rm rec_char_type

Evezerest · Oct 12, 2021 · 380dc6c · 380dc6c
1 parent af0bac5
commit 380dc6c
Show file tree

Hide file tree

Showing 35 changed files with 161 additions and 168 deletions.
diff --git a/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml b/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml
@@ -14,7 +14,6 @@ Global:
  use_visualdl: false
  infer_img: doc/imgs_words/ch/word_1.jpg
  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
- character_type: ch
  max_text_length: 25
  infer_mode: false
  use_space_char: true

diff --git a/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml b/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml
@@ -14,7 +14,6 @@ Global:
  use_visualdl: false
  infer_img: doc/imgs_words/ch/word_1.jpg
  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
- character_type: ch
  max_text_length: 25
  infer_mode: false
  use_space_char: true

diff --git a/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_enhanced_ctc_loss.yml b/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_enhanced_ctc_loss.yml
@@ -14,7 +14,6 @@ Global:
  use_visualdl: false
  infer_img: doc/imgs_words/ch/word_1.jpg
  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
- character_type: ch
  max_text_length: 25
  infer_mode: false
  use_space_char: true

diff --git a/configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml b/configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml
@@ -15,7 +15,6 @@ Global:
  infer_img: doc/imgs_words/ch/word_1.jpg
  # for data or label process
  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
- character_type: ch
  max_text_length: 25
  infer_mode: False
  use_space_char: True

diff --git a/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml b/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml
@@ -15,7 +15,6 @@ Global:
  infer_img: doc/imgs_words/ch/word_1.jpg
  # for data or label process
  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
- character_type: ch
  max_text_length: 25
  infer_mode: False
  use_space_char: True

diff --git a/configs/rec/multi_language/rec_arabic_lite_train.yml b/configs/rec/multi_language/rec_arabic_lite_train.yml
@@ -15,7 +15,6 @@ Global:
  use_visualdl: false
  infer_img: null
  character_dict_path: ppocr/utils/dict/arabic_dict.txt
- character_type: arabic
  max_text_length: 25
  infer_mode: false
  use_space_char: true

diff --git a/configs/rec/multi_language/rec_cyrillic_lite_train.yml b/configs/rec/multi_language/rec_cyrillic_lite_train.yml
@@ -15,7 +15,6 @@ Global:
  use_visualdl: false
  infer_img: null
  character_dict_path: ppocr/utils/dict/cyrillic_dict.txt
- character_type: cyrillic
  max_text_length: 25
  infer_mode: false
  use_space_char: true

diff --git a/configs/rec/multi_language/rec_devanagari_lite_train.yml b/configs/rec/multi_language/rec_devanagari_lite_train.yml
@@ -15,7 +15,6 @@ Global:
  use_visualdl: false
  infer_img: null
  character_dict_path: ppocr/utils/dict/devanagari_dict.txt
- character_type: devanagari
  max_text_length: 25
  infer_mode: false
  use_space_char: true

diff --git a/configs/rec/multi_language/rec_en_number_lite_train.yml b/configs/rec/multi_language/rec_en_number_lite_train.yml
@@ -16,7 +16,6 @@ Global:
  infer_img:
  # for data or label process
  character_dict_path: ppocr/utils/en_dict.txt
- character_type: EN
  max_text_length: 25
  infer_mode: False
  use_space_char: True

diff --git a/configs/rec/multi_language/rec_french_lite_train.yml b/configs/rec/multi_language/rec_french_lite_train.yml
@@ -16,7 +16,6 @@ Global:
  infer_img:
  # for data or label process
  character_dict_path: ppocr/utils/dict/french_dict.txt
- character_type: french
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/multi_language/rec_german_lite_train.yml b/configs/rec/multi_language/rec_german_lite_train.yml
@@ -16,7 +16,6 @@ Global:
  infer_img:
  # for data or label process
  character_dict_path: ppocr/utils/dict/german_dict.txt
- character_type: german
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/multi_language/rec_japan_lite_train.yml b/configs/rec/multi_language/rec_japan_lite_train.yml
@@ -16,7 +16,6 @@ Global:
  infer_img:
  # for data or label process
  character_dict_path: ppocr/utils/dict/japan_dict.txt
- character_type: japan
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/multi_language/rec_korean_lite_train.yml b/configs/rec/multi_language/rec_korean_lite_train.yml
@@ -16,7 +16,6 @@ Global:
  infer_img:
  # for data or label process
  character_dict_path: ppocr/utils/dict/korean_dict.txt
- character_type: korean
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/multi_language/rec_latin_lite_train.yml b/configs/rec/multi_language/rec_latin_lite_train.yml
@@ -15,7 +15,6 @@ Global:
  use_visualdl: false
  infer_img: null
  character_dict_path: ppocr/utils/dict/latin_dict.txt
- character_type: latin
  max_text_length: 25
  infer_mode: false
  use_space_char: true

diff --git a/configs/rec/rec_icdar15_train.yml b/configs/rec/rec_icdar15_train.yml
@@ -15,7 +15,6 @@ Global:
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
  character_dict_path: ppocr/utils/en_dict.txt
- character_type: EN
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_mtb_nrtr.yml b/configs/rec/rec_mtb_nrtr.yml
@@ -14,8 +14,7 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
- character_dict_path: 
- character_type: EN_symbol
+ character_dict_path: ppocr/utils/EN_symbol_dict.txt
  max_text_length: 25
  infer_mode: False
  use_space_char: True

diff --git a/configs/rec/rec_mv3_none_bilstm_ctc.yml b/configs/rec/rec_mv3_none_bilstm_ctc.yml
@@ -14,8 +14,7 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
- character_dict_path: 
- character_type: en
+ character_dict_path:
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_mv3_none_none_ctc.yml b/configs/rec/rec_mv3_none_none_ctc.yml
@@ -15,7 +15,6 @@ Global:
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
  character_dict_path:
- character_type: en
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_mv3_tps_bilstm_att.yml b/configs/rec/rec_mv3_tps_bilstm_att.yml
@@ -14,8 +14,7 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words/ch/word_1.jpg
  # for data or label process
- character_dict_path: 
- character_type: en
+ character_dict_path:
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_mv3_tps_bilstm_ctc.yml b/configs/rec/rec_mv3_tps_bilstm_ctc.yml
@@ -15,7 +15,6 @@ Global:
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
  character_dict_path:
- character_type: en
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_r31_sar.yml b/configs/rec/rec_r31_sar.yml
@@ -15,7 +15,6 @@ Global:
  infer_img: 
  # for data or label process
  character_dict_path: ppocr/utils/dict90.txt
- character_type: EN_symbol
  max_text_length: 30
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_r34_vd_none_bilstm_ctc.yml b/configs/rec/rec_r34_vd_none_bilstm_ctc.yml
@@ -14,8 +14,7 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
- character_dict_path: 
- character_type: en
+ character_dict_path:
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_r34_vd_none_none_ctc.yml b/configs/rec/rec_r34_vd_none_none_ctc.yml
@@ -15,7 +15,6 @@ Global:
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
  character_dict_path:
- character_type: en
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_r34_vd_tps_bilstm_att.yml b/configs/rec/rec_r34_vd_tps_bilstm_att.yml
@@ -14,8 +14,7 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words/ch/word_1.jpg
  # for data or label process
- character_dict_path: 
- character_type: en
+ character_dict_path:
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_r34_vd_tps_bilstm_ctc.yml b/configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
@@ -14,8 +14,7 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
- character_dict_path: 
- character_type: en
+ character_dict_path:
  max_text_length: 25
  infer_mode: False
  use_space_char: False

diff --git a/configs/rec/rec_r50_fpn_srn.yml b/configs/rec/rec_r50_fpn_srn.yml
@@ -14,8 +14,7 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words/ch/word_1.jpg
  # for data or label process
- character_dict_path: 
- character_type: en
+ character_dict_path:
  max_text_length: 25
  num_heads: 8
  infer_mode: False

diff --git a/configs/rec/rec_resnet_stn_bilstm_att.yml b/configs/rec/rec_resnet_stn_bilstm_att.yml
@@ -14,8 +14,7 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
- character_dict_path: 
- character_type: EN_symbol
+ character_dict_path: ppocr/utils/EN_symbol_dict.txt
  max_text_length: 100
  infer_mode: False
  use_space_char: False

diff --git a/doc/doc_ch/inference.md b/doc/doc_ch/inference.md
@@ -273,7 +273,7 @@ python3 tools/export_model.py -c configs/rec/rec_r34_vd_none_bilstm_ctc.yml -o G
 CRNN 文本识别模型推理，可以执行如下命令：
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rec_crnn/" --rec_image_shape="3, 32, 100" --rec_char_type="en"
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rec_crnn/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
 ```
 
 ![](../imgs_words_en/word_336.png)
@@ -288,7 +288,7 @@ Predicts of ./doc/imgs_words_en/word_336.png:('super', 0.9999073)
 
 - 训练时采用的图像分辨率不同，训练上述模型采用的图像分辨率是[3，32，100]，而中文模型训练时，为了保证长文本的识别效果，训练时采用的图像分辨率是[3, 32, 320]。预测推理程序默认的的形状参数是训练中文采用的图像分辨率，即[3, 32, 320]。因此，这里推理上述英文模型时，需要通过参数rec_image_shape设置识别图像的形状。
 
-- 字符列表，DTRB论文中实验只是针对26个小写英文本母和10个数字进行实验，总共36个字符。所有大小字符都转成了小写字符，不在上面列表的字符都忽略，认为是空格。因此这里没有输入字符字典，而是通过如下命令生成字典.因此在推理时需要设置参数rec_char_type，指定为英文"en"。
+- 字符列表，DTRB论文中实验只是针对26个小写英文本母和10个数字进行实验，总共36个字符。所有大小字符都转成了小写字符，不在上面列表的字符都忽略，认为是空格。因此这里没有输入字符字典，而是通过如下命令生成字典.因此在推理时需要设置参数rec_char_dict_path，指定为英文字典"./ppocr/utils/ic15_dict.txt"。
 
