Rotate/configs/table/table_mv3.yml

Global:
  use_gpu: true
  epoch_num: 400
  log_smooth_window: 20
  print_batch_step: 5
  save_model_dir: ./output/table_mv3/
  save_epoch_step: 400
  # evaluation is run every 400 iterations after the 0th iteration
  eval_batch_step: [0, 400]
  cal_metric_during_train: True
  pretrained_model:
  checkpoints:
  save_inference_dir:
  use_visualdl: False
  infer_img: ppstructure/docs/table/table.jpg
  save_res_path: output/table_mv3
  # for data or label process
  character_dict_path: ppocr/utils/dict/table_structure_dict.txt
  character_type: en
  max_text_length: &max_text_length 500
  box_format: &box_format 'xyxy' # 'xywh', 'xyxy', 'xyxyxyxy'
  infer_mode: False
  amp_custom_black_list: ['matmul_v2','elementwise_add']

Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  clip_norm: 5.0
  lr:
    learning_rate: 0.001
  regularizer:
    name: 'L2'
    factor: 0.00000

Architecture:
  model_type: table
  algorithm: TableAttn
  Backbone:
    name: MobileNetV3
    scale: 1.0
    model_name: small
    disable_se: true
  Head:
    name: TableAttentionHead
    hidden_size: 256
    max_text_length: *max_text_length
    loc_reg_num: &loc_reg_num 4

Loss:
  name: TableAttentionLoss
  structure_weight: 100.0
  loc_weight: 10000.0

PostProcess:
  name: TableLabelDecode

Metric:
  name: TableMetric
  main_indicator: acc
  compute_bbox_metric: false # cost many time, set False for training

Train:
  dataset:
    name: PubTabDataSet
    data_dir: train_data/table/pubtabnet/train/
    label_file_list: [train_data/table/pubtabnet/PubTabNet_2.0.0_train.jsonl]
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - TableLabelEncode:
          learn_empty_box: False
          merge_no_span_structure: False
          replace_empty_cell_token: False
          loc_reg_num: *loc_reg_num
          max_text_length: *max_text_length
      - TableBoxEncode:
      - ResizeTableImage:
          max_len: 488
      - NormalizeImage:
          scale: 1./255.
          mean: [0.485, 0.456, 0.406]
          std: [0.229, 0.224, 0.225]
          order: 'hwc'
      - PaddingTableImage:
          size: [488, 488]
      - ToCHWImage:
      - KeepKeys:
          keep_keys: [ 'image', 'structure', 'bboxes', 'bbox_masks', 'shape' ]
  loader:
    shuffle: True
    batch_size_per_card: 48
    drop_last: True
    num_workers: 1

Eval:
  dataset:
    name: PubTabDataSet
    data_dir: train_data/table/pubtabnet/val/
    label_file_list: [train_data/table/pubtabnet/PubTabNet_2.0.0_val.jsonl]
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - TableLabelEncode:
          learn_empty_box: False
          merge_no_span_structure: False
          replace_empty_cell_token: False
          loc_reg_num: *loc_reg_num
          max_text_length: *max_text_length
      - TableBoxEncode:
      - ResizeTableImage:
          max_len: 488
      - NormalizeImage:
          scale: 1./255.
          mean: [0.485, 0.456, 0.406]
          std: [0.229, 0.224, 0.225]
          order: 'hwc'
      - PaddingTableImage:
          size: [488, 488]
      - ToCHWImage:
      - KeepKeys:
          keep_keys: [ 'image', 'structure', 'bboxes', 'bbox_masks', 'shape' ]
  loader:
    shuffle: False
    drop_last: False
    batch_size_per_card: 48
    num_workers: 1