Merge pull request #923 from tink2123/add_dict_folder

Add dict and corpus folder

configs/rec/multi_languages/rec_french_lite_train.yml

@@ -12,7 +12,7 @@ Global:
   image_shape: [3, 32, 320]
   max_text_length: 25
   character_type: french
-  character_dict_path: ./ppocr/utils/french_dict.txt
+  character_dict_path: ./ppocr/utils/dict/french_dict.txt
   loss_type: ctc
   distort: true
   use_space_char: false

configs/rec/multi_languages/rec_ger_lite_train.yml

@@ -12,7 +12,7 @@ Global:
   image_shape: [3, 32, 320]
   max_text_length: 25
   character_type: german
-  character_dict_path: ./ppocr/utils/german_dict.txt
+  character_dict_path: ./ppocr/utils/dict/german_dict.txt
   loss_type: ctc
   distort: true
   use_space_char: false

configs/rec/multi_languages/rec_japan_lite_train.yml

@@ -12,7 +12,7 @@ Global:
   image_shape: [3, 32, 320]
   max_text_length: 25
   character_type: japan
-  character_dict_path: ./ppocr/utils/japan_dict.txt
+  character_dict_path: ./ppocr/utils/dict/japan_dict.txt
   loss_type: ctc
   distort: true
   use_space_char: false

configs/rec/multi_languages/rec_korean_lite_train.yml

@@ -12,7 +12,7 @@ Global:
   image_shape: [3, 32, 320]
   max_text_length: 25
   character_type: korean
-  character_dict_path: ./ppocr/utils/korean_dict.txt
+  character_dict_path: ./ppocr/utils/dict/korean_dict.txt
   loss_type: ctc
   distort: true
   use_space_char: false

deploy/lite/readme.md

@@ -221,11 +221,11 @@ demo/cxx/ocr/
 1. ppocr_keys_v1.txt是中文字典文件，如果使用的 nb 模型是英文数字或其他语言的模型，需要更换为对应语言的字典。
 PaddleOCR 在ppocr/utils/下存放了多种字典，包括：
 ```
-french_dict.txt     # 法语字典
-german_dict.txt     # 德语字典
+dict/french_dict.txt     # 法语字典
+dict/german_dict.txt     # 德语字典
 ic15_dict.txt       # 英文字典
-japan_dict.txt      # 日语字典
-korean_dict.txt     # 韩语字典
+dict/japan_dict.txt      # 日语字典
+dict/korean_dict.txt     # 韩语字典
 ppocr_keys_v1.txt   # 中文字典
 ```
 

deploy/lite/readme_en.md

@@ -185,11 +185,11 @@ demo/cxx/ocr/
 If the nb model is used for English recognition or other language recognition, dictionary file should be replaced with a dictionary of the corresponding language.
 PaddleOCR provides a variety of dictionaries under ppocr/utils/, including:
 ```
-french_dict.txt     # french
-german_dict.txt     # german
+dict/french_dict.txt     # french
+dict/german_dict.txt     # german
 ic15_dict.txt       # english
-japan_dict.txt      # japan
-korean_dict.txt     # korean
+dict/japan_dict.txt      # japan
+dict/korean_dict.txt     # korean
 ppocr_keys_v1.txt   # chinese
 ```
 

doc/doc_ch/inference.md

@@ -325,7 +325,7 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
 需要通过 `--vis_font_path` 指定可视化的字体路径，`doc/` 路径下有默认提供的小语种字体，例如韩文识别：
 
 ```
-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/korean_dict.txt" --vis_font_path="doc/korean.ttf"
+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/korean.ttf"
 ```
 ![](../imgs_words/korean/1.jpg)
 

doc/doc_ch/recognition.md

@@ -120,19 +120,19 @@ word_dict.txt 每行有一个单字，将字符与数字索引映射在一起，
 
 `ppocr/utils/ic15_dict.txt` 是一个包含36个字符的英文字典，
 
-`ppocr/utils/french_dict.txt` 是一个包含118个字符的法文字典
+`ppocr/utils/dict/french_dict.txt` 是一个包含118个字符的法文字典
 
-`ppocr/utils/japan_dict.txt` 是一个包含4399个字符的法文字典
+`ppocr/utils/dict/japan_dict.txt` 是一个包含4399个字符的法文字典
 
