Merge branch 'PaddlePaddle:dygraph' into dygraph

去除部分冗余代码

MANIFEST.in

@@ -6,3 +6,4 @@ recursive-include ppocr/data *.py
 recursive-include ppocr/postprocess *.py
 recursive-include tools/infer *.py
 recursive-include ppocr/utils/e2e_utils *.py
+recursive-include ppstructure *.py
\ No newline at end of file

PPOCRLabel/PPOCRLabel.py

@@ -819,12 +819,10 @@ class MainWindow(QMainWindow, WindowMixin):
             if self.itemsToShapesbox:
                 self.rotateImgWarn()
             else:
-                _value = True
-                self.rotateImg(filename=filename, k=1, _value=_value)
+                self.rotateImg(filename=filename, k=1, _value=True)
         else:
-            _value = False
             self.rotateImgWarn()
-            self.actions.rotateRight.setEnabled(_value)
+            self.actions.rotateRight.setEnabled(False)
 
     def rotateRightImg(self, _value=False):
 
@@ -834,12 +832,10 @@ class MainWindow(QMainWindow, WindowMixin):
             if self.itemsToShapesbox:
                 self.rotateImgWarn()
             else:
-                _value = True
-                self.rotateImg(filename=filename, k=-1, _value=_value)
+                self.rotateImg(filename=filename, k=-1, _value=True)
         else:
-            _value = False
             self.rotateImgWarn()
-            self.actions.rotateRight.setEnabled(_value)
+            self.actions.rotateRight.setEnabled(False)
 
     def toggleDrawingSensitive(self, drawing=True):
         """In the middle of drawing, toggling between modes should be disabled."""
@@ -1582,7 +1578,7 @@ class MainWindow(QMainWindow, WindowMixin):
         self.actions.reRec.setEnabled(True)
         self.actions.open_dataset_dir.setEnabled(True)
         self.actions.rotateLeft.setEnabled(True)
-        self.actions.rotateRight.setEnabled (True)
+        self.actions.rotateRight.setEnabled(True)
 
 
 

__init__.py

@@ -11,7 +11,8 @@
 # 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 paddleocr
+from .paddleocr import *
 
-__all__ = ['PaddleOCR', 'draw_ocr']
-from .paddleocr import PaddleOCR
-from .tools.infer.utility import draw_ocr
+__version__ = paddleocr.VERSION
+__all__ = ['PaddleOCR', 'PPStructure', 'draw_ocr', 'draw_structure_result', 'save_structure_res','download_with_progressbar']

deploy/cpp_infer/docs/windows_vs2019_build.md

@@ -14,7 +14,7 @@ PaddleOCR在Windows 平台下基于`Visual Studio 2019 Community` 进行了测
 
 ### Step1: 下载PaddlePaddle C++ 预测库 fluid_inference
 
-PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载:  [C++预测库下载列表](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/guides/05_inference_deployment/inference/windows_cpp_inference.html)
+PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载:  [C++预测库下载列表](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#windows)
 
 解压后`D:\projects\fluid_inference`目录包含内容为：
 ```

doc/doc_ch/whl.md

@@ -5,23 +5,29 @@
 ### 1.1 安装whl包
 
 pip安装
+
 ```bash
 pip install "paddleocr>=2.0.1" # 推荐使用2.0.1+版本
 ```
 
 本地构建并安装
+
 ```bash
 python3 setup.py bdist_wheel
 pip3 install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x是paddleocr的版本号
 ```
 
 ## 2 使用
+
 ### 2.1 代码使用
+
 paddleocr whl包会自动下载ppocr轻量级模型作为默认模型，可以根据第3节**自定义模型**进行自定义更换。
 
 * 检测+方向分类器+识别全流程
+
 ```python
 from paddleocr import PaddleOCR, draw_ocr
+
 # Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
 # 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
 ocr = PaddleOCR(use_angle_cls=True, lang="ch")  # need to run only once to download and load model into memory
@@ -32,6 +38,7 @@ for line in result:
 
 # 显示结果
 from PIL import Image
+
 image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
@@ -40,31 +47,36 @@ im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
+
 结果是一个list，每个item包含了文本框，文字和识别置信度
+
 ```bash
 [[[24.0, 36.0], [304.0, 34.0], [304.0, 72.0], [24.0, 74.0]], ['纯臻营养护发素', 0.964739]]
 [[[24.0, 80.0], [172.0, 80.0], [172.0, 104.0], [24.0, 104.0]], ['产品信息/参数', 0.98069626]]
 [[[24.0, 109.0], [333.0, 109.0], [333.0, 136.0], [24.0, 136.0]], ['（45元/每公斤，100公斤起订）', 0.9676722]]
 ......
 ```
+
 结果可视化
 
 <div align="center">
     <img src="../imgs_results/whl/11_det_rec.jpg" width="800">
 </div>
 
-
 * 检测+识别
+
 ```python
 from paddleocr import PaddleOCR, draw_ocr
+
 ocr = PaddleOCR()  # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs/11.jpg'
-result = ocr.ocr(img_path,cls=False)
+result = ocr.ocr(img_path, cls=False)
 for line in result:
     print(line)
 
 # 显示结果
 from PIL import Image
+
 image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
@@ -73,37 +85,45 @@ im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
+
 结果是一个list，每个item包含了文本框，文字和识别置信度
+
 ```bash
 [[[24.0, 36.0], [304.0, 34.0], [304.0, 72.0], [24.0, 74.0]], ['纯臻营养护发素', 0.964739]]
 [[[24.0, 80.0], [172.0, 80.0], [172.0, 104.0], [24.0, 104.0]], ['产品信息/参数', 0.98069626]]
 [[[24.0, 109.0], [333.0, 109.0], [333.0, 136.0], [24.0, 136.0]], ['（45元/每公斤，100公斤起订）', 0.9676722]]
 ......
 ```
+
 结果可视化
 
 <div align="center">
     <img src="../imgs_results/whl/11_det_rec.jpg" width="800">
 </div>
 
-
 * 方向分类器+识别
+
 ```python
 from paddleocr import PaddleOCR
+
 ocr = PaddleOCR(use_angle_cls=True)  # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs_words/ch/word_1.jpg'
 result = ocr.ocr(img_path, det=False, cls=True)
 for line in result:
     print(line)
 ```
+
 结果是一个list，每个item只包含识别结果和识别置信度
+
 ```bash
 ['韩国小馆', 0.9907421]
 ```
 
 * 单独执行检测
+
 ```python
 from paddleocr import PaddleOCR, draw_ocr
+
 ocr = PaddleOCR()  # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs/11.jpg'
 result = ocr.ocr(img_path, rec=False)
@@ -118,13 +138,16 @@ im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/Pa
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
+
 结果是一个list，每个item只包含文本框
+
 ```bash
 [[26.0, 457.0], [137.0, 457.0], [137.0, 477.0], [26.0, 477.0]]
 [[25.0, 425.0], [372.0, 425.0], [372.0, 448.0], [25.0, 448.0]]
 [[128.0, 397.0], [273.0, 397.0], [273.0, 414.0], [128.0, 414.0]]
 ......
 ```
+
 结果可视化
 