 ```
 self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
@@ -303,15 +303,15 @@ dict_character = list(self.character_str)
 python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" \
  --rec_model_dir="./inference/srn/" \
  --rec_image_shape="1, 64, 256" \
- --rec_char_type="en" \
+ --rec_char_dict_path="./ppocr/utils/ic15_dict.txt" \
  --rec_algorithm="SRN"
 ```
 
 ### 4. 自定义文本识别字典的推理
-如果训练时修改了文本的字典，在使用inference模型预测时，需要通过`--rec_char_dict_path`指定使用的字典路径，并且设置 `rec_char_type=ch`
+如果训练时修改了文本的字典，在使用inference模型预测时，需要通过`--rec_char_dict_path`指定使用的字典路径
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./your inference model" --rec_image_shape="3, 32, 100" --rec_char_type="ch" --rec_char_dict_path="your text dict path"
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./your inference model" --rec_image_shape="3, 32, 100" --rec_char_dict_path="your text dict path"
 ```
 
 <a name="多语言模型的推理"></a>
@@ -320,7 +320,7 @@ 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/fonts/` 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/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf"
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf"
 ```
 ![](../imgs_words/korean/1.jpg)
 
@@ -388,7 +388,7 @@ python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --de
 下面给出基于EAST文本检测和STAR-Net文本识别执行命令：
 
 ```
-python3 tools/infer/predict_system.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_east/" --det_algorithm="EAST" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_type="en"
+python3 tools/infer/predict_system.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_east/" --det_algorithm="EAST" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
 ```
 
 执行命令后，识别结果图像如下：

diff --git a/doc/doc_en/inference_en.md b/doc/doc_en/inference_en.md
@@ -21,7 +21,7 @@ Next, we first introduce how to convert a trained model into an inference model,
  - [2.2 DB Text Detection Model Inference](#DB_DETECTION)
  - [2.3 East Text Detection Model Inference](#EAST_DETECTION)
  - [2.4 Sast Text Detection Model Inference](#SAST_DETECTION)
- 
+
 - [3. Text Recognition Model Inference](#RECOGNITION_MODEL_INFERENCE)
  - [3.1 Lightweight Chinese Text Recognition Model Reference](#LIGHTWEIGHT_RECOGNITION)
  - [3.2 CTC-Based Text Recognition Model Inference](#CTC-BASED_RECOGNITION)
@@ -281,7 +281,7 @@ python3 tools/export_model.py -c configs/det/rec_r34_vd_none_bilstm_ctc.yml -o G
 For CRNN text recognition model inference, execute the following commands:
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_type="en"
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
 ```
 
 ![](../imgs_words_en/word_336.png)
@@ -314,7 +314,7 @@ with the training, such as: --rec_image_shape="1, 64, 256"
 python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" \
  --rec_model_dir="./inference/srn/" \
  --rec_image_shape="1, 64, 256" \
- --rec_char_type="en" \
+ --rec_char_dict_path="./ppocr/utils/ic15_dict.txt" \
  --rec_algorithm="SRN"
 ```
 
@@ -323,7 +323,7 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
 If the text dictionary is modified during training, when using the inference model to predict, you need to specify the dictionary path used by `--rec_char_dict_path`, and set `rec_char_type=ch`
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./your inference model" --rec_image_shape="3, 32, 100" --rec_char_type="ch" --rec_char_dict_path="your text dict path"
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./your inference model" --rec_image_shape="3, 32, 100" --rec_char_dict_path="your text dict path"
 ```
 
 <a name="MULTILINGUAL_MODEL_INFERENCE"></a>
@@ -333,7 +333,7 @@ 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/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"
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf"
 ```
 ![](../imgs_words/korean/1.jpg)
 
@@ -399,7 +399,7 @@ If you want to try other detection algorithms or recognition algorithms, please
 The following command uses the combination of the EAST text detection and STAR-Net text recognition:
 
 ```
-python3 tools/infer/predict_system.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_east/" --det_algorithm="EAST" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_type="en"
+python3 tools/infer/predict_system.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_east/" --det_algorithm="EAST" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
 ```
 
 After executing the command, the recognition result image is as follows: