存：点击“文件 - 保存标记结果”手动保存标记。
- 关闭应用程序保存
......@@ -145,9 +149,9 @@ PPOCRLabel支持三种保存方式：
pyrcc5 -o libs/resources.py resources.qrc
```
- 如果出现``` module 'cv2' has no attribute 'INTER_NEAREST'```错误，需要首先删除所有opencv相关包，然后重新安装headless版本的opencv
- 如果出现``` module 'cv2' has no attribute 'INTER_NEAREST'```错误，需要首先删除所有opencv相关包，然后重新安装4.2.0.32版本的headless opencv
```
pip install opencv-contrib-python-headless
pip install opencv-contrib-python-headless==4.2.0.32
```
### 参考资料
......
PPOCRLabel/libs/canvas.py
View file @ f7081e38
......@@ -37,7 +37,8 @@ class Canvas(QWidget):
zoomRequest = pyqtSignal(int)
scrollRequest = pyqtSignal(int, int)
newShape = pyqtSignal()
selectionChanged = pyqtSignal(bool)
# selectionChanged = pyqtSignal(bool)
selectionChanged = pyqtSignal(list)
shapeMoved = pyqtSignal()
drawingPolygon = pyqtSignal(bool)
......@@ -51,9 +52,11 @@ class Canvas(QWidget):
# Initialise local state.
self.mode = self.EDIT
self.shapes = []
self.shapesBackups = []
self.current = None
self.selectedShapes = []
self.selectedShape = None # save the selected shape here
self.selectedShapeCopy = None
self.selectedShapesCopy = []
self.drawingLineColor = QColor(0, 0, 255)
self.drawingRectColor = QColor(0, 0, 255)
self.line = Shape(line_color=self.drawingLineColor)
......@@ -77,6 +80,7 @@ class Canvas(QWidget):
self.drawSquare = False
self.fourpoint = True # ADD
self.pointnum = 0
self.movingShape = False
#initialisation for panning
self.pan_initial_pos = QPoint()
......@@ -149,37 +153,20 @@ class Canvas(QWidget):
clipped_x = min(max(0, pos.x()), size.width())
clipped_y = min(max(0, pos.y()), size.height())
pos = QPointF(clipped_x, clipped_y)
elif len(self.current) > 1 and self.closeEnough(pos, self.current[0]) and not self.fourpoint:
elif len(self.current) > 1 and self.closeEnough(pos, self.current[0]):
# Attract line to starting point and colorise to alert the
# user:
pos = self.current[0]
color = self.current.line_color
self.overrideCursor(CURSOR_POINT)
self.current.highlightVertex(0, Shape.NEAR_VERTEX)
elif ( # ADD
len(self.current) > 1
and self.fourpoint
and self.closeEnough(pos, self.current[0])
):
# Attract line to starting point and
# colorise to alert the user.
pos = self.current[0]
self.overrideCursor(CURSOR_POINT)
self.current.highlightVertex(0, Shape.NEAR_VERTEX)
if self.drawSquare:
initPos = self.current[0]
minX = initPos.x()
minY = initPos.y()
min_size = min(abs(pos.x() - minX), abs(pos.y() - minY))
directionX = -1 if pos.x() - minX < 0 else 1
directionY = -1 if pos.y() - minY < 0 else 1
self.line[1] = QPointF(minX + directionX * min_size, minY + directionY * min_size)
self.line.points = [self.current[0], pos]
self.line.close()
elif self.fourpoint:
# self.line[self.pointnum] = pos # OLD
self.line[0] = self.current[-1]
self.line[1] = pos
......@@ -196,12 +183,14 @@ class Canvas(QWidget):
