Merge pull request #1 from PaddlePaddle/dygraph

Dygraph

.gitignore

@@ -24,4 +24,8 @@ output/
 
 build/
 dist/
-paddleocr.egg-info/
+paddleocr.egg-info/
\ No newline at end of file
+/deploy/android_demo/app/OpenCV/
+/deploy/android_demo/app/PaddleLite/
+/deploy/android_demo/app/.cxx/
+/deploy/android_demo/app/cache/

MANIFEST.in

@@ -4,4 +4,5 @@ include README.md
 recursive-include ppocr/utils *.txt utility.py logging.py
 recursive-include ppocr/data/ *.py
 recursive-include ppocr/postprocess *.py
-recursive-include tools/infer *.py
+recursive-include tools/infer *.py
\ No newline at end of file
+recursive-include ppocr/utils/e2e_utils/ *.py
\ No newline at end of file

PPOCRLabel/PPOCRLabel.py

@@ -147,6 +147,7 @@ class MainWindow(QMainWindow, WindowMixin):
         self.itemsToShapesbox = {}
         self.shapesToItemsbox = {}
         self.prevLabelText = getStr('tempLabel')
+        self.noLabelText = getStr('nullLabel')
         self.model = 'paddle'
         self.PPreader = None
         self.autoSaveNum = 5
@@ -1020,7 +1021,7 @@ class MainWindow(QMainWindow, WindowMixin):
         item.setText(str([(int(p.x()), int(p.y())) for p in shape.points]))
         self.updateComboBox()
 
-    def updateComboBox(self): # TODO：貌似没用
+    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())]
 
@@ -1040,7 +1041,7 @@ class MainWindow(QMainWindow, WindowMixin):
             return dict(label=s.label,  # str
                         line_color=s.line_color.getRgb(),
                         fill_color=s.fill_color.getRgb(),
-                        points=[(p.x(), p.y()) for p in s.points],  # QPonitF
+                        points=[(int(p.x()), int(p.y())) for p in s.points],  # QPonitF
                        # add chris
                         difficult=s.difficult)  # bool
 
@@ -1069,7 +1070,7 @@ class MainWindow(QMainWindow, WindowMixin):
             # print('Image:{0} -> Annotation:{1}'.format(self.filePath, annotationFilePath))
             return True
         except:
-            self.errorMessage(u'Error saving label data')
+            self.errorMessage(u'Error saving label data', u'Error saving label data')
             return False
 
     def copySelectedShape(self):
@@ -1802,10 +1803,14 @@ class MainWindow(QMainWindow, WindowMixin):
                     result.insert(0, box)
                     print('result in reRec is ', result)
                     self.result_dic.append(result)
-                    if result[1][0] == shape.label:
-                        print('label no change')
-                    else:
-                        rec_flag += 1
+                else:
+                    print('Can not recognise the box')
+                    self.result_dic.append([box,(self.noLabelText,0)])
+
+                if self.noLabelText == shape.label or result[1][0] == shape.label:
+                    print('label no change')
+                else:
+                    rec_flag += 1
 
             if len(self.result_dic) > 0 and rec_flag > 0:
                 self.saveFile(mode='Auto')
@@ -1836,9 +1841,14 @@ class MainWindow(QMainWindow, WindowMixin):
                     print('label no change')
                 else:
                     shape.label = result[1][0]
-                self.singleLabel(shape)
-                self.setDirty()
-            print(box)
+            else:
+                print('Can not recognise the box')
+                if self.noLabelText == shape.label:
+                    print('label no change')
+                else:
+                    shape.label = self.noLabelText
+            self.singleLabel(shape)
+            self.setDirty()
 
     def autolcm(self):
         vbox = QVBoxLayout()

PPOCRLabel/README.md

@@ -29,9 +29,7 @@ PaddleOCR models has been built in PPOCRLabel, please refer to [PaddleOCR instal
 
 ### 2. Install PPOCRLabel
 
-#### Windows + Anaconda
-
-Download and install [Anaconda](https://www.anaconda.com/download/#download) (Python 3+)
+#### Windows
 
 ```
 pip install pyqt5

PPOCRLabel/README_ch.md

@@ -31,7 +31,7 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置P
 PPOCRLabel内置PaddleOCR模型，故请参考[PaddleOCR安装文档](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/installation.md)准备好PaddleOCR，并确保PaddleOCR安装成功。
 
 ### 2. 安装PPOCRLabel
-#### Windows + Anaconda
+#### Windows
 
 ```
 pip install pyqt5

PPOCRLabel/libs/canvas.py

@@ -45,7 +45,7 @@ class Canvas(QWidget):
     CREATE, EDIT = list(range(2))
     _fill_drawing = False # draw shadows
 
-    epsilon = 11.0
+    epsilon = 5.0
 
     def __init__(self, *args, **kwargs):
         super(Canvas, self).__init__(*args, **kwargs)

PPOCRLabel/libs/utils.py

@@ -124,6 +124,15 @@ def natural_sort(list, key=lambda s:s):
 
 
 def get_rotate_crop_image(img, points):
+    # Use Green's theory to judge clockwise or counterclockwise
+    # author: biyanhua
+    d = 0.0
+    for index in range(-1, 3):
+        d += -0.5 * (points[index + 1][1] + points[index][1]) * (
+                    points[index + 1][0] - points[index][0])
+    if d < 0: # counterclockwise
+        tmp = np.array(points)
+        points[1], points[3] = tmp[3], tmp[1]
 
     try:
         img_crop_width = int(

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

@@ -87,6 +87,7 @@ creatPolygon=四点标注
 drawSquares=正方形标注
 saveRec=保存识别结果
 tempLabel=待识别
+nullLabel=无法识别
 steps=操作步骤
 choseModelLg=选择模型语言
 cancel=取消

