first commit

f1506916 · sugon_cxj · 55c28ed5 · f1506916 · f1506916 · f1506916
Commit f1506916 authored May 18, 2023 by sugon_cxj
20 changed files
--- a/README.md
+++ b/README.md
-PaddleOCR
+# PaddleOCR
+## 模型介绍
+基于百度PaddleOCR的字符识别模型。
+## 模型结构
+整体包含检测和识别两个模型。
+## 数据集
+推荐使用icdar2015数据集[icdar2015](https://rrc.cvc.uab.es/?ch=4&com=downloads)。
+
+检测模型训练集文件结构
+```
+/PaddleOCR/train_data/icdar2015/text_localization/
+  └─ icdar_c4_train_imgs/         Training data of icdar dataset
+  └─ ch4_test_images/             Testing data of icdar dataset
+  └─ train_icdar2015_label.txt    Training annotation of icdar dataset
+  └─ test_icdar2015_label.txt     Test annotation of icdar dataset
+```
+识别模型训练集文件结构
+```
+|-train_data
+  |-rec
+    |- rec_gt_train.txt
+    |- train
+        |- word_001.png
+        |- word_002.jpg
+        |- word_003.jpg
+        | ...
+    |-ic15_data
+        |- rec_gt_test.txt
+        |- test
+            |- word_001.jpg
+            |- word_002.jpg
+            |- word_003.jpg
+            | ...
+```
+## 训练及推理
+### 环境配置
+在[光源](https://www.sourcefind.cn/#/service-details)可拉取训练以及推理的docker镜像，在[光合开发者社区](https://cancon.hpccube.com:65024/4/main/)可下载paddle安装包。PaddleOCR推荐的镜像如下：
+* 训练/推理镜像：docker pull image.sourcefind.cn:5000/dcu/admin/base/paddlepaddle:2.3.2-centos7.6-dtk-22.10.1-py37-latest
+
+### 训练
+以icdar2015数据集训练
+
+检测模型
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
+
+识别模型
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml -o Global.pretrained_model=en_PP-OCRv3_rec_train/best_accuracy
+
+### 测试
+检测模型
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/eval.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./output/db_mv3/best_accuracy.pdparams
+
+识别模型
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/eval.py -c configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml -o Global.pretrained_model=./v3_en_mobile/best_accuracy.pdparams
+
+### 推理
+python3 tools/infer/predict_system.py --image_dir="./doc/imgs/" --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 --warmup=1
+
+## 性能和准确率数据
+
+检测模型测试
+| Model | Precision | Recall |
+| :------: | :------: |:------: |
+| det | 0.7054 | 0.7193  |
+
+识别模型测试
+| Model | Acc | 
+| :------: | :------: |
+| rec | 0.6490 | 
+
+推理
+| 图片 | 检测数/识别数 | 检测时间(ms) |识别时间(s) |
+| :------: | :------: |:------: |:------: |
+| 00006737.jpg | 38 | 0.1446 |0.1450 |
+| 00009282.jpg | 13 | 0.1412 |0.0898 |
+| 00015504.jpg | 74 | 0.1891 |0.2880 |
+| 00018069.jpg | 69 | 0.1790 |0.1325 |
+| 00056221.jpg | 19 | 0.1326 |0.1175 |
+| 00057937.jpg | 50 | 0.1504 |0.1546 |
+| 00059985.jpg | 24 | 0.1372 |0.1146 |
+| 00077949.jpg | 20 | 0.1347 |0.0838 |
+| 00111002.jpg | 33 | 0.1446 |0.1259 |
+| 00207393.jpg | 4  | 0.1296 |0.0408 |
+| 1.jpg        | 2  | 0.1227 |0.0290 |
+| 11.jpg       | 16 | 0.1227 |0.0817 |
+| 12.jpg       | 4  | 0.1129 |0.0284 |
+| french_0.jpg | 11 | 0.1191 |0.0493 |
+| ger_1.jpg    | 4  | 0.1127 |0.0277 |
+| ger_2.jpg    | 3  | 0.1121 |0.0278 |
+| japan_1.jpg  | 3  | 0.1113 |0.0277 |
+| japan_2.jpg  | 59 | 0.1551 |0.1133 |
+| korean_1.jpg | 6  | 0.1161 |0.0395 |
+| model_prod_flow_ch.png | 11 | 0.1182 |0.0502 |
+## 参考
+* [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
+
--- a/ch_PP-OCRv3_det_infer/inference.pdiparams
+++ b/ch_PP-OCRv3_det_infer/inference.pdiparams
--- a/ch_PP-OCRv3_det_infer/inference.pdiparams.info
+++ b/ch_PP-OCRv3_det_infer/inference.pdiparams.info
--- a/ch_PP-OCRv3_det_infer/inference.pdmodel
+++ b/ch_PP-OCRv3_det_infer/inference.pdmodel
--- a/ch_PP-OCRv3_rec_infer/inference.pdiparams
+++ b/ch_PP-OCRv3_rec_infer/inference.pdiparams
--- a/ch_PP-OCRv3_rec_infer/inference.pdiparams.info
+++ b/ch_PP-OCRv3_rec_infer/inference.pdiparams.info
--- a/ch_PP-OCRv3_rec_infer/inference.pdmodel
+++ b/ch_PP-OCRv3_rec_infer/inference.pdmodel
--- a/configs/cls/ch_PP-OCRv3/ch_PP-OCRv3_rotnet.yml
+++ b/configs/cls/ch_PP-OCRv3/ch_PP-OCRv3_rotnet.yml
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v3_rotnet
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model: null
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  save_res_path: ./output/rec/predicts_chinese_lite_v2.0.txt
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: L2
+    factor: 1.0e-05
+Architecture:
+  model_type: cls
+  algorithm: CLS
+  Transform: null
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Neck:
+  Head:
+    name: ClsHead
+    class_dim: 4
+
+Loss:
+  name: ClsLoss
+  main_indicator: acc
+
+PostProcess:
+  name: ClsPostProcess
+
+Metric:
+  name: ClsMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecAug:
+        use_tia: False
+    - RandAugment:
+    - SSLRotateResize:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys: ["image", "label"]
+  loader:
+    collate_fn: "SSLRotateCollate"
+    shuffle: true
+    batch_size_per_card: 32
+    drop_last: true
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - SSLRotateResize:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys: ["image", "label"]
+  loader:
+    collate_fn: "SSLRotateCollate"
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 64
+    num_workers: 8
+profiler_options: null
--- a/configs/cls/cls_mv3.yml
+++ b/configs/cls/cls_mv3.yml
+Global:
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/cls/mv3/
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 1000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  label_list: ['0','180']
+
+Architecture:
+  model_type: cls
+  algorithm: CLS
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.35
+    model_name: small
+  Neck:
+  Head:
+    name: ClsHead
+    class_dim: 2
+
+Loss:
+  name: ClsLoss
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: ClsPostProcess
+
+Metric:
+  name: ClsMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/cls
+    label_file_list:
+      - ./train_data/cls/train.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - ClsLabelEncode: # Class handling label
+      - RecAug:
+          use_tia: False
+      - RandAugment:
