polish code

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

doc/doc_ch/recognition.md

@@ -303,7 +303,7 @@ PaddleOCR目前已支持26种（除中文外）语种识别，`configs/rec/multi
 
     ```bash
     # -l或者--language字段是必须的
-    # --train修改训练集，--val修改验证集，--data_dir修改数据集目录，-o修改对应默认参数
+    # --train修改训练集，--val修改验证集，--data_dir修改数据集目录，--dict修改字典路径， -o修改对应默认参数
     cd PaddleOCR/configs/rec/multi_language/
     python3 generate_multi_language_configs.py -l it \  # 语种
     --train {path/of/train_label.txt} \ # 训练标签文件的路径
@@ -348,7 +348,7 @@ PaddleOCR目前已支持26种（除中文外）语种识别，`configs/rec/multi
 | 配置文件 |  算法名称 |   backbone |   trans   |   seq      |     pred     |  language | character_type |
 | :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   | :-----:  | :-----:  |
 | rec_chinese_cht_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 中文繁体  | chinese_cht|
-| rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 英语   | ch |
+| rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 英语   | En |
 | rec_french_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 法语 |  french |
 | rec_ger_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 德语   | german |
 | rec_japan_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 日语  | japan |

doc/doc_en/inference_en.md

@@ -315,7 +315,7 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
 <a name="MULTILINGUAL_MODEL_INFERENCE"></a>
 ### 4. MULTILINGAUL MODEL INFERENCE
 If you need to predict other language models, when using inference model prediction, you need to specify the dictionary path used by `--rec_char_dict_path`. At the same time, in order to get the correct visualization results,
-You need to specify the visual font path through `--vis_font_path`. There are small language fonts provided by default under the `doc/` path, such as Korean recognition:
+You need to specify the visual font path through `--vis_font_path`. There are small language fonts provided by default under the `doc/fonts` path, such as Korean recognition:
 
 ```
 python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_type="korean" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf"

doc/doc_en/recognition_en.md

@@ -304,6 +304,7 @@ There are two ways to create the required configuration file:：
     # --train to modify the training set
     # --val to modify the validation set
     # --data_dir to modify the data set directory
+    # --dict to modify the dict path
     # -o to modify the corresponding default parameters
     cd PaddleOCR/configs/rec/multi_language/
     python3 generate_multi_language_configs.py -l it \  # language
@@ -346,10 +347,10 @@ There are two ways to create the required configuration file:：
 
 Currently, the multi-language algorithms supported by PaddleOCR are:
 
-| 配置文件 |  算法名称 |   backbone |   trans   |   seq      |     pred     |  language | character_type |
+| Configuration file |  Algorithm name |   backbone |   trans   |   seq      |     pred     |  language | character_type |
 | :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   | :-----:  | :-----:  |
 | rec_chinese_cht_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | chinese traditional  | chinese_cht|
-| rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | English   | ch |
+| rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | English   | En |
 | rec_french_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | French |  french |
 | rec_ger_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | German   | german |
 | rec_japan_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | Japanese | japan |

ppocr/data/imaug/label_ops.py

@@ -92,7 +92,10 @@ class BaseRecLabelEncode(object):
                  character_type='ch',
                  use_space_char=False):
         support_character_type = [
-            'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'korean'
+            'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'korean',
+            'EN', 'it', 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs',
+            'oc', 'rsc', 'bg', 'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi',
+            'mr', 'ne'
         ]
         assert character_type in support_character_type, "Only {} are supported now but get {}".format(
             support_character_type, character_type)
@@ -101,9 +104,15 @@ class BaseRecLabelEncode(object):
         if character_type == "en":
             self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
             dict_character = list(self.character_str)
-        elif character_type in ["ch", "french", "german", "japan", "korean"]:
+        elif character_type == "en_sensitive":
+            # same with ASTER setting (use 94 char).
+            import string
+            self.character_str = string.printable[:-6]
+            dict_character = list(self.character_str)
+        elif character_type in support_character_type:
             self.character_str = ""
-            assert character_dict_path is not None, "character_dict_path should not be None when character_type is ch"
+            assert character_dict_path is not None, "character_dict_path should not be None when character_type is {}".format(
+                character_type)
             with open(character_dict_path, "rb") as fin:
                 lines = fin.readlines()
                 for line in lines:
@@ -112,11 +121,6 @@ class BaseRecLabelEncode(object):
             if use_space_char:
                 self.character_str += " "
             dict_character = list(self.character_str)
-        elif character_type == "en_sensitive":
-            # same with ASTER setting (use 94 char).
-            import string
-            self.character_str = string.printable[:-6]
-            dict_character = list(self.character_str)
         self.character_type = character_type
         dict_character = self.add_special_char(dict_character)
         self.dict = {}

ppocr/postprocess/rec_postprocess.py

@@ -24,9 +24,10 @@ class BaseRecLabelDecode(object):
                  character_type='ch',
                  use_space_char=False):
         support_character_type = [
-            'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'korean', 'it',
-            'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', 'oc', 'rsc', 'bg',
-            'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi', 'mr', 'ne'
+            'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'korean',
+            'it', 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', 'oc',
+            'rsc', 'bg', 'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi', 'mr',
+            'ne', 'En'
         ]
         assert character_type in support_character_type, "Only {} are supported now but get {}".format(
             support_character_type, character_type)
@@ -34,9 +35,15 @@ class BaseRecLabelDecode(object):
         if character_type == "en":
             self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
             dict_character = list(self.character_str)
-        elif character_type in ["ch", "french", "german", "japan", "korean"]:
+        elif character_type == "en_sensitive":
+            # same with ASTER setting (use 94 char).
+            import string
+            self.character_str = string.printable[:-6]
+            dict_character = list(self.character_str)
+        elif character_type in support_character_type:
             self.character_str = ""
-            assert character_dict_path is not None, "character_dict_path should not be None when character_type is ch"
+            assert character_dict_path is not None, "character_dict_path should not be None when character_type is {}".format(
+                character_type)
             with open(character_dict_path, "rb") as fin:
                 lines = fin.readlines()
                 for line in lines:
@@ -45,11 +52,7 @@ class BaseRecLabelDecode(object):
             if use_space_char:
                 self.character_str += " "
             dict_character = list(self.character_str)
-        elif character_type == "en_sensitive":
-            # same with ASTER setting (use 94 char).
-            import string
-            self.character_str = string.printable[:-6]
-            dict_character = list(self.character_str)
+
         else:
             raise NotImplementedError
         self.character_type = character_type

tools/infer/utility.py

@@ -70,7 +70,7 @@ def parse_args():
         default="./ppocr/utils/ppocr_keys_v1.txt")
     parser.add_argument("--use_space_char", type=str2bool, default=True)
     parser.add_argument(
-        "--vis_font_path", type=str, default="./doc/simfang.ttf")
+        "--vis_font_path", type=str, default="./doc/fonts/simfang.ttf")
     parser.add_argument("--drop_score", type=float, default=0.5)
 
     # params for text classifier