PPOCRLabel/resources/strings/strings.properties

@@ -77,7 +77,7 @@ IR=Image Resize
 autoRecognition=Auto Recognition
 reRecognition=Re-recognition
 mfile=File
-medit=Eidt
+medit=Edit
 mview=View
 mhelp=Help
 iconList=Icon List
@@ -87,6 +87,7 @@ creatPolygon=Create Quadrilateral
 drawSquares=Draw Squares
 saveRec=Save Recognition Result
 tempLabel=TEMPORARY
+nullLabel=NULL
 steps=Steps
 choseModelLg=Choose Model Language
 cancel=Cancel

README.md

@@ -32,7 +32,8 @@ PaddleOCR supports both dynamic graph and static graph programming paradigm
 
 <div align="center">
     <img src="doc/imgs_results/ch_ppocr_mobile_v2.0/test_add_91.jpg" width="800">
-    <img src="doc/imgs_results/ch_ppocr_mobile_v2.0/00018069.jpg" width="800">
+    <img src="doc/imgs_results/multi_lang/img_01.jpg" width="800">
+    <img src="doc/imgs_results/multi_lang/img_02.jpg" width="800">
 </div>
 
 The above pictures are the visualizations of the general ppocr_server model. For more effect pictures, please see [More visualizations](./doc/doc_en/visualization_en.md).
@@ -42,7 +43,7 @@ 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="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/joinus.PNG"  width = "200" height = "200" />
+<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/dygraph/doc/joinus.PNG"  width = "200" height = "200" />
 </div>
 
 

README_ch.md

@@ -8,9 +8,9 @@ PaddleOCR同时支持动态图与静态图两种编程范式
 - 静态图版本：develop分支
 
 **近期更新**
+- 2021.4.8 release 2.1版本，新增AAAI 2021论文[端到端识别算法PGNet](./doc/doc_ch/pgnet.md)开源，[多语言模型](./doc/doc_ch/multi_languages.md)支持种类增加到80+。
 - 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)
+- 2021.1.21 更新多语言识别模型，目前支持语种超过27种，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
@@ -46,7 +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="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/joinus.PNG"  width = "200" height = "200" />
+<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/dygraph/doc/joinus.PNG"  width = "200" height = "200" />
 </div>
 
 ## 快速体验
@@ -74,11 +74,13 @@ PaddleOCR同时支持动态图与静态图两种编程范式
 ## 文档教程
 - [快速安装](./doc/doc_ch/installation.md)
 - [中文OCR模型快速使用](./doc/doc_ch/quickstart.md)
+- [多语言OCR模型快速使用](./doc/doc_ch/multi_languages.md)
 - [代码组织结构](./doc/doc_ch/tree.md)
 - 算法介绍
     - [文本检测](./doc/doc_ch/algorithm_overview.md)
     - [文本识别](./doc/doc_ch/algorithm_overview.md)
-    - [PP-OCR Pipline](#PP-OCR)
+    - [PP-OCR Pipeline](#PP-OCR)
+    - [端到端PGNet算法](./doc/doc_ch/pgnet.md)
 - 模型训练/评估
     - [文本检测](./doc/doc_ch/detection.md)
     - [文本识别](./doc/doc_ch/recognition.md)
@@ -112,7 +114,7 @@ PaddleOCR同时支持动态图与静态图两种编程范式
 
 
 <a name="PP-OCR"></a>
-## PP-OCR Pipline
+## PP-OCR Pipeline
 <div align="center">
     <img src="./doc/ppocr_framework.png" width="800">
 </div>

configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml

@@ -7,11 +7,6 @@ Global:
   save_epoch_step: 1200
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [3000, 2000]
-  # 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
   checkpoints:

configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml

@@ -7,11 +7,6 @@ Global:
   save_epoch_step: 1200
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [3000, 2000]
-  # 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
   checkpoints:

configs/det/det_mv3_db.yml

@@ -7,11 +7,6 @@ Global:
   save_epoch_step: 1200
   # evaluation is run every 2000 iterations
   eval_batch_step: [0, 2000]
-  # 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
   checkpoints:

configs/det/det_mv3_east.yml

@@ -7,11 +7,6 @@ Global:
   save_epoch_step: 1000
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [4000, 5000]
-  # 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
   checkpoints: 

configs/det/det_r50_vd_db.yml

@@ -7,11 +7,6 @@ Global:
   save_epoch_step: 1200
   # evaluation is run every 2000 iterations
   eval_batch_step: [0,2000]
-  # 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/ResNet50_vd_ssld_pretrained
   checkpoints:

configs/det/det_r50_vd_east.yml

@@ -7,11 +7,6 @@ Global:
   save_epoch_step: 1000
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [4000, 5000]
-  # 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/ResNet50_vd_pretrained/
   checkpoints: 

configs/det/det_r50_vd_sast_icdar15.yml

@@ -7,19 +7,15 @@ Global:
   save_epoch_step: 1000
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [4000, 5000]
-  # 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/ResNet50_vd_ssld_pretrained/
-  checkpoints: 
+  checkpoints:
   save_inference_dir:
   use_visualdl: False
-  infer_img: 
+  infer_img:
   save_res_path: ./output/sast_r50_vd_ic15/predicts_sast.txt
 
+
 Architecture:
   model_type: det
   algorithm: SAST

configs/det/det_r50_vd_sast_totaltext.yml

@@ -7,11 +7,6 @@ Global:
   save_epoch_step: 1000
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [4000, 5000]
-  # 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/ResNet50_vd_ssld_pretrained/
   checkpoints: