rec_arabic_lite_train.yml 2.1 KB
Newer Older
T
tink2123 已提交
1 2 3 4 5 6 7
Global:
  use_gpu: true
  epoch_num: 500
  log_smooth_window: 20
  print_batch_step: 10
  save_model_dir: ./output/rec_arabic_lite
  save_epoch_step: 3
8 9
  # evaluation is run every 2000 iterations after the 0th iteration
  eval_batch_step: [0, 2000]
T
tink2123 已提交
10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110
  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/arabic_dict.txt
  character_type: arabic
  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/arabic_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/arabic_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