 
@@ -133,29 +156,37 @@ im_show.save('result.jpg')
 </div>
 
 * 单独执行识别
+
 ```python
 from paddleocr import PaddleOCR
+
 ocr = PaddleOCR()  # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs_words/ch/word_1.jpg'
 result = ocr.ocr(img_path, det=False)
 for line in result:
     print(line)
 ```
+
 结果是一个list，每个item只包含识别结果和识别置信度
+
 ```bash
 ['韩国小馆', 0.9907421]
 ```
 
 * 单独执行方向分类器
+
 ```python
 from paddleocr import PaddleOCR
+
 ocr = PaddleOCR(use_angle_cls=True)  # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs_words/ch/word_1.jpg'
 result = ocr.ocr(img_path, det=False, rec=False, cls=True)
 for line in result:
     print(line)
 ```
+
 结果是一个list，每个item只包含分类结果和分类置信度
+
 ```bash
 ['0', 0.9999924]
 ```
@@ -163,15 +194,19 @@ for line in result:
 ### 2.2 通过命令行使用
 
 查看帮助信息
+
 ```bash
 paddleocr -h
 ```
 
 * 检测+方向分类器+识别全流程
+
 ```bash
 paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --use_angle_cls true
 ```
+
 结果是一个list，每个item包含了文本框，文字和识别置信度
+
 ```bash
 [[[24.0, 36.0], [304.0, 34.0], [304.0, 72.0], [24.0, 74.0]], ['纯臻营养护发素', 0.964739]]
 [[[24.0, 80.0], [172.0, 80.0], [172.0, 104.0], [24.0, 104.0]], ['产品信息/参数', 0.98069626]]
@@ -180,10 +215,13 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --use_angle_cls true
 ```
 
 * 检测+识别
+
 ```bash
 paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg
 ```
+
 结果是一个list，每个item包含了文本框，文字和识别置信度
+
 ```bash
 [[[24.0, 36.0], [304.0, 34.0], [304.0, 72.0], [24.0, 74.0]], ['纯臻营养护发素', 0.964739]]
 [[[24.0, 80.0], [172.0, 80.0], [172.0, 104.0], [24.0, 104.0]], ['产品信息/参数', 0.98069626]]
@@ -192,20 +230,25 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg
 ```
 
 * 方向分类器+识别
+
 ```bash
 paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --use_angle_cls true --det false
 ```
 
 结果是一个list，每个item只包含识别结果和识别置信度
+
 ```bash
 ['韩国小馆', 0.9907421]
 ```
 
 * 单独执行检测
+
 ```bash
 paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec false
 ```
+
 结果是一个list，每个item只包含文本框
+
 ```bash
 [[26.0, 457.0], [137.0, 457.0], [137.0, 477.0], [26.0, 477.0]]
 [[25.0, 425.0], [372.0, 425.0], [372.0, 448.0], [25.0, 448.0]]
@@ -214,34 +257,42 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec false
 ```
 
 * 单独执行识别
+
 ```bash
 paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --det false
 ```
 
 结果是一个list，每个item只包含识别结果和识别置信度
+
 ```bash
 ['韩国小馆', 0.9907421]
 ```
 
 * 单独执行方向分类器
+
 ```bash
 paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --use_angle_cls true --det false --rec false
 ```
 
 结果是一个list，每个item只包含分类结果和分类置信度
+
 ```bash
 ['0', 0.9999924]
 ```
 
 ## 3 自定义模型
-当内置模型无法满足需求时，需要使用到自己训练的模型。
-首先，参照[inference.md](./inference.md) 第一节转换将检测、分类和识别模型转换为inference模型，然后按照如下方式使用
+
+当内置模型无法满足需求时，需要使用到自己训练的模型。 首先，参照[inference.md](./inference.md) 第一节转换将检测、分类和识别模型转换为inference模型，然后按照如下方式使用
 
 ### 3.1 代码使用
+
 ```python
 from paddleocr import PaddleOCR, draw_ocr
+
 # 模型路径下必须含有model和params文件
-ocr = PaddleOCR(det_model_dir='{your_det_model_dir}', rec_model_dir='{your_rec_model_dir}', rec_char_dict_path='{your_rec_char_dict_path}', cls_model_dir='{your_cls_model_dir}', use_angle_cls=True)
+ocr = PaddleOCR(det_model_dir='{your_det_model_dir}', rec_model_dir='{your_rec_model_dir}',
+                rec_char_dict_path='{your_rec_char_dict_path}', cls_model_dir='{your_cls_model_dir}',
+                use_angle_cls=True)
 img_path = 'PaddleOCR/doc/imgs/11.jpg'
 result = ocr.ocr(img_path, cls=True)
 for line in result:
@@ -249,6 +300,7 @@ for line in result:
 
 # 显示结果
 from PIL import Image
+
 image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
@@ -269,8 +321,10 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_
 ### 4.1 网络图片
 
 - 代码使用
+
 ```python
-from paddleocr import PaddleOCR, draw_ocr
+from paddleocr import PaddleOCR, draw_ocr, download_with_progressbar
+
 # Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
 # 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
 ocr = PaddleOCR(use_angle_cls=True, lang="ch")  # need to run only once to download and load model into memory
@@ -281,7 +335,9 @@ for line in result:
 
 # 显示结果
 from PIL import Image
-image = Image.open(img_path).convert('RGB')
+
+download_with_progressbar(img_path, 'tmp.jpg')
+image = Image.open('tmp.jpg').convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
@@ -289,15 +345,21 @@ im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
+
 - 命令行模式
+
 ```bash
 paddleocr --image_dir http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-fypvuqf1838418.jpg --use_angle_cls=true
 ```
 
 ### 4.2 numpy数组
+
 仅通过代码使用时支持numpy数组作为输入
+
 ```python
+import cv2
 from paddleocr import PaddleOCR, draw_ocr
+
 # Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
 # 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
 ocr = PaddleOCR(use_angle_cls=True, lang="ch")  # need to run only once to download and load model into memory
@@ -310,6 +372,7 @@ for line in result:
 
 # 显示结果
 from PIL import Image
+
 image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
@@ -356,3 +419,4 @@ im_show.save('result.jpg')
 | rec                     | 前向时是否启动识别                                                                                                                                                                                                   | TRUE                    |
 | cls                     | 前向时是否启动分类 (命令行模式下使用use_angle_cls控制前向是否启动分类)                                                                                                                                                                                                | FALSE                    |
 | show_log                     | 是否打印det和rec等信息                                                                                                                                                                                                | FALSE                    |
+| type                     | 执行ocr或者表格结构化, 值可选['ocr','structure']                                                                                                                                                                                             | ocr                    |

doc/doc_en/whl_en.md

@@ -305,7 +305,8 @@ paddleocr --image_dir http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-f
 Support numpy array as input only when used by code
 
 ```python
-from paddleocr import PaddleOCR, draw_ocr
+import cv2
+from paddleocr import PaddleOCR, draw_ocr, download_with_progressbar
 ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs/11.jpg'
 img = cv2.imread(img_path)
@@ -316,7 +317,9 @@ for line in result:
 
 # show result
 from PIL import Image
-image = Image.open(img_path).convert('RGB')
+
+download_with_progressbar(img_path, 'tmp.jpg')
+image = Image.open('tmp.jpg').convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
@@ -362,5 +365,5 @@ im_show.save('result.jpg')
 | det                     | Enable detction when `ppocr.ocr` func exec                                                                                                                                                                                                   | TRUE                    |
 | rec                     | Enable recognition when `ppocr.ocr` func exec                                                                                                                                                                                                   | TRUE                    |
 | cls                     | Enable classification when `ppocr.ocr` func exec((Use use_angle_cls in command line mode to control whether to start classification in the forward direction)                                                                                                                                                                                                   | FALSE                    |
-| show_log                     | Whether to print log in det and rec 
-                                                                                                                                                                                               | FALSE                    |
\ No newline at end of file
+| show_log                     | Whether to print log in det and rec | FALSE                    |
+| type                     | Perform ocr or table structuring, the value is selected in ['ocr','structure']                                                                                                                                                                                             | ocr                    |
\ No newline at end of file

paddleocr.py

@@ -29,16 +29,19 @@ from ppocr.utils.logging import get_logger
 logger = get_logger()
 from ppocr.utils.utility import check_and_read_gif, get_image_file_list
 from ppocr.utils.network import maybe_download, download_with_progressbar, is_link, confirm_model_dir_url
-from tools.infer.utility import draw_ocr, init_args, str2bool
+from tools.infer.utility import draw_ocr, str2bool
+from ppstructure.utility import init_args, draw_structure_result
+from ppstructure.predict_system import OCRSystem, save_structure_res
 
-__all__ = ['PaddleOCR']
+__all__ = ['PaddleOCR', 'PPStructure', 'draw_ocr', 'draw_structure_result', 'save_structure_res','download_with_progressbar']
 
 model_urls = {
     'det': {
         'ch':
             'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar',
         'en':
-            'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar'
+            'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar',
+        'structure': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar'
     },
     'rec': {
         'ch': {
@@ -110,14 +113,21 @@ model_urls = {
             'url':
                 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar',
             'dict_path': './ppocr/utils/dict/devanagari_dict.txt'
+        },
+        'structure': {
+            'url': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar',
+            'dict_path': 'ppocr/utils/dict/table_dict.txt'
         }
     },
-    'cls':
-        'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar'
+    'cls': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
+    'table': {
+        'url': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar',
+        'dict_path': 'ppocr/utils/dict/table_structure_dict.txt'
+    }
 }
 
 SUPPORT_DET_MODEL = ['DB']
-VERSION = '2.1'
+VERSION = '2.2'
 SUPPORT_REC_MODEL = ['CRNN']
 BASE_DIR = os.path.expanduser("~/.paddleocr/")
 
@@ -129,9 +139,10 @@ def parse_args(mMain=True):
     parser.add_argument("--lang", type=str, default='ch')
     parser.add_argument("--det", type=str2bool, default=True)
     parser.add_argument("--rec", type=str2bool, default=True)
+    parser.add_argument("--type", type=str, default='ocr')
 
     for action in parser._actions:
-        if action.dest == 'rec_char_dict_path':
+        if action.dest in ['rec_char_dict_path', 'table_char_dict_path']:
             action.default = None
     if mMain:
         return parser.parse_args()
@@ -142,19 +153,7 @@ def parse_args(mMain=True):
         return argparse.Namespace(**inference_args_dict)
 
 
-class PaddleOCR(predict_system.TextSystem):
-    def __init__(self, **kwargs):
-        """
-        paddleocr package
-        args:
-            **kwargs: other params show in paddleocr --help
-        """
-        params = parse_args(mMain=False)
-        params.__dict__.update(**kwargs)
-        if not params.show_log:
-            logger.setLevel(logging.INFO)
-        self.use_angle_cls = params.use_angle_cls
-        lang = params.lang
+def parse_lang(lang):
     latin_lang = [
         'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga',
         'hr', 'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms',
@@ -183,23 +182,36 @@ class PaddleOCR(predict_system.TextSystem):
         model_urls['rec'].keys(), lang)
     if lang == "ch":
         det_lang = "ch"
+    elif lang == 'structure':
+        det_lang = 'structure'
     else:
         det_lang = "en"
-        use_inner_dict = False
-        if params.rec_char_dict_path is None:
-            use_inner_dict = True
-            params.rec_char_dict_path = model_urls['rec'][lang][
-                'dict_path']
+    return lang, det_lang
+
+
+class PaddleOCR(predict_system.TextSystem):
+    def __init__(self, **kwargs):
+        """
+        paddleocr package
+        args:
+            **kwargs: other params show in paddleocr --help
+        """
+        params = parse_args(mMain=False)
+        params.__dict__.update(**kwargs)
+        if not params.show_log:
+            logger.setLevel(logging.INFO)
+        self.use_angle_cls = params.use_angle_cls
+        lang, det_lang = parse_lang(params.lang)
 
