Merge remote-tracking branch 'origin/dygraph' into dygraph

PPOCRLabel/PPOCRLabel.py

@@ -1439,8 +1439,8 @@ class MainWindow(QMainWindow):
                                DEFAULT_LOCK_COLOR, key_cls, box['difficult']))
         if imgidx in self.PPlabel.keys():
             for box in self.PPlabel[imgidx]:
-                key_cls = None if not self.kie_mode else box['key_cls']
-                shapes.append((box['transcription'], box['points'], None, key_cls, box['difficult']))
+                key_cls = None if not self.kie_mode else box.get('key_cls', 'None')
+                shapes.append((box['transcription'], box['points'], None, key_cls, box.get('difficult', False)))
 
         self.loadLabels(shapes)
         self.canvas.verified = False
@@ -1492,7 +1492,7 @@ class MainWindow(QMainWindow):
             event.ignore()
         else:
             settings = self.settings
-            # If it loads images from dir, don't load it at the begining
+            # If it loads images from dir, don't load it at the beginning
             if self.dirname is None:
                 settings[SETTING_FILENAME] = self.filePath if self.filePath else ''
             else:
@@ -1584,7 +1584,7 @@ class MainWindow(QMainWindow):
         for image, info in label_dict.items():
             for box in info:
                 if "key_cls" not in box:
-                    continue
+                    box.update({"key_cls": "None"})
                 self.existed_key_cls_set.add(box["key_cls"])
         if len(self.existed_key_cls_set) > 0:
             for key_text in self.existed_key_cls_set:
@@ -1606,8 +1606,6 @@ class MainWindow(QMainWindow):
                 fit_to_content={'column': True, 'row': False},
                 flags=None
             )
-        else:
-            self.keyDialog.labelList.addItems(self.existed_key_cls_set)
 
     def importDirImages(self, dirpath, isDelete=False):
         if not self.mayContinue() or not dirpath:

PPOCRLabel/README.md

@@ -12,6 +12,7 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, w
   - Add KIE Mode by using `--kie`, for [detection + identification + keyword extraction] labeling.
 - 2022.01：（by [PeterH0323](https://github.com/peterh0323) ）
   - Improve user experience: prompt for the number of files and labels, optimize interaction, and fix bugs such as only use CPU when inference
+  - New functions: Support using `C` or `X` to rotate box.
 - 2021.11.17:
   - Support install and start PPOCRLabel through the whl package (by [d2623587501](https://github.com/d2623587501))
   - Dataset segmentation: Divide the annotation file into training, verification and testing parts (refer to section 3.5 below, by [MrCuiHao](https://github.com/MrCuiHao))

PPOCRLabel/README_ch.md

@@ -11,7 +11,8 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，内置P
 - 2022.02：（by [PeterH0323](https://github.com/peterh0323) ）
   - 新增：使用 `--kie` 进入 KIE 功能，用于打【检测+识别+关键字提取】的标签
 - 2022.01：（by [PeterH0323](https://github.com/peterh0323) ）
-  - 提升用户体验：新增文件与标记数目提示、优化交互、修复gpu使用等问题
+  - 提升用户体验：新增文件与标记数目提示、优化交互、修复gpu使用等问题。
+  - 新增功能：使用 `C` 和 `X` 对标记框进行旋转。
 - 2021.11.17：
   - 新增支持通过whl包安装和启动PPOCRLabel（by [d2623587501](https://github.com/d2623587501)）
   - 标注数据集切分：对标注数据进行训练、验证与测试集划分（参考下方3.5节，by [MrCuiHao](https://github.com/MrCuiHao)）

README.md

@@ -68,6 +68,8 @@ PaddleOCR support a variety of cutting-edge algorithms related to OCR, and devel
 
 | Model introduction                                           | Model name                   | Recommended scene | Detection model                                              | Direction classifier                                         | Recognition model                                            |
 | ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
+| Chinese and English ultra-lightweight PP-OCRv3 model（16.2M）     | ch_PP-OCRv3_xx          | Mobile & Server | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) |
+| English ultra-lightweight PP-OCRv3 model（13.4M）     | en_PP-OCRv3_xx          | Mobile & Server | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_distill_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) |
 | Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） |  ch_PP-OCRv2_xx |Mobile & Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
 | Chinese and English ultra-lightweight PP-OCR model (9.4M)       | ch_ppocr_mobile_v2.0_xx      | Mobile & server   |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar)      |
 | Chinese and English general PP-OCR model (143.4M)               | ch_ppocr_server_v2.0_xx      | Server            |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar)  |

README_ch.md

@@ -71,6 +71,8 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 
 | 模型简介                              | 模型名称                | 推荐场景        | 检测模型                                                     | 方向分类器                                                   | 识别模型                                                     |
 | ------------------------------------- | ----------------------- | --------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
+| 中英文超轻量PP-OCRv3模型（16.2M）     | ch_PP-OCRv3_xx          | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) |
+| 英文超轻量PP-OCRv3模型（13.4M）     | en_PP-OCRv3_xx          | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_distill_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) |
 | 中英文超轻量PP-OCRv2模型（13.0M）     | ch_PP-OCRv2_xx          | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) |
 | 中英文超轻量PP-OCR mobile模型（9.4M） | ch_ppocr_mobile_v2.0_xx | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) |
 | 中英文通用PP-OCR server模型（143.4M） | ch_ppocr_server_v2.0_xx | 服务器端        | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) |

applications/多模态表单识别.md

@@ -809,7 +809,7 @@ plt.imshow(img)
 ```
  fout.write(img_path + "\t" + json.dumps(
                 {
-                    "ser_resule": result,
+                    "ser_result": result,
                 }, ensure_ascii=False) + "\n")
 
 ```

configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_dml.yml

@@ -37,7 +37,7 @@ Architecture:
       Head:
         name: DBHead
         k: 50
-    Student2:
+    Teacher:
       pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
       freeze_params: false
       return_all_feats: false
@@ -62,15 +62,15 @@ Loss:
   loss_config_list:
   - DistillationDMLLoss:
       model_name_pairs:
-      - ["Student", "Student2"]
+      - ["Student", "Teacher"]
       maps_name: "thrink_maps"
       weight: 1.0
       act: "softmax"
-      model_name_pairs: ["Student", "Student2"]
+      model_name_pairs: ["Student", "Teacher"]
       key: maps
   - DistillationDBLoss:
       weight: 1.0
-      model_name_list: ["Student", "Student2"]
+      model_name_list: ["Student", "Teacher"]
       # key: maps
       name: DBLoss
       balance_loss: true
@@ -94,7 +94,7 @@ Optimizer:
 
 PostProcess:
   name: DistillationDBPostProcess
-  model_name: ["Student", "Student2"]
+  model_name: ["Student", "Teacher"]
   key: head_out
   thresh: 0.3
   box_thresh: 0.6

configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_dml.yml

+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  name: DistillationModel
+  algorithm: Distillation
+  model_type: det
+  Models:
+    Student:
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: ResNet
+        in_channels: 3
+        layers: 50
+      Neck:
+        name: LKPAN
+        out_channels: 256
+      Head:
+        name: DBHead
+        kernel_list: [7,2,2]
+        k: 50
+    Student2:
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: ResNet
+        in_channels: 3
+        layers: 50
+      Neck:
+        name: LKPAN
+        out_channels: 256
+      Head:
+        name: DBHead
+        kernel_list: [7,2,2]
+        k: 50
+
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - ["Student", "Student2"]
+      maps_name: "thrink_maps"
+      weight: 1.0
+      act: "softmax"
+      model_name_pairs: ["Student", "Student2"]
+      key: maps
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Student2"]
+      # key: maps
+      name: DBLoss
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DistillationDBPostProcess
+  model_name: ["Student", "Student2"]
+  key: head_out
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: DetMetric
+  main_indicator: hmean
+  key: "Student"
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - CopyPaste:
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/rec/ch_PP-OCRv3/ch_PP-OCRv3_rec.yml → configs/rec/PP-OCRv3/ch_PP-OCRv3_rec.yml

@@ -71,7 +71,7 @@ PostProcess:
 Metric:
   name: RecMetric
   main_indicator: acc
-  ignore_space: True
+  ignore_space: False
 
 Train:
   dataset:

configs/rec/ch_PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml → configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml

@@ -129,7 +129,7 @@ Loss:
       key: head_out
       multi_head: True
   - DistillationSARLoss:
-      weight: 1.0
+      weight: 0.5
       model_name_list: ["Student", "Teacher"]
       key: head_out
       multi_head: True
@@ -145,7 +145,7 @@ Metric:
   base_metric_name: RecMetric
   main_indicator: acc
   key: "Student"
-  ignore_space: True
+  ignore_space: False
 
 Train:
   dataset:

configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_en_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/en_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_en.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_arabic_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/arabic_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_arabic.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/chinese_cht_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_chinese_cht_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/chinese_cht_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_chinese_cht.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/cyrillic_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_cyrillic_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/cyrillic_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_cyrillic.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/devanagari_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_devanagari_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/devanagari_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_devanagari.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/japan_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_japan_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/japan_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_japan.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/ka_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_ka_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/ka_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_ka.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/korean_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_korean_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/korean_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_korean.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/latin_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_latin_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/latin_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_latin.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/ta_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_ta_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/ta_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_ta.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/te_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_te_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/te_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_te.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

deploy/Jetson/readme.md

+English | [简体中文](readme_ch.md)
+
+# Jetson Deployment for PaddleOCR
+
+This section introduces the deployment of PaddleOCR on Jetson NX, TX2, nano, AGX and other series of hardware.
+
+
+## 1. Prepare Environment
+
+You need to prepare a Jetson development hardware. If you need TensorRT, you need to prepare the TensorRT environment. It is recommended to use TensorRT version 7.1.3;
+
+1. Install PaddlePaddle in Jetson
+
+The PaddlePaddle download [link](https://www.paddlepaddle.org.cn/inference/user_guides/download_lib.html#python)
+Please select the appropriate installation package for your Jetpack version, cuda version, and trt version. Here, we download paddlepaddle_gpu-2.3.0rc0-cp36-cp36m-linux_aarch64.whl.
+
+Install PaddlePaddle：
+```shell
+pip3 install -U paddlepaddle_gpu-2.3.0rc0-cp36-cp36m-linux_aarch64.whl
+```
+
+
+2. Download PaddleOCR code and install dependencies
+
+Clone the PaddleOCR code:
+```
+git clone https://github.com/PaddlePaddle/PaddleOCR
+```
+
+and install dependencies：
+```
+cd PaddleOCR
+pip3 install -r requirements.txt
+```
+
+*Note: Jetson hardware CPU is poor, dependency installation is slow, please wait patiently*
+
+## 2. Perform prediction
+
+Obtain the PPOCR model from the [document](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_en/ppocr_introduction_en.md#6-model-zoo) model library. The following takes the PP-OCRv3 model as an example to introduce the use of the PPOCR model on Jetson:
+
+Download and unzip the PP-OCRv3 models.
+```
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+tar xf ch_PP-OCRv3_det_infer.tar
+tar xf ch_PP-OCRv3_rec_infer.tar
+```
+
+The text detection inference:
+```
+cd PaddleOCR
+python3 tools/infer/predict_det.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/  --image_dir=./doc/imgs/french_0.jpg  --use_gpu=True
+```
+
+After executing the command, the predicted information will be printed out in the terminal, and the visualization results will be saved in the `./inference_results/` directory.
+![](./images/det_res_french_0.jpg)
+
+
+The text recognition inference:
+```
+python3 tools/infer/predict_det.py --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/  --image_dir=./doc/imgs_words/en/word_2.png  --use_gpu=True --rec_image_shape="3,48,320"
+```
+
+After executing the command, the predicted information will be printed on the terminal, and the output is as follows:
+```
+[2022/04/28 15:41:45] root INFO: Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.98084533)
+```
+
+The text  detection and text recognition inference:
+
+```
+python3 tools/infer/predict_system.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/ --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/ --image_dir=./doc/imgs/00057937.jpg --use_gpu=True --rec_image_shape="3,48,320"
+```
+
+After executing the command, the predicted information will be printed out in the terminal, and the visualization results will be saved in the `./inference_results/` directory.
+![](./images/00057937.jpg)
+
+To enable TRT prediction, you only need to set `--use_tensorrt=True` on the basis of the above command:
+```
+python3 tools/infer/predict_system.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/ --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/ --image_dir=./doc/imgs/  --rec_image_shape="3,48,320" --use_gpu=True --use_tensorrt=True
+```
+
+For more ppocr model predictions, please refer to[document](../../doc/doc_en/models_list_en.md)

deploy/Jetson/readme_ch.md

+[English](readme.md) | 简体中文
+
+# Jetson部署PaddleOCR模型
+
+本节介绍PaddleOCR在Jetson NX、TX2、nano、AGX等系列硬件的部署。
+
+
+## 1. 环境准备
+
+需要准备一台Jetson开发板，如果需要TensorRT预测，需准备好TensorRT环境，建议使用7.1.3版本的TensorRT；
+
+1. Jetson安装PaddlePaddle
+
+PaddlePaddle下载[链接](https://www.paddlepaddle.org.cn/inference/user_guides/download_lib.html#python)
+请选择适合的您Jetpack版本、cuda版本、trt版本的安装包。
+
+安装命令：
+```shell
+# 安装paddle，以paddlepaddle_gpu-2.3.0rc0-cp36-cp36m-linux_aarch64.whl 为例
+pip3 install -U paddlepaddle_gpu-2.3.0rc0-cp36-cp36m-linux_aarch64.whl
+```
+
+
+2. 下载PaddleOCR代码并安装依赖
+
+首先 clone PaddleOCR 代码：
+```
+git clone https://github.com/PaddlePaddle/PaddleOCR
+```
+
+然后，安装依赖：
+```
+cd PaddleOCR
+pip3 install -r requirements.txt
+```
+
+*注：jetson硬件CPU较差，依赖安装较慢，请耐心等待*
+
+
+## 2. 执行预测
+
+从[文档](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/ppocr_introduction.md#6-%E6%A8%A1%E5%9E%8B%E5%BA%93) 模型库中获取PPOCR模型，下面以PP-OCRv3模型为例，介绍在PPOCR模型在jetson上的使用方式：
+
+下载并解压PP-OCRv3模型
+```
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+tar xf ch_PP-OCRv3_det_infer.tar
+tar xf ch_PP-OCRv3_rec_infer.tar
+```
+
+执行文本检测预测：
+```
+cd PaddleOCR
+python3 tools/infer/predict_det.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/  --image_dir=./doc/imgs/french_0.jpg  --use_gpu=True
+```
+
+执行命令后在终端会打印出预测的信息，并在 `./inference_results/` 下保存可视化结果。
+![](./images/det_res_french_0.jpg)
+
+
+执行文本识别预测：
+```
+python3 tools/infer/predict_det.py --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/  --image_dir=./doc/imgs_words/en/word_2.png  --use_gpu=True --rec_image_shape="3,48,320"
+```
+
+执行命令后在终端会打印出预测的信息，输出如下：
+```
+[2022/04/28 15:41:45] root INFO: Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.98084533)
+```
+
+执行文本检测+文本识别串联预测：
+
+```
+python3 tools/infer/predict_system.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/ --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/ --image_dir=./doc/imgs/ --use_gpu=True --rec_image_shape="3,48,320"
+```
+
+执行命令后在终端会打印出预测的信息，并在 `./inference_results/` 下保存可视化结果。
+![](./images/00057937.jpg)
+
+开启TRT预测只需要在以上命令基础上设置`--use_tensorrt=True`即可：
+```
+python3 tools/infer/predict_system.py --det_model_dir=./inference/ch_PP-OCRv2_det_infer/ --rec_model_dir=./inference/ch_PP-OCRv2_rec_infer/ --image_dir=./doc/imgs/00057937.jpg --use_gpu=True --use_tensorrt=True --rec_image_shape="3,48,320"
+```
+
+更多ppocr模型预测请参考[文档](../../doc/doc_ch/models_list.md)

deploy/README.md

@@ -23,10 +23,9 @@ PP-OCR has supported muti deployment schemes. Click the link to get the specific
 - [Python Inference](../doc/doc_en/inference_ppocr_en.md)
 - [C++ Inference](./cpp_infer/readme.md)
 - [Serving (Python/C++)](./pdserving/README.md)
-- [Paddle-Lite (ARM CPU/OpenCL ARM GPU/Metal ARM GPU)](./lite/readme.md)
+- [Paddle-Lite (ARM CPU/OpenCL ARM GPU)](./lite/readme.md)
 - [Paddle.js](./paddlejs/README.md)
-- [Jetson Inference]()
-- [XPU Inference]()
+- [Jetson Inference](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/deploy/Jetson/readme.md)
 - [Paddle2ONNX](./paddle2onnx/readme.md)
 
