configs/_base_/det_pipelines/dbnet_pipeline.py

img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

train_pipeline_r18 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='LoadTextAnnotations',
        with_bbox=True,
        with_mask=True,
        poly2mask=False),
    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(
        type='ImgAug',
        args=[['Fliplr', 0.5],
              dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
    dict(type='EastRandomCrop', target_size=(640, 640)),
    dict(type='DBNetTargets', shrink_ratio=0.4),
    dict(type='Pad', size_divisor=32),
    dict(
        type='CustomFormatBundle',
        keys=['gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'],
        visualize=dict(flag=False, boundary_key='gt_shrink')),
    dict(
        type='Collect',
        keys=['img', 'gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'])
]

test_pipeline_1333_736 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1333, 736),  # used by Resize
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]

# for dbnet_r50dcnv2_fpnc
img_norm_cfg_r50dcnv2 = dict(
    mean=[122.67891434, 116.66876762, 104.00698793],
    std=[58.395, 57.12, 57.375],
    to_rgb=True)

train_pipeline_r50dcnv2 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='LoadTextAnnotations',
        with_bbox=True,
        with_mask=True,
        poly2mask=False),
    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
    dict(type='Normalize', **img_norm_cfg_r50dcnv2),
    dict(
        type='ImgAug',
        args=[['Fliplr', 0.5],
              dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
    dict(type='EastRandomCrop', target_size=(640, 640)),
    dict(type='DBNetTargets', shrink_ratio=0.4),
    dict(type='Pad', size_divisor=32),
    dict(
        type='CustomFormatBundle',
        keys=['gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'],
        visualize=dict(flag=False, boundary_key='gt_shrink')),
    dict(
        type='Collect',
        keys=['img', 'gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'])
]

test_pipeline_4068_1024 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(4068, 1024),  # used by Resize
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='Normalize', **img_norm_cfg_r50dcnv2),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]