qdtrack_faster-rcnn_r50_fpn_4e_dancetrack.py

_base_ = [
    './qdtrack_faster-rcnn_r50_fpn_4e_base.py',
    '../../_base_/datasets/dancetrack.py',
]
img_norm_cfg = dict(
    mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
    dict(type='LoadMultiImagesFromFile', to_float32=True),
    dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True),
    dict(
        type='SeqResize',
        img_scale=(1088, 1088),
        share_params=True,
        ratio_range=(0.8, 1.2),
        keep_ratio=True,
        bbox_clip_border=False),
    dict(type='SeqPhotoMetricDistortion', share_params=True),
    dict(
        type='SeqRandomCrop',
        share_params=False,
        crop_size=(1088, 1088),
        bbox_clip_border=False),
    dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
    dict(type='SeqNormalize', **img_norm_cfg),
    dict(type='SeqPad', size_divisor=32),
    dict(type='MatchInstances', skip_nomatch=True),
    dict(
        type='VideoCollect',
        keys=[
            'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices',
            'gt_instance_ids'
        ]),
    dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1088, 1088),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='VideoCollect', keys=['img'])
        ])
]
data = dict(
    train=dict(pipeline=train_pipeline),
    val=dict(pipeline=test_pipeline),
    test=dict(pipeline=test_pipeline))

# learning policy
total_epochs = 4
lr_config = dict(policy='step', step=[3])