-If you need the deployment tutorial of academic algorithm models other than PP-OCR, please directly enter the main page of corresponding algorithms, [entrance](../doc/doc_en/algorithm_overview_en.md)。
\ No newline at end of file
+If you need the deployment tutorial of academic algorithm models other than PP-OCR, please directly enter the main page of corresponding algorithms, [entrance](../doc/doc_en/algorithm_overview_en.md)。

deploy/README_ch.md

@@ -23,10 +23,9 @@ PP-OCR模型已打通多种场景部署方案，点击链接获取具体的使
 - [Python 推理](../doc/doc_ch/inference_ppocr.md)
 - [C++ 推理](./cpp_infer/readme_ch.md)
 - [Serving 服务化部署（Python/C++）](./pdserving/README_CN.md)
-- [Paddle-Lite 端侧部署（ARM CPU/OpenCL ARM GPU/Metal ARM GPU）](./lite/readme_ch.md)
+- [Paddle-Lite 端侧部署（ARM CPU/OpenCL ARM GPU）](./lite/readme_ch.md)
 - [Paddle.js 部署](./paddlejs/README_ch.md)
-- [Jetson 推理]()
-- [XPU 推理]()
+- [Jetson 推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/deploy/Jetson/readme_ch.md)
 - [Paddle2ONNX 推理](./paddle2onnx/readme_ch.md)
 
 需要PP-OCR以外的学术算法模型的推理部署，请直接进入相应算法主页面，[入口](../doc/doc_ch/algorithm_overview.md)。
\ No newline at end of file

deploy/cpp_infer/readme.md

@@ -104,7 +104,7 @@ opencv3/
 tar -xf paddle_inference.tgz
 ```
 
-Finally you will see the the folder of `paddle_inference/` in the current path.
+Finally you will see the folder of `paddle_inference/` in the current path.
 
 #### 1.3.2 Compile the inference source code
 * If you want to get the latest Paddle inference library features, you can download the latest code from Paddle GitHub repository and compile the inference library from the source code. It is recommended to download the inference library with paddle version greater than or equal to 2.0.1.
@@ -208,6 +208,8 @@ Execute the built executable file:
 ./build/ppocr [--param1] [--param2] [...]
 ```
 
+**Note**:ppocr uses the `PP-OCRv3` model by default, and the input shape used by the recognition model is `3, 48, 320`, so if you use the recognition function, you need to add the parameter `--rec_img_h=48`, if you do not use the default `PP-OCRv3` model, you do not need to set this parameter.
+
 Specifically,
 
 ##### 1. det+cls+rec：
@@ -220,6 +222,7 @@ Specifically,
     --det=true \
     --rec=true \
     --cls=true \
+    --rec_img_h=48\
 ```
 
 ##### 2. det+rec：
@@ -231,6 +234,7 @@ Specifically,
     --det=true \
     --rec=true \
     --cls=false \
+    --rec_img_h=48\
 ```
 
 ##### 3. det
@@ -250,6 +254,7 @@ Specifically,
     --det=false \
     --rec=true \
     --cls=true \
+    --rec_img_h=48\
 ```
 
 ##### 5. rec
@@ -260,6 +265,7 @@ Specifically,
     --det=false \
     --rec=true \
     --cls=false \
+    --rec_img_h=48\
 ```
 
 ##### 6. cls
@@ -335,10 +341,10 @@ The detection results will be shown on the screen, which is as follows.
 ```bash
 predict img: ../../doc/imgs/12.jpg
 ../../doc/imgs/12.jpg
-0       det boxes: [[79,553],[399,541],[400,573],[80,585]] rec text: 打浦路252935号 rec score: 0.933757
-1       det boxes: [[31,509],[510,488],[511,529],[33,549]] rec text: 绿洲仕格维花园公寓 rec score: 0.951745
-2       det boxes: [[181,456],[395,448],[396,480],[182,488]] rec text: 打浦路15号 rec score: 0.91956
-3       det boxes: [[43,413],[480,391],[481,428],[45,450]] rec text: 上海斯格威铂尔多大酒店 rec score: 0.915914
+0       det boxes: [[74,553],[427,542],[428,571],[75,582]] rec text: 打浦路252935号 rec score: 0.947724
+1       det boxes: [[23,507],[513,488],[515,529],[24,548]] rec text: 绿洲仕格维花园公寓 rec score: 0.993728
+2       det boxes: [[187,456],[399,448],[400,480],[188,488]] rec text: 打浦路15号 rec score: 0.964994
+3       det boxes: [[42,413],[483,391],[484,428],[43,450]] rec text: 上海斯格威铂尔大酒店 rec score: 0.980086
 The detection visualized image saved in ./output//12.jpg
 ```
 

deploy/cpp_infer/readme_ch.md

@@ -12,7 +12,7 @@
     - [2.3 运行demo](#23)
 - [3. FAQ](#3)
 
-本章节介绍PaddleOCR 模型的的C++部署方法。C++在性能计算上优于Python，因此，在大多数CPU、GPU部署场景，多采用C++的部署方式，本节将介绍如何在Linux\Windows (CPU\GPU)环境下配置C++环境并完成PaddleOCR模型部署。
+本章节介绍PaddleOCR 模型的C++部署方法。C++在性能计算上优于Python，因此，在大多数CPU、GPU部署场景，多采用C++的部署方式，本节将介绍如何在Linux\Windows (CPU\GPU)环境下配置C++环境并完成PaddleOCR模型部署。
 
 
 <a name="1"></a>
@@ -213,6 +213,9 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
 
 本demo支持系统串联调用，也支持单个功能的调用，如，只使用检测或识别功能。
 
+**注意** ppocr默认使用`PP-OCRv3`模型，识别模型使用的输入shape为`3,48,320`, 因此如果使用识别功能，需要添加参数`--rec_img_h=48`，如果不使用默认的`PP-OCRv3`模型，则无需设置该参数。
+
+
 运行方式：  
 ```shell
 ./build/ppocr [--param1] [--param2] [...]
@@ -229,6 +232,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
     --det=true \
     --rec=true \
     --cls=true \
+    --rec_img_h=48\
 ```
 
 ##### 2. 检测+识别：
@@ -240,6 +244,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
     --det=true \
     --rec=true \
     --cls=false \
+    --rec_img_h=48\
 ```
 
 ##### 3. 检测：
@@ -259,6 +264,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
     --det=false \
     --rec=true \
     --cls=true \
+    --rec_img_h=48\
 ```
 
 ##### 5. 识别：
@@ -269,6 +275,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
     --det=false \
     --rec=true \
     --cls=false \
+    --rec_img_h=48\
 ```
 
 ##### 6. 分类：
@@ -343,10 +350,10 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
 ```bash
 predict img: ../../doc/imgs/12.jpg
 ../../doc/imgs/12.jpg
-0       det boxes: [[79,553],[399,541],[400,573],[80,585]] rec text: 打浦路252935号 rec score: 0.933757
-1       det boxes: [[31,509],[510,488],[511,529],[33,549]] rec text: 绿洲仕格维花园公寓 rec score: 0.951745
-2       det boxes: [[181,456],[395,448],[396,480],[182,488]] rec text: 打浦路15号 rec score: 0.91956
-3       det boxes: [[43,413],[480,391],[481,428],[45,450]] rec text: 上海斯格威铂尔多大酒店 rec score: 0.915914
+0       det boxes: [[74,553],[427,542],[428,571],[75,582]] rec text: 打浦路252935号 rec score: 0.947724
+1       det boxes: [[23,507],[513,488],[515,529],[24,548]] rec text: 绿洲仕格维花园公寓 rec score: 0.993728
+2       det boxes: [[187,456],[399,448],[400,480],[188,488]] rec text: 打浦路15号 rec score: 0.964994
+3       det boxes: [[42,413],[483,391],[484,428],[43,450]] rec text: 上海斯格威铂尔大酒店 rec score: 0.980086
 The detection visualized image saved in ./output//12.jpg
 ```
 

deploy/hubserving/ocr_det/params.py

@@ -26,7 +26,7 @@ def read_params():
 
     #params for text detector
     cfg.det_algorithm = "DB"
-    cfg.det_model_dir = "./inference/ch_PP-OCRv2_det_infer/"
+    cfg.det_model_dir = "./inference/ch_PP-OCRv3_det_infer/"
     cfg.det_limit_side_len = 960
     cfg.det_limit_type = 'max'
 

deploy/hubserving/ocr_rec/params.py

@@ -26,9 +26,9 @@ def read_params():
 
     #params for text recognizer
     cfg.rec_algorithm = "CRNN"
-    cfg.rec_model_dir = "./inference/ch_PP-OCRv2_rec_infer/"
+    cfg.rec_model_dir = "./inference/ch_PP-OCRv3_rec_infer/"
 
-    cfg.rec_image_shape = "3, 32, 320"
+    cfg.rec_image_shape = "3, 48, 320"
     cfg.rec_batch_num = 6
     cfg.max_text_length = 25
 

deploy/hubserving/ocr_system/params.py

@@ -26,7 +26,7 @@ def read_params():
 
     #params for text detector
     cfg.det_algorithm = "DB"
-    cfg.det_model_dir = "./inference/ch_PP-OCRv2_det_infer/"
+    cfg.det_model_dir = "./inference/ch_PP-OCRv3_det_infer/"
     cfg.det_limit_side_len = 960
     cfg.det_limit_type = 'max'
 
@@ -44,9 +44,9 @@ def read_params():
 
     #params for text recognizer
     cfg.rec_algorithm = "CRNN"
-    cfg.rec_model_dir = "./inference/ch_PP-OCRv2_rec_infer/"
+    cfg.rec_model_dir = "./inference/ch_PP-OCRv3_rec_infer/"
 
-    cfg.rec_image_shape = "3, 32, 320"
+    cfg.rec_image_shape = "3, 48, 320"
     cfg.rec_batch_num = 6
     cfg.max_text_length = 25
 

deploy/hubserving/readme.md

@@ -41,6 +41,7 @@ deploy/hubserving/ocr_system/
 ```
 ## 1. 近期更新
 
+* 2022.05.05 新增PP-OCRv3检测和识别模型。
 * 2022.03.30 新增PP-Structure和表格识别两种服务。
 
 ## 2. 快速启动服务
@@ -53,10 +54,10 @@ pip3 install paddlehub==2.1.0 --upgrade -i https://mirror.baidu.com/pypi/simple
 ```
 
 ### 2.2 下载推理模型
-安装服务模块前，需要准备推理模型并放到正确路径。默认使用的是PP-OCRv2模型，默认模型路径为：
+安装服务模块前，需要准备推理模型并放到正确路径。默认使用的是PP-OCRv3模型，默认模型路径为：
 ```
-检测模型：./inference/ch_PP-OCRv2_det_infer/
-识别模型：./inference/ch_PP-OCRv2_rec_infer/
+检测模型：./inference/ch_PP-OCRv3_det_infer/
+识别模型：./inference/ch_PP-OCRv3_rec_infer/
 方向分类器：./inference/ch_ppocr_mobile_v2.0_cls_infer/
 表格结构识别模型：./inference/en_ppocr_mobile_v2.0_table_structure_infer/
 ```  
@@ -223,6 +224,7 @@ hub serving start -c deploy/hubserving/ocr_system/config.json
 
 - 2、 到相应的`module.py`和`params.py`等文件中根据实际需求修改代码。  
 例如，如果需要替换部署服务所用模型，则需要到`params.py`中修改模型路径参数`det_model_dir`和`rec_model_dir`，如果需要关闭文本方向分类器，则将参数`use_angle_cls`置为`False`，当然，同时可能还需要修改其他相关参数，请根据实际情况修改调试。 **强烈建议修改后先直接运行`module.py`调试，能正确运行预测后再启动服务测试。**
+**注意** PPOCR-v3识别模型使用的图片输入shape为`3,48,320`,因此需要修改`params.py`中的`cfg.rec_image_shape = "3, 48, 320"`，如果不使用PPOCR-v3识别模型，则无需修改该参数。
 
 - 3、 卸载旧服务包  
 ```hub uninstall ocr_system```  

deploy/hubserving/readme_en.md

@@ -41,6 +41,7 @@ deploy/hubserving/ocr_system/
 ```
 ## 1. Update
 
+* 2022.05.05 add PP-OCRv3 text detection and recognition models.
 * 2022.03.30 add PP-Structure and table recognition services。
 
 
@@ -55,10 +56,10 @@ pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/sim
 ```
 
 ### 2.2 Download inference model
-Before installing the service module, you need to prepare the inference model and put it in the correct path. By default, the PP-OCRv2 models are used, and the default model path is:  
+Before installing the service module, you need to prepare the inference model and put it in the correct path. By default, the PP-OCRv3 models are used, and the default model path is:  
 ```
-text detection model: ./inference/ch_PP-OCRv2_det_infer/
-text recognition model: ./inference/ch_PP-OCRv2_rec_infer/
+text detection model: ./inference/ch_PP-OCRv3_det_infer/
+text recognition model: ./inference/ch_PP-OCRv3_rec_infer/
 text angle classifier: ./inference/ch_ppocr_mobile_v2.0_cls_infer/
 tanle recognition: ./inference/en_ppocr_mobile_v2.0_table_structure_infer/
 ```  
@@ -233,6 +234,7 @@ hub serving stop --port/-p XXXX
 ```
 - 2. Modify the code in the corresponding files, like `module.py` and `params.py`, according to the actual needs.  
 For example, if you need to replace the model used by the deployed service, you need to modify model path parameters `det_model_dir` and `rec_model_dir` in `params.py`. If you want to turn off the text direction classifier, set the parameter `use_angle_cls` to `False`. Of course, other related parameters may need to be modified at the same time. Please modify and debug according to the actual situation. It is suggested to run `module.py` directly for debugging after modification before starting the service test.  
+**Note** The image input shape used by the PPOCR-v3 recognition model is `3, 48, 320`, so you need to modify `cfg.rec_image_shape = "3, 48, 320"` in `params.py`, if you do not use the PPOCR-v3 recognition model, then there is no need to modify this parameter.
 - 3. Uninstall old service module
 ```shell
 hub uninstall ocr_system

deploy/lite/readme.md

-- [Tutorial of PaddleOCR Mobile deployment](#tutorial-of-paddleocr-mobile-deployment)
-  - [1. Preparation](#1-preparation)
+# Mobile deployment based on Paddle-Lite
+
+- [1. Preparation](#1-preparation)
     - [Preparation environment](#preparation-environment)
     - [1.1 Prepare the cross-compilation environment](#11-prepare-the-cross-compilation-environment)
     - [1.2 Prepare Paddle-Lite library](#12-prepare-paddle-lite-library)
-  - [2 Run](#2-run)
+- [2. Run](#2-run)
     - [2.1 Inference Model Optimization](#21-inference-model-optimization)
     - [2.2 Run optimized model on Phone](#22-run-optimized-model-on-phone)
-      - [注意：](#注意)
-  - [FAQ](#faq)
+- [FAQ](#faq)
 
-# Tutorial of PaddleOCR Mobile deployment
 
-This tutorial will introduce how to use [Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) to deploy PaddleOCR ultra-lightweight Chinese and English detection models on mobile phones.
+This tutorial will introduce how to use [Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite) to deploy PaddleOCR ultra-lightweight Chinese and English detection models on mobile phones.
 
