Merge pull request #757 from littletomatodonkey/fix_whl_language

fix whl doc and add multi-language

deploy/cpp_infer/readme.md

@@ -193,6 +193,9 @@ make -j
 sh tools/run.sh
 ```
 
+* 若需要使用方向分类器，则需要将`tools/config.txt`中的`use_angle_cls`参数修改为1，表示开启方向分类器的预测。
+
+
 最终屏幕上会输出检测结果如下。
 
 <div align="center">

deploy/cpp_infer/readme_en.md

@@ -162,7 +162,7 @@ inference/
 sh tools/build.sh
 ```
 
-具体地，`tools/build.sh`中内容如下。
+Specifically, the content in `tools/build.sh` is as follows.
 
 ```shell
 OPENCV_DIR=your_opencv_dir
@@ -201,6 +201,8 @@ make -j
 sh tools/run.sh
 ```
 
+* If you want to orientation classifier to correct the detected boxes, you can set `use_angle_cls` in the file `tools/config.txt` as 1 to enable the function.
+
 The detection results will be shown on the screen, which is as follows.
 
 <div align="center">

deploy/cpp_infer/tools/config.txt

@@ -15,7 +15,7 @@ det_model_dir  ./inference/det_db
 
 # cls config
 use_angle_cls 0
-cls_model_dir ../inference/cls
+cls_model_dir ./inference/cls
 cls_thresh  0.9
 
 # rec config

doc/doc_ch/whl.md

@@ -19,7 +19,9 @@ pip install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x是paddleocr的版本
 * 检测+分类+识别全流程
 ```python
 from paddleocr import PaddleOCR, draw_ocr
-ocr = PaddleOCR(use_angle_cls=True) # need to run only once to download and load model into memory
+# 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`zh`, `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
 img_path = 'PaddleOCR/doc/imgs/11.jpg'
 result = ocr.ocr(img_path, cls=True)
 for line in result:

doc/doc_en/whl_en.md

@@ -17,12 +17,16 @@ pip install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x is the version of padd
 * detection classification and recognition
 ```python
 from paddleocr import PaddleOCR,draw_ocr
+# Paddleocr supports Chinese, English, French, German, Korean and Japanese.
+# You can set the parameter `lang` as `zh`, `en`, `french`, `german`, `korean`, `japan`
+# to switch the language model in order.
 ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
 img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
 result = ocr.ocr(img_path, cls=True)
 for line in result:
     print(line)
 
+
 # draw result
 from PIL import Image
 image = Image.open(img_path).convert('RGB')

paddleocr.py

@@ -46,6 +46,26 @@ model_urls = {
             'url':
             'https://paddleocr.bj.bcebos.com/20-09-22/mobile/en/en_ppocr_mobile_v1.1_rec_infer.tar',
             'dict_path': './ppocr/utils/ic15_dict.txt'
+        },
+        'french': {
+            'url':
+            'https://paddleocr.bj.bcebos.com/20-09-22/mobile/fr/french_ppocr_mobile_v1.1_rec_infer.tar',
+            'dict_path': './ppocr/utils/french_dict.txt'
+        },
+        'german': {
+            'url':
+            'https://paddleocr.bj.bcebos.com/20-09-22/mobile/ge/german_ppocr_mobile_v1.1_rec_infer.tar',
+            'dict_path': './ppocr/utils/german_dict.txt'
+        },
+        'korean': {
+            'url':
+            'https://paddleocr.bj.bcebos.com/20-09-22/mobile/kr/korean_ppocr_mobile_v1.1_rec_infer.tar',
+            'dict_path': './ppocr/utils/korean_dict.txt'
+        },
+        'japan': {
+            'url':
+            'https://paddleocr.bj.bcebos.com/20-09-22/mobile/jp/japan_ppocr_mobile_v1.1_rec_infer.tar',
+            'dict_path': './ppocr/utils/japan_dict.txt'
         }
     },
     'cls':
@@ -165,8 +185,9 @@ class PaddleOCR(predict_system.TextSystem):
         postprocess_params.__dict__.update(**kwargs)
         self.use_angle_cls = postprocess_params.use_angle_cls
         lang = postprocess_params.lang
-        assert lang in model_urls['rec'], 'param lang must in {}'.format(
-            model_urls['rec'].keys())
+        assert lang in model_urls[
+            'rec'], 'param lang must in {}, but got {}'.format(
+                model_urls['rec'].keys(), lang)
         if postprocess_params.rec_char_dict_path is None:
             postprocess_params.rec_char_dict_path = model_urls['rec'][lang][
                 'dict_path']