Initial commit

configs/rec/multi_language/rec_devanagari_lite_train.yml

+Global:
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_devanagari_lite
+  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: null
+  character_dict_path: ppocr/utils/dict/devanagari_dict.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+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: rec
+  algorithm: CRNN
+  Transform: null
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride:
+    - 1
+    - 2
+    - 2
+    - 2
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTCHead
+    fc_decay: 1.0e-05
+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/devanagari_train.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecAug: null
+    - CTCLabelEncode: null
+    - RecResizeImg:
+        image_shape:
+        - 3
+        - 32
+        - 320
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: true
+    batch_size_per_card: 256
+    drop_last: true
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/
+    label_file_list:
+    - train_data/devanagari_val.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - CTCLabelEncode: null
+    - RecResizeImg:
+        image_shape:
+        - 3
+        - 32
+        - 320
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_en_number_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_en_number_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/en_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: True
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride: [1, 2, 2, 2]
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTCHead
+    fc_decay: 0.00001
+
+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: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_french_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_french_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model: 
+  checkpoints: 
+  save_inference_dir: 
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/french_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride: [1, 2, 2, 2]
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTCHead
+    fc_decay: 0.00001
+
+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: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_german_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_german_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/german_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride: [1, 2, 2, 2]
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTCHead
+    fc_decay: 0.00001
+
+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: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_japan_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_japan_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/japan_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride: [1, 2, 2, 2]
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTCHead
+    fc_decay: 0.00001
+
+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: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_korean_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_korean_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/korean_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride: [1, 2, 2, 2]
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTCHead
+    fc_decay: 0.00001
+
+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: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_latin_lite_train.yml

+Global:
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_latin_lite
+  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: null
+  character_dict_path: ppocr/utils/dict/latin_dict.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+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: rec
+  algorithm: CRNN
+  Transform: null
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride:
+    - 1
+    - 2
+    - 2
+    - 2
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTCHead
+    fc_decay: 1.0e-05
+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/latin_train.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecAug: null
+    - CTCLabelEncode: null
+    - RecResizeImg:
+        image_shape:
+        - 3
+        - 32
+        - 320
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: true
+    batch_size_per_card: 256
+    drop_last: true
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/
+    label_file_list:
+    - train_data/latin_val.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - CTCLabelEncode: null
+    - RecResizeImg:
+        image_shape:
+        - 3
+        - 32
+        - 320
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_multi_language_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_multi_language_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model: 
+  checkpoints: 
+  save_inference_dir: 
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: 
+  # Set the language of training, if set, select the default dictionary file
+  character_type: 
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: True
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride: [1, 2, 2, 2]
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTCHead
+    fc_decay: 0.00001
+
+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: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/
+    label_file_list: ["./train_data/val_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/rec_d28_can.yml