         # init model dir
         params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir,
-                                                              os.path.join(BASE_DIR, VERSION, 'det', det_lang),
+                                                              os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang),
                                                               model_urls['det'][det_lang])
         params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir,
-                                                              os.path.join(BASE_DIR, VERSION, 'rec', lang),
+                                                              os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang),
                                                               model_urls['rec'][lang]['url'])
         params.cls_model_dir, cls_url = confirm_model_dir_url(params.cls_model_dir,
-                                                              os.path.join(BASE_DIR, VERSION, 'cls'),
+                                                              os.path.join(BASE_DIR, VERSION, 'ocr', 'cls'),
                                                               model_urls['cls'])
         # download model
         maybe_download(params.det_model_dir, det_url)
@@ -212,9 +224,9 @@ class PaddleOCR(predict_system.TextSystem):
         if params.rec_algorithm not in SUPPORT_REC_MODEL:
             logger.error('rec_algorithm must in {}'.format(SUPPORT_REC_MODEL))
             sys.exit(0)
-        if use_inner_dict:
-            params.rec_char_dict_path = str(
-                Path(__file__).parent / params.rec_char_dict_path)
+
+        if params.rec_char_dict_path is None:
+            params.rec_char_dict_path = str(Path(__file__).parent / model_urls['rec'][lang]['dict_path'])
 
         print(params)
         # init det_model and rec_model
@@ -272,6 +284,59 @@ class PaddleOCR(predict_system.TextSystem):
             return rec_res
 
 
+class PPStructure(OCRSystem):
+    def __init__(self, **kwargs):
+        params = parse_args(mMain=False)
+        params.__dict__.update(**kwargs)
+        if not params.show_log:
+            logger.setLevel(logging.INFO)
+        lang, det_lang = parse_lang(params.lang)
+
+        # init model dir
+        params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir,
+                                                              os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang),
+                                                              model_urls['det'][det_lang])
+        params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir,
+                                                              os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang),
+                                                              model_urls['rec'][lang]['url'])
+        params.table_model_dir, table_url = confirm_model_dir_url(params.table_model_dir,
+                                                                  os.path.join(BASE_DIR, VERSION, 'ocr', 'table'),
+                                                                  model_urls['table']['url'])
+        # download model
+        maybe_download(params.det_model_dir, det_url)
+        maybe_download(params.rec_model_dir, rec_url)
+        maybe_download(params.table_model_dir, table_url)
+
+        if params.rec_char_dict_path is None:
+            params.rec_char_dict_path = str(Path(__file__).parent / model_urls['rec'][lang]['dict_path'])
+        if params.table_char_dict_path is None:
+            params.table_char_dict_path = str(Path(__file__).parent / model_urls['table']['dict_path'])
+
+        print(params)
+        super().__init__(params)
+
+    def __call__(self, img):
+        if isinstance(img, str):
+            # download net image
+            if img.startswith('http'):
+                download_with_progressbar(img, 'tmp.jpg')
+                img = 'tmp.jpg'
+            image_file = img
+            img, flag = check_and_read_gif(image_file)
+            if not flag:
+                with open(image_file, 'rb') as f:
+                    np_arr = np.frombuffer(f.read(), dtype=np.uint8)
+                    img = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)
+            if img is None:
+                logger.error("error in loading image:{}".format(image_file))
+                return None
+        if isinstance(img, np.ndarray) and len(img.shape) == 2:
+            img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+
+        res = super().__call__(img)
+        return res
+
+
 def main():
     # for cmd
     args = parse_args(mMain=True)
@@ -284,14 +349,29 @@ def main():
     if len(image_file_list) == 0:
         logger.error('no images find in {}'.format(args.image_dir))
         return
+    if args.type == 'ocr':
+        engine = PaddleOCR(**(args.__dict__))
+    elif args.type == 'structure':
+        engine = PPStructure(**(args.__dict__))
+    else:
+        raise NotImplementedError
 
-    ocr_engine = PaddleOCR(**(args.__dict__))
     for img_path in image_file_list:
+        img_name = os.path.basename(img_path).split('.')[0]
         logger.info('{}{}{}'.format('*' * 10, img_path, '*' * 10))
-        result = ocr_engine.ocr(img_path,
+        if args.type == 'ocr':
+            result = engine.ocr(img_path,
                                 det=args.det,
                                 rec=args.rec,
                                 cls=args.use_angle_cls)
             if result is not None:
                 for line in result:
                     logger.info(line)
+        elif args.type == 'structure':
+            result = engine(img_path)
+            save_structure_res(result, args.output, img_name)
+
+            for item in result:
+                item.pop('img')
+                logger.info(item)
+                

ppocr/data/imaug/label_ops.py

@@ -19,6 +19,7 @@ from __future__ import unicode_literals
 
 import numpy as np
 import string
+import json
 
 
 class ClsLabelEncode(object):
@@ -39,7 +40,6 @@ class DetLabelEncode(object):
         pass
 
     def __call__(self, data):
-        import json
         label = data['label']
         label = json.loads(label)
         nBox = len(label)
@@ -53,6 +53,8 @@ class DetLabelEncode(object):
                 txt_tags.append(True)
             else:
                 txt_tags.append(False)
+        if len(boxes) == 0:
+            return None
         boxes = self.expand_points_num(boxes)
         boxes = np.array(boxes, dtype=np.float32)
         txt_tags = np.array(txt_tags, dtype=np.bool)
@@ -352,19 +354,22 @@ class SRNLabelEncode(BaseRecLabelEncode):
                           % beg_or_end
         return idx
 
+
 class TableLabelEncode(object):
     """ Convert between text-label and text-index """
+
     def __init__(self,
                  max_text_length,
                  max_elem_length,
                  max_cell_num,
                  character_dict_path,
-        span_weight = 1.0, 
+                 span_weight=1.0,
                  **kwargs):
         self.max_text_length = max_text_length
         self.max_elem_length = max_elem_length
         self.max_cell_num = max_cell_num
-        list_character, list_elem = self.load_char_elem_dict(character_dict_path)
+        list_character, list_elem = self.load_char_elem_dict(
+            character_dict_path)
         list_character = self.add_special_char(list_character)
         list_elem = self.add_special_char(list_elem)
         self.dict_character = {}
@@ -380,14 +385,15 @@ class TableLabelEncode(object):
         list_elem = []
         with open(character_dict_path, "rb") as fin:
             lines = fin.readlines()
-            substr = lines[0].decode('utf-8').strip("\n").split("\t")
+            substr = lines[0].decode('utf-8').strip("\r\n").split("\t")
             character_num = int(substr[0])
             elem_num = int(substr[1])
-            for cno in range(1, 1+character_num):
-                character = lines[cno].decode('utf-8').strip("\n")
+
+            for cno in range(1, 1 + character_num):
+                character = lines[cno].decode('utf-8').strip("\r\n")
                 list_character.append(character)
-            for eno in range(1+character_num, 1+character_num+elem_num):
-                elem = lines[eno].decode('utf-8').strip("\n")
+            for eno in range(1 + character_num, 1 + character_num + elem_num):
+                elem = lines[eno].decode('utf-8').strip("\r\n")
                 list_elem.append(elem)
         return list_character, list_elem
 
