rec_mv3_tps_bilstm_att.yml 2.2 KB
Newer Older
L
LDOUBLEV 已提交
1
Global:
T
tink2123 已提交
2
  use_gpu: True
L
LDOUBLEV 已提交
3 4 5 6 7
  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
8
  # evaluation is run every 2000 iterations after the 0th iteration
L
LDOUBLEV 已提交
9 10 11 12 13 14 15 16 17 18 19 20 21
  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: 
  character_type: en
  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_mv3_tps_bilstm_att.txt
L
LDOUBLEV 已提交
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


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:
T
tink2123 已提交
68
    name: LMDBDataSet
W
WenmuZhou 已提交
69
    data_dir: ./train_data/data_lmdb_release/training/
L
LDOUBLEV 已提交
70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86
    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:
T
tink2123 已提交
87
    name: LMDBDataSet
W
WenmuZhou 已提交
88
    data_dir: ./train_data/data_lmdb_release/validation/
L
LDOUBLEV 已提交
89 90 91 92 93 94 95 96 97 98 99 100 101 102
    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