fix conflicts

PPOCRLabel/PPOCRLabel.py

@@ -106,7 +106,7 @@ class MainWindow(QMainWindow, WindowMixin):
         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=lang)
+        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)
@@ -274,6 +274,7 @@ class MainWindow(QMainWindow, WindowMixin):
         self.preButton.setIconSize(QSize(40, 100))
         self.preButton.clicked.connect(self.openPrevImg)
         self.preButton.setStyleSheet('border: none;')
+        self.preButton.setShortcut('a')
         self.iconlist = QListWidget()
         self.iconlist.setViewMode(QListView.IconMode)
         self.iconlist.setFlow(QListView.TopToBottom)
@@ -289,12 +290,12 @@ class MainWindow(QMainWindow, WindowMixin):
         self.nextButton.setIconSize(QSize(40, 100))
         self.nextButton.setStyleSheet('border: none;')
         self.nextButton.clicked.connect(self.openNextImg)
+        self.nextButton.setShortcut('d')
         
         hlayout.addWidget(self.preButton)
         hlayout.addWidget(self.iconlist)
         hlayout.addWidget(self.nextButton)
 
-        # self.setLayout(hlayout)
 
         iconListContainer = QWidget()
         iconListContainer.setLayout(hlayout)
@@ -359,11 +360,6 @@ class MainWindow(QMainWindow, WindowMixin):
         opendir = action(getStr('openDir'), self.openDirDialog,
                          'Ctrl+u', 'open', getStr('openDir'))
 
-        openNextImg = action(getStr('nextImg'), self.openNextImg,
-                             'd', 'next', getStr('nextImgDetail'))
-
-        openPrevImg = action(getStr('prevImg'), self.openPrevImg,
-                             'a', 'prev', getStr('prevImgDetail'))
 
         save = action(getStr('save'), self.saveFile,
                       'Ctrl+V', 'verify', getStr('saveDetail'), enabled=False)
@@ -371,7 +367,7 @@ class MainWindow(QMainWindow, WindowMixin):
         alcm = action(getStr('choosemodel'), self.autolcm,
                                         'Ctrl+M', 'next', getStr('tipchoosemodel'))
 
-        deleteImg = action(getStr('deleteImg'), self.deleteImg, 'Ctrl+D', 'close', getStr('deleteImgDetail'),
+        deleteImg = action(getStr('deleteImg'), self.deleteImg, 'Ctrl+Shift+D', 'close', getStr('deleteImgDetail'),
                            enabled=True)
 
         resetAll = action(getStr('resetAll'), self.resetAll, None, 'resetall', getStr('resetAllDetail'))
@@ -388,7 +384,7 @@ class MainWindow(QMainWindow, WindowMixin):
                         'w', 'new', getStr('crtBoxDetail'), enabled=False)
 
         delete = action(getStr('delBox'), self.deleteSelectedShape,
-                        'Delete', 'delete', getStr('delBoxDetail'), enabled=False)
+                        'backspace', 'delete', getStr('delBoxDetail'), enabled=False)
         copy = action(getStr('dupBox'), self.copySelectedShape,
                       'Ctrl+C', 'copy', getStr('dupBoxDetail'),
                       enabled=False)
@@ -446,8 +442,11 @@ class MainWindow(QMainWindow, WindowMixin):
         reRec = action(getStr('reRecognition'), self.reRecognition, 
                       'Ctrl+Shift+R', 'reRec', getStr('reRecognition'), enabled=False)
 
+        singleRere = action(getStr('singleRe'), self.singleRerecognition,
+                            'Ctrl+R', 'reRec', getStr('singleRe'), enabled=False)
+
         createpoly = action(getStr('creatPolygon'), self.createPolygon,
-                            'p', 'new', 'Creat Polygon', enabled=True)
+                            'q', 'new', 'Creat Polygon', enabled=True)
 
         saveRec = action(getStr('saveRec'), self.saveRecResult,
                             '', 'save', getStr('saveRec'), enabled=False)
@@ -491,6 +490,7 @@ class MainWindow(QMainWindow, WindowMixin):
                                 icon='color', tip=getStr('shapeFillColorDetail'),
                                 enabled=False)
 
+
         # Label list context menu.
         labelMenu = QMenu()
         addActions(labelMenu, (edit, delete))
@@ -501,7 +501,6 @@ class MainWindow(QMainWindow, WindowMixin):
 
         # Draw squares/rectangles
         self.drawSquaresOption = QAction(getStr('drawSquares'), self)
-        self.drawSquaresOption.setShortcut('Ctrl+Shift+R')
         self.drawSquaresOption.setCheckable(True)
         self.drawSquaresOption.setChecked(settings.get(SETTING_DRAW_SQUARE, False))
         self.drawSquaresOption.triggered.connect(self.toogleDrawSquare)
@@ -509,7 +508,7 @@ class MainWindow(QMainWindow, WindowMixin):
         # Store actions for further handling.
         self.actions = struct(save=save,  open=open,  resetAll=resetAll, deleteImg=deleteImg,
                               lineColor=color1, create=create, delete=delete, edit=edit, copy=copy,
-                              saveRec=saveRec,
+                              saveRec=saveRec, singleRere=singleRere,AutoRec=AutoRec,reRec=reRec,
                               createMode=createMode, editMode=editMode,
                               shapeLineColor=shapeLineColor, shapeFillColor=shapeFillColor,
                               zoom=zoom, zoomIn=zoomIn, zoomOut=zoomOut, zoomOrg=zoomOrg,
@@ -518,9 +517,9 @@ class MainWindow(QMainWindow, WindowMixin):
                               fileMenuActions=(
                                   open, opendir, saveLabel,  resetAll, quit),
                               beginner=(), advanced=(),
-                              editMenu=(createpoly, edit, copy, delete,
+                              editMenu=(createpoly, edit, copy, delete,singleRere,
                                         None, color1, self.drawSquaresOption),
-                              beginnerContext=(create, edit, copy, delete),
+                              beginnerContext=(create, edit, copy, delete, singleRere),
                               advancedContext=(createMode, editMode, edit, copy,
                                                delete, shapeLineColor, shapeFillColor),
                               onLoadActive=(
@@ -562,7 +561,7 @@ class MainWindow(QMainWindow, WindowMixin):
             zoomIn, zoomOut, zoomOrg, None,
             fitWindow, fitWidth))
 