+      - ClsResizeImg:
+          image_shape: [3, 48, 192]
+      - KeepKeys:
+          keep_keys: ['image', 'label'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 512
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/cls
+    label_file_list:
+      - ./train_data/cls/test.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - ClsLabelEncode: # Class handling label
+      - ClsResizeImg:
+          image_shape: [3, 48, 192]
+      - KeepKeys:
+          keep_keys: ['image', 'label'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 512
+    num_workers: 4
--- a/configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml
+++ b/configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.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: 
+  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:
+    Teacher:
+      pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
+      freeze_params: true
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Transform:
+      Backbone:
+        name: ResNet
+        layers: 18
+      Neck:
+        name: DBFPN
+        out_channels: 256
+      Head:
+        name: DBHead
+        k: 50
+    Student:
+      pretrained:
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+    Student2:
+      pretrained:
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Transform:
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+    
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDilaDBLoss:
+      weight: 1.0
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      - ["Student2", "Teacher"]
+      key: maps
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - ["Student", "Student2"]
+      maps_name: "thrink_maps"
+      weight: 1.0
+      # act: None
+      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", "Teacher"]
+  # key: maps
+  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
--- a/configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_distill.yml
+++ b/configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_distill.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:
+      pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+    Teacher:
+      pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
+      freeze_params: true
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Transform:
+      Backbone:
+        name: ResNet
+        layers: 18
+      Neck:
+        name: DBFPN
+        out_channels: 256
+      Head:
+        name: DBHead
+        k: 50
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDilaDBLoss:
+      weight: 1.0
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: maps
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student"]
+      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"]
+  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
--- a/configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_dml.yml
+++ b/configs/det/ch_PP-OCRv2/ch_PP-OCRv2_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:
+      pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+    Teacher:
+      pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+      freeze_params: false
+      return_all_feats: false
+      model_type: det
+      algorithm: DB
+      Transform:
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: True
+      Neck:
+        name: DBFPN
+        out_channels: 96
+      Head:
+        name: DBHead
+        k: 50
+
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      maps_name: "thrink_maps"
+      weight: 1.0
+      # act: None
+      model_name_pairs: ["Student", "Teacher"]
+      key: maps
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Teacher"]
+      # 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", "Teacher"]
+  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
--- a/configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_student.yml
+++ b/configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_student.yml
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 400]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/student.pdparams
+  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:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 96
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  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: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+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
+      - 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
--- a/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml
+++ b/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_PP-OCR_v3_det/
+  save_epoch_step: 100
+  eval_batch_step:
+  - 0
+  - 400
+  cal_metric_during_train: false
+  pretrained_model: null
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  distributed: true
+
+Architecture:
+  name: DistillationModel
+  algorithm: Distillation
+  model_type: det
+  Models:
+    Student:
+      pretrained:
+      model_type: det
+      algorithm: DB
+      Transform: null
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: true
+      Neck:
+        name: RSEFPN
+        out_channels: 96
+        shortcut: True
+      Head:
+        name: DBHead
+        k: 50
+    Student2:
+      pretrained:
+      model_type: det
+      algorithm: DB
+      Transform: null
+      Backbone:
+        name: MobileNetV3
+        scale: 0.5
+        model_name: large
+        disable_se: true
+      Neck:
+        name: RSEFPN
+        out_channels: 96
+        shortcut: True
+      Head:
+        name: DBHead
+        k: 50
+    Teacher:
+      pretrained:
+      freeze_params: true
+      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:
+  - DistillationDilaDBLoss:
+      weight: 1.0
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      - ["Student2", "Teacher"]
+      key: maps
+      balance_loss: true
+      main_loss_type: DiceLoss
+      alpha: 5
+      beta: 10
+      ohem_ratio: 3
+  - DistillationDMLLoss:
+      model_name_pairs:
