DocumentAIKit/configs/kie/vi_layoutxlm/ser_vi_layoutxlm_xfund_zh.yml

Global:
  use_gpu: True
  epoch_num: &epoch_num 200
  log_smooth_window: 10
  print_batch_step: 10
  save_model_dir: ./output/ser_vi_layoutxlm_xfund_zh
  save_epoch_step: 2000
  # evaluation is run every 10 iterations after the 0th iteration
  eval_batch_step: [ 0, 19 ]
  cal_metric_during_train: False
  save_inference_dir:
  use_visualdl: False
  seed: 2022
  infer_img: ppstructure/docs/kie/input/zh_val_42.jpg
  # if you want to predict using the groundtruth ocr info,
  # you can use the following config
  # infer_img: train_data/XFUND/zh_val/val.json
  # infer_mode: False

  save_res_path: ./output/ser/xfund_zh/res
  kie_rec_model_dir: 
  kie_det_model_dir:

Architecture:
  model_type: kie
  algorithm: &algorithm "LayoutXLM"
  Transform:
  Backbone:
    name: LayoutXLMForSer
    pretrained: True
    checkpoints:
    # one of base or vi
    mode: vi
    num_classes: &num_classes 7

Loss:
  name: VQASerTokenLayoutLMLoss
  num_classes: *num_classes
  key: "backbone_out"

Optimizer:
  name: AdamW
  beta1: 0.9
  beta2: 0.999
  lr:
    name: Linear
    learning_rate: 0.00005
    epochs: *epoch_num
    warmup_epoch: 2
  regularizer:
    name: L2
    factor: 0.00000
    
PostProcess:
  name: VQASerTokenLayoutLMPostProcess
  class_path: &class_path train_data/XFUND/class_list_xfun.txt

Metric:
  name: VQASerTokenMetric
  main_indicator: hmean

Train:
  dataset:
    name: SimpleDataSet
    data_dir: train_data/XFUND/zh_train/image
    label_file_list: 
      - train_data/XFUND/zh_train/train.json
    ratio_list: [ 1.0 ]
    transforms:
      - DecodeImage: # load image
          img_mode: RGB
          channel_first: False
      - VQATokenLabelEncode: # Class handling label
          contains_re: False
          algorithm: *algorithm
          class_path: *class_path
          use_textline_bbox_info: &use_textline_bbox_info True
          # one of [None, "tb-yx"]
          order_method: &order_method "tb-yx"
      - VQATokenPad:
          max_seq_len: &max_seq_len 512
          return_attention_mask: True
      - VQASerTokenChunk:
          max_seq_len: *max_seq_len
      - Resize:
          size: [224,224]
      - NormalizeImage:
          scale: 1
          mean: [ 123.675, 116.28, 103.53 ]
          std: [ 58.395, 57.12, 57.375 ]
          order: 'hwc'
      - ToCHWImage:
      - KeepKeys:
          keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
  loader:
    shuffle: True
    drop_last: False
    batch_size_per_card: 8
    num_workers: 4

Eval:
  dataset:
    name: SimpleDataSet
    data_dir: train_data/XFUND/zh_val/image
    label_file_list:
      - train_data/XFUND/zh_val/val.json
    transforms:
      - DecodeImage: # load image
          img_mode: RGB
          channel_first: False
      - VQATokenLabelEncode: # Class handling label
          contains_re: False
          algorithm: *algorithm
          class_path: *class_path
          use_textline_bbox_info: *use_textline_bbox_info
          order_method: *order_method
      - VQATokenPad:
          max_seq_len: *max_seq_len
          return_attention_mask: True
      - VQASerTokenChunk:
          max_seq_len: *max_seq_len
      - Resize:
          size: [224,224]
      - NormalizeImage:
          scale: 1
          mean: [ 123.675, 116.28, 103.53 ]
          std: [ 58.395, 57.12, 57.375 ]
          order: 'hwc'
      - ToCHWImage:
      - KeepKeys:
          keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
  loader:
    shuffle: False
    drop_last: False
    batch_size_per_card: 8
    num_workers: 4