-        addActions(self.menus.autolabel, (alcm, None, help)) #
+        addActions(self.menus.autolabel, (AutoRec, reRec, alcm, None, help)) #
 
         self.menus.file.aboutToShow.connect(self.updateFileMenu)
 
@@ -572,6 +571,7 @@ class MainWindow(QMainWindow, WindowMixin):
             action('&Copy here', self.copyShape),
             action('&Move here', self.moveShape)))
 
+
         self.statusBar().showMessage('%s started.' % __appname__)
         self.statusBar().show()
 
@@ -919,6 +919,7 @@ class MainWindow(QMainWindow, WindowMixin):
         self.actions.edit.setEnabled(selected)
         self.actions.shapeLineColor.setEnabled(selected)
         self.actions.shapeFillColor.setEnabled(selected)
+        self.actions.singleRere.setEnabled(selected)
 
     def addLabel(self, shape):
         shape.paintLabel = self.displayLabelOption.isChecked()
@@ -988,6 +989,19 @@ class MainWindow(QMainWindow, WindowMixin):
         self.updateComboBox()
         self.canvas.loadShapes(s)
 
+    def singleLabel(self, shape):
+        if shape is None:
+            # print('rm empty label')
+            return
+        item = self.shapesToItems[shape]
+        item.setText(shape.label)
+        self.updateComboBox()
+
+        # ADD:
+        item = self.shapesToItemsbox[shape]
+        item.setText(str([(int(p.x()), int(p.y())) for p in shape.points]))
+        self.updateComboBox()
+
     def updateComboBox(self):
         # Get the unique labels and add them to the Combobox.
         itemsTextList = [str(self.labelList.item(i).text()) for i in range(self.labelList.count())]
@@ -1441,6 +1455,8 @@ class MainWindow(QMainWindow, WindowMixin):
         self.haveAutoReced = False
         self.AutoRecognition.setEnabled(True)
         self.reRecogButton.setEnabled(True)
+        self.actions.AutoRec.setEnabled(True)
+        self.actions.reRec.setEnabled(True)
         self.actions.saveLabel.setEnabled(True)
 
 
@@ -1755,6 +1771,7 @@ class MainWindow(QMainWindow, WindowMixin):
         self.loadFile(self.filePath) # ADD
         self.haveAutoReced = True
         self.AutoRecognition.setEnabled(False)
+        self.actions.AutoRec.setEnabled(False)
         self.setDirty()
         self.saveCacheLabel()
 
@@ -1794,6 +1811,27 @@ class MainWindow(QMainWindow, WindowMixin):
         else:
             QMessageBox.information(self, "Information", "Draw a box!")
 
+    def singleRerecognition(self):
+        img = cv2.imread(self.filePath)
+        shape = self.canvas.selectedShape
+        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))
+        if img_crop is None:
+            msg = 'Can not recognise the detection box in ' + self.filePath + '. Please change manually'
+            QMessageBox.information(self, "Information", msg)
+            return
+        result = self.ocr.ocr(img_crop, cls=True, det=False)
+        if result[0][0] is not '':
+            result.insert(0, box)
+            print('result in reRec is ', result)
+            if result[1][0] == shape.label:
+                print('label no change')
+            else:
+                shape.label = result[1][0]
+            self.singleLabel(shape)
+            self.setDirty()
+        print(box)
 
     def autolcm(self):
         vbox = QVBoxLayout()
@@ -1825,6 +1863,7 @@ class MainWindow(QMainWindow, WindowMixin):
         self.dialog.exec_()
         if self.filePath:
             self.AutoRecognition.setEnabled(True)
+            self.actions.AutoRec.setEnabled(True)
 
 
     def modelChoose(self):

PPOCRLabel/README.md

@@ -6,6 +6,10 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field. I
 
 <img src="./data/gif/steps_en.gif" width="100%"/>
 
+### Recent Update
+
+- 2020.12.18: Support re-recognition of a single label box (by [ninetailskim](https://github.com/ninetailskim) ), perfect shortcut keys.
+
 ## Installation
 
 ### 1. Install PaddleOCR
@@ -92,11 +96,30 @@ Therefore, if the recognition result has been manually changed before, it may ch
 
 ## Explanation
 
+### 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 |
+| 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                    |
+| Backspace        | Delete the selected box                          |
+| Ctrl + V         | Check image                                      |
+| Ctrl + Shift + d | Delete image                                     |
+| D                | Next image                                       |
+| A                | Previous image                                   |
+| Ctrl++           | Zoom in                                          |
+| Ctrl--           | Zoom out                                         |
+| ↑→↓←             | Move selected box                                |
+
 ### Built-in Model
 
 - Default model: PPOCRLabel uses the Chinese and English ultra-lightweight OCR model in PaddleOCR by default, supports Chinese, English and number recognition, and multiple language detection.
 
-- Model language switching: Changing the built-in model language is supportable by clicking "PaddleOCR"-"Choose OCR Model" in the menu bar. Currently supported languages​include French, German, Korean, and Japanese.
+- Model language switching: Changing the built-in model language is supportable by clicking "PaddleOCR"-"Choose OCR Model" in the menu bar. Currently supported languages​include French, German, Korean, and Japanese. 
   For specific model download links, please refer to [PaddleOCR Model List](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/models_list_en.md#multilingual-recognition-modelupdating)
 
 - Custom model: The model trained by users can be replaced by modifying PPOCRLabel.py in [PaddleOCR class instantiation](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/PPOCRLabel/PPOCRLabel.py#L110) referring [Custom Model Code](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/whl_en.md#use-custom-model)

PPOCRLabel/README_ch.md

@@ -6,6 +6,10 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，使用p
 
 <img src="./data/gif/steps.gif" width="100%"/>
 
+#### 近期更新
+
+- 2020.12.18: 支持对单个标记框进行重新识别（by [ninetailskim](https://github.com/ninetailskim) ），完善快捷键。
+
 ## 安装
 
 ### 1. 安装PaddleOCR
@@ -72,6 +76,26 @@ python3 PPOCRLabel.py --lang ch
 |   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
+
+### 快捷键
+
+| 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             |
+| 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                 |
+| D                | 下一张图片                   |
+| A                | 上一张图片                   |
+| Ctrl++           | 缩小                         |
+| Ctrl--           | 放大                         |
+| ↑→↓←             | 移动标记框                   |
+
 ### 内置模型
 
  - 默认模型：PPOCRLabel默认使用PaddleOCR中的中英文超轻量OCR模型，支持中英文与数字识别，多种语言检测。

PPOCRLabel/libs/autoDialog.py

@@ -46,8 +46,9 @@ class Worker(QThread):
                             chars = res[1][0]
                             cond = res[1][1]
                             posi = res[0]
-                            strs += "Transcription: " + chars + " Probability: " + str(
-                                cond) + " Location: " + json.dumps(posi) + '\n'
+                            strs += "Transcription: " + chars + " Probability: " + str(cond) + \
+                                    " Location: " + json.dumps(posi) +'\n'
+                        # Sending large amounts of data repeatedly through pyqtSignal may affect the program efficiency
                         self.listValue.emit(strs)
                         self.mainThread.result_dic = self.result_dic
                         self.mainThread.filePath = Imgpath

PPOCRLabel/resources/strings/strings-zh-CN.properties

@@ -94,4 +94,5 @@ ok=确认
 autolabeling=自动标注中
 hideBox=隐藏所有标注
 showBox=显示所有标注
-saveLabel=保存标记结果
\ No newline at end of file
+saveLabel=保存标记结果
+singleRe=重识别此区块
\ No newline at end of file

PPOCRLabel/resources/strings/strings-zh-TW.properties

-saveAsDetail=將標籤保存到其他文件
-changeSaveDir=改變存放目錄
-openFile=開啟檔案
-shapeLineColorDetail=更改線條顏色
-resetAll=重置
-crtBox=創建區塊
-crtBoxDetail=畫一個區塊
-dupBoxDetail=複製區塊
-verifyImg=驗證圖像
-zoominDetail=放大
-verifyImgDetail=驗證圖像
-saveDetail=將標籤存到
-openFileDetail=打開圖像
-fitWidthDetail=調整到窗口寬度
-tutorial=YouTube教學
-editLabel=編輯標籤
-openAnnotationDetail=打開標籤文件
-quit=結束
-shapeFillColorDetail=更改填充顏色
-closeCurDetail=關閉目前檔案
-closeCur=關閉
-deleteImg=刪除圖像
-deleteImgDetail=刪除目前圖像
-fitWin=調整到跟窗口一樣大小
-delBox=刪除選取區塊
-boxLineColorDetail=選擇框線顏色
-originalsize=原始大小
-resetAllDetail=重設所有設定
-zoomoutDetail=畫面放大
-save=儲存
-saveAs=另存為
-fitWinDetail=縮放到窗口一樣
-openDir=開啟目錄
-copyPrevBounding=複製當前圖像中的上一個邊界框
-showHide=顯示/隱藏標籤
-changeSaveFormat=更改儲存格式
-shapeFillColor=填充顏色
-quitApp=離開本程式
-dupBox=複製區塊
-delBoxDetail=刪除區塊
-zoomin=放大畫面
-info=資訊
-openAnnotation=開啟標籤
-prevImgDetail=上一個圖像
-fitWidth=縮放到跟畫面一樣寬
-zoomout=縮小畫面
-changeSavedAnnotationDir=更改預設標籤存的目錄
-nextImgDetail=下一個圖像
-originalsizeDetail=放大到原始大小
-prevImg=上一個圖像
-tutorialDetail=顯示示範內容
-shapeLineColor=形狀線條顏色
-boxLineColor=日期分隔線顏色
-editLabelDetail=修改所選區塊的標籤
-nextImg=下一張圖片
-useDefaultLabel=使用預設標籤
-useDifficult=有難度的
-boxLabelText=區塊的標籤
-labels=標籤
-autoSaveMode=自動儲存模式
-singleClsMode=單一類別模式
-displayLabel=顯示類別
-fileList=檔案清單
-files=檔案
-iconList=XX
-icon=XX
-advancedMode=進階模式
-advancedModeDetail=切到進階模式
-showAllBoxDetail=顯示所有區塊
-hideAllBoxDetail=隱藏所有區塊

PPOCRLabel/resources/strings/strings.properties

@@ -94,4 +94,5 @@ ok=OK
 autolabeling=Automatic Labeling
 hideBox=Hide All Box
 showBox=Show All Box
-saveLabel=Save Label
\ No newline at end of file
+saveLabel=Save Label
+singleRe=Re-recognition RectBox
\ No newline at end of file