-paddle-lite is a lightweight inference engine for PaddlePaddle. It provides efficient inference capabilities for mobile phones and IoT, and extensively integrates cross-platform hardware to provide lightweight deployment solutions for end-side deployment issues.
+Paddle-Lite is a lightweight inference engine for PaddlePaddle. It provides efficient inference capabilities for mobile phones and IoT, and extensively integrates cross-platform hardware to provide lightweight deployment solutions for end-side deployment issues.
 
 ## 1. Preparation
 
@@ -223,7 +222,7 @@ demo/cxx/ocr/
 |-- ocr_db_crnn.cc              C++ main code
 ```
 
-#### 注意：
+**Note**:
 1. `ppocr_keys_v1.txt` is a Chinese dictionary file. 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:
 ```
 dict/french_dict.txt     # french

deploy/lite/readme_ch.md

-- [端侧部署](#端侧部署)
-  - [1. 准备环境](#1-准备环境)
+# 端侧部署
+
+- [1. 准备环境](#1-准备环境)
     - [运行准备](#运行准备)
     - [1.1 准备交叉编译环境](#11-准备交叉编译环境)
     - [1.2 准备预测库](#12-准备预测库)
-  - [2 开始运行](#2-开始运行)
+- [2 开始运行](#2-开始运行)
     - [2.1 模型优化](#21-模型优化)
     - [2.2 与手机联调](#22-与手机联调)
-      - [注意：](#注意)
-  - [FAQ](#faq)
+- [FAQ](#faq)
   
-# 端侧部署
 
 本教程将介绍基于[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) 在移动端部署PaddleOCR超轻量中文检测、识别模型的详细步骤。
 

deploy/paddle2onnx/readme_ch.md

@@ -39,14 +39,14 @@ python3.7 -m pip install onnxruntime==1.9.0
 有两种方式获取Paddle静态图模型：在 [model_list](../../doc/doc_ch/models_list.md) 中下载PaddleOCR提供的预测模型；
 参考[模型导出说明](../../doc/doc_ch/inference.md#训练模型转inference模型)把训练好的权重转为 inference_model。
 
-以 ppocr 中文检测、识别、分类模型为例：
+以 PP-OCRv3 中文检测、识别、分类模型为例：
 
 ```
-wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
-cd ./inference && tar xf ch_PP-OCRv2_det_infer.tar && cd ..
+wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && cd ..
 
-wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar
-cd ./inference && tar xf ch_PP-OCRv2_rec_infer.tar && cd ..
+wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+cd ./inference && tar xf ch_PP-OCRv3_rec_infer.tar && cd ..
 
 wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
 cd ./inference && tar xf ch_ppocr_mobile_v2.0_cls_infer.tar && cd ..
@@ -57,7 +57,7 @@ cd ./inference && tar xf ch_ppocr_mobile_v2.0_cls_infer.tar && cd ..
 使用 Paddle2ONNX 将Paddle静态图模型转换为ONNX模型格式：
 
 ```
-paddle2onnx --model_dir ./inference/ch_PP-OCRv2_det_infer \
+paddle2onnx --model_dir ./inference/ch_PP-OCRv3_det_infer \
 --model_filename inference.pdmodel \
 --params_filename inference.pdiparams \
 --save_file ./inference/det_onnx/model.onnx \
@@ -65,7 +65,7 @@ paddle2onnx --model_dir ./inference/ch_PP-OCRv2_det_infer \
 --input_shape_dict="{'x':[-1,3,-1,-1]}" \
 --enable_onnx_checker True
 
-paddle2onnx --model_dir ./inference/ch_PP-OCRv2_rec_infer \
+paddle2onnx --model_dir ./inference/ch_PP-OCRv3_rec_infer \
 --model_filename inference.pdmodel \
 --params_filename inference.pdiparams \
 --save_file ./inference/rec_onnx/model.onnx \
@@ -105,8 +105,8 @@ python3.7 tools/infer/predict_system.py --use_gpu=False --use_onnx=True \
 ```
 python3.7 tools/infer/predict_system.py --use_gpu=False \
 --cls_model_dir=./inference/ch_ppocr_mobile_v2.0_cls_infer \
---rec_model_dir=./inference/ch_PP-OCRv2_rec_infer \
---det_model_dir=./inference/ch_PP-OCRv2_det_infer \
+--rec_model_dir=./inference/ch_PP-OCRv3_rec_infer \
+--det_model_dir=./inference/ch_PP-OCRv3_det_infer \
 --image_dir=./deploy/lite/imgs/lite_demo.png
 ```
 

deploy/pdserving/README.md

@@ -15,6 +15,14 @@ Some Key Features of Paddle Serving:
 - Industrial serving features supported, such as models management, online loading, online A/B testing etc.
 - Highly concurrent and efficient communication between clients and servers supported.
 
+PaddleServing supports deployment in multiple languages. In this example, two deployment methods, python pipeline and C++, are provided. The comparison between the two is as follows:
+
+| Language | Speed | Secondary development | Do you need to compile |
+|-----|-----|---------|------------|
+| C++ | fast | Slightly difficult | Single model prediction does not need to be compiled, multi-model concatenation needs to be compiled |
+| python | general | easy | single-model/multi-model no compilation required |
+
+
 The introduction and tutorial of Paddle Serving service deployment framework reference [document](https://github.com/PaddlePaddle/Serving/blob/develop/README.md).
 
 
@@ -25,6 +33,7 @@ The introduction and tutorial of Paddle Serving service deployment framework ref
   - [Environmental preparation](#environmental-preparation)
   - [Model conversion](#model-conversion)
   - [Paddle Serving pipeline deployment](#paddle-serving-pipeline-deployment)
+  - [Paddle Serving C++ deployment](#C++)
   - [WINDOWS Users](#windows-users)
   - [FAQ](#faq)
 
@@ -41,23 +50,23 @@ PaddleOCR operating environment and Paddle Serving operating environment are nee
 
 ```bash
 # Install serving which used to start the service
-wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.7.0.post102-py3-none-any.whl
-pip3 install paddle_serving_server_gpu-0.7.0.post102-py3-none-any.whl
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.3.post102-py3-none-any.whl
+pip3 install paddle_serving_server_gpu-0.8.3.post102-py3-none-any.whl
 
 # Install paddle-serving-server for cuda10.1
-# wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.7.0.post101-py3-none-any.whl
-# pip3 install paddle_serving_server_gpu-0.7.0.post101-py3-none-any.whl
+# wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.3.post101-py3-none-any.whl
+# pip3 install paddle_serving_server_gpu-0.8.3.post101-py3-none-any.whl
 
 # Install serving which used to start the service
-wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.7.0-cp37-none-any.whl
-pip3 install paddle_serving_client-0.7.0-cp37-none-any.whl
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.3-cp37-none-any.whl
+pip3 install paddle_serving_client-0.8.3-cp37-none-any.whl
 
 # Install serving-app
-wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.7.0-py3-none-any.whl
-pip3 install paddle_serving_app-0.7.0-py3-none-any.whl
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.8.3-py3-none-any.whl
+pip3 install paddle_serving_app-0.8.3-py3-none-any.whl
 ```
 
-   **note:** If you want to install the latest version of PaddleServing, refer to [link](https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Latest_Packages_CN.md).
+   **note:** If you want to install the latest version of PaddleServing, refer to [link](https://github.com/PaddlePaddle/Serving/blob/v0.8.3/doc/Latest_Packages_CN.md).
 
 
 <a name="model-conversion"></a>
@@ -67,37 +76,37 @@ When using PaddleServing for service deployment, you need to convert the saved i
 Firstly, download the [inference model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/README_ch.md#pp-ocr%E7%B3%BB%E5%88%97%E6%A8%A1%E5%9E%8B%E5%88%97%E8%A1%A8%E6%9B%B4%E6%96%B0%E4%B8%AD) of PPOCR
 ```
 # Download and unzip the OCR text detection model
-wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar -O ch_PP-OCRv2_det_infer.tar && tar -xf ch_PP-OCRv2_det_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar -O ch_PP-OCRv3_det_infer.tar && tar -xf ch_PP-OCRv3_det_infer.tar
 # Download and unzip the OCR text recognition model
-wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar -O ch_PP-OCRv2_rec_infer.tar &&  tar -xf ch_PP-OCRv2_rec_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar -O ch_PP-OCRv3_rec_infer.tar &&  tar -xf ch_PP-OCRv3_rec_infer.tar
 ```
 Then, you can use installed paddle_serving_client tool to convert inference model to mobile model.
 ```
 #  Detection model conversion
-python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_det_infer/ \
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv3_det_infer/ \
                                          --model_filename inference.pdmodel          \
                                          --params_filename inference.pdiparams       \
-                                         --serving_server ./ppocr_det_mobile_2.0_serving/ \
-                                         --serving_client ./ppocr_det_mobile_2.0_client/
+                                         --serving_server ./ppocr_det_v3_serving/ \
+                                         --serving_client ./ppocr_det_v3_client/
 
 #  Recognition model conversion
-python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_rec_infer/ \
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv3_rec_infer/ \
                                          --model_filename inference.pdmodel          \
                                          --params_filename inference.pdiparams       \
-                                         --serving_server ./ppocr_rec_mobile_2.0_serving/  \
-                                         --serving_client ./ppocr_rec_mobile_2.0_client/
+                                         --serving_server ./ppocr_rec_v3_serving/  \
+                                         --serving_client ./ppocr_rec_v3_client/
 
 ```
 
-After the detection model is converted, there will be additional folders of `ppocr_det_mobile_2.0_serving` and `ppocr_det_mobile_2.0_client` in the current folder, with the following format:
+After the detection model is converted, there will be additional folders of `ppocr_det_v3_serving` and `ppocr_det_v3_client` in the current folder, with the following format:
 ```
-|- ppocr_det_mobile_2.0_serving/
+|- ppocr_det_v3_serving/
   |- __model__  
   |- __params__
   |- serving_server_conf.prototxt  
   |- serving_server_conf.stream.prototxt
 
-|- ppocr_det_mobile_2.0_client
+|- ppocr_det_v3_client
   |- serving_client_conf.prototxt  
   |- serving_client_conf.stream.prototxt
 
@@ -193,16 +202,13 @@ The recognition model is the same.
     2021-05-13 03:42:36,979         chl2(In: ['rec'], Out: ['@DAGExecutor']) size[0/0]
     ```
 
+<a name="C++"></a>
 ## C++ Serving
 
 Service deployment based on python obviously has the advantage of convenient secondary development. However, the real application often needs to pursue better performance. PaddleServing also provides a more performant C++ deployment version.
 
 The C++ service deployment is the same as python in the environment setup and data preparation stages, the difference is when the service is started and the client sends requests.
 
-| Language | Speed ​​| Secondary development | Do you need to compile |
-|-----|-----|---------|------------|
-| C++ | fast | Slightly difficult | Single model prediction does not need to be compiled, multi-model concatenation needs to be compiled |
-| python | general | easy | single-model/multi-model no compilation required |
 
 1. Compile Serving
 
@@ -211,7 +217,7 @@ The C++ service deployment is the same as python in the environment setup and da
 2. Run the following command to start the service.
     ```
     # Start the service and save the running log in log.txt
-    python3 -m paddle_serving_server.serve --model ppocrv2_det_serving ppocrv2_rec_serving --op GeneralDetectionOp GeneralInferOp --port 9293 &>log.txt &
+    python3 -m paddle_serving_server.serve --model ppocr_det_v3_serving ppocr_rec_v3_serving --op GeneralDetectionOp GeneralInferOp --port 9293 &>log.txt &
     ```
     After the service is successfully started, a log similar to the following will be printed in log.txt
     ![](./imgs/start_server.png)
@@ -219,7 +225,7 @@ The C++ service deployment is the same as python in the environment setup and da
 3. Send service request
 
    Due to the need for pre and post-processing in the C++Server part, in order to speed up the input to the C++Server is only the base64 encoded string of the picture, it needs to be manually modified
-   Change the feed_type field and shape field in ppocrv2_det_client/serving_client_conf.prototxt to the following:
+   Change the feed_type field and shape field in ppocr_det_v3_client/serving_client_conf.prototxt to the following:
 
    ```
     feed_var {
@@ -234,7 +240,7 @@ The C++ service deployment is the same as python in the environment setup and da
    start the client:
 
     ```
-    python3 ocr_cpp_client.py ppocrv2_det_client ppocrv2_rec_client
+    python3 ocr_cpp_client.py ppocr_det_v3_client ppocr_rec_v3_client
     ```
     After successfully running, the predicted result of the model will be printed in the cmd window. An example of the result is:
     ![](./imgs/results.png)  

deploy/pdserving/README_CN.md

@@ -9,13 +9,21 @@ PaddleOCR提供2种服务部署方式：
 
 # 基于PaddleServing的服务部署
 
-本文档将介绍如何使用[PaddleServing](https://github.com/PaddlePaddle/Serving/blob/develop/README_CN.md)工具部署PP-OCR动态图模型的pipeline在线服务。
+本文档将介绍如何使用[PaddleServing](https://github.com/PaddlePaddle/Serving/blob/develop/README_CN.md) 工具部署PP-OCR动态图模型的pipeline在线服务。
 
 相比较于hubserving部署，PaddleServing具备以下优点：
 - 支持客户端和服务端之间高并发和高效通信
 - 支持 工业级的服务能力 例如模型管理，在线加载，在线A/B测试等
 - 支持 多种编程语言 开发客户端，例如C++, Python和Java
 
+PaddleServing 支持多种语言部署，本例中提供了python pipeline 和 C++ 两种部署方式，两者的对比如下：
+
+| 语言 | 速度 | 二次开发 | 是否需要编译 |
+|-----|-----|---------|------------|
+| C++ | 很快 | 略有难度 | 单模型预测无需编译，多模型串联需要编译 |
+| python | 一般 | 容易 | 单模型/多模型 均无需编译|
+
+
 更多有关PaddleServing服务化部署框架介绍和使用教程参考[文档](https://github.com/PaddlePaddle/Serving/blob/develop/README_CN.md)。
 
 AIStudio演示案例可参考 [基于PaddleServing的OCR服务化部署实战](https://aistudio.baidu.com/aistudio/projectdetail/3630726)。
@@ -24,6 +32,7 @@ AIStudio演示案例可参考 [基于PaddleServing的OCR服务化部署实战](h
 - [环境准备](#环境准备)
 - [模型转换](#模型转换)
 - [Paddle Serving pipeline部署](#部署)
+- [Paddle Serving C++部署](#C++)
 - [Windows用户](#Windows用户)
 - [FAQ](#FAQ)
 
@@ -34,26 +43,33 @@ AIStudio演示案例可参考 [基于PaddleServing的OCR服务化部署实战](h
 
 - 准备PaddleOCR的运行环境[链接](../../doc/doc_ch/installation.md)
 
+    ```
+    git clone https://github.com/PaddlePaddle/PaddleOCR
+
+    # 进入到工作目录
+    cd PaddleOCR/deploy/pdserving/
+    ```
+
 - 准备PaddleServing的运行环境，步骤如下
 
 ```bash
 # 安装serving，用于启动服务
-wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.7.0.post102-py3-none-any.whl
-pip3 install paddle_serving_server_gpu-0.7.0.post102-py3-none-any.whl
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.3.post102-py3-none-any.whl
+pip3 install paddle_serving_server_gpu-0.8.3.post102-py3-none-any.whl
 # 如果是cuda10.1环境，可以使用下面的命令安装paddle-serving-server
-# wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.7.0.post101-py3-none-any.whl
-# pip3 install paddle_serving_server_gpu-0.7.0.post101-py3-none-any.whl
+# wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.3.post101-py3-none-any.whl
+# pip3 install paddle_serving_server_gpu-0.8.3.post101-py3-none-any.whl
 
 # 安装client，用于向服务发送请求
-wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.7.0-cp37-none-any.whl
-pip3 install paddle_serving_client-0.7.0-cp37-none-any.whl
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.3-cp37-none-any.whl
+pip3 install paddle_serving_client-0.8.3-cp37-none-any.whl
 
 # 安装serving-app
-wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.7.0-py3-none-any.whl
-pip3 install paddle_serving_app-0.7.0-py3-none-any.whl
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.8.3-py3-none-any.whl
+pip3 install paddle_serving_app-0.8.3-py3-none-any.whl
 ```
 
-**Note:** 如果要安装最新版本的PaddleServing参考[链接](https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Latest_Packages_CN.md)。
+**Note:** 如果要安装最新版本的PaddleServing参考[链接](https://github.com/PaddlePaddle/Serving/blob/v0.8.3/doc/Latest_Packages_CN.md)。
 
 <a name="模型转换"></a>
 ## 模型转换
@@ -64,38 +80,38 @@ pip3 install paddle_serving_app-0.7.0-py3-none-any.whl
 
 ```bash
 # 下载并解压 OCR 文本检测模型
-wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar -O ch_PP-OCRv2_det_infer.tar && tar -xf ch_PP-OCRv2_det_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar -O ch_PP-OCRv3_det_infer.tar && tar -xf ch_PP-OCRv3_det_infer.tar
 # 下载并解压 OCR 文本识别模型
-wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar -O ch_PP-OCRv2_rec_infer.tar &&  tar -xf ch_PP-OCRv2_rec_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar -O ch_PP-OCRv3_rec_infer.tar &&  tar -xf ch_PP-OCRv3_rec_infer.tar
 ```
 
 接下来，用安装的paddle_serving_client把下载的inference模型转换成易于server部署的模型格式。
 
 ```bash
 # 转换检测模型
-python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_det_infer/ \
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv3_det_infer/ \
                                          --model_filename inference.pdmodel          \
                                          --params_filename inference.pdiparams       \
-                                         --serving_server ./ppocr_det_mobile_2.0_serving/ \
-                                         --serving_client ./ppocr_det_mobile_2.0_client/
+                                         --serving_server ./ppocr_det_v3_serving/ \
+                                         --serving_client ./ppocr_det_v3_client/
 
 # 转换识别模型
-python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_rec_infer/ \
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv3_rec_infer/ \
                                          --model_filename inference.pdmodel          \
                                          --params_filename inference.pdiparams       \
-                                         --serving_server ./ppocr_rec_mobile_2.0_serving/  \
-                                         --serving_client ./ppocr_rec_mobile_2.0_client/
+                                         --serving_server ./ppocr_rec_v3_serving/  \
+                                         --serving_client ./ppocr_rec_v3_client/
 ```
 
-检测模型转换完成后，会在当前文件夹多出`ppocr_det_mobile_2.0_serving` 和`ppocr_det_mobile_2.0_client`的文件夹，具备如下格式：
+检测模型转换完成后，会在当前文件夹多出`ppocr_det_v3_serving` 和`ppocr_det_v3_client`的文件夹，具备如下格式：
 ```
-|- ppocr_det_mobile_2.0_serving/
+|- ppocr_det_v3_serving/
   |- __model__  
   |- __params__
   |- serving_server_conf.prototxt  
   |- serving_server_conf.stream.prototxt
 
-|- ppocr_det_mobile_2.0_client
+|- ppocr_det_v3_client
   |- serving_client_conf.prototxt  
   |- serving_client_conf.stream.prototxt
 
@@ -105,13 +121,8 @@ python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_rec_infer/ \
 <a name="部署"></a>
 ## Paddle Serving pipeline部署
 
-1. 下载PaddleOCR代码，若已下载可跳过此步骤
-    ```
-    git clone https://github.com/PaddlePaddle/PaddleOCR
+1. 确认工作目录下文件结构：
 
-    # 进入到工作目录
-    cd PaddleOCR/deploy/pdserving/
-    ```
     pdserver目录包含启动pipeline服务和发送预测请求的代码，包括：
     ```
     __init__.py
@@ -196,16 +207,12 @@ python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_rec_infer/ \
 
 C++ 服务部署在环境搭建和数据准备阶段与 python 相同，区别在于启动服务和客户端发送请求时不同。
 
-| 语言 | 速度 | 二次开发 | 是否需要编译 |
-|-----|-----|---------|------------|
-| C++ | 很快 | 略有难度 | 单模型预测无需编译，多模型串联需要编译 |
-| python | 一般 ｜ 容易 | 单模型/多模型 均无需编译|
-
 1. 准备 Serving 环境
 
 为了提高预测性能，C++ 服务同样提供了多模型串联服务。与python pipeline服务不同，多模型串联的过程中需要将模型前后处理代码写在服务端，因此需要在本地重新编译生成serving。
 
 首先需要下载Serving代码库, 把OCR文本检测预处理相关代码替换到Serving库中
+
 ```
 git clone https://github.com/PaddlePaddle/Serving
 
@@ -223,7 +230,7 @@ cp -rf general_detection_op.cpp Serving/core/general-server/op
 
     ```
     # 启动服务，运行日志保存在log.txt
-    python3 -m paddle_serving_server.serve --model ppocrv2_det_serving ppocrv2_rec_serving --op GeneralDetectionOp GeneralInferOp --port 9293 &>log.txt &
+    python3 -m paddle_serving_server.serve --model ppocr_det_v3_serving ppocr_rec_v3_serving --op GeneralDetectionOp GeneralInferOp --port 9293 &>log.txt &
     ```
     成功启动服务后，log.txt中会打印类似如下日志
     ![](./imgs/start_server.png)
@@ -231,7 +238,7 @@ cp -rf general_detection_op.cpp Serving/core/general-server/op
 3. 发送服务请求：
 
    由于需要在C++Server部分进行前后处理，为了加速传入C++Server的仅仅是图片的base64编码的字符串，故需要手动修改
-   ppocrv2_det_client/serving_client_conf.prototxt 中 feed_type 字段 和 shape 字段，修改成如下内容：
+   ppocr_det_v3_client/serving_client_conf.prototxt 中 feed_type 字段 和 shape 字段，修改成如下内容：
    ```
     feed_var {
     name: "x"
@@ -243,7 +250,7 @@ cp -rf general_detection_op.cpp Serving/core/general-server/op
    ```
    启动客户端
    ```
-    python3 ocr_cpp_client.py ppocrv2_det_client ppocrv2_rec_client
+    python3 ocr_cpp_client.py ppocr_det_v3_client ppocr_rec_v3_client
    ```
 
     成功运行后，模型预测的结果会打印在cmd窗口中，结果示例为：

deploy/pdserving/config.yml

@@ -34,10 +34,10 @@ op:
             client_type: local_predictor
 
             #det模型路径
-            model_config: ./ppocr_det_mobile_2.0_serving
+            model_config: ./ppocr_det_v3_serving
 
             #Fetch结果列表，以client_config中fetch_var的alias_name为准
-            fetch_list: ["save_infer_model/scale_0.tmp_1"]
+            fetch_list: ["sigmoid_0.tmp_0"]
 
             #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
             devices: "0"
@@ -60,10 +60,10 @@ op:
             client_type: local_predictor
 
             #rec模型路径
-            model_config: ./ppocr_rec_mobile_2.0_serving
+            model_config: ./ppocr_rec_v3_serving
 
             #Fetch结果列表，以client_config中fetch_var的alias_name为准
-            fetch_list: ["save_infer_model/scale_0.tmp_1"]  
+            fetch_list: ["softmax_5.tmp_0"]
 
             #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
             devices: "0"

deploy/pdserving/ocr_reader.py

@@ -392,38 +392,8 @@ class OCRReader(object):
 
         return norm_img_batch[0]
 
-    def postprocess_old(self, outputs, with_score=False):
-        rec_res = []
-        rec_idx_lod = outputs["ctc_greedy_decoder_0.tmp_0.lod"]
-        rec_idx_batch = outputs["ctc_greedy_decoder_0.tmp_0"]
-        if with_score:
-            predict_lod = outputs["softmax_0.tmp_0.lod"]
-        for rno in range(len(rec_idx_lod) - 1):
-            beg = rec_idx_lod[rno]
-            end = rec_idx_lod[rno + 1]
-            if isinstance(rec_idx_batch, list):
-                rec_idx_tmp = [x[0] for x in rec_idx_batch[beg:end]]
-            else:  #nd array
-                rec_idx_tmp = rec_idx_batch[beg:end, 0]
-            preds_text = self.char_ops.decode(rec_idx_tmp)
-            if with_score:
-                beg = predict_lod[rno]
-                end = predict_lod[rno + 1]
-                if isinstance(outputs["softmax_0.tmp_0"], list):
-                    outputs["softmax_0.tmp_0"] = np.array(outputs[
-                        "softmax_0.tmp_0"]).astype(np.float32)
-                probs = outputs["softmax_0.tmp_0"][beg:end, :]
-                ind = np.argmax(probs, axis=1)
-                blank = probs.shape[1]
-                valid_ind = np.where(ind != (blank - 1))[0]
-                score = np.mean(probs[valid_ind, ind[valid_ind]])
-                rec_res.append([preds_text, score])
-            else:
-                rec_res.append([preds_text])
-        return rec_res
-
     def postprocess(self, outputs, with_score=False):
-        preds = outputs["save_infer_model/scale_0.tmp_1"]
+        preds = outputs["softmax_5.tmp_0"]
         try:
             preds = preds.numpy()
         except:

deploy/pdserving/web_service.py

@@ -56,7 +56,7 @@ class DetOp(Op):
         return {"x": det_img[np.newaxis, :].copy()}, False, None, ""
 
     def postprocess(self, input_dicts, fetch_dict, data_id, log_id):
-        det_out = fetch_dict["save_infer_model/scale_0.tmp_1"]
+        det_out = fetch_dict["sigmoid_0.tmp_0"]
         ratio_list = [
             float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w
         ]

deploy/pdserving/web_service_det.py

@@ -55,7 +55,7 @@ class DetOp(Op):
         return {"x": det_img[np.newaxis, :].copy()}, False, None, ""
 
     def postprocess(self, input_dicts, fetch_dict, data_id, log_id):
-        det_out = fetch_dict["save_infer_model/scale_0.tmp_1"]
+        det_out = fetch_dict["sigmoid_0.tmp_0"]
         ratio_list = [
             float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w
         ]

deploy/pdserving/win/ocr_reader.py

@@ -392,38 +392,8 @@ class OCRReader(object):
 
         return norm_img_batch[0]
 
-    def postprocess_old(self, outputs, with_score=False):
-        rec_res = []
-        rec_idx_lod = outputs["ctc_greedy_decoder_0.tmp_0.lod"]
-        rec_idx_batch = outputs["ctc_greedy_decoder_0.tmp_0"]
-        if with_score:
-            predict_lod = outputs["softmax_0.tmp_0.lod"]
-        for rno in range(len(rec_idx_lod) - 1):
-            beg = rec_idx_lod[rno]
-            end = rec_idx_lod[rno + 1]
-            if isinstance(rec_idx_batch, list):
-                rec_idx_tmp = [x[0] for x in rec_idx_batch[beg:end]]
-            else:  #nd array
-                rec_idx_tmp = rec_idx_batch[beg:end, 0]
-            preds_text = self.char_ops.decode(rec_idx_tmp)
-            if with_score:
-                beg = predict_lod[rno]
-                end = predict_lod[rno + 1]
-                if isinstance(outputs["softmax_0.tmp_0"], list):
-                    outputs["softmax_0.tmp_0"] = np.array(outputs[
-                        "softmax_0.tmp_0"]).astype(np.float32)
-                probs = outputs["softmax_0.tmp_0"][beg:end, :]
-                ind = np.argmax(probs, axis=1)
-                blank = probs.shape[1]
-                valid_ind = np.where(ind != (blank - 1))[0]
-                score = np.mean(probs[valid_ind, ind[valid_ind]])
-                rec_res.append([preds_text, score])
-            else:
-                rec_res.append([preds_text])
-        return rec_res
-
     def postprocess(self, outputs, with_score=False):
-        preds = outputs["save_infer_model/scale_0.tmp_1"]
+        preds = outputs["softmax_5.tmp_0"]
         try:
             preds = preds.numpy()
         except:

deploy/slim/prune/README_en.md

 
 # PP-OCR Models Pruning
 
-Generally, a more complex model would achive better performance in the task, but it also leads to some redundancy in the model. Model Pruning is a technique that reduces this redundancy by removing the sub-models in the neural network model, so as to reduce model calculation complexity and improve model inference performance.
+Generally, a more complex model would achieve better performance in the task, but it also leads to some redundancy in the model. Model Pruning is a technique that reduces this redundancy by removing the sub-models in the neural network model, so as to reduce model calculation complexity and improve model inference performance.
 
 This example uses PaddleSlim provided[APIs of Pruning](https://github.com/PaddlePaddle/PaddleSlim/tree/develop/docs/zh_cn/api_cn/dygraph/pruners) to compress the OCR model.
 [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), an open source library which integrates model pruning, quantization (including quantization training and offline quantization), distillation, neural network architecture search, and many other commonly used and leading model compression technique in the industry.

deploy/slim/prune/sensitivity_anal.py

@@ -94,7 +94,7 @@ def main(config, device, logger, vdl_writer):
         config['Optimizer'],
         epochs=config['Global']['epoch_num'],
         step_each_epoch=len(train_dataloader),
-        parameters=model.parameters())
+        model=model)
 
     # build metric
     eval_class = build_metric(config['Metric'])

deploy/slim/quantization/README.md

@@ -22,9 +22,7 @@
 ### 1. 安装PaddleSlim
 