+Global:
+  use_gpu: True
+  epoch_num: 240
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/can/
+  save_epoch_step: 1
+  # evaluation is run every 1105 iterations (1 epoch)(batch_size = 8)
+  eval_batch_step: [0, 1105]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/datasets/crohme_demo/hme_00.jpg
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/latex_symbol_dict.txt
+  max_text_length: 36
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_can.txt
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  clip_norm_global: 100.0
+  lr:
+    name: TwoStepCosine
+    learning_rate: 0.01
+    warmup_epoch: 1
+  weight_decay: 0.0001
+
+Architecture:
+  model_type: rec
+  algorithm: CAN
+  in_channels: 1
+  Transform:
+  Backbone:
+    name: DenseNet 
+    growthRate: 24
+    reduction: 0.5
+    bottleneck: True
+    use_dropout: True
+    input_channel: 1 
+  Head:
+    name: CANHead
+    in_channel: 684
+    out_channel: 111
+    max_text_length: 36
+    ratio: 16
+    attdecoder:
+      is_train: True
+      input_size: 256
+      hidden_size: 256
+      encoder_out_channel: 684
+      dropout: True
+      dropout_ratio: 0.5
+      word_num: 111
+      counting_decoder_out_channel: 111
+      attention:
+        attention_dim: 512
+        word_conv_kernel: 1
+   
+Loss:
+  name: CANLoss
+
+PostProcess:
+  name: CANLabelDecode
+
+Metric:
+  name: CANMetric
+  main_indicator: exp_rate
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/CROHME/training/images/
+    label_file_list: ["./train_data/CROHME/training/labels.txt"]
+    transforms:
+      - DecodeImage:
+          channel_first: False
+      - NormalizeImage:
+          mean: [0,0,0]
+          std: [1,1,1]
+          order: 'hwc'
+      - GrayImageChannelFormat: 
+          inverse: True
+      - CANLabelEncode:
+          lower: False
+      - KeepKeys:
+          keep_keys: ['image', 'label']
+  loader:
+    shuffle: True
+    batch_size_per_card: 8
+    drop_last: False
+    num_workers: 4
+    collate_fn: DyMaskCollator
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/CROHME/evaluation/images/
+    label_file_list: ["./train_data/CROHME/evaluation/labels.txt"]
+    transforms: 
+      - DecodeImage:
+          channel_first: False
+      - NormalizeImage:
+          mean: [0,0,0]
+          std: [1,1,1]
+          order: 'hwc'
+      - GrayImageChannelFormat:
+          inverse: True
+      - CANLabelEncode:
+          lower: False
+      - KeepKeys:
+          keep_keys: ['image', 'label']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1
+    num_workers: 4
+    collate_fn: DyMaskCollator

configs/rec/rec_efficientb3_fpn_pren.yml

+Global:
+  use_gpu: True
+  epoch_num: 8
+  log_smooth_window: 20
+  print_batch_step: 5
+  save_model_dir: ./output/rec/pren_new
+  save_epoch_step: 3
+  # evaluation is run every 2000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 2000]
+  cal_metric_during_train: True
+  pretrained_model: 
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  # for data or label process
+  character_dict_path:
+  max_text_length: &max_text_length 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_pren.txt
+
+Optimizer:
+  name: Adadelta
+  lr:
+    name: Piecewise
+    decay_epochs: [2, 5, 7]
+    values: [0.5, 0.1, 0.01, 0.001]
+
+Architecture:
+  model_type: rec
+  algorithm: PREN
+  in_channels: 3
+  Backbone:
+    name: EfficientNetb3_PREN
+  Neck:
+    name: PRENFPN
+    n_r: 5
+    d_model: 384
+    max_len: *max_text_length
+    dropout: 0.1
+  Head:
+    name: PRENHead
+
+Loss:
+  name: PRENLoss
+
+PostProcess:
+  name: PRENLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage:
+          img_mode: BGR
+          channel_first: False
+      - PRENLabelEncode:
+      - RecAug:
+      - PRENResizeImg: 
+          image_shape: [64, 256]  # h,w
+      - KeepKeys:
+          keep_keys: ['image', 'label']
+  loader:
+    shuffle: True
+    batch_size_per_card: 128
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage:
+          img_mode: BGR
+          channel_first: False
+      - PRENLabelEncode:
+      - PRENResizeImg: 
+          image_shape: [64, 256]  # h,w
+      - KeepKeys:
+          keep_keys: ['image', 'label']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 64
+    num_workers: 8

configs/rec/rec_icdar15_train.yml

+Global:
+  use_gpu: true
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/ic15/
+  save_epoch_step: 3
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir: ./
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path: ppocr/utils/en_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_ic15.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 96
+  Head:
+    name: CTCHead
+    fc_decay: 0
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data/
+    label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+    use_shared_memory: False
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data
+    label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 4
+    use_shared_memory: False

