rec_icdar15_train.yml 2.2 KB
Newer Older
T
tink2123 已提交
1 2 3 4 5 6 7 8 9 10 11 12
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:
T
tink2123 已提交
13
  save_inference_dir: ./
T
tink2123 已提交
14 15 16 17 18 19 20 21
  use_visualdl: False
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
  character_dict_path: ppocr/utils/ic15_dict.txt
  character_type: ch
  max_text_length: 25
  infer_mode: False
  use_space_char: False
littletomatodonkey's avatar
littletomatodonkey 已提交
22
  save_res_path: ./output/rec/predicts_ic15.txt
T
tink2123 已提交
23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38

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:
T
tink2123 已提交
39 40 41
    name: MobileNetV3
    scale: 0.5
    model_name: large
T
tink2123 已提交
42 43 44
  Neck:
    name: SequenceEncoder
    encoder_type: rnn
T
tink2123 已提交
45
    hidden_size: 96
T
tink2123 已提交
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62
  Head:
    name: CTCHead
    fc_decay: 0

Loss:
  name: CTCLoss

PostProcess:
  name: CTCLabelDecode

Metric:
  name: RecMetric
  main_indicator: acc

Train:
  dataset:
    name: SimpleDataSet
T
tink2123 已提交
63 64
    data_dir: ./train_data/ic15_data/
    label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
T
tink2123 已提交
65 66 67 68 69 70 71 72 73 74 75 76 77 78
    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
79
    use_shared_memory: False
T
tink2123 已提交
80 81 82 83

Eval:
  dataset:
    name: SimpleDataSet
T
tink2123 已提交
84 85
    data_dir: ./train_data/ic15_data
    label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
T
tink2123 已提交
86 87 88 89 90 91 92 93 94 95 96 97 98 99
    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
100
    use_shared_memory: False