@@ -412,18 +418,22 @@ class TableLabelEncode(object):
             return None
         elem_num = len(structure)
         structure = [0] + structure + [len(self.dict_elem) - 1]
-        structure = structure + [0] * (self.max_elem_length + 2 - len(structure))
+        structure = structure + [0] * (self.max_elem_length + 2 - len(structure)
+                                       )
         structure = np.array(structure)
         data['structure'] = structure
         elem_char_idx1 = self.dict_elem['<td>']
         elem_char_idx2 = self.dict_elem['<td']
         span_idx_list = self.get_span_idx_list()
-        td_idx_list = np.logical_or(structure == elem_char_idx1, structure == elem_char_idx2)
+        td_idx_list = np.logical_or(structure == elem_char_idx1,
+                                    structure == elem_char_idx2)
         td_idx_list = np.where(td_idx_list)[0]
 
-        structure_mask = np.ones((self.max_elem_length + 2, 1), dtype=np.float32)
+        structure_mask = np.ones(
+            (self.max_elem_length + 2, 1), dtype=np.float32)
         bbox_list = np.zeros((self.max_elem_length + 2, 4), dtype=np.float32)
-        bbox_list_mask = np.zeros((self.max_elem_length + 2, 1), dtype=np.float32)
+        bbox_list_mask = np.zeros(
+            (self.max_elem_length + 2, 1), dtype=np.float32)
         img_height, img_width, img_ch = data['image'].shape
         if len(span_idx_list) > 0:
             span_weight = len(td_idx_list) * 1.0 / len(span_idx_list)
@@ -450,9 +460,11 @@ class TableLabelEncode(object):
         char_end_idx = self.get_beg_end_flag_idx('end', 'char')
         elem_beg_idx = self.get_beg_end_flag_idx('beg', 'elem')
         elem_end_idx = self.get_beg_end_flag_idx('end', 'elem')
-        data['sp_tokens'] = np.array([char_beg_idx, char_end_idx, elem_beg_idx, 
-            elem_end_idx, elem_char_idx1, elem_char_idx2, self.max_text_length, 
-            self.max_elem_length, self.max_cell_num, elem_num])
+        data['sp_tokens'] = np.array([
+            char_beg_idx, char_end_idx, elem_beg_idx, elem_end_idx,
+            elem_char_idx1, elem_char_idx2, self.max_text_length,
+            self.max_elem_length, self.max_cell_num, elem_num
+        ])
         return data
 
     def encode(self, text, char_or_elem):
@@ -509,4 +521,3 @@ class TableLabelEncode(object):
             assert False, "Unsupport type %s in char_or_elem" \
                               % char_or_elem
         return idx
-    
\ No newline at end of file

ppocr/postprocess/rec_postprocess.py

@@ -346,14 +346,14 @@ class TableLabelDecode(object):
         list_elem = []
         with open(character_dict_path, "rb") as fin:
             lines = fin.readlines()
-            substr = lines[0].decode('utf-8').strip("\n").split("\t")
+            substr = lines[0].decode('utf-8').strip("\n").strip("\r\n").split("\t")
             character_num = int(substr[0])
             elem_num = int(substr[1])
             for cno in range(1, 1 + character_num):
-                character = lines[cno].decode('utf-8').strip("\n")
+                character = lines[cno].decode('utf-8').strip("\n").strip("\r\n")
                 list_character.append(character)
             for eno in range(1 + character_num, 1 + character_num + elem_num):
-                elem = lines[eno].decode('utf-8').strip("\n")
+                elem = lines[eno].decode('utf-8').strip("\n").strip("\r\n")
                 list_elem.append(elem)
         return list_character, list_elem
 

ppstructure/MANIFEST.in

-include LICENSE
-include README.md
-
-recursive-include ppocr/utils *.txt utility.py logging.py network.py
-recursive-include ppocr/data *.py
-recursive-include ppocr/postprocess *.py
-recursive-include tools/infer *.py
-recursive-include ppstructure *.py
-

ppstructure/README.md

-# PaddleStructure
+English | [简体中文](README_ch.md)
 
-PaddleStructure is an OCR toolkit for complex layout analysis. It can divide document data in the form of pictures into **text, table, title, picture and list** 5 types of areas, and extract the table area as excel
-## 1. Quick start
+# PP-Structure
 
-### install
+PP-Structure is an OCR toolkit that can be used for complex documents analysis. The main features are as follows:
+- Support the layout analysis of documents, divide the documents into 5 types of areas **text, title, table, image and list** (conjunction with Layout-Parser)
+- Support to extract the texts from the text, title, picture and list areas (used in conjunction with PP-OCR)
+- Support to extract excel files from the table areas
+- Support python whl package and command line usage, easy to use
+- Support custom training for layout analysis and table structure tasks
 
-**install layoutparser**
-```sh
-pip3 install https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
+## 1. Visualization
+
+<img src="../doc/table/ppstructure.GIF" width="100%"/>
+
+
+
+## 2. Installation
+
+### 2.1 Install requirements
+
+- **（1) Install PaddlePaddle**
+
+```bash
+pip3 install --upgrade pip
+
+# GPU
+python3 -m pip install paddlepaddle-gpu==2.1.1 -i https://mirror.baidu.com/pypi/simple
+
+# CPU
+ python3 -m pip install paddlepaddle==2.1.1 -i https://mirror.baidu.com/pypi/simple
+
+# For more，refer[Installation](https://www.paddlepaddle.org.cn/install/quick)。
 ```
-**install paddlestructure**
 
-install by pypi
+- **(2) Install Layout-Parser**
 
 ```bash
-pip install paddlestructure
+pip3 install -U premailer paddleocr https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
 ```
 
-build own whl package and install
+### 2.2 Install PaddleOCR（including PP-OCR and PP-Structure）
+
+- **（1) PIP install PaddleOCR whl package（inference only）**
+
 ```bash
-python3 setup.py bdist_wheel
-pip3 install dist/paddlestructure-x.x.x-py3-none-any.whl # x.x.x is the version of paddlestructure
+pip install "paddleocr>=2.2"
 ```
 
-### 1.2 Use
+- **（2) Clone PaddleOCR（Inference+training）**
 
-#### 1.2.1 Use by command line
+```bash
+git clone https://github.com/PaddlePaddle/PaddleOCR
+```
+
+
+## 3. Quick Start
+
+### 3.1 Use by command line
 