# Polygon copy moving.
if Qt.RightButton & ev.buttons():
if self.selectedShapeCopy and self.prevPoint:
if self.selectedShapesCopy and self.prevPoint:
self.overrideCursor(CURSOR_MOVE)
self.boundedMoveShape(self.selectedShapeCopy, pos)
self.boundedMoveShape(self.selectedShapesCopy, pos)
self.repaint()
elif self.selectedShape:
self.selectedShapeCopy = self.selectedShape.copy()
elif self.selectedShapes:
self.selectedShapesCopy = [
s.copy() for s in self.selectedShapes
]
self.repaint()
return
......@@ -211,11 +200,13 @@ class Canvas(QWidget):
self.boundedMoveVertex(pos)
self.shapeMoved.emit()
self.repaint()
elif self.selectedShape and self.prevPoint:
self.movingShape = True
elif self.selectedShapes and self.prevPoint:
self.overrideCursor(CURSOR_MOVE)
self.boundedMoveShape(self.selectedShape, pos)
self.boundedMoveShape(self.selectedShapes, pos)
self.shapeMoved.emit()
self.repaint()
self.movingShape = True
else:
#pan
delta_x = pos.x() - self.pan_initial_pos.x()
......@@ -263,65 +254,60 @@ class Canvas(QWidget):
def mousePressEvent(self, ev):
pos = self.transformPos(ev.pos())
if ev.button() == Qt.LeftButton:
if self.drawing():
# self.handleDrawing(pos) # OLD
if self.current and self.fourpoint: # ADD IF
if self.current:
if self.fourpoint: # ADD IF
# Add point to existing shape.
print('Adding points in mousePressEvent is ', self.line[1])
# print('Adding points in mousePressEvent is ', self.line[1])
self.current.addPoint(self.line[1])
self.line[0] = self.current[-1]
if self.current.isClosed():
# print('1111')
self.finalise()
elif self.drawSquare: # 增加
assert len(self.current.points) == 1
self.current.points = self.line.points
self.finalise()
elif not self.outOfPixmap(pos):
# Create new shape.
self.current = Shape()# self.current = Shape(shape_type=self.createMode)
self.current = Shape()
self.current.addPoint(pos)
# if self.createMode == "point":
# self.finalise()
# else:
# if self.createMode == "circle":
# self.current.shape_type = "circle"
self.line.points = [pos, pos]
self.setHiding()
self.drawingPolygon.emit(True)
self.update()
else:
selection = self.selectShapePoint(pos)
group_mode = int(ev.modifiers()) == Qt.ControlModifier
self.selectShapePoint(pos, multiple_selection_mode=group_mode)
self.prevPoint = pos
if selection is None:
#pan
QApplication.setOverrideCursor(QCursor(Qt.OpenHandCursor))
self.pan_initial_pos = pos
elif ev.button() == Qt.RightButton and self.editing():
self.selectShapePoint(pos)
group_mode = int(ev.modifiers()) == Qt.ControlModifier
self.selectShapePoint(pos, multiple_selection_mode=group_mode)
self.prevPoint = pos
self.update()
def mouseReleaseEvent(self, ev):
if ev.button() == Qt.RightButton:
menu = self.menus[bool(self.selectedShapeCopy)]
menu = self.menus[bool(self.selectedShapesCopy)]
self.restoreCursor()
if not menu.exec_(self.mapToGlobal(ev.pos()))\
and self.selectedShapeCopy:
and self.selectedShapesCopy:
# Cancel the move by deleting the shadow copy.
self.selectedShapeCopy = None
# self.selectedShapeCopy = None
self.selectedShapesCopy = []
self.repaint()
elif ev.button() == Qt.LeftButton and self.selectedShape: # OLD
elif ev.button() == Qt.LeftButton and self.selectedShapes:
if self.selectedVertex():
self.overrideCursor(CURSOR_POINT)
else:
self.overrideCursor(CURSOR_GRAB)
elif ev.button() == Qt.LeftButton and not self.fourpoint:
pos = self.transformPos(ev.pos())
if self.drawing():
......@@ -330,24 +316,37 @@ class Canvas(QWidget):
#pan
QApplication.restoreOverrideCursor() # ?
if self.movingShape and self.hShape:
index = self.shapes.index(self.hShape)
if (
self.shapesBackups[-1][index].points
!= self.shapes[index].points
):
self.storeShapes()
self.shapeMoved.emit() # connect to updateBoxlist in PPOCRLabel.py
self.movingShape = False
def endMove(self, copy=False):
assert self.selectedShape and self.selectedShapeCopy
shape = self.selectedShapeCopy
#del shape.fill_color
#del shape.line_color
assert self.selectedShapes and self.selectedShapesCopy
assert len(self.selectedShapesCopy) == len(self.selectedShapes)
if copy:
for i, shape in enumerate(self.selectedShapesCopy):
self.shapes.append(shape)
self.selectedShape.selected = False
self.selectedShape = shape
self.repaint()
self.selectedShapes[i].selected = False
self.selectedShapes[i] = shape
else:
self.selectedShape.points = [p for p in shape.points]
self.selectedShapeCopy = None
for i, shape in enumerate(self.selectedShapesCopy):
self.selectedShapes[i].points = shape.points
self.selectedShapesCopy = []
self.repaint()
self.storeShapes()
return True
def hideBackroundShapes(self, value):
self.hideBackround = value
if self.selectedShape:
if self.selectedShapes:
