ppocrv3_rec_qat_dist.yaml 2.3 KB
Newer Older
Z
zhouzj 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 99 100 101 102 103 104 105 106 107 108 109
Global:
  model_dir: ch_PP-OCRv3_rec_infer
  model_filename: inference.pdmodel
  params_filename: inference.pdiparams
  model_type: rec
  algorithm: SVTR
  character_dict_path: ./ppocr_keys_v1.txt
  max_text_length: &max_text_length 25
  use_space_char: true

Distillation:
  alpha: [1.0, 1.0]
  loss: ['skd', 'l2']
  node:
   - ['linear_43.tmp_1']
   - ['linear_43.tmp_1']

Quantization:
  use_pact: true
  activation_bits: 8
  is_full_quantize: false
  onnx_format: True
  activation_quantize_type: moving_average_abs_max
  weight_quantize_type: channel_wise_abs_max
  not_quant_pattern:
  - skip_quant
  quantize_op_types:
  - conv2d
  - depthwise_conv2d
  weight_bits: 8

TrainConfig:
  epochs: 10
  eval_iter: 2000
  logging_iter: 100
  learning_rate: 
    type: CosineAnnealingDecay 
    learning_rate: 0.00005
  optimizer_builder:
    optimizer:
      type: Adam
    weight_decay: 5.0e-05

PostProcess:
  name: CTCLabelDecode 

Metric:
  name: RecMetric
  main_indicator: acc
  ignore_space: False 

Train:
  dataset:
    name: SimpleDataSet
    data_dir: ./train_data/icdar2015/text_localization/
    ext_op_transform_idx: 1
    label_file_list:
    - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
    transforms:
    - DecodeImage:
        img_mode: BGR
        channel_first: false
    - RecConAug:
        prob: 0.5
        ext_data_num: 2
        image_shape: [48, 320, 3]
        max_text_length: *max_text_length
    - RecAug:
    - MultiLabelEncode:
    - RecResizeImg:
        image_shape: [3, 48, 320]
    - KeepKeys:
        keep_keys:
        - image
        - label_ctc
        - label_sar
        - length
        - valid_ratio
  loader:
    shuffle: true
    batch_size_per_card: 64
    drop_last: true
    num_workers: 0

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:
        img_mode: BGR
        channel_first: false
    - MultiLabelEncode:
    - RecResizeImg:
        image_shape: [3, 48, 320]
    - KeepKeys:
        keep_keys:
        - image
        - label_ctc
        - label_sar
        - length
        - valid_ratio
  loader:
    shuffle: false
    drop_last: false
    batch_size_per_card: 64
    num_workers: 0