 ```bash
-git clone https://github.com/PaddlePaddle/PaddleSlim.git
-cd PaddleSlim
-python setup.py install
+pip3 install paddleslim==2.2.2
 ```
 
 ### 2. 准备训练好的模型
@@ -43,7 +41,15 @@ python deploy/slim/quantization/quant.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3
 wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar
 tar -xf ch_ppocr_mobile_v2.0_det_train.tar
 python deploy/slim/quantization/quant.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o Global.pretrained_model=./ch_ppocr_mobile_v2.0_det_train/best_accuracy   Global.save_model_dir=./output/quant_model
+```
+
+模型蒸馏和模型量化可以同时使用，以PPOCRv3检测模型为例：
+```
+# 下载检测预训练模型：
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar
+tar xf https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar
 
+python deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv3_det/ch_PP-OCRv3_det_cml.yml -o Global.pretrained_model='./ch_PP-OCRv3_det_distill_train/best_accuracy'   Global.save_model_dir=./output/quant_model_distill/
 ```
 如果要训练识别模型的量化，修改配置文件和加载的模型参数即可。
 

deploy/slim/quantization/README_en.md

@@ -25,9 +25,7 @@ After training, if you want to further compress the model size and accelerate th
 ### 1. Install PaddleSlim
 
 ```bash
-git clone https://github.com/PaddlePaddle/PaddleSlim.git
-cd PaddlSlim
-python setup.py install
+pip3 install paddleslim==2.2.2
 ```
 