README.md

@@ -122,8 +122,7 @@ For a new language request, please refer to [Guideline for new language_requests
     <img src="./doc/ppocr_framework.png" width="800">
 </div>
 
-PP-OCR is a practical ultra-lightweight OCR system. It is mainly composed of three parts: DB text detection, detection frame correction and CRNN text recognition. The system adopts 19 effective strategies from 8 aspects including backbone network selection and adjustment, prediction head design, data augmentation, learning rate transformation strategy, regularization parameter selection, pre-training model use, and automatic model tailoring and quantization to optimize and slim down the models of each module. The final results are an ultra-lightweight Chinese and English OCR model with an overall size of 3.5M and a 2.8M English digital OCR model. For more details, please refer to the PP-OCR technical article (https://arxiv.org/abs/2009.09941). Besides, The implementation of the FPGM Pruner and PACT quantization is based on [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim).
-
+PP-OCR is a practical ultra-lightweight OCR system. It is mainly composed of three parts: DB text detection[2], detection frame correction and CRNN text recognition[7]. The system adopts 19 effective strategies from 8 aspects including backbone network selection and adjustment, prediction head design, data augmentation, learning rate transformation strategy, regularization parameter selection, pre-training model use, and automatic model tailoring and quantization to optimize and slim down the models of each module. The final results are an ultra-lightweight Chinese and English OCR model with an overall size of 3.5M and a 2.8M English digital OCR model. For more details, please refer to the PP-OCR technical article (https://arxiv.org/abs/2009.09941). Besides, The implementation of the FPGM Pruner [8] and PACT quantization [9] is based on [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim).
 
 
 ## Visualization [more](./doc/doc_en/visualization_en.md)

README_ch.md

@@ -115,7 +115,7 @@ PaddleOCR同时支持动态图与静态图两种编程范式
     <img src="./doc/ppocr_framework.png" width="800">
 </div>
 
-PP-OCR是一个实用的超轻量OCR系统。主要由DB文本检测、检测框矫正和CRNN文本识别三部分组成。该系统从骨干网络选择和调整、预测头部的设计、数据增强、学习率变换策略、正则化参数选择、预训练模型使用以及模型自动裁剪量化8个方面，采用19个有效策略，对各个模块的模型进行效果调优和瘦身，最终得到整体大小为3.5M的超轻量中英文OCR和2.8M的英文数字OCR。更多细节请参考PP-OCR技术方案 https://arxiv.org/abs/2009.09941 。其中FPGM裁剪器和PACT量化的实现可以参考[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)。
+PP-OCR是一个实用的超轻量OCR系统。主要由DB文本检测[2]、检测框矫正和CRNN文本识别三部分组成[7]。该系统从骨干网络选择和调整、预测头部的设计、数据增强、学习率变换策略、正则化参数选择、预训练模型使用以及模型自动裁剪量化8个方面，采用19个有效策略，对各个模块的模型进行效果调优和瘦身，最终得到整体大小为3.5M的超轻量中英文OCR和2.8M的英文数字OCR。更多细节请参考PP-OCR技术方案 https://arxiv.org/abs/2009.09941 。其中FPGM裁剪器[8]和PACT量化[9]的实现可以参考[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)。
 
 <a name="效果展示"></a>
 ## 效果展示 [more](./doc/doc_ch/visualization.md)

StyleText/README.md

@@ -22,7 +22,7 @@ English | [简体中文](README_ch.md)
 </div>
 
 
-The Style-Text data synthesis tool is a tool based on Baidu's self-developed text editing algorithm "Editing Text in the Wild" [https://arxiv.org/abs/1908.03047](https://arxiv.org/abs/1908.03047).
+The Style-Text data synthesis tool is a tool based on Baidu and HUST cooperation research work, "Editing Text in the Wild" [https://arxiv.org/abs/1908.03047](https://arxiv.org/abs/1908.03047).
 
 Different from the commonly used GAN-based data synthesis tools, the main framework of Style-Text includes:
 * (1) Text foreground style transfer module.
@@ -69,10 +69,15 @@ fusion_generator:
 1. You can run `tools/synth_image` and generate the demo image, which is saved in the current folder.
 
 ```python
-python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
+python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
 ```
 
-* Note: 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, Simplified Chinese and Korean.
+* 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.
+
+
 
 For example, enter the following image and corpus `PaddleOCR`.
 
@@ -136,9 +141,21 @@ We provide a general dataset containing Chinese, English and Korean (50,000 imag
 2. You can run the following command to start synthesis task:
 
    ``` bash
-   python3 -m tools.synth_dataset.py -c configs/dataset_config.yml
+   python3 tools/synth_dataset.py -c configs/dataset_config.yml
    ```
 
+We also provide example corpus and images in `examples` folder.
+    <div align="center">
+        <img src="examples/style_images/1.jpg" width="300">
+        <img src="examples/style_images/2.jpg" width="300">
+    </div>
+If you run the code above directly, you will get example output data in `output_data` folder.
+You will get synthesis images and labels as below:
+   <div align="center">
+       <img src="doc/images/12.png" width="800">
+   </div>
+There will be some cache under the `label` folder. If the program exit unexpectedly, you can find cached labels there.
+When the program finish normally, you will find all the labels in `label.txt` which give the final results.
 