-`ppocr/utils/korean_dict.txt` 是一个包含3636个字符的法文字典
+`ppocr/utils/dict/korean_dict.txt` 是一个包含3636个字符的法文字典
 
-`ppocr/utils/german_dict.txt` 是一个包含131个字符的法文字典
+`ppocr/utils/dict/german_dict.txt` 是一个包含131个字符的法文字典
 
 
 您可以按需使用。
 
 目前的多语言模型仍处在demo阶段，会持续优化模型并补充语种，**非常欢迎您为我们提供其他语言的字典和字体**，
-如您愿意可将字典文件提交至 [utils](../../ppocr/utils) ，我们会在Repo中感谢您。
+如您愿意可将字典文件提交至 [dict](../../ppocr/utils/dict) 将语料文件提交至[corpus](../../ppocr/utils/corpus)，我们会在Repo中感谢您。
 
 - 自定义字典
 
@@ -269,7 +269,7 @@ PaddleOCR也提供了多语言的， `configs/rec/multi_languages` 路径下的
 Global:
   ...
   # 添加自定义字典，如修改字典请将路径指向新字典
-  character_dict_path: ./ppocr/utils/french_dict.txt
+  character_dict_path: ./ppocr/utils/dict/french_dict.txt
   # 训练时添加数据增强
   distort: true
   # 识别空格

doc/doc_en/inference_en.md

@@ -330,7 +330,7 @@ If you need to predict other language models, when using inference model predict
 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:
 
 ```
-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/korean_dict.txt" --vis_font_path="doc/korean.ttf"
+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/korean.ttf"
 ```
 ![](../imgs_words/korean/1.jpg)
 

doc/doc_en/recognition_en.md

@@ -112,18 +112,18 @@ In `word_dict.txt`, there is a single word in each line, which maps characters a
 
 `ppocr/utils/ic15_dict.txt` is an English dictionary with 63 characters
 
-`ppocr/utils/french_dict.txt` is a French dictionary with 118 characters
+`ppocr/utils/dict/french_dict.txt` is a French dictionary with 118 characters
 
-`ppocr/utils/japan_dict.txt` is a French dictionary with 4399 characters
+`ppocr/utils/dict/japan_dict.txt` is a French dictionary with 4399 characters
 
-`ppocr/utils/korean_dict.txt` is a French dictionary with 3636 characters
+`ppocr/utils/dict/korean_dict.txt` is a French dictionary with 3636 characters
 
-`ppocr/utils/german_dict.txt` is a French dictionary with 131 characters
+`ppocr/utils/dict/german_dict.txt` is a French dictionary with 131 characters
 
 You can use it on demand.
 
 The current multi-language model is still in the demo stage and will continue to optimize the model and add languages. **You are very welcome to provide us with dictionaries and fonts in other languages**,
-If you like, you can submit the dictionary file to [utils](../../ppocr/utils) and we will thank you in the Repo.
+If you like, you can submit the dictionary file to [dict](../../ppocr/utils/dict) or corpus file to [corpus](../../ppocr/utils/corpus) and we will thank you in the Repo.
 
 
 To customize the dict file, please modify the `character_dict_path` field in `configs/rec/rec_icdar15_train.yml` and set `character_type` to `ch`.
@@ -259,7 +259,7 @@ Global:
   ...
   # Add a custom dictionary, if you modify the dictionary
   # please point the path to the new dictionary
-  character_dict_path: ./ppocr/utils/french_dict.txt
+  character_dict_path: ./ppocr/utils/dict/french_dict.txt
   # Add data augmentation during training
   distort: true
   # Identify spaces

ppocr/utils/corpus/readme.md

@@ -0,0 +1,6 @@
+# Waiting for your contribution
+
+PaddleOCR welcomes you to provide multilingual corpus for us to synthesize more data to optimize the model.
+
+If you are interested, you can submit the corpus text to this directory and name it with {language}_corpus.txt.
+PaddleOCR thanks for your contribution.

ppocr/utils/corpus/readme_ch.md

@@ -0,0 +1,8 @@
+# 欢迎贡献语料
+
+PaddleOCR非常欢迎你提供多语言的语料，以供我们合成更多数据来优化模型。
+
+如你感兴趣，可将语料文本提交到此目录，并以 {语言}_corpus.txt 命名，PaddleOCR团队感谢你的贡献。
+
+
+