configs/detection/common/dataset/autoaug_coco_detection.py [19:94]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

train_pipeline = [
    dict(type='MMRandomFlip', flip_ratio=0.5),
    dict(
        type='MMAutoAugment',
        policies=[
            [
                dict(
                    type='MMResize',
                    img_scale=[(480, 1333), (512, 1333), (544, 1333),
                               (576, 1333), (608, 1333), (640, 1333),
                               (672, 1333), (704, 1333), (736, 1333),
                               (768, 1333), (800, 1333)],
                    multiscale_mode='value',
                    keep_ratio=True)
            ],
            [
                dict(
                    type='MMResize',
                    # The radio of all image in train dataset < 7
                    # follow the original impl
                    img_scale=[(400, 4200), (500, 4200), (600, 4200)],
                    multiscale_mode='value',
                    keep_ratio=True),
                dict(
                    type='MMRandomCrop',
                    crop_type='absolute_range',
                    crop_size=(384, 600),
                    allow_negative_crop=True),
                dict(
                    type='MMResize',
                    img_scale=[(480, 1333), (512, 1333), (544, 1333),
                               (576, 1333), (608, 1333), (640, 1333),
                               (672, 1333), (704, 1333), (736, 1333),
                               (768, 1333), (800, 1333)],
                    multiscale_mode='value',
                    override=True,
                    keep_ratio=True)
            ]
        ]),
    dict(type='MMNormalize', **img_norm_cfg),
    dict(type='MMPad', size_divisor=1),
    dict(type='DefaultFormatBundle'),
    dict(
        type='Collect',
        keys=['img', 'gt_bboxes', 'gt_labels'],
        meta_keys=('filename', 'ori_filename', 'ori_shape', 'ori_img_shape',
                   'img_shape', 'pad_shape', 'scale_factor', 'flip',
                   'flip_direction', 'img_norm_cfg'))
]
test_pipeline = [
    dict(
        type='MMMultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='MMResize', keep_ratio=True),
            dict(type='MMRandomFlip'),
            dict(type='MMNormalize', **img_norm_cfg),
            dict(type='MMPad', size_divisor=1),
            dict(type='ImageToTensor', keys=['img']),
            dict(
                type='Collect',
                keys=['img'],
                meta_keys=('filename', 'ori_filename', 'ori_shape',
                           'ori_img_shape', 'img_shape', 'pad_shape',
                           'scale_factor', 'flip', 'flip_direction',
                           'img_norm_cfg'))
        ])
]

train_dataset = dict(
    type='DetDataset',
    data_source=dict(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



configs/detection/common/dataset/autoaug_obj365_val5k_detection.py [69:144]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

train_pipeline = [
    dict(type='MMRandomFlip', flip_ratio=0.5),
    dict(
        type='MMAutoAugment',
        policies=[
            [
                dict(
                    type='MMResize',
                    img_scale=[(480, 1333), (512, 1333), (544, 1333),
                               (576, 1333), (608, 1333), (640, 1333),
                               (672, 1333), (704, 1333), (736, 1333),
                               (768, 1333), (800, 1333)],
                    multiscale_mode='value',
                    keep_ratio=True)
            ],
            [
                dict(
                    type='MMResize',
                    # The radio of all image in train dataset < 7
                    # follow the original impl
                    img_scale=[(400, 4200), (500, 4200), (600, 4200)],
                    multiscale_mode='value',
                    keep_ratio=True),
                dict(
                    type='MMRandomCrop',
                    crop_type='absolute_range',
                    crop_size=(384, 600),
                    allow_negative_crop=True),
                dict(
                    type='MMResize',
                    img_scale=[(480, 1333), (512, 1333), (544, 1333),
                               (576, 1333), (608, 1333), (640, 1333),
                               (672, 1333), (704, 1333), (736, 1333),
                               (768, 1333), (800, 1333)],
                    multiscale_mode='value',
                    override=True,
                    keep_ratio=True)
            ]
        ]),
    dict(type='MMNormalize', **img_norm_cfg),
    dict(type='MMPad', size_divisor=1),
    dict(type='DefaultFormatBundle'),
    dict(
        type='Collect',
        keys=['img', 'gt_bboxes', 'gt_labels'],
        meta_keys=('filename', 'ori_filename', 'ori_shape', 'ori_img_shape',
                   'img_shape', 'pad_shape', 'scale_factor', 'flip',
                   'flip_direction', 'img_norm_cfg'))
]
test_pipeline = [
    dict(
        type='MMMultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='MMResize', keep_ratio=True),
            dict(type='MMRandomFlip'),
            dict(type='MMNormalize', **img_norm_cfg),
            dict(type='MMPad', size_divisor=1),
            dict(type='ImageToTensor', keys=['img']),
            dict(
                type='Collect',
                keys=['img'],
                meta_keys=('filename', 'ori_filename', 'ori_shape',
                           'ori_img_shape', 'img_shape', 'pad_shape',
                           'scale_factor', 'flip', 'flip_direction',
                           'img_norm_cfg'))
        ])
]

train_dataset = dict(
    type='DetDataset',
    data_source=dict(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -