Merge pull request #2357 from caopulan/fix_srn_post

fix srn_postprocess

PPOCRLabel/PPOCRLabel.py

@@ -1031,7 +1031,7 @@ 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)
 
@@ -1450,7 +1450,7 @@ 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 +1459,6 @@ 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):
@@ -1764,7 +1763,7 @@ 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)
@@ -1795,7 +1794,7 @@ 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 +1861,8 @@ 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):
@@ -1919,22 +1920,29 @@ class MainWindow(QMainWindow, WindowMixin):
 
         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)
-                for i, label in enumerate(self.PPlabel[idx]):
-                    if label['difficult']: continue
+                try:
                     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))
+                    for i, label in enumerate(self.PPlabel[idx]):
+                        if label['difficult']: continue
+                        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')
+                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():
@@ -1991,7 +1999,7 @@ 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

@@ -9,7 +9,7 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w
 ### Recent Update
 
 - 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". 
+  - 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.
   - Click to modify the recognition result.(If you can't change the result, please switch to the system default input method, or switch back to the original input method again)
 - 2020.12.18: Support re-recognition of a single label box (by [ninetailskim](https://github.com/ninetailskim) ), perfect shortcut keys.
@@ -49,7 +49,7 @@ 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
 ```
@@ -127,7 +127,7 @@ Therefore, if the recognition result has been manually changed before, it may ch
 
 - 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)
@@ -160,11 +160,11 @@ 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
 
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)

PPOCRLabel/README_ch.md

@@ -49,7 +49,7 @@ 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
 ```
@@ -132,22 +132,22 @@ PPOCRLabel支持三种保存方式：
 
 ### 错误提示
 - 如果同时使用whl包安装了paddleocr，其优先级大于通过paddleocr.py调用PaddleOCR类，whl包未更新时会导致程序异常。
-  
+
 - PPOCRLabel**不支持对中文文件名**的图片进行自动标注。
 
 - 针对Linux用户：如果您在打开软件过程中出现**objc[XXXXX]**开头的错误，证明您的opencv版本太高，建议安装4.2版本：
     ```
     pip install opencv-python==4.2.0.32
     ```
-    
+
 - 如果出现 ```Missing string id``` 开头的错误，需要重新编译资源：
     ```
     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

README.md

@@ -5,10 +5,12 @@ 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**
+- 2021.2.8 Release PaddleOCRv2.0(branch release/2.0) and set as default branch. Check release note here: https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v2.0.0
+- 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

README_ch.md

@@ -4,11 +4,14 @@
 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。
+- 2021.3.22 [FAQ](./doc/doc_ch/FAQ.md)新增5个高频问题，总数193个，每周一都会更新，欢迎大家持续关注。
+- 2021.2.8 正式发布PaddleOCRv2.0(branch release/2.0)并设置为推荐用户使用的默认分支. 发布的详细内容，请参考: https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v2.0.0
+- 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
@@ -101,8 +104,8 @@ PaddleOCR同时支持动态图与静态图两种编程范式
 - [效果展示](#效果展示)
 - FAQ
     - [【精选】OCR精选10个问题](./doc/doc_ch/FAQ.md)
-    - [【理论篇】OCR通用32个问题](./doc/doc_ch/FAQ.md)
-    - [【实战篇】PaddleOCR实战110个问题](./doc/doc_ch/FAQ.md)
+    - [【理论篇】OCR通用37个问题](./doc/doc_ch/FAQ.md)
+    - [【实战篇】PaddleOCR实战141个问题](./doc/doc_ch/FAQ.md)
 - [技术交流群](#欢迎加入PaddleOCR技术交流群)
 - [参考文献](./doc/doc_ch/reference.md)
 - [许可证书](#许可证书)

StyleText/README.md

@@ -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.
@@ -98,7 +98,7 @@ What's more, the medium result `fake_bg.jpg` will also be saved, which is the ba
 </div>
 
 
-`fake_text.jpg` * `fake_text.jpg` is the generated image with the same font style as `Style Input`.
+`fake_text.jpg` is the generated image with the same font style as `Style Input`.
 
 
 <div align="center">
@@ -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

@@ -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/examples/image_list.txt

@@ -1,2 +1,2 @@
 style_images/1.jpg	NEATNESS
-style_images/2.jpg	锁店君和宾馆
+style_images/2.jpg	卡丹鑫宇通

configs/rec/multi_language/generate_multi_language_configs.py

@@ -19,21 +19,38 @@ import logging
 logging.basicConfig(level=logging.INFO)
 
 support_list = {
-    'it':'italian', 'xi':'spanish', 'pu':'portuguese', 'ru':'russian', 'ar':'arabic',
-    'ta':'tamil', 'ug':'uyghur', 'fa':'persian', 'ur':'urdu', 'rs':'serbian latin',
-    'oc':'occitan', 'rsc':'serbian cyrillic', 'bg':'bulgarian', 'uk':'ukranian', 'be':'belarusian',
-    'te':'telugu', 'ka':'kannada', 'chinese_cht':'chinese tradition','hi':'hindi','mr':'marathi',
-    'ne':'nepali',
+    'it': 'italian',
+    'es': 'spanish',
+    'pt': 'portuguese',
+    'ru': 'russian',
+    'ar': 'arabic',
+    'ta': 'tamil',
+    'ug': 'uyghur',
+    'fa': 'persian',
+    'ur': 'urdu',
+    'rs_latin': 'serbian latin',
+    'oc': 'occitan',
+    'rs_cyrillic': 'serbian cyrillic',
+    'bg': 'bulgarian',
+    'uk': 'ukranian',
+    'be': 'belarusian',
+    'te': 'telugu',
+    'kn': 'kannada',
+    'ch_tra': 'chinese tradition',
+    'hi': 'hindi',
+    'mr': 'marathi',
+    'ne': 'nepali',
 }
-assert(
-    os.path.isfile("./rec_multi_language_lite_train.yml")
-    ),"Loss basic configuration file rec_multi_language_lite_train.yml.\
+assert (os.path.isfile("./rec_multi_language_lite_train.yml")
+        ), "Loss basic configuration file rec_multi_language_lite_train.yml.\
 You can download it from \
 https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/configs/rec/multi_language/"
- 
-global_config = yaml.load(open("./rec_multi_language_lite_train.yml", 'rb'), Loader=yaml.Loader)
+
+global_config = yaml.load(
+    open("./rec_multi_language_lite_train.yml", 'rb'), Loader=yaml.Loader)
 project_path = os.path.abspath(os.path.join(os.getcwd(), "../../../"))
 
+
 class ArgsParser(ArgumentParser):
     def __init__(self):
         super(ArgsParser, self).__init__(
@@ -41,15 +58,30 @@ class ArgsParser(ArgumentParser):
         self.add_argument(
             "-o", "--opt", nargs='+', help="set configuration options")
         self.add_argument(
-            "-l", "--language", nargs='+', help="set language type, support {}".format(support_list))
+            "-l",
+            "--language",
+            nargs='+',
+            help="set language type, support {}".format(support_list))
         self.add_argument(
-            "--train",type=str,help="you can use this command to change the train dataset default path")
+            "--train",
+            type=str,
+            help="you can use this command to change the train dataset default path"
+        )
         self.add_argument(
-            "--val",type=str,help="you can use this command to change the eval dataset default path")
+            "--val",
+            type=str,
+            help="you can use this command to change the eval dataset default path"
+        )
         self.add_argument(
-            "--dict",type=str,help="you can use this command to change the dictionary default path")
+            "--dict",
+            type=str,
+            help="you can use this command to change the dictionary default path"
+        )
         self.add_argument(
-            "--data_dir",type=str,help="you can use this command to change the dataset default root path")
+            "--data_dir",
+            type=str,
+            help="you can use this command to change the dataset default root path"
+        )
 
     def parse_args(self, argv=None):
         args = super(ArgsParser, self).parse_args(argv)
@@ -68,20 +100,28 @@ class ArgsParser(ArgumentParser):
         return config
 
     def _set_language(self, type):
-        assert(type),"please use -l or --language to choose language type"
+        assert (type), "please use -l or --language to choose language type"
         assert(
                 type[0] in support_list.keys()
                ),"the sub_keys(-l or --language) can only be one of support list: \n{},\nbut get: {}, " \
                  "please check your running command".format(support_list, type)
-        global_config['Global']['character_dict_path'] = 'ppocr/utils/dict/{}_dict.txt'.format(type[0])
-        global_config['Global']['save_model_dir'] = './output/rec_{}_lite'.format(type[0])
-        global_config['Train']['dataset']['label_file_list'] = ["train_data/{}_train.txt".format(type[0])]
-        global_config['Eval']['dataset']['label_file_list'] = ["train_data/{}_val.txt".format(type[0])]
+        global_config['Global'][
+            'character_dict_path'] = 'ppocr/utils/dict/{}_dict.txt'.format(type[
+                0])
+        global_config['Global'][
+            'save_model_dir'] = './output/rec_{}_lite'.format(type[0])
+        global_config['Train']['dataset'][
+            'label_file_list'] = ["train_data/{}_train.txt".format(type[0])]
+        global_config['Eval']['dataset'][
+            'label_file_list'] = ["train_data/{}_val.txt".format(type[0])]
         global_config['Global']['character_type'] = type[0]
-        assert(
-                os.path.isfile(os.path.join(project_path,global_config['Global']['character_dict_path']))
-              ),"Loss default dictionary file {}_dict.txt.You can download it from \
-https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/ppocr/utils/dict/".format(type[0])
+        assert (
+            os.path.isfile(
+                os.path.join(project_path, global_config['Global'][
+                    'character_dict_path']))
+        ), "Loss default dictionary file {}_dict.txt.You can download it from \
+https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/ppocr/utils/dict/".format(
+            type[0])
         return type[0]
 
 
@@ -110,43 +150,51 @@ def merge_config(config):
                     cur[sub_key] = value
                 else:
                     cur = cur[sub_key]
-                    
+
+
 def loss_file(path):
-    assert(
-            os.path.exists(path)
-          ),"There is no such file:{},Please do not forget to put in the specified file".format(path)
+    assert (
+        os.path.exists(path)
+    ), "There is no such file:{},Please do not forget to put in the specified file".format(
+        path)
+
 
-        
 if __name__ == '__main__':
     FLAGS = ArgsParser().parse_args()
     merge_config(FLAGS.opt)
     save_file_path = 'rec_{}_lite_train.yml'.format(FLAGS.language)
     if os.path.isfile(save_file_path):
         os.remove(save_file_path)
-        
+
     if FLAGS.train:
         global_config['Train']['dataset']['label_file_list'] = [FLAGS.train]
-        train_label_path = os.path.join(project_path,FLAGS.train)
+        train_label_path = os.path.join(project_path, FLAGS.train)
         loss_file(train_label_path)
     if FLAGS.val:
         global_config['Eval']['dataset']['label_file_list'] = [FLAGS.val]
-        eval_label_path = os.path.join(project_path,FLAGS.val)
-        loss_file(Eval_label_path)
+        eval_label_path = os.path.join(project_path, FLAGS.val)
+        loss_file(eval_label_path)
     if FLAGS.dict:
         global_config['Global']['character_dict_path'] = FLAGS.dict
-        dict_path = os.path.join(project_path,FLAGS.dict)
+        dict_path = os.path.join(project_path, FLAGS.dict)
         loss_file(dict_path)
     if FLAGS.data_dir:
         global_config['Eval']['dataset']['data_dir'] = FLAGS.data_dir
         global_config['Train']['dataset']['data_dir'] = FLAGS.data_dir
-        data_dir = os.path.join(project_path,FLAGS.data_dir)
+        data_dir = os.path.join(project_path, FLAGS.data_dir)
         loss_file(data_dir)
-        
+
     with open(save_file_path, 'w') as f:
-        yaml.dump(dict(global_config), f, default_flow_style=False, sort_keys=False)
+        yaml.dump(
+            dict(global_config), f, default_flow_style=False, sort_keys=False)
     logging.info("Project path is          :{}".format(project_path))
-    logging.info("Train list path set to   :{}".format(global_config['Train']['dataset']['label_file_list'][0]))
-    logging.info("Eval list path set to    :{}".format(global_config['Eval']['dataset']['label_file_list'][0]))
-    logging.info("Dataset root path set to :{}".format(global_config['Eval']['dataset']['data_dir']))
-    logging.info("Dict path set to         :{}".format(global_config['Global']['character_dict_path']))
-    logging.info("Config file set to       :configs/rec/multi_language/{}".format(save_file_path))
+    logging.info("Train list path set to   :{}".format(global_config['Train'][
+        'dataset']['label_file_list'][0]))
+    logging.info("Eval list path set to    :{}".format(global_config['Eval'][
+        'dataset']['label_file_list'][0]))
+    logging.info("Dataset root path set to :{}".format(global_config['Eval'][
+        'dataset']['data_dir']))
+    logging.info("Dict path set to         :{}".format(global_config['Global'][
+        'character_dict_path']))
+    logging.info("Config file set to       :configs/rec/multi_language/{}".
+                 format(save_file_path))

configs/rec/multi_language/rec_en_number_lite_train.yml

@@ -16,7 +16,7 @@ Global:
   infer_img:
   # for data or label process
   character_dict_path: ppocr/utils/dict/en_dict.txt
-  character_type: ch
+  character_type: EN
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_mv3_none_bilstm_ctc.yml

@@ -1,5 +1,5 @@
 Global:
-  use_gpu: true
+  use_gpu: True
   epoch_num: 72
   log_smooth_window: 20
   print_batch_step: 10
@@ -59,7 +59,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -78,7 +78,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_mv3_none_none_ctc.yml

@@ -58,7 +58,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -77,7 +77,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_mv3_tps_bilstm_att.yml

@@ -0,0 +1,102 @@
+Global:
+  use_gpu: True
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/rec_mv3_tps_bilstm_att/
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  # for data or label process
+  character_dict_path: 
+  character_type: en
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: RARE
+  Transform:
+    name: TPS
+    num_fiducial: 20
+    loc_lr: 0.1
+    model_name: small
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn 
+    hidden_size: 96
+  Head:
+    name: AttentionHead  
+    hidden_size: 96
+    
+
+Loss:
+  name: AttentionLoss
+
+PostProcess:
+  name: AttnLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 1

configs/rec/rec_mv3_tps_bilstm_ctc.yml

@@ -1,5 +1,5 @@
 Global:
-  use_gpu: true
+  use_gpu: True
   epoch_num: 72
   log_smooth_window: 20
   print_batch_step: 10
@@ -63,7 +63,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -82,7 +82,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_r34_vd_none_bilstm_ctc.yml

@@ -58,7 +58,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -77,7 +77,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_r34_vd_none_none_ctc.yml

@@ -56,7 +56,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -75,7 +75,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_r34_vd_tps_bilstm_att.yml

@@ -0,0 +1,101 @@
+Global:
+  use_gpu: True
+  epoch_num: 400
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/b3_rare_r34_none_gru/
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  # for data or label process
+  character_dict_path: 
+  character_type: en
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0.00000
+
+Architecture:
+  model_type: rec
+  algorithm: RARE
+  Transform:
+    name: TPS
+    num_fiducial: 20
+    loc_lr: 0.1
+    model_name: large
+  Backbone:
+    name: ResNet  
+    layers: 34
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn 
+    hidden_size: 256 #96
+  Head:
+    name: AttentionHead  # AttentionHead
+    hidden_size: 256 #
+    l2_decay: 0.00001
+
+Loss:
+  name: AttentionLoss
+
+PostProcess:
+  name: AttnLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/rec_r34_vd_tps_bilstm_ctc.yml

@@ -62,7 +62,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -81,7 +81,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_r50_fpn_srn.yml

@@ -0,0 +1,107 @@
+Global:
+  use_gpu: True
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 5
+  save_model_dir: ./output/rec/srn_new
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 5000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model: 
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  # for data or label process
+  character_dict_path: 
+  character_type: en
+  max_text_length: 25
+  num_heads: 8
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  clip_norm: 10.0
+  lr:
+    learning_rate: 0.0001
+
+Architecture:
+  model_type: rec
+  algorithm: SRN
+  in_channels: 1
+  Transform:
+  Backbone:
+    name: ResNetFPN
+  Head:
+    name: SRNHead
+    max_text_length: 25
+    num_heads: 8
+    num_encoder_TUs: 2
+    num_decoder_TUs: 4
+    hidden_dims: 512
+
+Loss:
+  name: SRNLoss
+
+PostProcess:
+  name: SRNLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SRNLabelEncode: # Class handling label
+      - SRNRecResizeImg:
+          image_shape: [1, 64, 256]
+      - KeepKeys:
+          keep_keys: ['image',
+                      'label',
+                      'length',
+                      'encoder_word_pos',
+                      'gsrm_word_pos',
+                      'gsrm_slf_attn_bias1',
+                      'gsrm_slf_attn_bias2'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    batch_size_per_card: 64
+    drop_last: False
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SRNLabelEncode: # Class handling label
+      - SRNRecResizeImg:
+          image_shape: [1, 64, 256]
+      - KeepKeys:
+          keep_keys: ['image',
+                      'label',
+                      'length',
+                      'encoder_word_pos',
+                      'gsrm_word_pos',
+                      'gsrm_slf_attn_bias1',
+                      'gsrm_slf_attn_bias2'] 
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 32
+    num_workers: 4

deploy/cpp_infer/readme.md

@@ -1,6 +1,8 @@
 # 服务器端C++预测
 
-本教程将介绍在服务器端部署PaddleOCR超轻量中文检测、识别模型的详细步骤。
+本章节介绍PaddleOCR 模型的的C++部署方法，与之对应的python预测部署方式参考[文档](../../doc/doc_ch/inference.md)。
+C++在性能计算上优于python，因此，在大多数CPU、GPU部署场景，多采用C++的部署方式，本节将介绍如何在Linux\Windows (CPU\GPU)环境下配置C++环境并完成
+PaddleOCR模型部署。
 
 
 ## 1. 准备环境

deploy/cpp_infer/readme_en.md

@@ -1,7 +1,9 @@
 # Server-side C++ inference
 
-
-In this tutorial, we will introduce the detailed steps of deploying PaddleOCR ultra-lightweight Chinese detection and recognition models on the server side.
+This chapter introduces the C++ deployment method of the PaddleOCR model, and the corresponding python predictive deployment method refers to [document](../../doc/doc_ch/inference.md).
+C++ is better than python in terms of performance calculation. Therefore, in most CPU and GPU deployment scenarios, C++ deployment is mostly used.
+This section will introduce how to configure the C++ environment and complete it in the Linux\Windows (CPU\GPU) environment
+PaddleOCR model deployment.
 
 
 ## 1. Prepare the environment

deploy/cpp_infer/src/ocr_rec.cpp

@@ -76,7 +76,7 @@ void CRNNRecognizer::Run(std::vector<std::vector<std::vector<int>>> boxes,
           float(*std::max_element(&predict_batch[n * predict_shape[2]],
                                   &predict_batch[(n + 1) * predict_shape[2]]));
 
-      if (argmax_idx > 0 && (!(i > 0 && argmax_idx == last_index))) {
+      if (argmax_idx > 0 && (!(n > 0 && argmax_idx == last_index))) {
         score += max_value;
         count += 1;
         str_res.push_back(label_list_[argmax_idx]);

deploy/cpp_infer/tools/config.txt

@@ -9,7 +9,7 @@ use_mkldnn 0
 max_side_len  960
 det_db_thresh  0.3
 det_db_box_thresh  0.5
-det_db_unclip_ratio  2.0
+det_db_unclip_ratio  1.6
 det_model_dir  ./inference/ch_ppocr_mobile_v2.0_det_infer/
 
 # cls config

deploy/hubserving/ocr_det/params.py

@@ -20,7 +20,8 @@ def read_params():
     #DB parmas
     cfg.det_db_thresh = 0.3
     cfg.det_db_box_thresh = 0.5
-    cfg.det_db_unclip_ratio = 2.0
+    cfg.det_db_unclip_ratio = 1.6
+    cfg.use_dilation = False
 
     # #EAST parmas
     # cfg.det_east_score_thresh = 0.8

deploy/hubserving/ocr_system/params.py

@@ -20,7 +20,8 @@ def read_params():
     #DB parmas
     cfg.det_db_thresh = 0.3
     cfg.det_db_box_thresh = 0.5
-    cfg.det_db_unclip_ratio = 2.0
+    cfg.det_db_unclip_ratio = 1.6
+    cfg.use_dilation = False
 
     #EAST parmas
     cfg.det_east_score_thresh = 0.8