 ```bash
-paddlestructure --image_dir=../doc/table/1.png
+paddleocr --image_dir=../doc/table/1.png --type=structure
 ```
 
-#### 1.2.2 Use by code
+### 3.2 Use by python API
 
 ```python
 import os
 import cv2
-from paddlestructure import PaddleStructure,draw_result,save_res
+from paddleocr import PPStructure,draw_structure_result,save_structure_res
 
-table_engine = PaddleStructure(show_log=True)
+table_engine = PPStructure(show_log=True)
 
 save_folder = './output/table'
 img_path = '../doc/table/1.png'
 img = cv2.imread(img_path)
 result = table_engine(img)
-save_res(result, save_folder,os.path.basename(img_path).split('.')[0])
+save_structure_res(result, save_folder,os.path.basename(img_path).split('.')[0])
 
 for line in result:
+    line.pop('img')
     print(line)
 
 from PIL import Image
 
-font_path = '../doc/fonts/simfang.ttf' # PaddleOCR下提供字体包
+font_path = '../doc/fonts/simfang.ttf'
 image = Image.open(img_path).convert('RGB')
-im_show = draw_result(image, result,font_path=font_path)
+im_show = draw_structure_result(image, result,font_path=font_path)
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
+### 3.3 Returned results format
+The returned results of PP-Structure is a list composed of a dict, an example is as follows
+
+```shell
+[
+  {   'type': 'Text',
+      'bbox': [34, 432, 345, 462],
+      'res': ([[36.0, 437.0, 341.0, 437.0, 341.0, 446.0, 36.0, 447.0], [41.0, 454.0, 125.0, 453.0, 125.0, 459.0, 41.0, 460.0]],
+                [('Tigure-6. The performance of CNN and IPT models using difforen', 0.90060663), ('Tent  ', 0.465441)])
+  }
+]
+```
+The description of each field in dict is as follows
+
+| Parameter            | Description           |
+| --------------- | -------------|
+|type|Type of image area|
+|bbox|The coordinates of the image area in the original image, respectively [left upper x, left upper y, right bottom x, right bottom y]|
+|res|OCR or table recognition result of image area。<br> Table: HTML string of the table; <br> OCR: A tuple containing the detection coordinates and recognition results of each single line of text|
+
 
-#### 1.2.3 Parameter Description：
+### 3.4 Parameter description：
 
 | Parameter            | Description                                     | Default value                                        |
 | --------------- | ---------------------------------------- | ------------------------------------------- |
@@ -69,37 +121,69 @@ im_show.save('result.jpg')
 
 Most of the parameters are consistent with the paddleocr whl package, see [doc of whl](../doc/doc_en/whl_en.md)
 
-After running, each image will have a directory with the same name under the directory specified in the output field. Each table in the picture will be stored as an excel, and the excel file name will be the coordinates of the table in the image.
+After running, each image will have a directory with the same name under the directory specified in the output field. Each table in the picture will be stored as an excel and figure area will be cropped and saved, the excel and image file name will be the coordinates of the table in the image.
 
-## 2. PaddleStructure Pipeline
+## 4. PP-Structure Pipeline
 
 the process is as follows
 ![pipeline](../doc/table/pipeline_en.jpg)
 
-In PaddleStructure, the image will be analyzed by layoutparser first. In the layout analysis, the area in the image will be classified, including **text, title, image, list and table** 5 categories. For the first 4 types of areas, directly use the PP-OCR to complete the text detection and recognition. The table area will  be converted to an excel file of the same table style via Table OCR.
+In PP-Structure, the image will be analyzed by layoutparser first. In the layout analysis, the area in the image will be classified, including **text, title, image, list and table** 5 categories. For the first 4 types of areas, directly use the PP-OCR to complete the text detection and recognition. The table area will  be converted to an excel file of the same table style via Table OCR.
 
-### 2.1 LayoutParser
+### 4.1 LayoutParser
 
-Layout analysis divides the document data into regions, including the use of Python scripts for layout analysis tools, extraction of special category detection boxes, performance indicators, and custom training layout analysis models. For details, please refer to [document](layout/README.md).
+Layout analysis divides the document data into regions, including the use of Python scripts for layout analysis tools, extraction of special category detection boxes, performance indicators, and custom training layout analysis models. For details, please refer to [document](layout/README_en.md).
 
-### 2.2 Table OCR
+### 4.2 Table Recognition
 
-Table OCR converts table image into excel documents, which include the detection and recognition of table text and the prediction of table structure and cell coordinates. For detailed, please refer to [document](table/README.md)
+Table Recognition converts table image into excel documents, which include the detection and recognition of table text and the prediction of table structure and cell coordinates. For detailed, please refer to [document](table/README.md)
 
-### 3. Predictive by inference engine
+## 5. Prediction by inference engine
 
 Use the following commands to complete the inference.
 
 ```python
-python3 table/predict_system.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
+cd PaddleOCR/ppstructure
+
+# download model
+mkdir inference && cd inference
+# Download the detection model of the ultra-lightweight Chinese OCR model and uncompress it
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_det_infer.tar
+# Download the recognition model of the ultra-lightweight Chinese OCR model and uncompress it
+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
+# Download the table structure model of the ultra-lightweight Chinese OCR model and uncompress it
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
+cd ..
+
+python3 predict_system.py --det_model_dir=inference/ch_ppocr_mobile_v2.0_det_infer --rec_model_dir=inference/ch_ppocr_mobile_v2.0_rec_infer --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=ch --output=../output/table --vis_font_path=../doc/fonts/simfang.ttf
 ```
-After running, each image will have a directory with the same name under the directory specified in the output field. Each table in the picture will be stored as an excel, and the excel file name will be the coordinates of the table in the image.
+After running, each image will have a directory with the same name under the directory specified in the output field. Each table in the picture will be stored as an excel and figure area will be cropped and saved, the excel and image file name will be the coordinates of the table in the image.
 