 <a name="Applications"></a>
 ### Applications

StyleText/README_ch.md

@@ -21,7 +21,7 @@
 </div>
 
 
-Style-Text数据合成工具是基于百度自研的文本编辑算法《Editing Text in the Wild》https://arxiv.org/abs/1908.03047
+Style-Text数据合成工具是基于百度和华科合作研发的文本编辑算法《Editing Text in the Wild》https://arxiv.org/abs/1908.03047
 
 不同于常用的基于GAN的数据合成工具，Style-Text主要框架包括：1.文本前景风格迁移模块 2.背景抽取模块 3.融合模块。经过这样三步，就可以迅速实现图像文本风格迁移。下图是一些该数据合成工具效果图。
 
@@ -61,9 +61,13 @@ fusion_generator:
 输入一张风格图和一段文字语料，运行tools/synth_image，合成单张图片，结果图像保存在当前目录下：
 
 ```python
-python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
+python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
 ```
-* 注意：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，目前该工具只支持英文、简体中文和韩语。
+* 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。
+
 
 例如，输入如下图片和语料"PaddleOCR":
 
@@ -124,8 +128,21 @@ python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_
 2. 运行`tools/synth_dataset`合成数据：
 
    ``` bash
-   python3 -m tools.synth_dataset -c configs/dataset_config.yml
+   python3 tools/synth_dataset.py -c configs/dataset_config.yml
    ```
+   我们在examples目录下提供了样例图片和语料。
+    <div align="center">
+        <img src="examples/style_images/1.jpg" width="300">
+        <img src="examples/style_images/2.jpg" width="300">
+    </div>
+
+   直接运行上述命令，可以在output_data中产生样例输出，包括图片和用于训练识别模型的标注文件：
+   <div align="center">
+       <img src="doc/images/12.png" width="800">
+   </div>
+
+   其中label目录下的标注文件为程序运行过程中产生的缓存，如果程序在中途异常终止，可以使用缓存的标注文件。
+   如果程序正常运行完毕，则会在output_data下生成label.txt，为最终的标注结果。
 
 <a name="应用案例"></a>
 ### 四、应用案例

StyleText/configs/dataset_config.yml

@@ -33,7 +33,7 @@ Predictor:
   - 0.5
   expand_result: false
   bg_generator:
-    pretrain: models/style_text_rec/bg_generator
+    pretrain: style_text_models/bg_generator
     module_name: bg_generator
     generator_type: BgGeneratorWithMask
     encode_dim: 64
@@ -43,7 +43,7 @@ Predictor:
     conv_block_dilation: true
     output_factor: 1.05
   text_generator:
-    pretrain: models/style_text_rec/text_generator
+    pretrain: style_text_models/text_generator
     module_name: text_generator
     generator_type: TextGenerator
     encode_dim: 64
@@ -52,7 +52,7 @@ Predictor:
     conv_block_dropout: false
     conv_block_dilation: true
   fusion_generator:
-    pretrain: models/style_text_rec/fusion_generator
+    pretrain: style_text_models/fusion_generator
     module_name: fusion_generator
     generator_type: FusionGeneratorSimple
     encode_dim: 64

StyleText/engine/predictors.py

@@ -28,6 +28,7 @@ class StyleTextRecPredictor(object):
                              ], "Generator {} not supported.".format(algorithm)
         use_gpu = config["Global"]['use_gpu']
         check_gpu(use_gpu)
+        paddle.set_device('gpu' if use_gpu else 'cpu')
         self.logger = get_logger()
         self.generator = getattr(style_text_rec, algorithm)(config)
         self.height = config["Global"]["image_height"]

StyleText/examples/corpus/example.txt

-PaddleOCR
+Paddle
 飞桨文字识别

StyleText/tools/synth_dataset.py

@@ -11,6 +11,14 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
+import os
+import sys
+
+__dir__ = os.path.dirname(os.path.abspath(__file__))
+sys.path.append(__dir__)
+sys.path.append(os.path.abspath(os.path.join(__dir__, '..')))
+
 from engine.synthesisers import DatasetSynthesiser
 
 

StyleText/tools/synth_image.py

@@ -16,13 +16,13 @@ import cv2
 import sys
 import glob
 
-from utils.config import ArgsParser
-from engine.synthesisers import ImageSynthesiser
-
 __dir__ = os.path.dirname(os.path.abspath(__file__))
 sys.path.append(__dir__)
 sys.path.append(os.path.abspath(os.path.join(__dir__, '..')))
 
+from utils.config import ArgsParser
+from engine.synthesisers import ImageSynthesiser
+
 
 def synth_image():
     args = ArgsParser().parse_args()

configs/det/det_r50_vd_sast_totaltext.yml

@@ -60,7 +60,8 @@ Metric:
 Train:
   dataset:
     name: SimpleDataSet
-    label_file_path: [./train_data/art_latin_icdar_14pt/train_no_tt_test/train_label_json.txt, ./train_data/total_text_icdar_14pt/train_label_json.txt]
+    data_dir: ./train_data/
+    label_file_list: [./train_data/art_latin_icdar_14pt/train_no_tt_test/train_label_json.txt, ./train_data/total_text_icdar_14pt/train_label_json.txt]
     data_ratio_list: [0.5, 0.5]
     transforms:
       - DecodeImage: # load image

deploy/cpp_infer/tools/config.txt

@@ -11,7 +11,7 @@ max_side_len  960
 det_db_thresh  0.3
 det_db_box_thresh  0.5
 det_db_unclip_ratio  2.0
-det_model_dir  ./inference/ch__ppocr_mobile_v2.0_det_infer/
+det_model_dir  ./inference/ch_ppocr_mobile_v2.0_det_infer/
 
 # cls config
 use_angle_cls 0

doc/doc_ch/algorithm_overview.md

@@ -9,9 +9,9 @@
 ### 1.文本检测算法
 
 PaddleOCR开源的文本检测算法列表：
-- [x]  DB([paper]( https://arxiv.org/abs/1911.08947) )（ppocr推荐）
-- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))
-- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))
+- [x]  DB([paper]( https://arxiv.org/abs/1911.08947)) [2]（ppocr推荐）
+- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))[1]
+- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))[4]
 