 
@@ -52,6 +50,17 @@ python deploy/slim/quantization/quant.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3
 ```
 
 
+Model distillation and model quantization can be used at the same time, taking the PPOCRv3 detection model as an example:
+```
+# download provided model
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar
+tar xf https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar
+
+python deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv3_det/ch_PP-OCRv3_det_cml.yml -o Global.pretrained_model='./ch_PP-OCRv3_det_distill_train/best_accuracy'   Global.save_model_dir=./output/quant_model_distill/
+```
+
+If you want to quantify the text recognition model, you can modify the configuration file and loaded model parameters.
+
 ### 4. Export inference model
 
 Once we got the model after pruning and fine-tuning, we can export it as an inference model for the deployment of predictive tasks:

deploy/slim/quantization/export_model.py

@@ -17,9 +17,9 @@ import sys
 
 __dir__ = os.path.dirname(os.path.abspath(__file__))
 sys.path.append(__dir__)
-sys.path.append(os.path.abspath(os.path.join(__dir__, '..', '..', '..')))
-sys.path.append(
-    os.path.abspath(os.path.join(__dir__, '..', '..', '..', 'tools')))
+sys.path.insert(0, os.path.abspath(os.path.join(__dir__, '..', '..', '..')))
+sys.path.insert(
+    0, os.path.abspath(os.path.join(__dir__, '..', '..', '..', 'tools')))
 
 import argparse
 
@@ -129,7 +129,6 @@ def main():
     quanter.quantize(model)
 
     load_model(config, model)
-    model.eval()
 
     # build metric
     eval_class = build_metric(config['Metric'])
@@ -142,6 +141,7 @@ def main():
     # start eval
     metric = program.eval(model, valid_dataloader, post_process_class,
                           eval_class, model_type, use_srn)
+    model.eval()
 
     logger.info('metric eval ***************')
     for k, v in metric.items():
@@ -156,7 +156,6 @@ def main():
     if arch_config["algorithm"] in ["Distillation", ]:  # distillation model
         archs = list(arch_config["Models"].values())
         for idx, name in enumerate(model.model_name_list):
-            model.model_list[idx].eval()
             sub_model_save_path = os.path.join(save_path, name, "inference")
             export_single_model(model.model_list[idx], archs[idx],
                                 sub_model_save_path, logger, quanter)

deploy/slim/quantization/quant.py

@@ -161,7 +161,13 @@ def main(config, device, logger, vdl_writer):
     if config["Global"]["pretrained_model"] is not None:
         pre_best_model_dict = load_model(config, model)
 
-    quanter = QAT(config=quant_config, act_preprocess=PACT)
+    freeze_params = False
+    if config['Architecture']["algorithm"] in ["Distillation"]:
+        for key in config['Architecture']["Models"]:
+            freeze_params = freeze_params or config['Architecture']['Models'][
+                key].get('freeze_params', False)
+    act = None if freeze_params else PACT
+    quanter = QAT(config=quant_config, act_preprocess=act)
     quanter.quantize(model)
 
     if config['Global']['distributed']:

doc/doc_ch/FAQ.md

@@ -114,7 +114,7 @@ A: PGNet不需要字符级别的标注，NMS操作以及ROI操作。同时提出
 （3）端到端统计：
 端对端召回率：准确检测并正确识别文本行在全部标注文本行的占比；
 端到端准确率：准确检测并正确识别文本行在 检测到的文本行数量 的占比；
-准确检测的标准是检测框与标注框的IOU大于某个阈值，正确识别的的检测框中的文本与标注的文本相同。
+准确检测的标准是检测框与标注框的IOU大于某个阈值，正确识别的检测框中的文本与标注的文本相同。
 
 <a name="15"></a>
 

doc/doc_ch/PP-OCRv3_introduction.md

+[English](../doc_en/PP-OCRv3_introduction_en.md) | 简体中文
+
+# PP-OCRv3
+
+- [1. 简介](#1)
+- [2. 检测优化](#2)
+- [3. 识别优化](#3)
+- [4. 端到端评估](#4)
+
+
+
+<a name="1"></a>
+## 1. 简介
+
+PP-OCRv3在PP-OCRv2的基础上进一步升级。检测模型仍然基于DB算法，优化策略采用了带残差注意力机制的FPN结构RSEFPN、增大感受野的PAN结构LKPAN、基于DML训练的更优的教师模型；识别模型将base模型从CRNN替换成了IJCAI 2022论文[SVTR]()，并采用SVTR轻量化、带指导训练CTC、数据增广策略RecConAug、自监督训练的更好的预训练模型、无标签数据的使用进行模型加速和效果提升。更多细节请参考PP-OCRv3[技术报告](./PP-OCRv3_introduction.md)。
+
+PP-OCRv3系统pipeline如下：
+
+<div align="center">
+    <img src="../ppocrv3_framework.png" width="800">
+</div>
+
+<a name="2"></a>
+## 2. 检测优化
+
+PP-OCRv3采用PP-OCRv2的[CML](https://arxiv.org/pdf/2109.03144.pdf)蒸馏策略，在蒸馏的student模型、teacher模型精度提升，CML蒸馏策略上分别做了优化。
+
+- 在蒸馏student模型精度提升方面，提出了基于残差结构的通道注意力模块RSEFPN（Residual Squeeze-and-Excitation FPN），用于提升student模型精度和召回。
+
+RSEFPN的网络结构如下图所示，RSEFPN在PP-OCRv2的FPN基础上，将FPN中的卷积层更换为了通道注意力结构的RSEConv层。
+
+<div align="center">
+    <img src=".././ppocr_v3/RSEFPN.png" width="800">
+</div>
+
+RSEFPN将PP-OCR检测模型的精度hmean从81.3%提升到84.5%。模型大小从3M变为3.6M。
+
+*注：PP-OCRv2的FPN通道数仅为96和24，如果直接用SE模块代替FPN的卷积会导致精度下降，RSEConv引入残差结构可以防止训练中包含重要特征的通道被抑制。*
+
+- 在蒸馏的teacher模型精度提升方面，提出了LKPAN结构替换PP-OCRv2的FPN结构，并且使用ResNet50作为Backbone，更大的模型带来更多的精度提升。另外，对teacher模型使用[DML](https://arxiv.org/abs/1706.00384)蒸馏策略进一步提升teacher模型的精度。最终teacher的模型指标相比ppocr_server_v2.0从83.2%提升到了86.0%。
+
+*注：[PP-OCRv2的FPN结构](https://github.com/PaddlePaddle/PaddleOCR/blob/77acb3bfe51c8a46c684527f73cd218cefedb4a3/ppocr/modeling/necks/db_fpn.py#L107)对DB算法FPN结构做了轻量级设计*
+
+LKPAN的网络结构如下图所示：
+
+<div align="center">
+    <img src="../ppocr_v3/LKPAN.png" width="800">
+</div>
+
+LKPAN(Large Kernel PAN)是一个具有更大感受野的轻量级[PAN](https://arxiv.org/pdf/1803.01534.pdf)结构。在LKPAN的path augmentation中，使用kernel size为`9*9`的卷积；更大的kernel size意味着更大的感受野，更容易检测大字体的文字以及极端长宽比的文字。LKPAN将PP-OCR检测模型的精度hmean从81.3%提升到84.9%。
+
+*注：LKPAN相比RSEFPN有更多的精度提升，但是考虑到模型大小和预测速度等因素，在student模型中使用RSEFPN。*
+
+采用上述策略，PP-OCRv3相比PP-OCRv2，hmean指标从83.3%提升到85.4%；预测速度从平均117ms/image变为124ms/image。
+
+3. PP-OCRv3检测模型消融实验
+
+|序号|策略|模型大小|hmean|Intel Gold 6148CPU+mkldnn预测耗时|
+|-|-|-|-|-|
+|0|PP-OCR|3M|81.3%|117ms|
+|1|PP-OCRV2|3M|83.3%|117ms|
+|2|0 + RESFPN|3.6M|84.5%|124ms|
+|3|0 + LKPAN|4.6M|84.9%|156ms|
+|4|ppocr_server_v2.0 |124M|83.2%||171ms|
+|5|teacher + DML + LKPAN|124M|86.0%|396ms|
+|6|0 + 2 + 5 + CML|3.6M|85.4%|124ms|
+
+
+
+<a name="3"></a>
+## 3. 识别优化
+
+[SVTR](https://arxiv.org/abs/2205.00159) 证明了强大的单视觉模型（无需序列模型）即可高效准确完成文本识别任务，在中英文数据上均有优秀的表现。经过实验验证，SVTR_Tiny在自建的 [中文数据集上](https://arxiv.org/abs/2109.03144) ，识别精度可以提升10.7%，网络结构如下所示：
+
+<img src="../ppocr_v3/svtr_tiny.jpg" width=800>
+
+由于 MKLDNN 加速库支持的模型结构有限，SVTR 在CPU+MKLDNN上相比PP-OCRv2慢了10倍。
+
+PP-OCRv3 期望在提升模型精度的同时，不带来额外的推理耗时。通过分析发现，SVTR_Tiny结构的主要耗时模块为Mixing Block，因此我们对 SVTR_Tiny 的结构进行了一系列优化（详细速度数据请参考下方消融实验表格）:
+
+1. 将SVTR网络前半部分替换为PP-LCNet的前三个stage，保留4个 Global Mixing Block ，精度为76%，加速69%，网络结构如下所示：
+<img src="../ppocr_v3/svtr_g4.png" width=800>
+2. 将4个 Global Attenntion Block 减小到2个，精度为72.9%，加速69%，网络结构如下所示：
+<img src="../ppocr_v3/svtr_g2.png" width=800>
+3. 实验发现 Global Attention 的预测速度与输入其特征的shape有关，因此后移Global Mixing Block的位置到池化层之后，精度下降为71.9%，速度超越 CNN-base 的PP-OCRv2 22%，网络结构如下所示：
+<img src="../ppocr_v3/ppocr_v3.png" width=800>
+
+为了提升模型精度同时不引入额外推理成本，PP-OCRv3参考GTC策略，使用Attention监督CTC训练，预测时完全去除Attention模块，在推理阶段不增加任何耗时, 精度提升3.8%，训练流程如下所示：
+<img src="../ppocr_v3/GTC.png" width=800>
+
+在训练策略方面，PP-OCRv3参考 [SSL](https://github.com/ku21fan/STR-Fewer-Labels) 设计了文本方向任务，训练了适用于文本识别的预训练模型，加速模型收敛过程，精度提升了0.6%; 使用UDML蒸馏策略，进一步提升精度1.5%，训练流程所示：
+
+<img src="../ppocr_v3/SSL.png" width="300"> <img src="../ppocr_v3/UDML.png" width="500">
+
+
+数据增强方面：
+
+1. 基于 [ConCLR](https://www.cse.cuhk.edu.hk/~byu/papers/C139-AAAI2022-ConCLR.pdf) 中的ConAug方法，设计了 RecConAug 数据增强方法，增强数据多样性，精度提升0.5%，增强可视化效果如下所示：
+<img src="../ppocr_v3/recconaug.png" width=800>
+
+2. 使用训练好的 SVTR_large 预测 120W 的 lsvt 无标注数据，取出其中得分大于0.95的数据，共得到81W识别数据加入到PP-OCRv3的训练数据中，精度提升1%。
+
+总体来讲PP-OCRv3识别从网络结构、训练策略、数据增强三个方向做了进一步优化:
+
+- 网络结构上：考虑[SVTR](https://arxiv.org/abs/2205.00159) 在中英文效果上的优越性，采用SVTR_Tiny作为base，选取Global Mixing Block和卷积组合提取特征，并将Global Mixing Block位置后移进行加速; 参考 [GTC](https://arxiv.org/pdf/2002.01276.pdf) 策略，使用注意力机制模块指导CTC训练，定位和识别字符，提升不规则文本的识别精度。
+- 训练策略上：参考 [SSL](https://github.com/ku21fan/STR-Fewer-Labels) 设计了方向分类前序任务，获取更优预训练模型，加速模型收敛过程，提升精度; 使用UDML蒸馏策略、监督attention、ctc两个分支得到更优模型。
+- 数据增强上：基于 [ConCLR](https://www.cse.cuhk.edu.hk/~byu/papers/C139-AAAI2022-ConCLR.pdf) 中的ConAug方法，改进得到 RecConAug 数据增广方法，支持随机结合任意多张图片，提升训练数据的上下文信息丰富度，增强模型鲁棒性；使用 SVTR_large 预测无标签数据，向训练集中补充81w高质量真实数据。
+
+基于上述策略，PP-OCRv3识别模型相比PP-OCRv2，在速度可比的情况下，精度进一步提升4.5%。 具体消融实验如下所示：
+
+实验细节：
+
+| id | 策略 |  模型大小 | 精度 | 速度（cpu + mkldnn)|
+|-----|-----|--------|----| --- |
+| 01 | PP-OCRv2 | 8M | 69.3% | 8.54ms |
+| 02 | SVTR_Tiny | 21M | 80.1% | 97ms |
+| 03 | LCNet_SVTR_G4 | 9.2M | 76% | 30ms |
+| 04 | LCNet_SVTR_G2 | 13M | 72.98% | 9.37ms |
+| 05 | PP-OCRv3 | 12M | 71.9% | 6.6ms |
+| 06 | + large input_shape | 12M | 73.98% | 7.6ms |
+| 06 | + GTC | 12M | 75.8% | 7.6ms |
+| 07 | + RecConAug | 12M | 76.3% | 7.6ms |
+| 08 | + SSL pretrain | 12M | 76.9% | 7.6ms |
+| 09 | + UDML | 12M | 78.4% | 7.6ms |
+| 10 | + unlabeled data | 12M | 79.4% | 7.6ms |
+
+注： 测试速度时，实验01-05输入图片尺寸均为(3,32,320)，06-10输入图片尺寸均为(3,48,320)
+
+<a name="4"></a>
+## 4. 端到端评估

doc/doc_ch/add_new_algorithm.md

@@ -246,7 +246,7 @@ class MyMetric(object):
 
     def get_metric(self):
         """
-        return metircs {
+        return metrics {
                  'acc': 0,
                  'norm_edit_dis': 0,
             }

doc/doc_ch/algorithm_det_east.md

+# EAST
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [EAST: An Efficient and Accurate Scene Text Detector](https://arxiv.org/abs/1704.03155)
+> Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, Jiajun Liang
+> CVPR, 2017
+
+
+在ICDAR2015文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|EAST|ResNet50_vd|88.71%|    81.36%|    84.88%|    [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)|
+|EAST|    MobileNetV3| 78.2%|    79.1%|    78.65%|    [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)|
+
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+上表中的EAST训练模型使用ICDAR2015文本检测公开数据集训练得到，数据集下载可参考 [ocr_datasets](./dataset/ocr_datasets.md)。
+
+数据下载完成后，请参考[文本检测训练教程](./detection.md)进行训练。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+
+首先将EAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例（[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar))，可以使用如下命令进行转换：
+
+```shell
+python3 tools/export_model.py -c configs/det/det_r50_vd_east.yml -o Global.pretrained_model=./det_r50_vd_east_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_r50_east/
+```
+
+EAST文本检测模型推理，需要设置参数--det_algorithm="EAST"，执行预测：
+```shell
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_r50_east/" --det_algorithm="EAST"
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。
+
+![](../imgs_results/det_res_img_10_east.jpg)
+
+<a name="4-2"></a>
+### 4.2 C++推理
+
+由于后处理暂未使用CPP编写，EAST文本检测模型暂不支持CPP推理。
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+暂未支持
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+暂未支持
+
+<a name="5"></a>
+## 5. FAQ
+
+
+## 引用
+
+```bibtex
+@inproceedings{zhou2017east,
+  title={East: an efficient and accurate scene text detector},
+  author={Zhou, Xinyu and Yao, Cong and Wen, He and Wang, Yuzhi and Zhou, Shuchang and He, Weiran and Liang, Jiajun},
+  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
+  pages={5551--5560},
+  year={2017}
+}
+```

doc/doc_ch/algorithm_det_sast.md

+# SAST
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning](https://arxiv.org/abs/1908.05498)
+> Wang, Pengfei and Zhang, Chengquan and Qi, Fei and Huang, Zuming and En, Mengyi and Han, Junyu and Liu, Jingtuo and Ding, Errui and Shi, Guangming
+> ACM MM, 2019
+
+在ICDAR2015文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|SAST|ResNet50_vd|[configs/det/det_r50_vd_sast_icdar15.yml](../../configs/det/det_r50_vd_sast_icdar15.yml)|91.39%|83.77%|87.42%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
+
+
+在Total-text文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|SAST|ResNet50_vd|[configs/det/det_r50_vd_sast_totaltext.yml](../../configs/det/det_r50_vd_sast_totaltext.yml)|89.63%|78.44%|83.66%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
+
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+请参考[文本检测训练教程](./detection.md)。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+#### (1). 四边形文本检测模型（ICDAR2015）  
+首先将SAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例([模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar))，可以使用如下命令进行转换：
+```
+python3 tools/export_model.py -c configs/det/det_r50_vd_sast_icdar15.yml -o Global.pretrained_model=./det_r50_vd_sast_icdar15_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_ic15
+
+```
+**SAST文本检测模型推理，需要设置参数`--det_algorithm="SAST"`**，可以执行如下命令：
+```
+python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_sast_ic15/"
+```
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
+
+![](../imgs_results/det_res_img_10_sast.jpg)
+
+#### (2). 弯曲文本检测模型（Total-Text）  
+首先将SAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在Total-Text英文数据集训练的模型为例（[模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar))，可以使用如下命令进行转换：
+
+```
+python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.pretrained_model=./det_r50_vd_sast_totaltext_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_tt
+
+```
+
+SAST文本检测模型推理，需要设置参数`--det_algorithm="SAST"`，同时，还需要增加参数`--det_sast_polygon=True`，可以执行如下命令：
+```
+python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_sast_tt/" --det_sast_polygon=True
+```
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
+
+![](../imgs_results/det_res_img623_sast.jpg)
+
+**注意**：本代码库中，SAST后处理Locality-Aware NMS有python和c++两种版本，c++版速度明显快于python版。由于c++版本nms编译版本问题，只有python3.5环境下会调用c++版nms，其他情况将调用python版nms。
+
+<a name="4-2"></a>
+### 4.2 C++推理
+
+暂未支持
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+暂未支持
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+暂未支持
+
+<a name="5"></a>
+## 5. FAQ
+
+
+## 引用
+
+```bibtex
+@inproceedings{wang2019single,
+  title={A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning},
+  author={Wang, Pengfei and Zhang, Chengquan and Qi, Fei and Huang, Zuming and En, Mengyi and Han, Junyu and Liu, Jingtuo and Ding, Errui and Shi, Guangming},
+  booktitle={Proceedings of the 27th ACM International Conference on Multimedia},
+  pages={1277--1285},
+  year={2019}
+}
+```

doc/doc_ch/algorithm_inference.md

@@ -296,7 +296,7 @@ Predicts of ./doc/imgs_words_en/word_336.png:('super', 0.9999073)
 
 **注意**：由于上述模型是参考[DTRB](https://arxiv.org/abs/1904.01906)文本识别训练和评估流程，与超轻量级中文识别模型训练有两方面不同：
 
-- 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。
+- 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_dict_path，指定为英文字典"./ppocr/utils/ic15_dict.txt"。
 

doc/doc_ch/algorithm_rec_crnn.md

+# CRNN
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://arxiv.org/abs/1507.05717)
+
+> Baoguang Shi, Xiang Bai, Cong Yao
+
+> IEEE, 2015
+
+参考[DTRB](https://arxiv.org/abs/1904.01906) 文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
+
+|模型|骨干网络|Avg Accuracy|配置文件|下载链接|
+|---|---|---|---|---|
+|CRNN|Resnet34_vd|81.04%|[configs/rec/rec_r34_vd_none_bilstm_ctc.yml](../../configs/rec/rec_r34_vd_none_bilstm_ctc.yml)|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar)|
+|CRNN|MobileNetV3|77.95%|[configs/rec/rec_mv3_none_bilstm_ctc.yml](../../configs/rec/rec_mv3_none_bilstm_ctc.yml)|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_bilstm_ctc_v2.0_train.tar)|
+
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练不同的识别模型只需要**更换配置文件**即可。
+
+- 训练
+
+在完成数据准备后，便可以启动训练，训练命令如下：
+
+```
+#单卡训练（训练周期长，不建议）
+python3 tools/train.py -c configs/rec/rec_r34_vd_none_bilstm_ctc.yml
+
+#多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c rec_r34_vd_none_bilstm_ctc.yml
+
+```
+
+- 评估
+
+```
+# GPU 评估， Global.pretrained_model 为待测权重
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_r34_vd_none_bilstm_ctc.yml -o Global.pretrained_model={path/to/weights}/best_accuracy
+```
+
+- 预测：
+
+```
+# 预测使用的配置文件必须与训练一致
+python3 tools/infer_rec.py -c configs/rec/rec_r34_vd_none_bilstm_ctc.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png
+```
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+
+首先将 CRNN 文本识别训练过程中保存的模型，转换成inference model。以基于Resnet34_vd骨干网络，使用MJSynth和SynthText两个英文文本识别合成数据集训练的[模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar) 为例，可以使用如下命令进行转换：
+```shell
+python3 tools/export_model.py -c configs/rec/rec_r34_vd_none_bilstm_ctc.yml -o Global.pretrained_model=./rec_r34_vd_none_bilstm_ctc_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/rec_crnn
+```
+CRNN 文本识别模型推理，可以执行如下命令：
+
+```shell
+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)
+
+执行命令后，上面图像的识别结果如下：
+
+```bash
+Predicts of ./doc/imgs_words_en/word_336.png:('super', 0.9999073)
+```
+
+**注意**：由于上述模型是参考[DTRB](https://arxiv.org/abs/1904.01906)文本识别训练和评估流程，与超轻量级中文识别模型训练有两方面不同：
+
+- 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_dict_path，指定为英文字典"./ppocr/utils/ic15_dict.txt"。
+
+```
+self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
+dict_character = list(self.character_str)
+```
+
+
+<a name="4-2"></a>
+### 4.2 C++推理
+
+准备好推理模型后，参考[cpp infer](../../deploy/cpp_infer/)教程进行操作即可。
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+准备好推理模型后，参考[pdserving](../../deploy/pdserving/)教程进行Serving服务化部署，包括Python Serving和C++ Serving两种模式。
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+CRNN模型还支持以下推理部署方式：
+
+- Paddle2ONNX推理：准备好推理模型后，参考[paddle2onnx](../../deploy/paddle2onnx/)教程操作。
+
+<a name="5"></a>
+## 5. FAQ
+
+
+## 引用
+
+```bibtex
+@ARTICLE{7801919,
+  author={Shi, Baoguang and Bai, Xiang and Yao, Cong},
+  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+  title={An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition},
+  year={2017},
+  volume={39},
+  number={11},
+  pages={2298-2304},
+  doi={10.1109/TPAMI.2016.2646371}}
+```

doc/doc_ch/algorithm_rec_nrtr.md

+# 场景文本识别算法-NRTR
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://arxiv.org/abs/1806.00926)
+> Fenfen Sheng and Zhineng Chen and Bo Xu
+> ICDAR, 2019
+
+
+<a name="model"></a>
+`NRTR`使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法复现效果如下：
+
+|模型|骨干网络|配置文件|Acc|下载链接|
+| --- | --- | --- | --- | --- |
+|NRTR|MTB|[rec_mtb_nrtr.yml](../../configs/rec/rec_mtb_nrtr.yml)|84.21%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar)|
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+<a name="3-1"></a>
+### 3.1 模型训练
+
+请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练`NRTR`识别模型时需要**更换配置文件**为`NRTR`的[配置文件](../../configs/rec/rec_mtb_nrtr.yml)。
+
+#### 启动训练
+
+
+具体地，在完成数据准备后，便可以启动训练，训练命令如下：
+```shell
+#单卡训练（训练周期长，不建议）
+python3 tools/train.py -c configs/rec/rec_mtb_nrtr.yml
+
+#多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_mtb_nrtr.yml
+```
+
+<a name="3-2"></a>
+### 3.2 评估
+
+可下载已训练完成的[模型文件](#model)，使用如下命令进行评估：
+
+```shell
+# 注意将pretrained_model的路径设置为本地路径。
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_mtb_nrtr.yml -o Global.pretrained_model=./rec_mtb_nrtr_train/best_accuracy
+```
+
+<a name="3-3"></a>
+### 3.3 预测
+
+使用如下命令进行单张图片预测：
+```shell
+# 注意将pretrained_model的路径设置为本地路径。
+python3 tools/infer_rec.py -c configs/rec/rec_mtb_nrtr.yml -o Global.infer_img='./doc/imgs_words_en/word_10.png' Global.pretrained_model=./rec_mtb_nrtr_train/best_accuracy
+# 预测文件夹下所有图像时，可修改infer_img为文件夹，如 Global.infer_img='./doc/imgs_words_en/'。
+```
+
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+首先将训练得到best模型，转换成inference model。这里以训练完成的模型为例（[模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) )，可以使用如下命令进行转换：
+
+```shell
+# 注意将pretrained_model的路径设置为本地路径。
+python3 tools/export_model.py -c configs/rec/rec_mtb_nrtr.yml -o Global.pretrained_model=./rec_mtb_nrtr_train/best_accuracy Global.save_inference_dir=./inference/rec_mtb_nrtr/
+```
+**注意：**
+- 如果您是在自己的数据集上训练的模型，并且调整了字典文件，请注意修改配置文件中的`character_dict_path`是否是所需要的字典文件。
+- 如果您修改了训练时的输入大小，请修改`tools/export_model.py`文件中的对应NRTR的`infer_shape`。
+
+转换成功后，在目录下有三个文件：
+```
+/inference/rec_mtb_nrtr/
+    ├── inference.pdiparams         # 识别inference模型的参数文件
+    ├── inference.pdiparams.info    # 识别inference模型的参数信息，可忽略
+    └── inference.pdmodel           # 识别inference模型的program文件
+```
+
+执行如下命令进行模型推理：
+
+```shell
+python3 tools/infer/predict_rec.py --image_dir='./doc/imgs_words_en/word_10.png' --rec_model_dir='./inference/rec_mtb_nrtr/' --rec_algorithm='NRTR' --rec_image_shape='1,32,100' --rec_char_dict_path='./ppocr/utils/EN_symbol_dict.txt'
+# 预测文件夹下所有图像时，可修改image_dir为文件夹，如 --image_dir='./doc/imgs_words_en/'。
+```
+
+![](../imgs_words_en/word_10.png)
+
+执行命令后，上面图像的预测结果（识别的文本和得分）会打印到屏幕上，示例如下：
+结果如下：
+```shell
+Predicts of ./doc/imgs_words_en/word_10.png:('pain', 0.9265879392623901)
+```
+
+**注意**：
+
+- 训练上述模型采用的图像分辨率是[1，32，100]，需要通过参数`rec_image_shape`设置为您训练时的识别图像形状。
+- 在推理时需要设置参数`rec_char_dict_path`指定字典，如果您修改了字典，请修改该参数为您的字典文件。
+- 如果您修改了预处理方法，需修改`tools/infer/predict_rec.py`中NRTR的预处理为您的预处理方法。
+
+
+<a name="4-2"></a>
+### 4.2 C++推理部署
+
+由于C++预处理后处理还未支持NRTR，所以暂未支持
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+暂不支持
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+暂不支持
+
+<a name="5"></a>
+## 5. FAQ
+
+1. `NRTR`论文中使用Beam搜索进行解码字符，但是速度较慢，这里默认未使用Beam搜索，以贪婪搜索进行解码字符。
+
+## 引用
+
+```bibtex
+@article{Sheng2019NRTR,
+  title     = {NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition},
+  author    = {Fenfen Sheng and Zhineng Chen andBo Xu},
+  booktitle = {ICDAR},
+  year      = {2019},
+  url       = {http://arxiv.org/abs/1806.00926},
+  pages     = {781-786}
+}
+```