configs/rec/rec_mtb_nrtr.yml

+Global:
+  use_gpu: True
+  epoch_num: 21
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/nrtr/
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path: ppocr/utils/EN_symbol_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_nrtr.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.99
+  clip_norm: 5.0
+  lr:
+    name: Cosine
+    learning_rate: 0.0005
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0.
+
+Architecture:
+  model_type: rec
+  algorithm: NRTR
+  in_channels: 1
+  Transform:
+  Backbone:
+    name: MTB
+    cnn_num: 2
+  Head:
+    name: Transformer
+    d_model: 512
+    num_encoder_layers: 6
+    beam_size: -1 # When Beam size is greater than 0, it means to use beam search when evaluation.
+    
+
+Loss:
+  name: CELoss
+  smoothing: True
+
+PostProcess:
+  name: NRTRLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - NRTRLabelEncode: # Class handling label
+      - GrayRecResizeImg:
+          image_shape: [100, 32] # W H
+          resize_type: PIL # PIL or OpenCV
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 512
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/evaluation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - NRTRLabelEncode: # Class handling label
+      - GrayRecResizeImg:
+          image_shape: [100, 32] # W H
+          resize_type: PIL # PIL or OpenCV
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 4
+    use_shared_memory: False

configs/rec/rec_mv3_none_bilstm_ctc.yml

+Global:
+  use_gpu: True
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/mv3_none_bilstm_ctc/
+  save_epoch_step: 3
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path:
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_mv3_none_bilstm_ctc.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 96
+  Head:
+    name: CTCHead
+    fc_decay: 0
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 4

configs/rec/rec_mv3_none_none_ctc.yml

+Global:
+  use_gpu: True
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/mv3_none_none_ctc/
+  save_epoch_step: 3
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path:
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_mv3_none_none_ctc.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: Rosetta
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: SequenceEncoder
+    encoder_type: reshape
+  Head:
+    name: CTCHead
+    fc_decay: 0.0004
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/rec_mv3_tps_bilstm_att.yml

+Global:
+  use_gpu: True
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/rec_mv3_tps_bilstm_att/
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th 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
+  # for data or label process
+  character_dict_path:
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_mv3_tps_bilstm_att.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: RARE
+  Transform:
+    name: TPS
+    num_fiducial: 20
+    loc_lr: 0.1
+    model_name: small
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn 
+    hidden_size: 96
+  Head:
+    name: AttentionHead  
+    hidden_size: 96
+    
+
+Loss:
+  name: AttentionLoss
+
+PostProcess:
+  name: AttnLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 1

configs/rec/rec_mv3_tps_bilstm_ctc.yml

+Global:
+  use_gpu: True
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/mv3_tps_bilstm_ctc/
+  save_epoch_step: 3
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path:
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_mv3_tps_bilstm_ctc.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: STARNet
+  Transform:
+    name: TPS
+    num_fiducial: 20
+    loc_lr: 0.1
+    model_name: small
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 96
+  Head:
+    name: CTCHead
+    fc_decay: 0.0004
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 4

configs/rec/rec_r31_robustscanner.yml

+Global:
+  use_gpu: true
+  epoch_num: 5
+  log_smooth_window: 20
+  print_batch_step: 20
+  save_model_dir: ./output/rec/rec_r31_robustscanner/
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path: ppocr/utils/dict90.txt
+  max_text_length: &max_text_length 40
+  infer_mode: False
+  use_space_char: False
+  rm_symbol: True
+  save_res_path: ./output/rec/predicts_robustscanner.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs: [3, 4]
+    values: [0.001, 0.0001, 0.00001] 
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: RobustScanner
+  Transform:
+  Backbone:
+    name: ResNet31
+    init_type: KaimingNormal
+  Head:
+    name: RobustScannerHead
+    enc_outchannles: 128
+    hybrid_dec_rnn_layers: 2
+    hybrid_dec_dropout: 0
+    position_dec_rnn_layers: 2
+    start_idx: 91
+    mask: True
+    padding_idx: 92
+    encode_value: False
+    max_text_length: *max_text_length
+
+Loss:
+  name: SARLoss
+
+PostProcess:
+  name: SARLabelDecode
+
+Metric:
+  name: RecMetric
+  is_filter: True
+
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SARLabelEncode: # Class handling label
+      - RobustScannerRecResizeImg:
+          image_shape: [3, 48, 48, 160] # h:48 w:[48,160]
+          width_downsample_ratio: 0.25
+          max_text_length: *max_text_length
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'valid_ratio', 'word_positons'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 64
+    drop_last: True
+    num_workers: 8
+    use_shared_memory: False
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/evaluation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SARLabelEncode: # Class handling label
+      - RobustScannerRecResizeImg:
+          image_shape: [3, 48, 48, 160]
+          max_text_length: *max_text_length
+          width_downsample_ratio: 0.25
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'valid_ratio', 'word_positons'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 64
+    num_workers: 4
+    use_shared_memory: False
+  