# Only hide other shapes if there is a current selection.
# Otherwise the user will not be able to select a shape.
self.setHiding(True)
......@@ -363,7 +362,7 @@ class Canvas(QWidget):
if self.pointnum == 3:
self.finalise()
else: # 按住送掉后跳到这里
else:
initPos = self.current[0]
print('initPos', self.current[0])
minX = initPos.x()
......@@ -399,28 +398,33 @@ class Canvas(QWidget):
self.current.popPoint()
self.finalise()
def selectShape(self, shape):
self.deSelectShape()
shape.selected = True
self.selectedShape = shape
def selectShapes(self, shapes):
for s in shapes: s.seleted = True
self.setHiding()
self.selectionChanged.emit(True)
self.selectionChanged.emit(shapes)
self.update()
def selectShapePoint(self, point):
def selectShapePoint(self, point, multiple_selection_mode):
"""Select the first shape created which contains this point."""
self.deSelectShape()
if self.selectedVertex(): # A vertex is marked for selection.
index, shape = self.hVertex, self.hShape
shape.highlightVertex(index, shape.MOVE_VERTEX)
self.selectShape(shape)
return self.hVertex
else:
for shape in reversed(self.shapes):
if self.isVisible(shape) and shape.containsPoint(point):
self.selectShape(shape)
self.calculateOffsets(shape, point)
return self.selectedShape
return None
self.setHiding()
if multiple_selection_mode:
if shape not in self.selectedShapes: # list
self.selectionChanged.emit(
self.selectedShapes + [shape]
)
else:
self.selectionChanged.emit([shape])
return
self.deSelectShape()
def calculateOffsets(self, shape, point):
rect = shape.boundingRect()
......@@ -465,8 +469,9 @@ class Canvas(QWidget):
else:
shiftPos = pos - point
if [shape[0].x(), shape[0].y(), shape[2].x(), shape[2].y()] \
== [shape[3].x(),shape[1].y(),shape[1].x(),shape[3].y()]:
shape.moveVertexBy(index, shiftPos)
lindex = (index + 1) % 4
rindex = (index + 3) % 4
lshift = None
......@@ -480,7 +485,12 @@ class Canvas(QWidget):
shape.moveVertexBy(rindex, rshift)
shape.moveVertexBy(lindex, lshift)
def boundedMoveShape(self, shape, pos):
else:
shape.moveVertexBy(index, shiftPos)
def boundedMoveShape(self, shapes, pos):
if type(shapes).__name__ != 'list': shapes = [shapes]
if self.outOfPixmap(pos):
return False # No need to move
o1 = pos + self.offsets[0]
......@@ -497,40 +507,49 @@ class Canvas(QWidget):
#self.calculateOffsets(self.selectedShape, pos)
dp = pos - self.prevPoint
if dp:
for shape in shapes:
shape.moveBy(dp)
self.prevPoint = pos
return True
return False
def deSelectShape(self):
if self.selectedShape:
self.selectedShape.selected = False
self.selectedShape = None
if self.selectedShapes:
for shape in self.selectedShapes: shape.selected=False
self.setHiding(False)
self.selectionChanged.emit(False)
self.selectionChanged.emit([])
self.update()
def deleteSelected(self):
if self.selectedShape:
shape = self.selectedShape
self.shapes.remove(self.selectedShape)
self.selectedShape = None
deleted_shapes = []
if self.selectedShapes:
for shape in self.selectedShapes:
self.shapes.remove(shape)
deleted_shapes.append(shape)
self.storeShapes()
self.selectedShapes = []
self.update()
return shape
return deleted_shapes
def storeShapes(self):
shapesBackup = []
for shape in self.shapes:
shapesBackup.append(shape.copy())
if len(self.shapesBackups) >= 10:
self.shapesBackups = self.shapesBackups[-9:]
self.shapesBackups.append(shapesBackup)
def copySelectedShape(self):
if self.selectedShape:
shape = self.selectedShape.copy()
self.deSelectShape()
self.shapes.append(shape)
shape.selected = True
self.selectedShape = shape
self.boundedShiftShape(shape)
return shape
if self.selectedShapes:
self.selectedShapesCopy = [s.copy() for s in self.selectedShapes]
self.boundedShiftShapes(self.selectedShapesCopy)
self.endMove(copy=True)
return self.selectedShapes
def boundedShiftShape(self, shape):
def boundedShiftShapes(self, shapes):
