rec_r34_vd_tps_bilstm_att.yml 2.2 KB
Newer Older
L
LDOUBLEV 已提交
1 2 3 4 5 6 7 8 9 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
Global:
  use_gpu: true
  epoch_num: 400
  log_smooth_window: 20
  print_batch_step: 10
  save_model_dir: ./output/rec/b3_rare_r34_none_gru/
  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: doc/imgs_words/ch/word_1.jpg
  # for data or label process
  character_dict_path: 
  character_type: en
  max_text_length: 25
  infer_mode: False
  use_space_char: False


Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
    learning_rate: 0.0005
  regularizer:
    name: 'L2'
    factor: 0.00000

Architecture:
  model_type: rec
  algorithm: RARE
  Transform:
    name: TPS
    num_fiducial: 20
    loc_lr: 0.1
    model_name: large
  Backbone:
    name: ResNet  
    layers: 34
  Neck:
    name: SequenceEncoder
    encoder_type: rnn 
    hidden_size: 256 #96
  Head:
    name: AttentionHead  # AttentionHead
    hidden_size: 256 #
    l2_decay: 0.00001

Loss:
  name: AttentionLoss

PostProcess:
  name: AttnLabelDecode

Metric:
  name: RecMetric
  main_indicator: acc

Train:
  dataset:
    name: LMDBDateSet
    data_dir: ../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: LMDBDateSet
    data_dir: ../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: 8