Initial commit

configs/rec/PP-OCRv4/PP-OCRv4_mobile_rec_distillation.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_dkd_400w_svtr_ctc_lcnet_blank_dkd0.1/
+  save_epoch_step: 40
+  eval_batch_step:
+  - 0
+  - 2000
+  cal_metric_during_train: true
+  pretrained_model: null
+  checkpoints: ./output/rec_dkd_400w_svtr_ctc_lcnet_blank_dkd0.1/latest
+  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: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.txt
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+Architecture:
+  model_type: rec
+  name: DistillationModel
+  algorithm: Distillation
+  Models:
+    Teacher:
+      pretrained: 
+      freeze_params: true
+      return_all_feats: true
+      model_type: rec
+      algorithm: SVTR
+      Transform: null
+      Backbone:
+        name: SVTRNet
+        img_size:
+        - 48
+        - 320
+        out_char_num: 40
+        out_channels: 192
+        patch_merging: Conv
+        embed_dim:
+        - 64
+        - 128
+        - 256
+        depth:
+        - 3
+        - 6
+        - 3
+        num_heads:
+        - 2
+        - 4
+        - 8
+        mixer:
+        - Conv
+        - Conv
+        - Conv
+        - Conv
+        - Conv
+        - Conv
+        - Global
+        - Global
+        - Global
+        - Global
+        - Global
+        - Global
+        local_mixer:
+        - - 5
+          - 5
+        - - 5
+          - 5
+        - - 5
+          - 5
+        last_stage: false
+        prenorm: true
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 120
+                depth: 2
+                hidden_dims: 120
+                kernel_size: [1, 3]
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - NRTRHead:
+              nrtr_dim: 384
+              max_text_length: *max_text_length
+    Student:
+      pretrained: 
+      freeze_params: false
+      return_all_feats: true
+      model_type: rec
+      algorithm: SVTR
+      Transform: null
+      Backbone:
+        name: PPLCNetV3
+        scale: 0.95
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 120
+                depth: 2
+                hidden_dims: 120
+                kernel_size: [1, 3]
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - NRTRHead:
+              nrtr_dim: 384
+              max_text_length: *max_text_length
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDKDLoss:
+      weight: 0.1
+      model_name_pairs:
+      - - Student
+        - Teacher
+      key: head_out
+      multi_head: true
+      alpha: 1.0
+      beta: 2.0
+      dis_head: gtc
+      name: dkd
+  - DistillationCTCLoss:
+      weight: 1.0
+      model_name_list:
+      - Student
+      key: head_out
+      multi_head: true
+  - DistillationNRTRLoss:
+      weight: 1.0
+      smoothing: false
+      model_name_list:
+      - Student
+      key: head_out
+      multi_head: true
+  - DistillCTCLogits:
+      weight: 1.0
+      reduction: mean
+      model_name_pairs:
+      - - Student
+        - Teacher
+      key: head_out
+PostProcess:
+  name: DistillationCTCLabelDecode
+  model_name:
+  - Student
+  key: head_out
+  multi_head: true
+Metric:
+  name: DistillationMetric
+  base_metric_name: RecMetric
+  main_indicator: acc
+  key: Student
+  ignore_space: false
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list:
+    - ./train_data/train_list.txt
+    ratio_list:
+    - 1.0
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 8
+    use_shared_memory: true
+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:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4
+profiler_options: null

configs/rec/PP-OCRv4/PP-OCRv4_mobile_rec_fp32_ultra.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v4
+  save_epoch_step: 10
+  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/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.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_LCNet
+  Transform:
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.95
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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]
+        max_text_length: *max_text_length
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 192
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    drop_last: true
+    num_workers: 16
+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:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 16

configs/rec/PP-OCRv4/PP-OCRv4_server_rec.yml

+Global:
+  model_name: PP-OCRv4_server_rec # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v4_hgnet
+  save_epoch_step: 10
+  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/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.txt
+  d2s_train_image_shape: [3, 48, 320]
+
+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_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNet_small
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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]
+        max_text_length: *max_text_length
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 128
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv4/PP-OCRv4_server_rec_ampO2_ultra.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v4_hgnet
+  save_epoch_step: 10
+  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/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.txt
+  use_amp: True
+  amp_level: O2
+
+
+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_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNet_small
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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]
+        max_text_length: *max_text_length
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 256
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    drop_last: true
+    num_workers: 16
+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:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 16

configs/rec/PP-OCRv4/PP-OCRv4_server_rec_doc.yml

+Global:
+  model_name: PP-OCRv4_server_rec_doc # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v4_hgnet
+  save_epoch_step: 10
+  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/ppocrv4_doc_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.txt
+  d2s_train_image_shape: [3, 48, 320]
+
+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_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNet_small
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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]
+        max_text_length: *max_text_length
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 128
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv4/PP-OCRv4_server_rec_fp32_ultra.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v4_hgnet
+  save_epoch_step: 10
+  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/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.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_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNet_small
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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]
+        max_text_length: *max_text_length
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 256
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    drop_last: true
+    num_workers: 16
+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:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 16

configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_svtr_large.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/svtr_large/
+  save_epoch_step: 10
+  # evaluation is run every 2000 iterations after the 0th iteration
+  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/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 40
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_svtr_large.txt
+
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.99
+  epsilon: 1.0e-08
+  weight_decay: 0.05
+  no_weight_decay_name: norm pos_embed char_node_embed pos_node_embed char_pos_embed vis_pos_embed
+  one_dim_param_no_weight_decay: true
+  lr:
+    name: Cosine
+    learning_rate: 0.00025 # 8gpus 64bs
+    warmup_epoch: 5
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR_LCNet
+  Transform: null    
+  Backbone:
+    name: SVTRNet
+    img_size:
+    - 48
+    - 320
+    out_char_num: 40
+    out_channels: 512
+    patch_merging: Conv
+    embed_dim: [192, 256, 512]
+    depth: [6, 6, 9]
+    num_heads: [6, 8, 16]
+    mixer: ['Conv','Conv','Conv','Conv','Conv','Conv','Conv','Conv','Conv','Global','Global','Global','Global','Global','Global','Global','Global','Global','Global','Global','Global']
+    local_mixer: [[5, 5], [5, 5], [5, 5]]
+    last_stage: False
+    prenorm: True
+  Head:
+    name: MultiHead
+    use_pool: true
+    use_pos: true
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 256
+            depth: 2
+            hidden_dims: 256
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: true
+
+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
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 64
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - SVTRRecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv4/en_PP-OCRv4_mobile_rec.yml

+Global:
+  model_name: en_PP-OCRv4_mobile_rec  # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 50
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v4
+  save_epoch_step: 10
+  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/en_dict.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.txt
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.0005
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+Architecture:
+  model_type: rec
+  algorithm: SVTR_LCNet
+  Transform: null
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.95
+  Head:
+    name: MultiHead
+    head_list:
+    - CTCHead:
+        Neck:
+          name: svtr
+          dims: 120
+          depth: 2
+          hidden_dims: 120
+          kernel_size:
+          - 1
+          - 3
+          use_guide: true
+        Head:
+          fc_decay: 1.0e-05
+    - NRTRHead:
+        nrtr_dim: 384
+        max_text_length: 25
+Loss:
+  name: MultiLoss
+  loss_config_list:
+  - CTCLoss: null
+  - NRTRLoss: null
+PostProcess:
+  name: CTCLabelDecode
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: false
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+        max_text_length: 25
+    - RecAug: null
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales:
+    - - 320
+      - 32
+    - - 320
+      - 48
+    - - 320
+      - 64
+    first_bs: 96
+    fix_bs: false
+    divided_factor:
+    - 8
+    - 16
+    is_training: true
+  loader:
+    shuffle: true
+    batch_size_per_card: 96
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape:
+        - 3
+        - 48
+        - 320
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4
+profiler_options: null

configs/rec/PP-OCRv5/PP-OCRv5_mobile_rec.yml

+Global:
+  model_name: PP-OCRv5_mobile_rec # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 75
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/PP-OCRv5_mobile_rec
+  save_epoch_step: 10
+  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/ppocrv5_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv5.txt
+  d2s_train_image_shape: [3, 48, 320]
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.0005
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR_LCNet
+  Transform:
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.95
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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]
+        max_text_length: *max_text_length
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 128
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv5/PP-OCRv5_server_rec.yml