doc/doc_ch/algorithm_rec_rare.md

+# RARE
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [Robust Scene Text Recognition with Automatic Rectification](https://arxiv.org/abs/1603.03915v2)
+> Baoguang Shi, Xinggang Wang, Pengyuan Lyu, Cong Yao, Xiang Bai∗
+> CVPR, 2016
+
+使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法复现效果如下：
+
+|模型|骨干网络|配置文件|Avg Accuracy|下载链接|
+| --- | --- | --- | --- | --- |
+|RARE|Resnet34_vd|[configs/rec/rec_r34_vd_tps_bilstm_att.yml](../../configs/rec/rec_r34_vd_tps_bilstm_att.yml)|83.6%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_att_v2.0_train.tar)|
+|RARE|MobileNetV3|[configs/rec/rec_mv3_tps_bilstm_att.yml](../../configs/rec/rec_mv3_tps_bilstm_att.yml)|82.5%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_att_v2.0_train.tar)|
+
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练不同的识别模型只需要**更换配置文件**即可。以基于Resnet34_vd骨干网络为例:
+
+<a name="3-1"></a>
+### 3.1 训练
+
+```
+#单卡训练（训练周期长，不建议）
+python3 tools/train.py -c configs/rec/rec_r34_vd_tps_bilstm_att.yml
+#多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_r34_vd_tps_bilstm_att.yml
+```
+
+<a name="3-2"></a>
+### 3.2 评估
+
+```
+# GPU评估, Global.pretrained_model为待评估模型
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_r34_vd_tps_bilstm_att.yml -o Global.pretrained_model={path/to/weights}/best_accuracy
+```
+
+<a name="3-3"></a>
+### 3.3 预测
+
+```
+python3 tools/infer_rec.py -c configs/rec/rec_r34_vd_tps_bilstm_att.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png
+```
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+首先将RARE文本识别训练过程中保存的模型，转换成inference model。以基于Resnet34_vd骨干网络，在MJSynth和SynthText两个文字识别数据集训练得到的模型为例（ [模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_att_v2.0_train.tar) )，可以使用如下命令进行转换：
+
+```shell
+python3 tools/export_model.py -c configs/rec/rec_r34_vd_tps_bilstm_att.yml -o Global.pretrained_model=./rec_r34_vd_tps_bilstm_att_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/rec_rare
+```
+
+RARE文本识别模型推理，可以执行如下命令：
+
+```shell
+python3 tools/infer/predict_rec.py --image_dir="doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_rare/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
+```
+推理结果如下所示：
+
+![](../../doc/imgs_words/en/word_1.png)
+
+```
+Predicts of doc/imgs_words/en/word_1.png:('joint ', 0.9999969601631165)
+```
+
+
+<a name="4-2"></a>
+### 4.2 C++推理
+
+暂不支持
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+暂不支持
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+RARE模型还支持以下推理部署方式：
+
+- Paddle2ONNX推理：准备好推理模型后，参考[paddle2onnx](../../deploy/paddle2onnx/)教程操作。
+
+<a name="5"></a>
+## 5. FAQ
+
+
+## 引用
+
+```bibtex
+@inproceedings{2016Robust,
+  title={Robust Scene Text Recognition with Automatic Rectification},
+  author={ Shi, B.  and  Wang, X.  and  Lyu, P.  and  Cong, Y.  and  Xiang, B. },
+  booktitle={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2016},
+}
+```

doc/doc_ch/algorithm_rec_rosetta.md

+# Rosetta
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [Rosetta: Large Scale System for Text Detection and Recognition in Images](https://arxiv.org/abs/1910.05085)
+> Borisyuk F ,  Gordo A ,  V  Sivakumar
+> KDD, 2018
+
+使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估， 算法复现效果如下：
+
+|模型|骨干网络|配置文件|Avg Accuracy|下载链接|
+| --- | --- | --- | --- | --- |
+|Rosetta|Resnet34_vd|[configs/rec/rec_r34_vd_none_none_ctc.yml](../../configs/rec/rec_r34_vd_none_none_ctc.yml)|79.11%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_none_ctc_v2.0_train.tar)|
+|Rosetta|MobileNetV3|[configs/rec/rec_mv3_none_none_ctc.yml](../../configs/rec/rec_mv3_none_none_ctc.yml)|75.80%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_none_ctc_v2.0_train.tar)|
+
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练不同的识别模型只需要**更换配置文件**即可。 以基于Resnet34_vd骨干网络为例:
+
+<a name="3-1"></a>
+### 3.1 训练
+
+```
+#单卡训练（训练周期长，不建议）
+python3 tools/train.py -c configs/rec/rec_r34_vd_none_none_ctc.yml
+#多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_r34_vd_none_none_ctc.yml
+```
+
+<a name="3-2"></a>
+### 3.2 评估
+
+```
+# GPU评估, Global.pretrained_model为待评估模型
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_r34_vd_none_none_ctc.yml -o Global.pretrained_model={path/to/weights}/best_accuracy
+```
+
+<a name="3-3"></a>
+### 3.3 预测
+
+```
+python3 tools/infer_rec.py -c configs/rec/rec_r34_vd_none_none_ctc.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png
+```
+
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+首先将Rosetta文本识别训练过程中保存的模型，转换成inference model。以基于Resnet34_vd骨干网络，在MJSynth和SynthText两个文字识别数据集训练得到的模型为例（ [模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_none_ctc_v2.0_train.tar) )，可以使用如下命令进行转换：
+
+```shell
+python3 tools/export_model.py -c configs/rec/rec_r34_vd_none_none_ctc.yml -o Global.pretrained_model=./rec_r34_vd_none_none_ctc_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/rec_rosetta
+```
+
+Rosetta文本识别模型推理，可以执行如下命令：
+
+```shell
+python3 tools/infer/predict_rec.py --image_dir="doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_rosetta/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
+```
+
+推理结果如下所示：
+
+![](../../doc/imgs_words/en/word_1.png)
+
+```
+Predicts of doc/imgs_words/en/word_1.png:('joint', 0.9999982714653015)
+```
+
+<a name="4-2"></a>
+### 4.2 C++推理
+
+暂不支持
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+暂不支持
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+Rosetta模型还支持以下推理部署方式：
+
+- Paddle2ONNX推理：准备好推理模型后，参考[paddle2onnx](../../deploy/paddle2onnx/)教程操作。
+
+<a name="5"></a>
+## 5. FAQ
+
+
+## 引用
+
+```bibtex
+@inproceedings{2018Rosetta,
+  title={Rosetta: Large Scale System for Text Detection and Recognition in Images},
+  author={ Borisyuk, Fedor  and  Gordo, Albert  and  Sivakumar, Viswanath },
+  booktitle={the 24th ACM SIGKDD International Conference},
+  year={2018},
+}
+```

doc/doc_ch/algorithm_rec_sar.md

@@ -24,7 +24,7 @@
 使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法复现效果如下：
 
 |模型|骨干网络|配置文件|Acc|下载链接|
-| --- | --- | --- | --- | --- | --- | --- |
+| --- | --- | --- | --- | --- |
 |SAR|ResNet31|[rec_r31_sar.yml](../../configs/rec/rec_r31_sar.yml)|87.20%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar)|
 
 注：除了使用MJSynth和SynthText两个文字识别数据集外，还加入了[SynthAdd](https://pan.baidu.com/share/init?surl=uV0LtoNmcxbO-0YA7Ch4dg)数据（提取码：627x），和部分真实数据，具体数据细节可以参考论文。

doc/doc_ch/algorithm_rec_seed.md

+# SEED
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://arxiv.org/pdf/2005.10977.pdf)
+
+> Qiao, Zhi and Zhou, Yu and Yang, Dongbao and Zhou, Yucan and Wang, Weiping
+
+> CVPR, 2020
+
+参考[DTRB](https://arxiv.org/abs/1904.01906) 文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
+
+|模型|骨干网络|Avg Accuracy|配置文件|下载链接|
+|---|---|---|---|---|
+|SEED|Aster_Resnet| 85.2% | [configs/rec/rec_resnet_stn_bilstm_att.yml](../../configs/rec/rec_resnet_stn_bilstm_att.yml) | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_resnet_stn_bilstm_att.tar) |
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练不同的识别模型只需要**更换配置文件**即可。
+
+- 训练
+
+SEED模型需要额外加载FastText训练好的[语言模型](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.en.300.bin.gz) ,并且安装 fasttext 依赖：
+
+```
+python3 -m pip install fasttext==0.9.1
+```
+
+然后，在完成数据准备后，便可以启动训练，训练命令如下：
+
+```
+#单卡训练（训练周期长，不建议）
+python3 tools/train.py -c configs/rec/rec_resnet_stn_bilstm_att.yml
+
+#多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c rec_resnet_stn_bilstm_att.yml
+
+```
+
+- 评估
+
+```
+# GPU 评估， Global.pretrained_model 为待测权重
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_resnet_stn_bilstm_att.yml -o Global.pretrained_model={path/to/weights}/best_accuracy
+```
+
+- 预测：
+
+```
+# 预测使用的配置文件必须与训练一致
+python3 tools/infer_rec.py -c configs/rec/rec_resnet_stn_bilstm_att.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png
+```
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+
+coming soon
+
+
+<a name="4-2"></a>
+### 4.2 C++推理
+
+coming soon
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+coming soon
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+coming soon
+
+<a name="5"></a>
+## 5. FAQ
+
+
+## 引用
+
+```bibtex
+@inproceedings{qiao2020seed,
+  title={Seed: Semantics enhanced encoder-decoder framework for scene text recognition},
+  author={Qiao, Zhi and Zhou, Yu and Yang, Dongbao and Zhou, Yucan and Wang, Weiping},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={13528--13537},
+  year={2020}
+}
+```

doc/doc_ch/algorithm_rec_srn.md

@@ -24,7 +24,7 @@
 使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法复现效果如下：
 
 |模型|骨干网络|配置文件|Acc|下载链接|
-| --- | --- | --- | --- | --- | --- | --- |
+| --- | --- | --- | --- | --- |
 |SRN|Resnet50_vd_fpn|[rec_r50_fpn_srn.yml](../../configs/rec/rec_r50_fpn_srn.yml)|86.31%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar)|
 
 

doc/doc_ch/algorithm_rec_starnet.md

+# STAR-Net
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [STAR-Net: a spatial attention residue network for scene text recognition.](http://www.bmva.org/bmvc/2016/papers/paper043/paper043.pdf)
+
+> Wei Liu, Chaofeng Chen, Kwan-Yee K. Wong, Zhizhong Su and Junyu Han.
+
+> BMVC, pages 43.1-43.13, 2016
+
+参考[DTRB](https://arxiv.org/abs/1904.01906) 文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
+
+|模型|骨干网络|Avg Accuracy|配置文件|下载链接|
+|---|---|---|---|---|
+|StarNet|Resnet34_vd|84.44%|[configs/rec/rec_r34_vd_tps_bilstm_ctc.yml](../../configs/rec/rec_r34_vd_tps_bilstm_ctc.yml)|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_ctc_v2.0_train.tar)|
+|StarNet|MobileNetV3|81.42%|[configs/rec/rec_mv3_tps_bilstm_ctc.yml](../../configs/rec/rec_mv3_tps_bilstm_ctc.yml)|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_ctc_v2.0_train.tar)|
+
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练不同的识别模型只需要**更换配置文件**即可。
+
+- 训练
+
+在完成数据准备后，便可以启动训练，训练命令如下：
+
+```
+#单卡训练（训练周期长，不建议）
+python3 tools/train.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
+
+#多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c rec_r34_vd_tps_bilstm_ctc.yml
+
+```
+
+- 评估
+
+```
+# GPU 评估， Global.pretrained_model 为待测权重
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml -o Global.pretrained_model={path/to/weights}/best_accuracy
+```
+
+- 预测：
+
+```
+# 预测使用的配置文件必须与训练一致
+python3 tools/infer_rec.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png
+```
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+
+首先将 STAR-Net 文本识别训练过程中保存的模型，转换成inference model。以基于Resnet34_vd骨干网络，使用MJSynth和SynthText两个英文文本识别合成数据集训练的[模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar) 为例，可以使用如下命令进行转换：
+```shell
+python3 tools/export_model.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml -o Global.pretrained_model=./rec_r34_vd_tps_bilstm_ctc_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/rec_starnet
+```
+STAR-Net 文本识别模型推理，可以执行如下命令：
+
+```shell
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rec_starnet/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
+```
+
+![](../imgs_words_en/word_336.png)
+
+执行命令后，上面图像的识别结果如下：
+
+```bash
+Predicts of ./doc/imgs_words_en/word_336.png:('super', 0.9999073)
+```
+
+**注意**：由于上述模型是参考[DTRB](https://arxiv.org/abs/1904.01906)文本识别训练和评估流程，与超轻量级中文识别模型训练有两方面不同：
+
+- 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_dict_path，指定为英文字典"./ppocr/utils/ic15_dict.txt"。
+
+```
+self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
+dict_character = list(self.character_str)
+```
+
+
+<a name="4-2"></a>
+### 4.2 C++推理
+
+准备好推理模型后，参考[cpp infer](../../deploy/cpp_infer/)教程进行操作即可。
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+准备好推理模型后，参考[pdserving](../../deploy/pdserving/)教程进行Serving服务化部署，包括Python Serving和C++ Serving两种模式。
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+STAR-Net模型还支持以下推理部署方式：
+
+- Paddle2ONNX推理：准备好推理模型后，参考[paddle2onnx](../../deploy/paddle2onnx/)教程操作。
+
+<a name="5"></a>
+## 5. FAQ
+
+
+## 引用
+
+```bibtex
+@inproceedings{liu2016star,
+  title={STAR-Net: a spatial attention residue network for scene text recognition.},
+  author={Liu, Wei and Chen, Chaofeng and Wong, Kwan-Yee K and Su, Zhizhong and Han, Junyu},
+  booktitle={BMVC},
+  volume={2},
+  pages={7},
+  year={2016}
+}
+```

doc/doc_ch/algorithm_rec_svtr.md

+# 场景文本识别算法-SVTR
+
+- [1. 算法简介](#1)
+- [2. 环境配置](#2)
+- [3. 模型训练、评估、预测](#3)
+    - [3.1 训练](#3-1)
+    - [3.2 评估](#3-2)
+    - [3.3 预测](#3-3)
+- [4. 推理部署](#4)
+    - [4.1 Python推理](#4-1)
+    - [4.2 C++推理](#4-2)
+    - [4.3 Serving服务化部署](#4-3)
+    - [4.4 更多推理部署](#4-4)
+- [5. FAQ](#5)
+
+<a name="1"></a>
+## 1. 算法简介
+
+论文信息：
+> [SVTR: Scene Text Recognition with a Single Visual Model](https://arxiv.org/abs/2205.00159)
+> Yongkun Du and Zhineng Chen and Caiyan Jia Xiaoting Yin and Tianlun Zheng and Chenxia Li and Yuning Du and Yu-Gang Jiang
+> IJCAI, 2022
+
+场景文本识别旨在将自然图像中的文本转录为数字字符序列，从而传达对场景理解至关重要的高级语义。这项任务由于文本变形、字体、遮挡、杂乱背景等方面的变化具有一定的挑战性。先前的方法为提高识别精度做出了许多工作。然而文本识别器除了准确度外，还因为实际需求需要考虑推理速度等因素。
+
+### SVTR算法简介
+
+主流的场景文本识别模型通常包含两个模块：用于特征提取的视觉模型和用于文本转录的序列模型。这种架构虽然准确，但复杂且效率较低，限制了在实际场景中的应用。SVTR提出了一种用于场景文本识别的单视觉模型，该模型在patch-wise image tokenization框架内，完全摒弃了序列建模，在精度具有竞争力的前提下，模型参数量更少，速度更快，主要有以下几点贡献：
+1. 首次发现单视觉模型可以达到与视觉语言模型相媲美甚至更高的准确率，并且其具有效率高和适应多语言的优点，在实际应用中很有前景。
+2. SVTR从字符组件的角度出发，逐渐的合并字符组件，自下而上地完成字符的识别。
+3. SVTR引入了局部和全局Mixing，分别用于提取字符组件特征和字符间依赖关系，与多尺度的特征一起，形成多粒度特征描述。
+
+
+<a name="model"></a>
+SVTR在场景文本识别公开数据集上的精度(%)和模型文件如下：
+
+* 中文数据集来自于[Chinese Benckmark](https://arxiv.org/abs/2112.15093) ，SVTR的中文训练评估策略遵循该论文。
+
+|    模型      |IC13<br/>857 |  SVT  |IIIT5k<br/>3000 |IC15<br/>1811| SVTP  |CUTE80 | Avg_6 |IC15<br/>2077 |IC13<br/>1015 |IC03<br/>867|IC03<br/>860|Avg_10 | Chinese<br/>scene_test|      下载链接       |
+|:----------:|:------:|:-----:|:---------:|:------:|:-----:|:-----:|:-----:|:-------:|:-------:|:-----:|:-----:|:---------------------------------------------:|:-----:|:-----:|
+| SVTR Tiny  | 96.85  | 91.34 |   94.53   | 83.99  | 85.43 | 89.24 | 90.87 |  80.55  |  95.37  | 95.27 | 95.70 | 90.13 | 67.90 | [英文](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_en_train.tar)  / [中文](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_ch_train.tar)  |
+| SVTR Small | 95.92  | 93.04 |   95.03   | 84.70  | 87.91 | 92.01 | 91.63 |  82.72  |  94.88  | 96.08 | 96.28 | 91.02 | 69.00 | [英文](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_small_none_ctc_en_train.tar) / [中文](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_small_none_ctc_ch_train.tar) |
+| SVTR Base  | 97.08  | 91.50 |   96.03   | 85.20  | 89.92 | 91.67 | 92.33 |  83.73  |  95.66  | 95.62 | 95.81 | 91.61 | 71.40 | [英文](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_base_none_ctc_en_train.tar)  /                                              -                                             |
+| SVTR Large | 97.20  | 91.65 |   96.30   | 86.58  | 88.37 | 95.14 | 92.82 |  84.54  |  96.35  | 96.54 | 96.74 | 92.24 | 72.10 | [英文](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_large_none_ctc_en_train.tar) / [中文](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_large_none_ctc_ch_train.tar) |
+
+
+
+<a name="2"></a>
+## 2. 环境配置
+请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。
+
+
+<a name="3"></a>
+## 3. 模型训练、评估、预测
+
+<a name="3-1"></a>
+### 3.1 模型训练
+
+#### 数据集准备
+
+[英文数据集下载](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here)
+[中文数据集下载](https://github.com/fudanvi/benchmarking-chinese-text-recognition#download)
+
+#### 启动训练
+
+请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练`SVTR`识别模型时需要**更换配置文件**为`SVTR`的[配置文件](../../configs/rec/rec_svtrnet.yml)。
+
+具体地，在完成数据准备后，便可以启动训练，训练命令如下：
+```shell
+#单卡训练（训练周期长，不建议）
+python3 tools/train.py -c configs/rec/rec_svtrnet.yml
+
+#多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_svtrnet.yml
+```
+
+<a name="3-2"></a>
+### 3.2 评估
+
+可下载`SVTR`提供的模型文件和配置文件：[下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_en_train.tar) ，以`SVTR-T`为例，使用如下命令进行评估：
+
+```shell
+# 下载包含SVTR-T的模型文件和配置文件的tar压缩包并解压
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_en_train.tar && tar xf rec_svtr_tiny_none_ctc_en_train.tar
+# 注意将pretrained_model的路径设置为本地路径。
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c ./rec_svtr_tiny_none_ctc_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.pretrained_model=./rec_svtr_tiny_none_ctc_en_train/best_accuracy
+```
+
+<a name="3-3"></a>
+### 3.3 预测
+
+使用如下命令进行单张图片预测：
+```shell
+# 注意将pretrained_model的路径设置为本地路径。
+python3 tools/infer_rec.py -c ./rec_svtr_tiny_none_ctc_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.infer_img='./doc/imgs_words_en/word_10.png' Global.pretrained_model=./rec_svtr_tiny_none_ctc_en_train/best_accuracy
+# 预测文件夹下所有图像时，可修改infer_img为文件夹，如 Global.infer_img='./doc/imgs_words_en/'。
+```
+
+
+<a name="4"></a>
+## 4. 推理部署
+
+<a name="4-1"></a>
+### 4.1 Python推理
+首先将训练得到best模型，转换成inference model。下面以基于`SVTR-T`，在英文数据集训练的模型为例（[模型和配置文件下载地址](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_en_train.tar) )，可以使用如下命令进行转换：
+
+```shell
+# 注意将pretrained_model的路径设置为本地路径。
+python3 tools/export_model.py -c ./rec_svtr_tiny_none_ctc_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.pretrained_model=./rec_svtr_tiny_none_ctc_en_train/best_accuracy Global.save_inference_dir=./inference/rec_svtr_tiny_stn_en
+```
+
+**注意：**
+- 如果您是在自己的数据集上训练的模型，并且调整了字典文件，请注意修改配置文件中的`character_dict_path`是否为所正确的字典文件。
+- 如果您修改了训练时的输入大小，请修改`tools/export_model.py`文件中的对应SVTR的`infer_shape`。
+
+转换成功后，在目录下有三个文件：
+```
+/inference/rec_svtr_tiny_stn_en/
+    ├── inference.pdiparams         # 识别inference模型的参数文件
+    ├── inference.pdiparams.info    # 识别inference模型的参数信息，可忽略
+    └── inference.pdmodel           # 识别inference模型的program文件
+```
+
+
+执行如下命令进行模型推理：
+
+```shell
+python3 tools/infer/predict_rec.py --image_dir='./doc/imgs_words_en/word_10.png' --rec_model_dir='./inference/rec_svtr_tiny_stn_en/' --rec_algorithm='SVTR' --rec_image_shape='3,64,256' --rec_char_dict_path='./ppocr/utils/ic15_dict.txt'
+# 预测文件夹下所有图像时，可修改image_dir为文件夹，如 --image_dir='./doc/imgs_words_en/'。
+```
+![](../imgs_words_en/word_10.png)
+
+执行命令后，上面图像的预测结果（识别的文本和得分）会打印到屏幕上，示例如下：
+结果如下：
+```shell
+Predicts of ./doc/imgs_words_en/word_10.png:('pain', 0.9999998807907104)
+```
+
+**注意**：
+
+- 如果您调整了训练时的输入分辨率，需要通过参数`rec_image_shape`设置为您需要的识别图像形状。
+- 在推理时需要设置参数`rec_char_dict_path`指定字典，如果您修改了字典，请修改该参数为您的字典文件。
+- 如果您修改了预处理方法，需修改`tools/infer/predict_rec.py`中SVTR的预处理为您的预处理方法。
+
+<a name="4-2"></a>
+### 4.2 C++推理部署
+
+由于C++预处理后处理还未支持SVTR，所以暂未支持
+
+<a name="4-3"></a>
+### 4.3 Serving服务化部署
+
+暂不支持
+
+<a name="4-4"></a>
+### 4.4 更多推理部署
+
+暂不支持
+
+<a name="5"></a>
+## 5. FAQ
+
+1. 由于`SVTR`使用的算子大多为矩阵相乘，在GPU环境下，速度具有优势，但在CPU开启mkldnn加速环境下，`SVTR`相比于被优化的卷积网络没有优势。
+
+
+## 引用
+
+```bibtex
+@article{Du2022SVTR,
+  title     = {SVTR: Scene Text Recognition with a Single Visual Model},
+  author    = {Du, Yongkun and Chen, Zhineng and Jia, Caiyan and Yin, Xiaoting and Zheng, Tianlun and Li, Chenxia and Du, Yuning and Jiang, Yu-Gang},
+  booktitle = {IJCAI},
+  year      = {2022},
+  url       = {https://arxiv.org/abs/2205.00159}
+}
+```

doc/doc_ch/benchmark.md

@@ -13,7 +13,7 @@
 
 说明：
 
-- 检测输入图像的的长边尺寸是960。
+- 检测输入图像的长边尺寸是960。
 - 评估耗时阶段为图像预测耗时，不包括图像的预处理和后处理。  
 - `Intel至强6148`为服务器端CPU型号，测试中使用Intel MKL-DNN 加速。
 - `骁龙855`为移动端处理平台型号。  

doc/doc_ch/config.md

@@ -94,7 +94,7 @@
 |      name        |         网络loss类名          |  CTCLoss  |  目前支持`CTCLoss`,`DBLoss`,`ClsLoss`  |
 |      balance_loss        |        DBLossloss中是否对正负样本数量进行均衡(使用OHEM)         |  True  |  \  |
 |      ohem_ratio        |        DBLossloss中的OHEM的负正样本比例         |  3  |  \  |
-|      main_loss_type        |        DBLossloss中shrink_map所采用的的loss        |  DiceLoss  |  支持`DiceLoss`,`BCELoss`  |
+|      main_loss_type        |        DBLossloss中shrink_map所采用的loss        |  DiceLoss  |  支持`DiceLoss`,`BCELoss`  |
 |      alpha        |        DBLossloss中shrink_map_loss的系数       |  5  |  \  |
 |      beta        |        DBLossloss中threshold_map_loss的系数       |  10  |  \  |
 

doc/doc_ch/dataset/docvqa_datasets.md

+## DocVQA数据集
+这里整理了常见的DocVQA数据集，持续更新中，欢迎各位小伙伴贡献数据集～
+- [FUNSD数据集](#funsd)
+- [XFUND数据集](#xfund)
+
+<a name="funsd"></a>
+#### 1、FUNSD数据集
+- **数据来源**：https://guillaumejaume.github.io/FUNSD/
+- **数据简介**：FUNSD数据集是一个用于表单理解的数据集，它包含199张真实的、完全标注的扫描版图片，类型包括市场报告、广告以及学术报告等，并分为149张训练集以及50张测试集。FUNSD数据集适用于多种类型的DocVQA任务，如字段级实体分类、字段级实体连接等。部分图像以及标注框可视化如下所示:
+<div align="center">
+    <img src="../../datasets/funsd_demo/gt_train_00040534.jpg" width="500">
+    <img src="../../datasets/funsd_demo/gt_train_00070353.jpg" width="500">
+</div>
+    图中，橙色区域代表`header`，淡蓝色区域代表`question`, 绿色区域表`answer`，粉红色代区域表`other`。
+
+- **下载地址**：https://guillaumejaume.github.io/FUNSD/download/
+
+<a name="xfund"></a>
+#### 2、XFUND数据集
+- **数据来源**：https://github.com/doc-analysis/XFUND
+- **数据简介**：XFUND是一个多语种表单理解数据集，它包含7种不同语种的表单数据，并且全部用人工进行了键-值对形式的标注。其中每个语种的数据都包含了199张表单数据，并分为149张训练集以及50张测试集。部分图像以及标注框可视化如下所示:
+<div align="center">
+    <img src="../../datasets/xfund_demo/gt_zh_train_0.jpg" width="500">
+    <img src="../../datasets/xfund_demo/gt_zh_train_1.jpg" width="500">
+</div>
+
+- **下载地址**：https://github.com/doc-analysis/XFUND/releases/tag/v1.0

doc/doc_ch/inference_ppocr.md

@@ -19,9 +19,9 @@
 