configs/rec/rec_r31_sar.yml

+Global:
+  use_gpu: true
+  epoch_num: 5
+  log_smooth_window: 20
+  print_batch_step: 20
+  save_model_dir: ./sar_rec
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: 
+  # for data or label process
+  character_dict_path: ppocr/utils/dict90.txt
+  max_text_length: 30
+  infer_mode: False
+  use_space_char: False
+  rm_symbol: True
+  save_res_path: ./output/rec/predicts_sar.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs: [3, 4]
+    values: [0.001, 0.0001, 0.00001] 
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: SAR
+  Transform:
+  Backbone:
+    name: ResNet31
+  Head:
+    name: SARHead
+
+Loss:
+  name: SARLoss
+
+PostProcess:
+  name: SARLabelDecode
+
+Metric:
+  name: RecMetric
+
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    label_file_list: ['./train_data/train_list.txt']
+    data_dir: ./train_data/
+    ratio_list: 1.0
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SARLabelEncode: # Class handling label
+      - SARRecResizeImg:
+          image_shape: [3, 48, 48, 160] # h:48 w:[48,160]
+          width_downsample_ratio: 0.25
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'valid_ratio'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 64
+    drop_last: True
+    num_workers: 8
+    use_shared_memory: False
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/evaluation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SARLabelEncode: # Class handling label
+      - SARRecResizeImg:
+          image_shape: [3, 48, 48, 160]
+          width_downsample_ratio: 0.25
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'valid_ratio'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 64
+    num_workers: 4
+    use_shared_memory: False
+  

configs/rec/rec_r32_gaspin_bilstm_att.yml

+Global:
+  use_gpu: True
+  epoch_num: 6
+  log_smooth_window: 50
+  print_batch_step: 50
+  save_model_dir: ./output/rec/rec_r32_gaspin_bilstm_att/
+  save_epoch_step: 3
+  # evaluation is run every 2000 iterations after the 4000th 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_en/word_10.png
+  # for data or label process
+  character_dict_path: ./ppocr/utils/dict/spin_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_r32_gaspin_bilstm_att.txt
+
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs: [3, 4, 5]
+    values: [0.001, 0.0003, 0.00009, 0.000027] 
+  clip_norm: 5
+
+Architecture:
+  model_type: rec
+  algorithm: SPIN
+  in_channels: 1
+  Transform:
+    name: GA_SPIN
+    offsets: True
+    default_type: 6
+    loc_lr: 0.1
+    stn: True
+  Backbone:
+    name: ResNet32
+    out_channels: 512
+  Neck:
+    name: SequenceEncoder
+    encoder_type: cascadernn 
+    hidden_size: 256
+    out_channels: [256, 512]
+    with_linear: True
+  Head:
+    name: SPINAttentionHead  
+    hidden_size: 256
+    
+
+Loss:
+  name: SPINAttentionLoss
+  ignore_index: 0
+
+PostProcess:
+  name: SPINLabelDecode
+  use_space_char: False
+
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  is_filter: True
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data/
+    label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SPINLabelEncode: # Class handling label
+      - SPINRecResizeImg:
+          image_shape: [100, 32]
+          interpolation : 2
+          mean: [127.5]
+          std: [127.5]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 8
+    drop_last: True
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data
+    label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SPINLabelEncode: # Class handling label
+      - SPINRecResizeImg:
+          image_shape: [100, 32]
+          interpolation : 2
+          mean: [127.5]
+          std: [127.5]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 2

configs/rec/rec_r34_vd_none_bilstm_ctc.yml

+Global:
+  use_gpu: true
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/r34_vd_none_bilstm_ctc/
+  save_epoch_step: 3
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path:
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_r34_vd_none_bilstm_ctc.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 34
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 256
+  Head:
+    name: CTCHead
+    fc_decay: 0
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 4