# Try to move in one direction, and if it fails in another.
# Give up if both fail.
for shape in shapes:
point = shape[0]
offset = QPointF(2.0, 2.0)
self.calculateOffsets(shape, point)
......@@ -560,8 +579,9 @@ class Canvas(QWidget):
if self.current:
self.current.paint(p)
self.line.paint(p)
if self.selectedShapeCopy:
self.selectedShapeCopy.paint(p)
if self.selectedShapesCopy:
for s in self.selectedShapesCopy:
s.paint(p)
# Paint rect
if self.current is not None and len(self.line) == 2 and not self.fourpoint:
......@@ -739,6 +759,7 @@ class Canvas(QWidget):
if fill_color:
self.shapes[-1].fill_color = fill_color
self.storeShapes()
return self.shapes[-1]
......@@ -749,6 +770,17 @@ class Canvas(QWidget):
self.line.points = [self.current[-1], self.current[0]]
self.drawingPolygon.emit(True)
def undoLastPoint(self):
if not self.current or self.current.isClosed():
return
self.current.popPoint()
if len(self.current) > 0:
self.line[0] = self.current[-1]
else:
self.current = None
self.drawingPolygon.emit(False)
self.repaint()
def resetAllLines(self):
assert self.shapes
self.current = self.shapes.pop()
......@@ -762,11 +794,18 @@ class Canvas(QWidget):
def loadPixmap(self, pixmap):
self.pixmap = pixmap
self.shapes = []
self.repaint() # 这函数在哪
self.repaint()
def loadShapes(self, shapes):
def loadShapes(self, shapes, replace=True):
if replace:
self.shapes = list(shapes)
else:
self.shapes.extend(shapes)
self.current = None
self.hShape = None
self.hVertex = None
# self.hEdge = None
self.storeShapes()
self.repaint()
def setShapeVisible(self, shape, value):
......@@ -793,6 +832,24 @@ class Canvas(QWidget):
self.restoreCursor()
self.pixmap = None
self.update()
self.shapesBackups = []
def setDrawingShapeToSquare(self, status):
self.drawSquare = status
def restoreShape(self):
if not self.isShapeRestorable:
return
self.shapesBackups.pop() # latest
shapesBackup = self.shapesBackups.pop()
self.shapes = shapesBackup
self.selectedShapes = []
for shape in self.shapes:
shape.selected = False
self.repaint()
@property
def isShapeRestorable(self):
if len(self.shapesBackups) < 2:
return False
return True
\ No newline at end of file
PPOCRLabel/libs/resources.py
View file @ f7081e38
This source diff could not be displayed because it is too large. You can view the blob instead.
PPOCRLabel/libs/shape.py
View file @ f7081e38
......@@ -82,7 +82,7 @@ class Shape(object):
return False
def addPoint(self, point):
if not self.reachMaxPoints():
if not self.reachMaxPoints(): # 4个点时发出close信号
self.points.append(point)
def popPoint(self):
......
PPOCRLabel/resources/strings/strings-zh-CN.properties
View file @ f7081e38
......@@ -97,3 +97,6 @@ showBox=显示所有标注
saveLabel=保存标记结果
singleRe=重识别此区块
labelDialogOption=弹出标记输入框
undo=撤销
undoLastPoint=撤销上个点
autoSaveMode=自动保存标记结果
\ No newline at end of file
PPOCRLabel/resources/strings/strings.properties
View file @ f7081e38
......@@ -97,3 +97,6 @@ showBox=Show All Box
saveLabel=Save Label
singleRe=Re-recognition RectBox
labelDialogOption=Pop-up Label Input Dialog
undo=Undo
undoLastPoint=Undo Last Point
autoSaveMode=Auto Save Label Mode
\ No newline at end of file
README.md
View file @ f7081e38
......@@ -5,10 +5,11 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools
## Notice
PaddleOCR supports both dynamic graph and static graph programming paradigm
- Dynamic graph: dygraph branch (default), **supported by paddle 2.0rc1+ ([installation](./doc/doc_en/installation_en.md))**
- Dynamic graph: dygraph branch (default), **supported by paddle 2.0.0 ([installation](./doc/doc_en/installation_en.md))**
- Static graph: develop branch
**Recent updates**
- 2021.1.21 update more than 25+ multilingual recognition models [models list](./doc/doc_en/models_list_en.md), including：English, Chinese, German, French, Japanese，Spanish，Portuguese Russia Arabic and so on. Models for more languages will continue to be updated [Develop Plan](https://github.com/PaddlePaddle/PaddleOCR/issues/1048).