 在ICDAR2015文本检测公开数据集上，算法效果如下：
 
@@ -38,13 +38,13 @@ PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训
 ### 2.文本识别算法
 
 PaddleOCR基于动态图开源的文本识别算法列表：
-- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717) )（ppocr推荐）
-- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))
-- [ ]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html)) coming soon
-- [ ]  RARE([paper](https://arxiv.org/abs/1603.03915v1)) coming soon
-- [ ]  SRN([paper](https://arxiv.org/abs/2003.12294)) coming soon
+- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))[7]（ppocr推荐）
+- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))[10]
+- [ ]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11] coming soon
+- [ ]  RARE([paper](https://arxiv.org/abs/1603.03915v1))[12] coming soon
+- [ ]  SRN([paper](https://arxiv.org/abs/2003.12294))[5] coming soon
 
-参考[DTRB](https://arxiv.org/abs/1904.01906)文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
+参考[DTRB][3](https://arxiv.org/abs/1904.01906)文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
 
 |模型|骨干网络|Avg Accuracy|模型存储命名|下载链接|
 |-|-|-|-|-|

doc/doc_ch/angle_class.md

@@ -117,7 +117,7 @@ python3 tools/eval.py -c configs/cls/cls_mv3.yml -o Global.checkpoints={path/to/
 
 ```
 # 预测分类结果
-python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/ch/word_1.jpg
+python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/ch/word_1.jpg
 ```
 
 预测图片：

doc/doc_ch/detection.md

@@ -120,16 +120,16 @@ python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{pat
 
 测试单张图像的检测效果
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy"
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
 ```
 
 测试DB模型时，调整后处理阈值，
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy" PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
 ```
 
 
 测试文件夹下所有图像的检测效果
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.checkpoints="./output/det_db/best_accuracy"
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
 ```

doc/doc_ch/inference.md

@@ -245,7 +245,10 @@ python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/img
 超轻量中文识别模型推理，可以执行如下命令：
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./inference/rec_crnn/"
+# 下载超轻量中文识别模型：
+wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
+tar xf ch_ppocr_mobile_v2.0_rec_infer.tar
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="ch_ppocr_mobile_v2.0_rec_infer"
 ```
 
 ![](../imgs_words/ch/word_4.jpg)
@@ -266,7 +269,6 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153)
 
 ```
 python3 tools/export_model.py -c configs/rec/rec_r34_vd_none_bilstm_ctc.yml -o Global.pretrained_model=./rec_r34_vd_none_bilstm_ctc_v2.0_train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/rec_crnn
-
 ```
 
 CRNN 文本识别模型推理，可以执行如下命令：
@@ -327,7 +329,10 @@ Predicts of ./doc/imgs_words/korean/1.jpg:('바탕으로', 0.9948904)
 方向分类模型推理，可以执行如下命令：
 
 ```
-python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --cls_model_dir="./inference/cls/"
+# 下载超轻量中文方向分类器模型：
+wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
+tar xf ch_ppocr_mobile_v2.0_cls_infer.tar
+python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer"
 ```
 
 ![](../imgs_words/ch/word_1.jpg)

doc/doc_ch/recognition.md

@@ -324,7 +324,6 @@ Eval:
 
 评估数据集可以通过 `configs/rec/rec_icdar15_train.yml`  修改Eval中的 `label_file_path` 设置。
 
-*注意* 评估时必须确保配置文件中 infer_img 字段为空
 ```
 # GPU 评估， Global.checkpoints 为待测权重
 python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy
@@ -342,7 +341,7 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec
 
 ```
 # 预测英文结果
-python3 tools/infer_rec.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png
+python3 tools/infer_rec.py -c configs/rec/rec_icdar15_train.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/en/word_1.png
 ```
 
 预测图片：
@@ -361,7 +360,7 @@ infer_img: doc/imgs_words/en/word_1.png
 
