Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
det_r50_vd_east.yml 2.5 KB
Newer Older
MissPenguin's avatar
add east & sast  
MissPenguin committed
1
2
3
4
5
6
7
8
9
10 
Global:
  use_gpu: true
  epoch_num: 10000
  log_smooth_window: 20
  print_batch_step: 2
  save_model_dir: ./output/east_r50_vd/
  save_epoch_step: 1000
  # evaluation is run every 5000 iterations after the 4000th iteration
  eval_batch_step: [4000, 5000]
  cal_metric_during_train: False
LDOUBLEV's avatar
fix comment  
LDOUBLEV committed
11 
  pretrained_model: ./pretrain_models/ResNet50_vd_pretrained
MissPenguin's avatar
add east & sast  
MissPenguin committed
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 
  checkpoints: 
  save_inference_dir:
  use_visualdl: False
  infer_img: 
  save_res_path: ./output/det_east/predicts_east.txt

Architecture:
  model_type: det
  algorithm: EAST
  Transform:
  Backbone:
    name: ResNet
    layers: 50
  Neck:
    name: EASTFPN
    model_name: large
  Head:
    name: EASTHead
    model_name: large

Loss:
  name: EASTLoss
  
Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
  #  name: Cosine
    learning_rate: 0.001
  #  warmup_epoch: 0
  regularizer:
    name: 'L2'
    factor: 0

PostProcess:
  name: EASTPostProcess
  score_thresh: 0.8
  cover_thresh: 0.1
  nms_thresh: 0.2

Metric:
  name: DetMetric
  main_indicator: hmean

Train:
  dataset:
    name: SimpleDataSet
    data_dir: ./train_data/icdar2015/text_localization/
    label_file_list:
      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
    ratio_list: [1.0]
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - DetLabelEncode: # Class handling label
      - EASTProcessTrain:
          image_shape: [512, 512]
          background_ratio: 0.125
          min_crop_side_ratio: 0.1
          min_text_size: 10
      - KeepKeys:
          keep_keys: ['image', 'score_map', 'geo_map', 'training_mask'] # dataloader will return list in this order
  loader:
    shuffle: True
    drop_last: False
    batch_size_per_card: 8
    num_workers: 8

Eval:
  dataset:
    name: SimpleDataSet
    data_dir: ./train_data/icdar2015/text_localization/
    label_file_list:
      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - DetLabelEncode: # Class handling label
      - DetResizeForTest:
          limit_side_len: 2400
          limit_type: max
      - NormalizeImage:
          scale: 1./255.
          mean: [0.485, 0.456, 0.406]
          std: [0.229, 0.224, 0.225]
          order: 'hwc'
      - ToCHWImage:
      - KeepKeys:
          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
  loader:
    shuffle: False
    drop_last: False
    batch_size_per_card: 1 # must be 1
    num_workers: 2