- 2020.12.15 update Data synthesis tool, i.e., [Style-Text](./StyleText/README.md)，easy to synthesize a large number of images which are similar to the target scene image.
- 2020.11.25 Update a new data annotation tool, i.e., [PPOCRLabel](./PPOCRLabel/README.md), which is helpful to improve the labeling efficiency. Moreover, the labeling results can be used in training of the PP-OCR system directly.
- 2020.9.22 Update the PP-OCR technical article, https://arxiv.org/abs/2009.09941
......@@ -41,7 +42,7 @@ The above pictures are the visualizations of the general ppocr_server model. For
- Scan the QR code below with your Wechat, you can access to official technical exchange group. Look forward to your participation.
<div align="center">
<img src="./doc/joinus.PNG" width = "200" height = "200" />
<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/joinus.PNG" width = "200" height = "200" />
</div>
......
README_ch.md
View file @ f7081e38
......@@ -4,11 +4,13 @@
PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力使用者训练出更好的模型，并应用落地。
## 注意
PaddleOCR同时支持动态图与静态图两种编程范式
- 动态图版本：dygraph分支（默认），需将paddle版本升级至2.0rc1+（[快速安装](./doc/doc_ch/installation.md)）
- 动态图版本：dygraph分支（默认），需将paddle版本升级至2.0.0（[快速安装](./doc/doc_ch/installation.md)）
- 静态图版本：develop分支
**近期更新**
- 2021.1.18 [FAQ](./doc/doc_ch/FAQ.md)新增5个高频问题，总数152个，每周一都会更新，欢迎大家持续关注。
- 2021.2.1 [FAQ](./doc/doc_ch/FAQ.md)新增5个高频问题，总数162个，每周一都会更新，欢迎大家持续关注。
- 2021.1.26,28,29 PaddleOCR官方研发团队带来技术深入解读三日直播课，1月26日、28日、29日晚上19:30，[直播地址](https://live.bilibili.com/21689802)
- 2021.1.21 更新多语言识别模型，目前支持语种超过27种，[多语言模型下载](./doc/doc_ch/models_list.md)，包括中文简体、中文繁体、英文、法文、德文、韩文、日文、意大利文、西班牙文、葡萄牙文、俄罗斯文、阿拉伯文等，后续计划可以参考[多语言研发计划](https://github.com/PaddlePaddle/PaddleOCR/issues/1048)
- 2020.12.15 更新数据合成工具[Style-Text](./StyleText/README_ch.md)，可以批量合成大量与目标场景类似的图像，在多个场景验证，效果明显提升。
- 2020.11.25 更新半自动标注工具[PPOCRLabel](./PPOCRLabel/README_ch.md)，辅助开发者高效完成标注任务，输出格式与PP-OCR训练任务完美衔接。
- 2020.9.22 更新PP-OCR技术文章，https://arxiv.org/abs/2009.09941
......@@ -44,7 +46,7 @@ PaddleOCR同时支持动态图与静态图两种编程范式
- 微信扫描二维码加入官方交流群，获得更高效的问题答疑，与各行各业开发者充分交流，期待您的加入。
<div align="center">
<img src="./doc/joinus.PNG" width = "200" height = "200" />
<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/joinus.PNG" width = "200" height = "200" />
</div>
## 快速体验
......
StyleText/README.md
View file @ f7081e38
......@@ -72,7 +72,7 @@ fusion_generator:
python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
```
* Note 1: The language options is correspond to the corpus. Currently, the tool only supports English, Simplified Chinese and Korean.