 ```
 # 预测中文结果
-python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/ch/word_1.jpg
+python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/ch/word_1.jpg
 ```
 
 预测图片：

doc/doc_ch/reference.md

@@ -11,11 +11,12 @@
 }
 
 2. DB:
-@article{liao2019real,
-  title={Real-time Scene Text Detection with Differentiable Binarization},
+@inproceedings{liao2020real,
+  title={Real-Time Scene Text Detection with Differentiable Binarization.},
   author={Liao, Minghui and Wan, Zhaoyi and Yao, Cong and Chen, Kai and Bai, Xiang},
-  journal={arXiv preprint arXiv:1911.08947},
-  year={2019}
+  booktitle={AAAI},
+  pages={11474--11481},
+  year={2020}
 }
 
 3. DTRB:
@@ -37,10 +38,11 @@
 }
 
 5. SRN:
-@article{yu2020towards,
-  title={Towards Accurate Scene Text Recognition with Semantic Reasoning Networks},
-  author={Yu, Deli and Li, Xuan and Zhang, Chengquan and Han, Junyu and Liu, Jingtuo and Ding, Errui},
-  journal={arXiv preprint arXiv:2003.12294},
+@inproceedings{yu2020towards,
+  title={Towards accurate scene text recognition with semantic reasoning networks},
+  author={Yu, Deli and Li, Xuan and Zhang, Chengquan and Liu, Tao and Han, Junyu and Liu, Jingtuo and Ding, Errui},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={12113--12122},
   year={2020}
 }
 
@@ -52,4 +54,62 @@
   pages={9086--9095},
   year={2019}
 }
-```
\ No newline at end of file
+
+7. CRNN:
+@article{shi2016end,
+  title={An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition},
+  author={Shi, Baoguang and Bai, Xiang and Yao, Cong},
+  journal={IEEE transactions on pattern analysis and machine intelligence},
+  volume={39},
+  number={11},
+  pages={2298--2304},
+  year={2016},
+  publisher={IEEE}
+}
+
+8. FPGM:
+@inproceedings{he2019filter,
+  title={Filter pruning via geometric median for deep convolutional neural networks acceleration},
+  author={He, Yang and Liu, Ping and Wang, Ziwei and Hu, Zhilan and Yang, Yi},
+  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
+  pages={4340--4349},
+  year={2019}
+}
+
+9. PACT:
+@article{choi2018pact,
+  title={Pact: Parameterized clipping activation for quantized neural networks},
+  author={Choi, Jungwook and Wang, Zhuo and Venkataramani, Swagath and Chuang, Pierce I-Jen and Srinivasan, Vijayalakshmi and Gopalakrishnan, Kailash},
+  journal={arXiv preprint arXiv:1805.06085},
+  year={2018}
+}
+
+10.Rosetta
+@inproceedings{borisyuk2018rosetta,
+  title={Rosetta: Large scale system for text detection and recognition in images},
+  author={Borisyuk, Fedor and Gordo, Albert and Sivakumar, Viswanath},
+  booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
+  pages={71--79},
+  year={2018}
+}
+
+11.STAR-Net
+@inproceedings{liu2016star,
+  title={STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition.},
+  author={Liu, Wei and Chen, Chaofeng and Wong, Kwan-Yee K and Su, Zhizhong and Han, Junyu},
+  booktitle={BMVC},
+  volume={2},
+  pages={7},
+  year={2016}
+}
+
+12.RARE
+@inproceedings{shi2016robust,
+  title={Robust scene text recognition with automatic rectification},
+  author={Shi, Baoguang and Wang, Xinggang and Lyu, Pengyuan and Yao, Cong and Bai, Xiang},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={4168--4176},
+  year={2016}
+}
+
+```

doc/doc_en/algorithm_overview_en.md

@@ -11,9 +11,9 @@ This tutorial lists the text detection algorithms and text recognition algorithm
 ### 1. Text Detection Algorithm
 
 PaddleOCR open source text detection algorithms list:
-- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))
-- [x]  DB([paper](https://arxiv.org/abs/1911.08947))
-- [x]  SAST([paper](https://arxiv.org/abs/1908.05498) )(Baidu Self-Research)
+- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))[2]
+- [x]  DB([paper](https://arxiv.org/abs/1911.08947))[1]
+- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))[4]
 
 On the ICDAR2015 dataset, the text detection result is as follows:
 
@@ -39,11 +39,11 @@ For the training guide and use of PaddleOCR text detection algorithms, please re
 ### 2. Text Recognition Algorithm
 
 PaddleOCR open-source text recognition algorithms list:
-- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))
-- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))
-- [ ]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html)) coming soon
-- [ ]  RARE([paper](https://arxiv.org/abs/1603.03915v1)) coming soon
-- [ ]  SRN([paper](https://arxiv.org/abs/2003.12294) )(Baidu Self-Research) coming soon
+- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))[7]
+- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))[10]
+- [ ]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11] coming soon
+- [ ]  RARE([paper](https://arxiv.org/abs/1603.03915v1))[12] coming soon
+- [ ]  SRN([paper](https://arxiv.org/abs/2003.12294))[5] coming soon
 
 Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow:
 

doc/doc_en/angle_class_en.md

@@ -119,7 +119,7 @@ Use `Global.infer_img` to specify the path of the predicted picture or folder, a
 
 ```
 # Predict English results
-python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words_en/word_10.png
+python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words_en/word_10.png
 ```
 
 Input image:

doc/doc_en/detection_en.md

@@ -113,16 +113,16 @@ python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{pat
 
 Test the detection result on a single image:
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy"
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
 ```
 
 When testing the DB model, adjust the post-processing threshold:
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy" PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
 ```
 
 
 Test the detection result on all images in the folder:
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.checkpoints="./output/det_db/best_accuracy"
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
 ```

doc/doc_en/inference_en.md

@@ -255,15 +255,18 @@ The following will introduce the lightweight Chinese recognition model inference
 For lightweight Chinese recognition model inference, you can execute the following commands:
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./inference/rec_crnn/"
+# download CRNN text recognition inference model
+wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
+tar xf ch_ppocr_mobile_v2.0_rec_infer.tar
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_10.png" --rec_model_dir="ch_ppocr_mobile_v2.0_rec_infer"
 ```
 
-![](../imgs_words/ch/word_4.jpg)
+![](../imgs_words_en/word_10.png)
 
 After executing the command, the prediction results (recognized text and score) of the above image will be printed on the screen.
 
 ```bash
-Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153)
+Predicts of ./doc/imgs_words_en/word_10.png:('PAIN', 0.9897658)
 ```
 
 <a name="CTC-BASED_RECOGNITION"></a>
@@ -339,7 +342,12 @@ For angle classification model inference, you can execute the following commands
 ```
 python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words_en/word_10.png" --cls_model_dir="./inference/cls/"
 ```
-
+```
+# download text angle class inference model：
+wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
+tar xf ch_ppocr_mobile_v2.0_cls_infer.tar
+python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words_en/word_10.png" --cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer"
+```
 ![](../imgs_words_en/word_10.png)
 
 After executing the command, the prediction results (classification angle and score) of the above image will be printed on the screen.

doc/doc_en/recognition_en.md

@@ -317,11 +317,11 @@ Eval:
 <a name="EVALUATION"></a>
 ### EVALUATION
 
-The evaluation data set can be modified via `configs/rec/rec_icdar15_reader.yml` setting of `label_file_path` in EvalReader.
+The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/rec_icdar15_train.yml` file.
 