+Global:
+  model_name: PP-OCRv5_server_rec # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 75
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/PP-OCRv5_server_rec
+  save_epoch_step: 1
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  calc_epoch_interval: 1
+  pretrained_model: 
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ./ppocr/utils/dict/ppocrv5_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv5.txt
+  d2s_train_image_shape: [3, 48, 320]
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.0005
+    warmup_epoch: 1
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNetV2_B4
+    text_rec: True
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 128
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    drop_last: true
+    num_workers: 16
+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:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/SVTRv2/ch_RepSVTR_rec.yml

+Global:
+  model_name: ch_RepSVTR_rec  # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_RepSVTR_rec
+  save_epoch_step: 10
+  eval_batch_step: [0, 1000]
+  cal_metric_during_train: False
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_repsvtr.txt
+  d2s_train_image_shape: [3, 48, 320]
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1.e-8
+  weight_decay: 0.025
+  no_weight_decay_name: norm
+  one_dim_param_no_weight_decay: True
+  lr:
+    name: Cosine
+    learning_rate: 0.001 # 8gpus 192bs
+    warmup_epoch: 5
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: RepSVTR
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 256
+            depth: 2
+            hidden_dims: 256
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+          num_decoder_layers: 2
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 192
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/SVTRv2/ch_RepSVTR_rec_gtc.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_RepSVTR_rec_gtc
+  save_epoch_step: 10
+  eval_batch_step: [0, 1000]
+  cal_metric_during_train: False
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_repsvtr.txt
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1.e-8
+  weight_decay: 0.025
+  no_weight_decay_name: norm
+  one_dim_param_no_weight_decay: True
+  lr:
+    name: Cosine
+    learning_rate: 0.001 # 8gpus 192bs
+    warmup_epoch: 5
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: RepSVTR
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 256
+            depth: 2
+            hidden_dims: 256
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+          num_decoder_layers: 2
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 192
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/SVTRv2/ch_SVTRv2_rec.yml