* Note 1: The language options is correspond to the corpus. Currently, the tool only supports English(en), Simplified Chinese(ch) and Korean(ko).
* Note 2: Synth-Text is mainly used to generate images for OCR recognition models.
So the height of style images should be around 32 pixels. Images in other sizes may behave poorly.
* Note 3: You can modify `use_gpu` in `configs/config.yml` to determine whether to use GPU for prediction.
......@@ -120,7 +120,7 @@ In actual application scenarios, it is often necessary to synthesize pictures in
* `with_label`：Whether the `label_file` is label file list.
* `CorpusGenerator`：
* `method`：Method of CorpusGenerator，supports `FileCorpus` and `EnNumCorpus`. If `EnNumCorpus` is used，No other configuration is needed，otherwise you need to set `corpus_file` and `language`.
* `language`：Language of the corpus.
* `language`：Language of the corpus. Currently, the tool only supports English(en), Simplified Chinese(ch) and Korean(ko).
* `corpus_file`: Filepath of the corpus. Corpus file should be a text file which will be split by line-endings（'\n'）. Corpus generator samples one line each time.
......
StyleText/README_ch.md
View file @ f7081e38
......@@ -63,10 +63,10 @@ fusion_generator:
```python
python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
```
* 注1：语言选项和语料相对应，目前该工具只支持英文、简体中文和韩语。
* 注1：语言选项和语料相对应，目前支持英文(en)、简体中文(ch)和韩语(ko)。
* 注2：Style-Text生成的数据主要应用于OCR识别场景。基于当前PaddleOCR识别模型的设计，我们主要支持高度在32左右的风格图像。
如果输入图像尺寸相差过多，效果可能不佳。
* 注3：可以通过修改配置文件中的`use_gpu`(true或者false)参数来决定是否使用GPU进行预测。
* 注3：可以通过修改配置文件`configs/config.yml`中的`use_gpu`(true或者false)参数来决定是否使用GPU进行预测。
例如，输入如下图片和语料"PaddleOCR":
......@@ -105,7 +105,7 @@ python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_
* `with_label`：标志`label_file`是否为label文件。
* `CorpusGenerator`：
* `method`：语料生成方法，目前有`FileCorpus`和`EnNumCorpus`可选。如果使用`EnNumCorpus`，则不需要填写其他配置，否则需要修改`corpus_file`和`language`；
* `language`：语料的语种；
* `language`：语料的语种，目前支持英文(en)、简体中文(ch)和韩语(ko)；
* `corpus_file`: 语料文件路径。语料文件应使用文本文件。语料生成器首先会将语料按行切分，之后每次随机选取一行。
语料文件格式示例：
......
StyleText/engine/predictors.py
View file @ f7081e38
......@@ -38,7 +38,15 @@ class StyleTextRecPredictor(object):
self.std = config["Predictor"]["std"]
self.expand_result = config["Predictor"]["expand_result"]
def predict(self, style_input, text_input):
def reshape_to_same_height(self, img_list):
h = img_list[0].shape[0]
for idx in range(1, len(img_list)):
new_w = round(1.0 * img_list[idx].shape[1] /
img_list[idx].shape[0] * h)
img_list[idx] = cv2.resize(img_list[idx], (new_w, h))
return img_list
def predict_single_image(self, style_input, text_input):
style_input = self.rep_style_input(style_input, text_input)
tensor_style_input = self.preprocess(style_input)
tensor_text_input = self.preprocess(text_input)
......@@ -64,6 +72,21 @@ class StyleTextRecPredictor(object):
"fake_bg": fake_bg,
}
def predict(self, style_input, text_input_list):
if not isinstance(text_input_list, (tuple, list)):
return self.predict_single_image(style_input, text_input_list)
synth_result_list = []
for text_input in text_input_list:
synth_result = self.predict_single_image(style_input, text_input)
synth_result_list.append(synth_result)
for key in synth_result:
res = [r[key] for r in synth_result_list]
res = self.reshape_to_same_height(res)
synth_result[key] = np.concatenate(res, axis=1)
return synth_result
def preprocess(self, img):
img = (img.astype('float32') * self.scale - self.mean) / self.std
img_height, img_width, channel = img.shape
......
