Hugging Face's logo

Spaces:
topdu
/
OpenOCR-Demo
Running

App Files Community
OpenOCR-Demo
File size: 4,167 Bytes 
29f689c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
 
Global:
  device: gpu
  epoch_num: 20
  log_smooth_window: 20
  print_batch_step: 10
  output_dir: ./output/rec/svtrv2_lnconv_smtr_gtc_nodetach_smtr_long_infer
  save_epoch_step: 1
  # evaluation is run every 2000 iterations
  eval_batch_step: [0, 1000]
  eval_epoch_step: [0, 1]
  cal_metric_during_train: True
  pretrained_model:
  checkpoints:
  use_tensorboard: false
  infer_img:
  # for data or label process
  character_dict_path: &character_dict_path ./tools/utils/EN_symbol_dict.txt # 96en
  # ./tools/utils/ppocr_keys_v1.txt  # ch
  max_text_length: &max_text_length 25
  use_space_char: &use_space_char False
  save_res_path: ./output/rec/predicts_smtr.txt
  use_amp: True
  distributed: true

Optimizer:
  name: AdamW
  lr: 0.000325
  weight_decay: 0.05
  filter_bias_and_bn: True

LRScheduler:
  name: OneCycleLR
  warmup_epoch: 1.5 # pct_start 0.075*20 = 1.5ep
  cycle_momentum: False
Architecture:
  model_type: rec
  algorithm: BGPD
  in_channels: 3
  Transform:
  Encoder:
    name: SVTRv2LNConvTwo33
    use_pos_embed: False
    out_channels: 256
    dims: [128, 256, 384]
    depths: [6, 6, 6]
    num_heads: [4, 8, 12]
    mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','FGlobal','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
    local_k: [[5, 5], [5, 5], [-1, -1]]
    sub_k: [[1, 1], [2, 1], [-1, -1]]
    last_stage: false
    feat2d: True
  Decoder:
    name: GTCDecoder
    infer_gtc: True
    detach: False
    gtc_decoder:
      name: SMTRDecoder
      num_layer: 1
      ds: True
      max_len: *max_text_length
      next_mode: &next True
      sub_str_len: &subsl 5
      infer_aug: True
    ctc_decoder:
      name: RCTCDecoder

Loss:
  name: GTCLoss
  ctc_weight: 0.1
  gtc_loss:
    name: SMTRLoss

PostProcess:
  name: GTCLabelDecode
  gtc_label_decode:
    name: SMTRLabelDecode
    next_mode: *next
  character_dict_path: *character_dict_path
  use_space_char: *use_space_char
  only_gtc: True

Metric:
  name: RecGTCMetric
  main_indicator: acc
  is_filter: True

Train:
  dataset:
    name: RatioDataSetTVResize
    ds_width: True
    padding: false
    data_dir_list: ['../Union14M-L-LMDB-Filtered/filter_train_challenging',
    '../Union14M-L-LMDB-Filtered/filter_train_hard',
    '../Union14M-L-LMDB-Filtered/filter_train_medium',
    '../Union14M-L-LMDB-Filtered/filter_train_normal',
    '../Union14M-L-LMDB-Filtered/filter_train_easy',
    ]
    transforms:
      - DecodeImagePIL: # load image
          img_mode: RGB
      - PARSeqAugPIL:
      - SMTRLabelEncode: # Class handling label
          sub_str_len: *subsl
          character_dict_path: *character_dict_path
          use_space_char: *use_space_char
          max_text_length: *max_text_length
      - KeepKeys:
          keep_keys: ['image', 'label', 'label_subs', 'label_next', 'length_subs',
          'label_subs_pre', 'label_next_pre', 'length_subs_pre', 'length'] # dataloader will return list in this order
  sampler:
    name: RatioSampler
    scales: [[128, 32]] # w, h
    # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
    first_bs: &bs 256
    fix_bs: false
    divided_factor: [4, 16] # w, h
    is_training: True
  loader:
    shuffle: True
    batch_size_per_card: *bs
    drop_last: True
    max_ratio: &max_ratio 12
    num_workers: 4

Eval:
  dataset:
    name: SimpleDataSet
    data_dir: ../ltb/
    label_file_list: ['../ltb/ultra_long_70_list.txt']
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - GTCLabelEncode: # Class handling label
          gtc_label_encode:
            name: ARLabelEncode
          character_dict_path: *character_dict_path
          use_space_char: *use_space_char
          max_text_length: 200
      - SliceResize:
          image_shape: [3, 32, 128]
          padding: False
          max_ratio: 12
      - KeepKeys:
          keep_keys: ['image', 'label', 'length', 'ctc_label', 'ctc_length'] # dataloader will return list in this order
  loader:
    shuffle: False
    drop_last: False
    batch_size_per_card: 1
    num_workers: 2