 ```
 # GPU evaluation, Global.checkpoints is the weight to be tested
-python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_reader.yml -o Global.checkpoints={path/to/weights}/best_accuracy
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy
 ```
 
 <a name="PREDICTION"></a>
@@ -336,7 +336,7 @@ The default prediction picture is stored in `infer_img`, and the weight is speci
 
 ```
 # Predict English results
-python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints={path/to/weights}/best_accuracy TestReader.infer_img=doc/imgs_words/en/word_1.jpg
+python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/en/word_1.jpg
 ```
 
 Input image:
@@ -354,7 +354,7 @@ The configuration file used for prediction must be consistent with the training.
 
 ```
 # Predict Chinese results
-python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints={path/to/weights}/best_accuracy TestReader.infer_img=doc/imgs_words/ch/word_1.jpg
+python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/ch/word_1.jpg
 ```
 
 Input image:

paddleocr.py

@@ -262,8 +262,8 @@ class PaddleOCR(predict_system.TextSystem):
             logger.error('rec_algorithm must in {}'.format(SUPPORT_REC_MODEL))
             sys.exit(0)
 
-        postprocess_params.rec_char_dict_path = Path(
-            __file__).parent / postprocess_params.rec_char_dict_path
+        postprocess_params.rec_char_dict_path = str(
+            Path(__file__).parent / postprocess_params.rec_char_dict_path)
 
         # init det_model and rec_model
         super().__init__(postprocess_params)

ppocr/losses/det_basic_loss.py

@@ -45,7 +45,6 @@ class BalanceLoss(nn.Layer):
         self.balance_loss = balance_loss
         self.main_loss_type = main_loss_type
         self.negative_ratio = negative_ratio
-        self.main_loss_type = main_loss_type
         self.return_origin = return_origin
         self.eps = eps
 

ppocr/utils/save_load.py

@@ -102,7 +102,6 @@ def init_model(config, model, logger, optimizer=None, lr_scheduler=None):
             best_model_dict = states_dict.get('best_model_dict', {})
             if 'epoch' in states_dict:
                 best_model_dict['start_epoch'] = states_dict['epoch'] + 1
-            best_model_dict['start_epoch'] = best_model_dict['best_epoch'] + 1
 
         logger.info("resume from {}".format(checkpoints))
     elif pretrained_model:

setup.py

@@ -32,7 +32,7 @@ setup(
     package_dir={'paddleocr': ''},
     include_package_data=True,
     entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
-    version='2.0.1',
+    version='2.0.2',
     install_requires=requirements,
     license='Apache License 2.0',
     description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',

tools/infer/predict_det.py

@@ -71,6 +71,9 @@ class TextDetector(object):
             postprocess_params["cover_thresh"] = args.det_east_cover_thresh
             postprocess_params["nms_thresh"] = args.det_east_nms_thresh
         elif self.det_algorithm == "SAST":
+            pre_process_list[0] = {
+                'DetResizeForTest': {'resize_long': args.det_limit_side_len}
+            }
             postprocess_params['name'] = 'SASTPostProcess'
             postprocess_params["score_thresh"] = args.det_sast_score_thresh
             postprocess_params["nms_thresh"] = args.det_sast_nms_thresh

tools/infer/utility.py

@@ -34,7 +34,6 @@ def parse_args():
     parser.add_argument("--ir_optim", type=str2bool, default=True)
     parser.add_argument("--use_tensorrt", type=str2bool, default=False)
     parser.add_argument("--use_fp16", type=str2bool, default=False)
-    parser.add_argument("--max_batch_size", type=int, default=10)
     parser.add_argument("--gpu_mem", type=int, default=8000)
 
     # params for text detector

tools/program.py

@@ -332,7 +332,7 @@ def eval(model, valid_dataloader, post_process_class, eval_class):
     return metirc
 
 
-def preprocess():
+def preprocess(is_train=False):
     FLAGS = ArgsParser().parse_args()
     config = load_config(FLAGS.config)
     merge_config(FLAGS.opt)
@@ -350,15 +350,17 @@ def preprocess():
     device = paddle.set_device(device)
 
     config['Global']['distributed'] = dist.get_world_size() != 1
-
-    # save_config
-    save_model_dir = config['Global']['save_model_dir']
-    os.makedirs(save_model_dir, exist_ok=True)
-    with open(os.path.join(save_model_dir, 'config.yml'), 'w') as f:
-        yaml.dump(dict(config), f, default_flow_style=False, sort_keys=False)
-
-    logger = get_logger(
-        name='root', log_file='{}/train.log'.format(save_model_dir))
+    if is_train:
+        # save_config
+        save_model_dir = config['Global']['save_model_dir']
+        os.makedirs(save_model_dir, exist_ok=True)
+        with open(os.path.join(save_model_dir, 'config.yml'), 'w') as f:
+            yaml.dump(
+                dict(config), f, default_flow_style=False, sort_keys=False)
+        log_file = '{}/train.log'.format(save_model_dir)
+    else:
+        log_file = None
+    logger = get_logger(name='root', log_file=log_file)
     if config['Global']['use_visualdl']:
         from visualdl import LogWriter
         vdl_writer_path = '{}/vdl/'.format(save_model_dir)

tools/train.py

@@ -110,6 +110,6 @@ def test_reader(config, device, logger):
 
 
 if __name__ == '__main__':
-    config, device, logger, vdl_writer = program.preprocess()
+    config, device, logger, vdl_writer = program.preprocess(is_train=True)
     main(config, device, logger, vdl_writer)
     # test_reader(config, device, logger)