-# 3. Model List
+**Model List**
 
 
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
-|en_ppocr_mobile_v2.0_table_det|Text detection in English table scene|[ch_det_mv3_db_v2.0.yml](../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)| 4.7M |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) |
-|en_ppocr_mobile_v2.0_table_rec|Text recognition in English table scene|[rec_chinese_lite_train_v2.0.yml](..//configs/rec/rec_mv3_none_bilstm_ctc.yml)|6.9M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) |
 |en_ppocr_mobile_v2.0_table_structure|Table structure prediction for English table scenarios|[table_mv3.yml](../configs/table/table_mv3.yml)|18.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) |
+
+**Model List**
+
+LayoutParser model
+
+|model name|description|download|
+| --- | --- | --- |
+| ppyolov2_r50vd_dcn_365e_publaynet | The layout analysis model trained on the PubLayNet data set can be divided into 5 types of areas **text, title, table, picture and list** | [PubLayNet](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_publaynet.tar) |
+| ppyolov2_r50vd_dcn_365e_tableBank_word | The layout analysis model trained on the TableBank Word dataset can only detect tables | [TableBank Word](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_tableBank_word.tar) |
+| ppyolov2_r50vd_dcn_365e_tableBank_latex | The layout analysis model trained on the TableBank Latex dataset can only detect tables | [TableBank Latex](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_tableBank_latex.tar) |
+
+OCR and table recognition model
+
+|model name|description|model size|download|
+| --- | --- | --- | --- |
+|ch_ppocr_mobile_slim_v2.0_det|Slim pruned lightweight model, supporting Chinese, English, multilingual text detection|2.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_infer.tar) |
+|ch_ppocr_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition|6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) |
+|en_ppocr_mobile_v2.0_table_det|Text detection of English table scenes trained on PubLayNet dataset|4.7M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) |
+|en_ppocr_mobile_v2.0_table_rec|Text recognition of English table scene trained on PubLayNet dataset|6.9M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) |
+|en_ppocr_mobile_v2.0_table_structure|Table structure prediction of English table scene trained on PubLayNet dataset|18.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) |
+
+If you need to use other models, you can download the model in [model_list](../doc/doc_en/models_list_en.md) or use your own trained model to configure it to the three fields of `det_model_dir`, `rec_model_dir`, `table_model_dir` .

ppstructure/README_ch.md

-# PaddleStructure
+[English](README.md) | 简体中文
 
-PaddleStructure是一个用于复杂版面分析的OCR工具包，其能够对图片形式的文档数据划分**文字、表格、标题、图片以及列表**5类区域，并将表格区域提取为excel
+# PP-Structure
 
-## 1. 快速开始
+PP-Structure是一个可用于复杂文档结构分析和处理的OCR工具包，主要特性如下：
+- 支持对图片形式的文档进行版面分析，可以划分**文字、标题、表格、图片以及列表**5类区域（与Layout-Parser联合使用）
+- 支持文字、标题、图片以及列表区域提取为文字字段（与PP-OCR联合使用）
+- 支持表格区域进行结构化分析，最终结果输出Excel文件
+- 支持python whl包和命令行两种方式，简单易用
+- 支持版面分析和表格结构化两类任务自定义训练
 
-### 1.1 安装
+## 1. 效果展示
 
-**安装 layoutparser**
-```sh
-pip3 install https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
+<img src="../doc/table/ppstructure.GIF" width="100%"/>
+
+
+
+## 2. 安装
+
+### 2.1 安装依赖
+
+- **（1) 安装PaddlePaddle**
+
+```bash
+pip3 install --upgrade pip
+
+# GPU安装
+python3 -m pip install paddlepaddle-gpu==2.1.1 -i https://mirror.baidu.com/pypi/simple
+
+# CPU安装
+ python3 -m pip install paddlepaddle==2.1.1 -i https://mirror.baidu.com/pypi/simple
+
+# 更多需求，请参照[安装文档](https://www.paddlepaddle.org.cn/install/quick)中的说明进行操作。
+```
+
+- **(2) 安装 Layout-Parser**
+
+```bash
+pip3 install -U premailer paddleocr https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
 ```
-**安装 paddlestructure**
 
-pip安装
+### 2.2 安装PaddleOCR（包含PP-OCR和PP-Structure）
+
+- **（1) PIP快速安装PaddleOCR whl包（仅预测）**
+
 ```bash
-pip install paddlestructure
+pip install "paddleocr>=2.2" # 推荐使用2.2+版本
 ```
 
-本地构建并安装
+- **（2) 完整克隆PaddleOCR源码（预测+训练）**
+
 ```bash
-python3 setup.py bdist_wheel
-pip3 install dist/paddlestructure-x.x.x-py3-none-any.whl # x.x.x是 paddlestructure 的版本号
+【推荐】git clone https://github.com/PaddlePaddle/PaddleOCR
+
+#如果因为网络问题无法pull成功，也可选择使用码云上的托管：
+git clone https://gitee.com/paddlepaddle/PaddleOCR
+
+#注：码云托管代码可能无法实时同步本github项目更新，存在3~5天延时，请优先使用推荐方式。
 ```
 
-### 1.2 PaddleStructure whl包使用
 
-#### 1.2.1 命令行使用
+## 3. PP-Structure 快速开始
+
+### 3.1 命令行使用（默认参数，极简）
 
 ```bash
-paddlestructure --image_dir=../doc/table/1.png
+paddleocr --image_dir=../doc/table/1.png --type=structure
 ```
 
-#### 1.2.2 Python脚本使用
+### 3.2 Python脚本使用（自定义参数，灵活）
 
 ```python
 import os
 import cv2
-from paddlestructure import PaddleStructure,draw_result,save_res
+from paddleocr import PPStructure,draw_structure_result,save_structure_res
 
-table_engine = PaddleStructure(show_log=True)
+table_engine = PPStructure(show_log=True)
 
 save_folder = './output/table'
 img_path = '../doc/table/1.png'
 img = cv2.imread(img_path)
 result = table_engine(img)
-save_res(result, save_folder,os.path.basename(img_path).split('.')[0])
+save_structure_res(result, save_folder,os.path.basename(img_path).split('.')[0])
 
 for line in result:
+    line.pop('img')
     print(line)
 
 from PIL import Image
 
 font_path = '../doc/fonts/simfang.ttf' # PaddleOCR下提供字体包
 image = Image.open(img_path).convert('RGB')
-im_show = draw_result(image, result,font_path=font_path)
+im_show = draw_structure_result(image, result,font_path=font_path)
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
 
+### 3.3 返回结果说明
+PP-Structure的返回结果为一个dict组成的list，示例如下
+
+```shell
+[
+  {   'type': 'Text',
+      'bbox': [34, 432, 345, 462],
+      'res': ([[36.0, 437.0, 341.0, 437.0, 341.0, 446.0, 36.0, 447.0], [41.0, 454.0, 125.0, 453.0, 125.0, 459.0, 41.0, 460.0]],
+                [('Tigure-6. The performance of CNN and IPT models using difforen', 0.90060663), ('Tent  ', 0.465441)])
+  }
+]
+```
+dict 里各个字段说明如下
+
+| 字段            | 说明           |
+| --------------- | -------------|
+|type|图片区域的类型|
+|bbox|图片区域的在原图的坐标，分别[左上角x，左上角y，右下角x，右下角y]|
+|res|图片区域的OCR或表格识别结果。<br> 表格: 表格的HTML字符串; <br> OCR: 一个包含各个单行文字的检测坐标和识别结果的元组|
+
 