+      - ["Student", "Student2"]
+      maps_name: "thrink_maps"
+      weight: 1.0
+      model_name_pairs: ["Student", "Student2"]
+      key: maps
+  - DistillationDBLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Student2"]
+      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: 5.0e-05
+
+PostProcess:
+  name: DistillationDBPostProcess
+  model_name: ["Student"]
+  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:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - 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: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  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:
+    - 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
--- a/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_dml.yml
+++ b/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: None
+      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
--- a/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_student.yml
+++ b/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_student.yml
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_PP-OCR_V3_det/
+  save_epoch_step: 100
+  eval_batch_step:
+  - 0
+  - 400
+  cal_metric_during_train: false
+  pretrained_model: null
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./checkpoints/det_db/predicts_db.txt
+  distributed: true
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  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: 5.0e-05
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+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:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - 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: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - threshold_map
+        - threshold_mask
+        - shrink_map
+        - shrink_mask
+  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:
+        img_mode: BGR
+        channel_first: false
+    - DetLabelEncode: null
+    - DetResizeForTest: null
+    - NormalizeImage:
+        scale: 1./255.
+        mean:
+        - 0.485
+        - 0.456
+        - 0.406
+        std:
+        - 0.229
+        - 0.224
+        - 0.225
+        order: hwc
+    - ToCHWImage: null
+    - KeepKeys:
+        keep_keys:
+        - image
+        - shape
+        - polys
+        - ignore_tags
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 1
+    num_workers: 2
--- a/configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml
+++ b/configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.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:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 96
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  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: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+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
+      - 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
--- a/configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml
+++ b/configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_res18/
+  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/ResNet18_vd_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:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 18
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 256
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  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: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+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
+      - 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
--- a/configs/det/det_mv3_db.yml
+++ b/configs/det/det_mv3_db.yml
+Global:
+  use_gpu: true
+  use_xpu: false
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 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:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: DBFPN
+    out_channels: 256
+  Head:
+    name: DBHead
+    k: 50
+
+Loss:
+  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:
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.6
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+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
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [640, 640]
+          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: 16
+    num_workers: 8
+    use_shared_memory: False
+
+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
+      - DetResizeForSingle:
+      - 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: 8
+    use_shared_memory: False
--- a/configs/det/det_mv3_east.yml
+++ b/configs/det/det_mv3_east.yml
+Global:
+  use_gpu: true
+  epoch_num: 10000
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/east_mv3/
+  save_epoch_step: 1000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: 
+  save_res_path: ./output/det_east/predicts_east.txt
+
+Architecture:
+  model_type: det
+  algorithm: EAST
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: EASTFPN
+    model_name: small
+  Head:
+    name: EASTHead
+    model_name: small
+
+Loss:
+  name: EASTLoss
+  
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+  #  name: Cosine
+    learning_rate: 0.001
+  #  warmup_epoch: 0
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: EASTPostProcess
+  score_thresh: 0.8
+  cover_thresh: 0.1
+  nms_thresh: 0.2
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+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
+      - EASTProcessTrain:
+          image_shape: [512, 512]
+          background_ratio: 0.125
+          min_crop_side_ratio: 0.1
+          min_text_size: 10
+      - KeepKeys:
+          keep_keys: ['image', 'score_map', 'geo_map', 'training_mask'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 16
+    num_workers: 8
+
+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:
+          limit_side_len: 2400
+          limit_type: max
+      - 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
\ No newline at end of file