mmdetection/configs/sparse_rcnn/sparse-rcnn_r50_fpn_300-proposals_crop-ms-480-800-3x_coco.py

_base_ = './sparse-rcnn_r50_fpn_ms-480-800-3x_coco.py'
num_proposals = 300
model = dict(
    rpn_head=dict(num_proposals=num_proposals),
    test_cfg=dict(
        _delete_=True, rpn=None, rcnn=dict(max_per_img=num_proposals)))

# augmentation strategy originates from DETR.
train_pipeline = [
    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='RandomFlip', prob=0.5),
    dict(
        type='RandomChoice',
        transforms=[[
            dict(
                type='RandomChoiceResize',
                scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
                        (608, 1333), (640, 1333), (672, 1333), (704, 1333),
                        (736, 1333), (768, 1333), (800, 1333)],
                keep_ratio=True)
        ],
                    [
                        dict(
                            type='RandomChoiceResize',
                            scales=[(400, 1333), (500, 1333), (600, 1333)],
                            keep_ratio=True),
                        dict(
                            type='RandomCrop',
                            crop_type='absolute_range',
                            crop_size=(384, 600),
                            allow_negative_crop=True),
                        dict(
                            type='RandomChoiceResize',
                            scales=[(480, 1333), (512, 1333), (544, 1333),
                                    (576, 1333), (608, 1333), (640, 1333),
                                    (672, 1333), (704, 1333), (736, 1333),
                                    (768, 1333), (800, 1333)],
                            keep_ratio=True)
                    ]]),
    dict(type='PackDetInputs')
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))