+Global:
+  model_name: ch_SVTRv2_rec  # To use static model for inference.
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_SVTRv2_rec
+  save_epoch_step: 10
+  eval_batch_step: [0, 1000]
+  cal_metric_during_train: False
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_svrtv2.txt
+  d2s_train_image_shape: [3, 48, 320]
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1.e-8
+  weight_decay: 0.05
+  no_weight_decay_name: norm
+  one_dim_param_no_weight_decay: True
+  lr:
+    name: Cosine
+    learning_rate: 0.001 # 8gpus 192bs
+    warmup_epoch: 5
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: SVTRv2
+    use_pos_embed: False
+    dims: [128, 256, 384]
+    depths: [6, 6, 6]
+    num_heads: [4, 8, 12]
+    mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','Global','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
+    local_k: [[5, 5], [5, 5], [-1, -1]]
+    sub_k: [[2, 1], [2, 1], [-1, -1]]
+    last_stage: False
+    use_pool: True
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 256
+            depth: 2
+            hidden_dims: 256
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+          num_decoder_layers: 2
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 192
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/SVTRv2/ch_SVTRv2_rec_distillation.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_SVTRv2_rec_distill_lr00002/
+  save_epoch_step: 5
+  eval_batch_step:
+  - 0
+  - 1000
+  cal_metric_during_train: False
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_svtrv2_ch_distill.txt
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.99
+  epsilon: 1.e-8
+  weight_decay: 0.05
+  no_weight_decay_name: norm pos_embed patch_embed downsample
+  one_dim_param_no_weight_decay: True
+  lr:
+    name: Cosine
+    learning_rate: 0.0002 # 8gpus 192bs
+    warmup_epoch: 5
+Architecture:
+  model_type: rec
+  name: DistillationModel
+  algorithm: Distillation
+  Models:
+    Teacher:
+      pretrained: ./output/ch_SVTRv2_rec/best_accuracy
+      freeze_params: true
+      return_all_feats: true
+      model_type: rec
+      algorithm: SVTR_LCNet
+      Transform: null
+      Backbone:
+        name: SVTRv2
+        use_pos_embed: False
+        dims: [128, 256, 384]
+        depths: [6, 6, 6]
+        num_heads: [4, 8, 12]
+        mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','Global','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
+        local_k: [[5, 5], [5, 5], [-1, -1]]
+        sub_k: [[2, 1], [2, 1], [-1, -1]]
+        last_stage: False
+        use_pool: True
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 256
+                depth: 2
+                hidden_dims: 256
+                kernel_size: [1, 3]
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - NRTRHead:
+              nrtr_dim: 384
+              num_decoder_layers: 2
+              max_text_length: *max_text_length
+    Student:
+      pretrained: ./output/ch_RepSVTR_rec/best_accuracy
+      freeze_params: false
+      return_all_feats: true
+      model_type: rec
+      algorithm: SVTR_LCNet
+      Transform: null
+      Backbone:
+        name: RepSVTR
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 256
+                depth: 2
+                hidden_dims: 256
+                kernel_size: [1, 3]
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - NRTRHead:
+              nrtr_dim: 384
+              num_decoder_layers: 2
+              max_text_length: *max_text_length
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDKDLoss:
+      weight: 0.1
+      model_name_pairs:
+      - - Student
+        - Teacher
+      key: head_out
+      multi_head: true
+      alpha: 1.0
+      beta: 2.0
+      dis_head: gtc
+      name: dkd
+  - DistillationCTCLoss:
+      weight: 1.0
+      model_name_list:
+      - Student
+      key: head_out
+      multi_head: true
+  - DistillationNRTRLoss:
+      weight: 1.0
+      smoothing: false
+      model_name_list:
+      - Student
+      key: head_out
+      multi_head: true
+  - DistillCTCLogits:
+      weight: 1.0
+      reduction: mean
+      model_name_pairs:
+      - - Student
+        - Teacher
+      key: head_out
+PostProcess:
+  name: DistillationCTCLabelDecode
+  model_name:
+  - Student
+  key: head_out
+  multi_head: true
+Metric:
+  name: DistillationMetric
+  base_metric_name: RecMetric
+  main_indicator: acc
+  key: Student
+
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 192
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/SVTRv2/ch_SVTRv2_rec_gtc.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_SVTRv2_rec_gtc
+  save_epoch_step: 10
+  eval_batch_step: [0, 1000]
+  cal_metric_during_train: False
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_svrtv2.txt
+
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1.e-8
+  weight_decay: 0.05
+  no_weight_decay_name: norm
+  one_dim_param_no_weight_decay: True
+  lr:
+    name: Cosine
+    learning_rate: 0.001 # 8gpus 192bs
+    warmup_epoch: 5
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: SVTRv2
+    use_pos_embed: False
+    dims: [128, 256, 384]
+    depths: [6, 6, 6]
+    num_heads: [4, 8, 12]
+    mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','Global','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
+    local_k: [[5, 5], [5, 5], [-1, -1]]
+    sub_k: [[2, 1], [2, 1], [-1, -1]]
+    last_stage: False
+    use_pool: True
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 256
+            depth: 2
+            hidden_dims: 256
+            kernel_size: [1, 3]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: *max_text_length
+          num_decoder_layers: 2
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - NRTRLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 192
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/SVTRv2/ch_SVTRv2_rec_gtc_distill.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_SVTRv2_rec_gtc_distill_lr00002/
+  save_epoch_step: 5
+  eval_batch_step:
+  - 0
+  - 1000
+  cal_metric_during_train: False
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_svtrv2_gtc_distill.txt
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.99
+  epsilon: 1.e-8
+  weight_decay: 0.05
+  no_weight_decay_name: norm pos_embed patch_embed downsample
+  one_dim_param_no_weight_decay: True
+  lr:
+    name: Cosine
+    learning_rate: 0.0002 # 8gpus 192bs
+    warmup_epoch: 5
+Architecture:
+  model_type: rec
+  name: DistillationModel
+  algorithm: Distillation
+  Models:
+    Teacher:
+      pretrained: ./output/ch_SVTRv2_rec_gtc/best_accuracy
+      freeze_params: true
+      return_all_feats: true
+      model_type: rec
+      algorithm: SVTR_LCNet
+      Transform: null
+      Backbone:
+        name: SVTRv2
+        use_pos_embed: False
+        dims: [128, 256, 384]
+        depths: [6, 6, 6]
+        num_heads: [4, 8, 12]
+        mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','Global','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
+        local_k: [[5, 5], [5, 5], [-1, -1]]
+        sub_k: [[2, 1], [2, 1], [-1, -1]]
+        last_stage: False
+        use_pool: True
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 256
+                depth: 2
+                hidden_dims: 256
+                kernel_size: [1, 3]
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - NRTRHead:
+              nrtr_dim: 384
+              num_decoder_layers: 2
+              max_text_length: *max_text_length
+    Student:
+      pretrained: ./output/ch_RepSVTR_rec_gtc/best_accuracy
+      freeze_params: false
+      return_all_feats: true
+      model_type: rec
+      algorithm: SVTR_LCNet
+      Transform: null
+      Backbone:
+        name: repvit_svtr
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 256
+                depth: 2
+                hidden_dims: 256
+                kernel_size: [1, 3]
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - NRTRHead:
+              nrtr_dim: 384
+              num_decoder_layers: 2
+              max_text_length: *max_text_length
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDKDLoss:
+      weight: 0.1
+      model_name_pairs:
+      - - Student
+        - Teacher
+      key: head_out
+      multi_head: true
+      alpha: 1.0
+      beta: 2.0
+      dis_head: gtc
+      name: dkd
+  - DistillationCTCLoss:
+      weight: 1.0
+      model_name_list:
+      - Student
+      key: head_out
+      multi_head: true
+  - DistillationNRTRLoss:
+      weight: 1.0
+      smoothing: false
+      model_name_list:
+      - Student
+      key: head_out
+      multi_head: true
+  - DistillCTCLogits:
+      weight: 1.0
+      reduction: mean
+      model_name_pairs:
+      - - Student
+        - Teacher
+      key: head_out
+PostProcess:
+  name: DistillationCTCLabelDecode
+  model_name:
+  - Student
+  key: head_out
+  multi_head: true
+Metric:
+  name: DistillationMetric
+  base_metric_name: RecMetric
+  main_indicator: acc
+  key: Student
+
+
+Train:
+  dataset:
+    name: MultiScaleDataSet
+    ds_width: false
+    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
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  sampler:
+    name: MultiScaleSampler
+    scales: [[320, 32], [320, 48], [320, 64]]
+    first_bs: &bs 192
+    fix_bs: false
+    divided_factor: [8, 16] # w, h
+    is_training: True
+  loader:
+    shuffle: true
+    batch_size_per_card: *bs
+    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
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/UniMERNet.yaml