StyleText/engine/synthesisers.py
View file @ f7081e38
......@@ -12,6 +12,8 @@
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import numpy as np
import cv2
from utils.config import ArgsParser, load_config, override_config
from utils.logging import get_logger
......@@ -36,8 +38,9 @@ class ImageSynthesiser(object):
self.predictor = getattr(predictors, predictor_method)(self.config)
def synth_image(self, corpus, style_input, language="en"):
corpus, text_input = self.text_drawer.draw_text(corpus, language)
synth_result = self.predictor.predict(style_input, text_input)
corpus_list, text_input_list = self.text_drawer.draw_text(
corpus, language, style_input_width=style_input.shape[1])
synth_result = self.predictor.predict(style_input, text_input_list)
return synth_result
......@@ -59,12 +62,15 @@ class DatasetSynthesiser(ImageSynthesiser):
for i in range(self.output_num):
style_data = self.style_sampler.sample()
style_input = style_data["image"]
corpus_language, text_input_label = self.corpus_generator.generate(
)
text_input_label, text_input = self.text_drawer.draw_text(
text_input_label, corpus_language)
corpus_language, text_input_label = self.corpus_generator.generate()
text_input_label_list, text_input_list = self.text_drawer.draw_text(
text_input_label,
corpus_language,
style_input_width=style_input.shape[1])
synth_result = self.predictor.predict(style_input, text_input)
text_input_label = "".join(text_input_label_list)
synth_result = self.predictor.predict(style_input, text_input_list)
fake_fusion = synth_result["fake_fusion"]
self.writer.save_image(fake_fusion, text_input_label)
self.writer.save_label()
......
StyleText/engine/text_drawers.py
View file @ f7081e38
from PIL import Image, ImageDraw, ImageFont
import numpy as np
import cv2
from utils.logging import get_logger
......@@ -28,7 +29,11 @@ class StdTextDrawer(object):
else:
return int((self.height - 4)**2 / font_height)
def draw_text(self, corpus, language="en", crop=True):
def draw_text(self,
corpus,
language="en",
crop=True,
style_input_width=None):
if language not in self.support_languages:
self.logger.warning(
"language {} not supported, use en instead.".format(language))
......@@ -37,21 +42,43 @@ class StdTextDrawer(object):
width = min(self.max_width, len(corpus) * self.height) + 4
else:
width = len(corpus) * self.height + 4
if style_input_width is not None:
width = min(width, style_input_width)
corpus_list = []
text_input_list = []
while len(corpus) != 0:
bg = Image.new("RGB", (width, self.height), color=(127, 127, 127))
draw = ImageDraw.Draw(bg)
char_x = 2
font = self.font_dict[language]
for i, char_i in enumerate(corpus):
i = 0
while i < len(corpus):
char_i = corpus[i]
char_size = font.getsize(char_i)[0]
# split when char_x exceeds char size and index is not 0 (at least 1 char should be wroten on the image)
if char_x + char_size >= width and i != 0:
text_input = np.array(bg).astype(np.uint8)
text_input = text_input[:, 0:char_x, :]
corpus_list.append(corpus[0:i])
text_input_list.append(text_input)
corpus = corpus[i:]
break
draw.text((char_x, 2), char_i, fill=(0, 0, 0), font=font)
char_x += char_size
if char_x >= width:
corpus = corpus[0:i + 1]
self.logger.warning("corpus length exceed limit: {}".format(
corpus))
break
i += 1
# the whole text is shorter than style input
if i == len(corpus):
text_input = np.array(bg).astype(np.uint8)
text_input = text_input[:, 0:char_x, :]
return corpus, text_input
corpus_list.append(corpus[0:i])
text_input_list.append(text_input)
corpus = corpus[i:]
break
return corpus_list, text_input_list
configs/cls/cls_mv3.yml
View file @ f7081e38
......@@ -7,7 +7,6 @@ Global:
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [0, 1000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True
pretrained_model:
checkpoints:
......
configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml
View file @ f7081e38
......@@ -7,7 +7,10 @@ Global:
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
......
configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml
View file @ f7081e38
......@@ -7,7 +7,10 @@ Global:
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet18_vd_pretrained
......
configs/det/det_mv3_db.yml
View file @ f7081e38
......@@ -7,7 +7,10 @@ Global:
save_epoch_step: 1200
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
......
configs/det/det_mv3_east.yml
View file @ f7081e38
......@@ -7,7 +7,10 @@ Global:
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
......
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