DBNet.yml

Global:
    use_gpu: true
    epoch_num: 15
    log_smooth_window: 20
    print_batch_step: 369
    save_model_dir: ./output/dbnet/
    save_epoch_step: 369
    eval_batch_step: 369
    cal_metric_during_train: False
    pretrained_model:
    checkpoints:
    save_inference_dir:
    use_visualdl: False
    infer_img:
    save_res_path: ./output/det_db/predicts_db.txt

Architecture:
    model_type: det
    algorithm: DB
    Transform:
    Backbone:
        name: ResNet
        layers: 18
        disable_se: True
    Neck:
        name: DBFPN
        out_channels: 256
    Head:
        name: DBHead
        k: 50

Loss:
    name: DBLoss
    balance_loss: true
    main_loss_type: DiceLoss
    alpha: 5
    beta: 10
    ohem_ratio: 3

Optimizer:
    name: Adam
    beta1: 0.9
    beta2: 0.999
    lr:
        name: Cosine
        learning_rate: 0.001
        warmup_epoch: 2
    regularizer:
        name: 'L2'
        factor: 0

PostProcess:
    name: DBPostProcess
    thresh: 0.3
    box_thresh: 0.6
    max_candidates: 1000
    unclip_ratio: 1.5

Metric:
    name: DetMetric
    main_indicator: hmean

Train:
    dataset:
        name: SimpleDataSet
        data_dir: /tmp/Pages
        label_file_list:
            - /tmp/Pages/PaddleOCR-Train.txt
        ratio_list: [1.0]
        transforms:
            - DecodeImage: # load image
                  img_mode: BGR
                  channel_first: False
            - DetLabelEncode: # Class handling label
            - IaaAugment:
                  augmenter_args:
                      - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
                      - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
            - EastRandomCropData:
                  size: [960, 960]
                  max_tries: 50
                  keep_ratio: true
            - MakeBorderMap:
                  shrink_ratio: 0.4
                  thresh_min: 0.3
                  thresh_max: 0.7
            - MakeShrinkMap:
                  shrink_ratio: 0.4
                  min_text_size: 8
            - 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',
                          'threshold_map',
                          'threshold_mask',
                          'shrink_map',
                          'shrink_mask',
                      ] # the order of the dataloader list
    loader:
        shuffle: True
        drop_last: False
        batch_size_per_card: 8
        num_workers: 0

Eval:
    dataset:
        name: SimpleDataSet
        data_dir: /tmp/Pages
        label_file_list:
            - /tmp/Pages/PaddleOCR-Validate.txt
        transforms:
            - DecodeImage: # load image
                  img_mode: BGR
                  channel_first: False
            - DetLabelEncode: # Class handling label
            - DetResizeForTest:
            #           image_shape: [736, 1280]
            - 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: 0