+Global:
+  model_name: UniMERNet # To use static model for inference.
+  use_gpu: True
+  epoch_num: 40
+  log_smooth_window: 10
+  print_batch_step: 10
+  save_model_dir: ./output/rec/unimernet/
+  save_epoch_step: 5
+  # evaluation is run every 37880 iterations after the 0th iteration
+  eval_batch_step: [0, 37880]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/datasets/pme_demo/0000013.png
+  infer_mode: False
+  use_space_char: False
+  rec_char_dict_path: &rec_char_dict_path ppocr/utils/dict/unimernet_tokenizer
+  input_size: &input_size [192, 672]
+  max_seq_len: &max_seq_len 1024
+  save_res_path: ./output/rec/predicts_unimernet.txt
+  allow_resize_largeImg: False
+  d2s_train_image_shape: [1,192,672]
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  weight_decay: 0.05
+  lr:
+    name: LinearWarmupCosine
+    learning_rate: 1e-4
+    start_lr: 1e-5
+    min_lr: 1e-8
+    warmup_steps: 5000
+
+Architecture:
+  model_type: rec
+  algorithm: UniMERNet
+  in_channels: 3
+  Transform:
+  Backbone:
+    name: DonutSwinModel
+    hidden_size : 1024
+    num_layers: 4
+    num_heads: [4, 8, 16, 32]
+    add_pooling_layer: True
+    use_mask_token: False
+  Head:
+    name: UniMERNetHead
+    max_new_tokens: 1536
+    decoder_start_token_id: 0
+    temperature: 0.2
+    do_sample: False
+    top_p: 0.95 
+    encoder_hidden_size: 1024
+    is_export: False
+    length_aware: True 
+
+Loss:
+  name: UniMERNetLoss
+
+PostProcess:
+  name:  UniMERNetDecode
+  rec_char_dict_path: *rec_char_dict_path
+
+Metric:
+  name: LaTeXOCRMetric
+  main_indicator:  exp_rate
+  cal_bleu_score: True
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/UniMERNet/
+    label_file_list: ["./train_data/UniMERNet/train_unimernet_1M.txt"]
+    transforms:
+      - UniMERNetImgDecode:
+          input_size: *input_size
+      - UniMERNetTrainTransform: 
+      - UniMERNetImageFormat:
+      - UniMERNetLabelEncode:
+          rec_char_dict_path: *rec_char_dict_path
+          max_seq_len: *max_seq_len
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'attention_mask']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 7
+    num_workers: 0
+    collate_fn: UniMERNetCollator
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/UniMERNet/UniMER-Test/cpe
+    label_file_list: ["./train_data/UniMERNet/test_unimernet_cpe.txt"]
+    transforms:
+      - UniMERNetImgDecode:
+          input_size: *input_size
+      - UniMERNetTestTransform:
+      - UniMERNetImageFormat:
+      - UniMERNetLabelEncode:
+          max_seq_len: *max_seq_len
+          rec_char_dict_path: *rec_char_dict_path
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'attention_mask']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 30
+    num_workers: 0
+    collate_fn: UniMERNetCollator

configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 800
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_mobile_pp-OCRv2
+  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/ppocr_keys_v1.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_mobile_pp-OCRv2.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs : [700]
+    values : [0.001, 0.0001]
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 2.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 64
+  Head:
+    name: CTCHead
+    mid_channels: 96
+    fc_decay: 0.00002
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  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:
+    - CTCLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 32, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    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
+    - CTCLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 32, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 8

configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 800
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_pp-OCRv2_distillation
+  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/ppocr_keys_v1.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_pp-OCRv2_distillation.txt
+  amp_custom_black_list: ['matmul','matmul_v2','elementwise_add']
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs : [700]
+    values : [0.001, 0.0001]
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 2.0e-05
+
+Architecture:
+  model_type: &model_type "rec"
+  name: DistillationModel
+  algorithm: Distillation
+  Models:
+    Teacher:
+      pretrained:
+      freeze_params: false
+      return_all_feats: true
+      model_type: *model_type
+      algorithm: CRNN
+      Transform:
+      Backbone:
+        name: MobileNetV1Enhance
+        scale: 0.5
+      Neck:
+        name: SequenceEncoder
+        encoder_type: rnn
+        hidden_size: 64
+      Head:
+        name: CTCHead
+        mid_channels: 96
+        fc_decay: 0.00002
+    Student:
+      pretrained:
+      freeze_params: false
+      return_all_feats: true
+      model_type: *model_type
+      algorithm: CRNN
+      Transform:
+      Backbone:
+        name: MobileNetV1Enhance
+        scale: 0.5
+      Neck:
+        name: SequenceEncoder
+        encoder_type: rnn
+        hidden_size: 64
+      Head:
+        name: CTCHead
+        mid_channels: 96
+        fc_decay: 0.00002
+  
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationCTCLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Teacher"]
+      key: head_out
+  - DistillationDMLLoss:
+      weight: 1.0
+      act: "softmax"
+      use_log: true
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: head_out
+  - DistillationDistanceLoss:
+      weight: 1.0
+      mode: "l2"
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: backbone_out
+
+PostProcess:
+  name: DistillationCTCLabelDecode
+  model_name: ["Student", "Teacher"]
+  key: head_out
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: RecMetric
+  main_indicator: acc
+  key: "Student"
+
+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:
+    - CTCLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 32, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_sections: 1
+    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
+    - CTCLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 32, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 8

configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_enhanced_ctc_loss.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 800
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_mobile_pp-OCRv2_enhanced_ctc_loss
+  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/ppocr_keys_v1.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_mobile_pp-OCRv2_enhanced_ctc_loss.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs : [700]
+    values : [0.001, 0.0001]
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 2.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 64
+  Head:
+    name: CTCHead
+    mid_channels: 96
+    fc_decay: 0.00002
+    return_feats: true
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - CTCLoss:
+      use_focal_loss: false
+      weight: 1.0
+  - CenterLoss:
+      weight: 0.05
+      num_classes: 6625
+      feat_dim: 96
+      center_file_path:
+  # you can also try to add ace loss on your own dataset
+  # - ACELoss:
+  #     weight: 0.1
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  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:
+    - CTCLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 32, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+        - label_ace
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    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
+    - CTCLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 32, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 8