Merge pull request #2487 from tink2123/new_multi_lang_for_dygraph

replace path.join for windows

README.md

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

configs/rec/multi_language/generate_multi_language_configs.py

@@ -118,7 +118,6 @@ class ArgsParser(ArgumentParser):
         return config
 
     def _set_language(self, type):
-        print("type:", type)
         lang = type[0]
         assert (type), "please use -l or --language to choose language type"
         assert(

doc/doc_ch/models_list.md

@@ -113,7 +113,7 @@ python3 generate_multi_language_configs.py -l it \
 | cyrillic_mobile_v2.0_rec | 斯拉夫字母 | [rec_cyrillic_lite_train.yml](../../configs/rec/multi_language/rec_cyrillic_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_train.tar) |
 | devanagari_mobile_v2.0_rec | 梵文字母 | [rec_devanagari_lite_train.yml](../../configs/rec/multi_language/rec_devanagari_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_train.tar) |
 
-更多支持语种请参考: [多语言模型](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_ch/multi_languages.md#%E8%AF%AD%E7%A7%8D%E7%BC%A9%E5%86%99)
+更多支持语种请参考: [多语言模型](./multi_languages.md)
 
 
 <a name="文本方向分类模型"></a>

doc/doc_ch/multi_languages.md

@@ -134,7 +134,7 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec false
 <a name="python_脚本运行"></a>
 ### 2.2 python 脚本运行
 
-ppocr 也支持在python脚本中运行，便于嵌入到您自己的代码中：
+ppocr 也支持在python脚本中运行，便于嵌入到您自己的代码中 ：
 
 * 整图预测（检测+识别）
 
@@ -155,7 +155,7 @@ image = Image.open(img_path).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]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/korean.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/korean.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -240,7 +240,7 @@ ppocr 支持使用自己的数据进行自定义训练或finetune, 其中识别
 |德文|german|german|
 |日文|japan|japan|
 |韩文|korean|korean|
-|中文繁体|chinese traditional |ch_tra|
+|中文繁体|chinese traditional |chinese_cht|
 |意大利文| Italian |it|
 |西班牙文|Spanish |es|
 |葡萄牙文| Portuguese|pt|
@@ -259,10 +259,9 @@ ppocr 支持使用自己的数据进行自定义训练或finetune, 其中识别
 |乌克兰文|Ukranian|uk|
 |白俄罗斯文|Belarusian|be|
 |泰卢固文|Telugu |te|
-|卡纳达文|Kannada |kn|
 |泰米尔文|Tamil |ta|
 |南非荷兰文 |Afrikaans |af|
-|阿塞拜疆文 |Azerbaijani    |az|
+|阿塞拜疆文 |Azerbaijani  |az|
 |波斯尼亚文|Bosnian|bs|
 |捷克文|Czech|cs|
 |威尔士文 |Welsh |cy|

doc/doc_en/models_list_en.md

@@ -111,7 +111,7 @@ python3 generate_multi_language_configs.py -l it \
 | cyrillic_mobile_v2.0_rec | Lightweight model for cyrillic recognition | [rec_cyrillic_lite_train.yml](../../configs/rec/multi_language/rec_cyrillic_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_train.tar) |
 | devanagari_mobile_v2.0_rec | Lightweight model for devanagari recognition | [rec_devanagari_lite_train.yml](../../configs/rec/multi_language/rec_devanagari_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_train.tar) |
 
-For more supported languages, please refer to : [Multi-language model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md#4-support-languages-and-abbreviations)
+For more supported languages, please refer to : [Multi-language model](./multi_languages_en.md)
 
 
 <a name="Angle"></a>

doc/doc_en/multi_languages_en.md

@@ -153,7 +153,7 @@ image = Image.open(img_path).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]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/korean.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/korean.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -232,7 +232,7 @@ For functions such as data annotation, you can read the complete [Document Tutor
 |german|german|
 |japan|japan|
 |korean|korean|
-|chinese traditional |ch_tra|
+|chinese traditional |chinese_cht|
 | Italian |it|
 |Spanish |es|
 | Portuguese|pt|
@@ -251,7 +251,6 @@ For functions such as data annotation, you can read the complete [Document Tutor
 |Ukranian|uk|
 |Belarusian|be|
 |Telugu |te|
-|Kannada |kn|
 |Tamil |ta|
 |Afrikaans |af|
 |Azerbaijani    |az|

paddleocr.py

@@ -30,6 +30,7 @@ from ppocr.utils.logging import get_logger
 
 logger = get_logger()
 from ppocr.utils.utility import check_and_read_gif, get_image_file_list
+from tools.infer.utility import draw_ocr
 
 __all__ = ['PaddleOCR']
 
@@ -117,7 +118,7 @@ model_urls = {
 }
 
 SUPPORT_DET_MODEL = ['DB']
-VERSION = 2.1
+VERSION = '2.1'
 SUPPORT_REC_MODEL = ['CRNN']
 BASE_DIR = os.path.expanduser("~/.paddleocr/")
 
@@ -315,14 +316,13 @@ class PaddleOCR(predict_system.TextSystem):
 
         # init model dir
         if postprocess_params.det_model_dir is None:
-            postprocess_params.det_model_dir = os.path.join(
-                BASE_DIR, '{}/det/{}'.format(VERSION, det_lang))
+            postprocess_params.det_model_dir = os.path.join(BASE_DIR, VERSION,
+                                                            'det', det_lang)
         if postprocess_params.rec_model_dir is None:
-            postprocess_params.rec_model_dir = os.path.join(
-                BASE_DIR, '{}/rec/{}'.format(VERSION, lang))
+            postprocess_params.rec_model_dir = os.path.join(BASE_DIR, VERSION,
+                                                            'rec', lang)
         if postprocess_params.cls_model_dir is None:
-            postprocess_params.cls_model_dir = os.path.join(
-                BASE_DIR, '{}/cls'.format(VERSION))
+            postprocess_params.cls_model_dir = os.path.join(BASE_DIR, 'cls')
         print(postprocess_params)
         # download model
         maybe_download(postprocess_params.det_model_dir,

ppocr/data/imaug/label_ops.py

@@ -96,7 +96,7 @@ class BaseRecLabelEncode(object):
             'ch', 'en', 'EN_symbol', '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'
+            'mr', 'ne', 'latin', 'arabic', 'cyrillic', 'devanagari'
         ]
         assert character_type in support_character_type, "Only {} are supported now but get {}".format(
             support_character_type, character_type)

ppocr/postprocess/rec_postprocess.py

@@ -28,7 +28,7 @@ class BaseRecLabelDecode(object):
             'ch', 'en', 'EN_symbol', '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'
+            'ne', 'EN', 'latin', 'arabic', 'cyrillic', 'devanagari'
         ]
         assert character_type in support_character_type, "Only {} are supported now but get {}".format(
             support_character_type, character_type)