 ```
 # 下载超轻量中文检测模型：
-wget  https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
-tar xf ch_PP-OCRv2_det_infer.tar
-python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv2_det_infer/"
+wget  https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
+tar xf ch_PP-OCRv3_det_infer.tar
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/"
 
 ```
 
@@ -40,13 +40,13 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_m
 如果输入图片的分辨率比较大，而且想使用更大的分辨率预测，可以设置det_limit_side_len 为想要的值，比如1216：
 
 ```
-python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --det_limit_type=max --det_limit_side_len=1216
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --det_limit_type=max --det_limit_side_len=1216
 ```
 
 如果想使用CPU进行预测，执行命令如下
 
 ```
-python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/"  --use_gpu=False
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/"  --use_gpu=False
 ```
 
 
@@ -59,13 +59,15 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_di
 
 ### 2.1 超轻量中文识别模型推理
 
+**注意** `PP-OCRv3`的识别模型使用的输入shape为`3,48,320`, 需要添加参数`--rec_image_shape=3,48,320`，如果不使用`PP-OCRv3`的识别模型，则无需设置该参数。
+
 超轻量中文识别模型推理，可以执行如下命令：
 
 ```
 # 下载超轻量中文识别模型：
-wget  https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar
-tar xf ch_PP-OCRv2_rec_infer.tar
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./ch_PP-OCRv2_rec_infer/"
+wget  https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+tar xf ch_PP-OCRv3_rec_infer.tar
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --rec_image_shape=3,48,320
 ```
 
 ![](../imgs_words/ch/word_4.jpg)
@@ -73,7 +75,7 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg"
 执行命令后，上面图像的预测结果（识别的文本和得分）会打印到屏幕上，示例如下：
 
 ```bash
-Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153)
+Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.9956803321838379)
 ```
 
 <a name="多语言模型的推理"></a>
@@ -119,17 +121,19 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:['0', 0.9999982]
 
 ## 4. 文本检测、方向分类和文字识别串联推理
 
+**注意** `PP-OCRv3`的识别模型使用的输入shape为`3,48,320`, 需要添加参数`--rec_image_shape=3,48,320`，如果不使用`PP-OCRv3`的识别模型，则无需设置该参数。
+
 以超轻量中文OCR模型推理为例，在执行预测时，需要通过参数`image_dir`指定单张图像或者图像集合的路径、参数`det_model_dir`,`cls_model_dir`和`rec_model_dir`分别指定检测，方向分类和识别的inference模型路径。参数`use_angle_cls`用于控制是否启用方向分类模型。`use_mp`表示是否使用多进程。`total_process_num`表示在使用多进程时的进程数。可视化识别结果默认保存到 ./inference_results 文件夹里面。
 
 ```shell
 # 使用方向分类器
-python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --cls_model_dir="./inference/cls/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=true
+python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --cls_model_dir="./cls/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=true --rec_image_shape=3,48,320
 # 不使用方向分类器
-python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=false
+python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=false --rec_image_shape=3,48,320
 # 使用多进程
-python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=false --use_mp=True --total_process_num=6
+python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=false --use_mp=True --total_process_num=6 --rec_image_shape=3,48,320
 ```
 
 执行命令后，识别结果图像如下：
 
-![](../imgs_results/system_res_00018069.jpg)
+![](../imgs_results/system_res_00018069_v3.jpg)

doc/doc_ch/multi_languages.md

@@ -176,8 +176,62 @@ ppocr 还支持方向分类， 更多使用方式请参考：[whl包使用说明
 ppocr 支持使用自己的数据进行自定义训练或finetune, 其中识别模型可以参考 [法语配置文件](../../configs/rec/multi_language/rec_french_lite_train.yml)
 修改训练数据路径、字典等参数。
 
-具体数据准备、训练过程可参考：[文本检测](../doc_ch/detection.md)、[文本识别](../doc_ch/recognition.md)，更多功能如预测部署、
-数据标注等功能可以阅读完整的[文档教程](../../README_ch.md)。
+详细数据准备、训练过程可参考：[文本识别](../doc_ch/recognition.md)、[文本检测](../doc_ch/detection.md)。
+
+假设已经准备好了训练数据，可根据以下步骤快速启动训练：
+
+- 修改配置文件
+
+以 `rec_french_lite_train.yml` 为例：
+
+```
+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/dict/french_dict.txt
+  ...
+  # 识别空格
+  use_space_char: True
+
+...
+
+Train:
+  dataset:
+    # 数据集格式，支持LMDBDataSet以及SimpleDataSet
+    name: SimpleDataSet
+    # 数据集路径
+    data_dir: ./train_data/
+    # 训练集标签文件
+    label_file_list: ["./train_data/french_train.txt"]
+    ...
+
+Eval:
+  dataset:
+    # 数据集格式，支持LMDBDataSet以及SimpleDataSet
+    name: SimpleDataSet
+    # 数据集路径
+    data_dir: ./train_data
+    # 验证集标签文件
+    label_file_list: ["./train_data/french_val.txt"]
+    ...
+```
+
+- 启动训练：
+
+```
+# 下载预训练模型
+wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_train.tar
+tar -xf french_mobile_v2.0_rec_train.tar
+
+#加载预训练模型 单卡训练
+python3 tools/train.py -c configs/rec/rec_french_lite_train.yml -o Global.pretrained_model=french_mobile_v2.0_rec_train/best_accuracy
+
+#加载预训练模型  多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_french_lite_train.yml -o Global.pretrained_model=french_mobile_v2.0_rec_train/best_accuracy
+```
+
+
+更多功能如预测部署、数据标注等功能可以阅读完整的[文档教程](../../README_ch.md)。
 
 <a name="预测部署"></a>
 ## 4 预测部署

doc/doc_en/PP-OCRv3_introduction_en.md

+English | [简体中文](../doc_ch/PP-OCRv3_introduction.md)