-#### 1.2.3 参数说明
+### 3.4 参数说明
 
 | 字段            | 说明                                     | 默认值                                      |
 | --------------- | ---------------------------------------- | ------------------------------------------- |
@@ -70,38 +127,62 @@ im_show.save('result.jpg')
 
 大部分参数和paddleocr whl包保持一致，见 [whl包文档](../doc/doc_ch/whl.md)
 
-运行完成后，每张图片会在`output`字段指定的目录下有一个同名目录，图片里的每个表格会存储为一个excel，excel文件名为表格在图片里的坐标。
+运行完成后，每张图片会在`output`字段指定的目录下有一个同名目录，图片里的每个表格会存储为一个excel，图片区域会被裁剪之后保存下来，excel文件和图片名名为表格在图片里的坐标。
 
 
-## 2. PaddleStructure Pipeline
+## 4. PP-Structure Pipeline介绍
 
-流程如下
 ![pipeline](../doc/table/pipeline.jpg)
 
-在PaddleStructure中，图片会先经由layoutparser进行版面分析，在版面分析中，会对图片里的区域进行分类，包括**文字、标题、图片、列表和表格**5类。对于前4类区域，直接使用PP-OCR完成对应区域文字检测与识别。对于表格类区域，经过Table OCR处理后，表格图片转换为相同表格样式的Excel文件。
+在PP-Structure中，图片会先经由Layout-Parser进行版面分析，在版面分析中，会对图片里的区域进行分类，包括**文字、标题、图片、列表和表格**5类。对于前4类区域，直接使用PP-OCR完成对应区域文字检测与识别。对于表格类区域，经过表格结构化处理后，表格图片转换为相同表格样式的Excel文件。
 
-### 2.1 LayoutParser
+### 4.1 版面分析
 
-版面分析对文档数据进行区域分类，其中包括版面分析工具的Python脚本使用、提取指定类别检测框、性能指标以及自定义训练版面分析模型，详细内容可以参考[文档](layout/README.md)。
+版面分析对文档数据进行区域分类，其中包括版面分析工具的Python脚本使用、提取指定类别检测框、性能指标以及自定义训练版面分析模型，详细内容可以参考[文档](layout/README_ch.md)。
 
-### 2.2 Table OCR
+### 4.2 表格识别
 
-Table OCR将表格图片转换为excel文档，其中包含对于表格文本的检测和识别以及对于表格结构和单元格坐标的预测，详细说明参考[文档](table/README_ch.md)
+表格识别将表格图片转换为excel文档，其中包含对于表格文本的检测和识别以及对于表格结构和单元格坐标的预测，详细说明参考[文档](table/README_ch.md)
 
-### 3. 预测引擎推理
+## 5. 预测引擎推理（与whl包效果相同）
 
 使用如下命令即可完成预测引擎的推理
 
 ```python
-python3 table/predict_system.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
+cd ppstructure
+
+# 下载模型
+mkdir inference && cd inference
+# 下载超轻量级中文OCR模型的检测模型并解压
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_det_infer.tar
+# 下载超轻量级中文OCR模型的识别模型并解压
+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
+# 下载超轻量级英文表格英寸模型并解压
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
+cd ..
+
+python3 predict_system.py --det_model_dir=inference/ch_ppocr_mobile_v2.0_det_infer --rec_model_dir=inference/ch_ppocr_mobile_v2.0_rec_infer --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=ch --output=../output/table --vis_font_path=../doc/fonts/simfang.ttf
 ```
-运行完成后，每张图片会output字段指定的目录下有一个同名目录，图片里的每个表格会存储为一个excel，excel文件名为表格在图片里的坐标。
+运行完成后，每张图片会在`output`字段指定的目录下有一个同名目录，图片里的每个表格会存储为一个excel，图片区域会被裁剪之后保存下来，excel文件和图片名名为表格在图片里的坐标。
+
+**Model List**
+
+LayoutParser 模型
+
+|模型名称|模型简介|下载地址|
+| --- | --- | --- |
+| ppyolov2_r50vd_dcn_365e_publaynet | PubLayNet 数据集训练的版面分析模型，可以划分**文字、标题、表格、图片以及列表**5类区域 | [PubLayNet](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_publaynet.tar) |
+| ppyolov2_r50vd_dcn_365e_tableBank_word | TableBank Word 数据集训练的版面分析模型，只能检测表格 | [TableBank Word](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_tableBank_word.tar) |
+| ppyolov2_r50vd_dcn_365e_tableBank_latex | TableBank Latex 数据集训练的版面分析模型，只能检测表格 | [TableBank Latex](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_tableBank_latex.tar) |
 
-# 3. Model List
+OCR和表格识别模型
 
+|模型名称|模型简介|推理模型大小|下载地址|
+| --- | --- | --- | --- |
+|ch_ppocr_mobile_slim_v2.0_det|slim裁剪版超轻量模型，支持中英文、多语种文本检测|2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_infer.tar) |
+|ch_ppocr_mobile_slim_v2.0_rec|slim裁剪量化版超轻量模型，支持中英文、数字识别|6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) |
+|en_ppocr_mobile_v2.0_table_det|PubLayNet数据集训练的英文表格场景的文字检测|4.7M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) |
+|en_ppocr_mobile_v2.0_table_rec|PubLayNet数据集训练的英文表格场景的文字识别|6.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) |
+|en_ppocr_mobile_v2.0_table_structure|PubLayNet数据集训练的英文表格场景的表格结构预测|18.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) |
 
-|模型名称|模型简介|配置文件|推理模型大小|下载地址|
-| --- | --- | --- | --- | --- |
-|en_ppocr_mobile_v2.0_table_det|英文表格场景的文字检测|[ch_det_mv3_db_v2.0.yml](../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)| 4.7M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) |
-|en_ppocr_mobile_v2.0_table_rec|英文表格场景的文字识别|[rec_chinese_lite_train_v2.0.yml](..//configs/rec/rec_mv3_none_bilstm_ctc.yml)|6.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) |
-|en_ppocr_mobile_v2.0_table_structure|英文表格场景的表格结构预测|[table_mv3.yml](../configs/table/table_mv3.yml)|18.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) |
\ No newline at end of file
+如需要使用其他模型，可以在 [model_list](../doc/doc_ch/models_list.md) 下载模型或者使用自己训练好的模型配置到`det_model_dir`,`rec_model_dir`,`table_model_dir`三个字段即可。