hv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py

# model settings
voxel_size = [0.16, 0.16, 4]
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
model = dict(
    type='VoxelNet',
    voxel_layer=dict(
        max_num_points=64,
        point_cloud_range=point_cloud_range,
        voxel_size=voxel_size,
        max_voxels=(12000, 20000)),
    voxel_encoder=dict(
        type='PillarFeatureNet',
        in_channels=4,
        feat_channels=[64],
        with_distance=False,
        voxel_size=voxel_size,
        point_cloud_range=point_cloud_range),
    middle_encoder=dict(
        type='PointPillarsScatter', in_channels=64, output_shape=[496, 432]),
    backbone=dict(
        type='SECOND',
        in_channels=64,
        layer_nums=[3, 5, 5],
        layer_strides=[2, 2, 2],
        out_channels=[64, 128, 256]),
    neck=dict(
        type='SECONDFPN',
        in_channels=[64, 128, 256],
        upsample_strides=[1, 2, 4],
        out_channels=[128, 128, 128]),
    bbox_head=dict(
        type='Anchor3DHead',
        num_classes=1,
        in_channels=384,
        feat_channels=384,
        use_direction_classifier=True,
        anchor_generator=dict(
            type='Anchor3DRangeGenerator',
            ranges=[[0, -39.68, -1.78, 69.12, 39.68, -1.78]],
            sizes=[[1.6, 3.9, 1.56]],
            rotations=[0, 1.57],
            reshape_out=True),
        diff_rad_by_sin=True,
        bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0),
        loss_dir=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)))
# model training and testing settings
train_cfg = dict(
    assigner=dict(
        type='MaxIoUAssigner',
        iou_calculator=dict(type='BboxOverlapsNearest3D'),
        pos_iou_thr=0.6,
        neg_iou_thr=0.45,
        min_pos_iou=0.45,
        ignore_iof_thr=-1),
    allowed_border=0,
    pos_weight=-1,
    debug=False)
test_cfg = dict(
    use_rotate_nms=True,
    nms_across_levels=False,
    nms_thr=0.01,
    score_thr=0.1,
    min_bbox_size=0,
    nms_pre=100,
    max_num=50)

# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
    data_root=data_root,
    info_path=data_root + 'kitti_dbinfos_train.pkl',
    rate=1.0,
    object_rot_range=[0.0, 0.0],
    prepare=dict(filter_by_difficulty=[-1], filter_by_min_points=dict(Car=5)),
    sample_groups=dict(Car=15),
    classes=class_names)

train_pipeline = [
    dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
    dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
    dict(type='ObjectSample', db_sampler=db_sampler),
    dict(
        type='ObjectNoise',
        num_try=100,
        loc_noise_std=[0.25, 0.25, 0.25],
        global_rot_range=[0.0, 0.0],
        rot_uniform_noise=[-0.15707963267, 0.15707963267]),
    dict(type='RandomFlip3D', flip_ratio=0.5),
    dict(
        type='GlobalRotScale',
        rot_uniform_noise=[-0.78539816, 0.78539816],
        scaling_uniform_noise=[0.95, 1.05]),
    dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
    dict(type='PointShuffle'),
    dict(type='DefaultFormatBundle3D', class_names=class_names),
    dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
    dict(type='LoadPointsFromFile', load_dim=4, use_dim=4),
    dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
    dict(
        type='DefaultFormatBundle3D',
        class_names=class_names,
        with_label=False),
    dict(type='Collect3D', keys=['points'])
]

data = dict(
    samples_per_gpu=6,
    workers_per_gpu=4,
    train=dict(
        type='RepeatDataset',
        times=2,
        dataset=dict(
            type=dataset_type,
            data_root=data_root,
            ann_file=data_root + 'kitti_infos_train.pkl',
            split='training',
            pts_prefix='velodyne_reduced',
            pipeline=train_pipeline,
            modality=input_modality,
            classes=class_names,
            test_mode=False)),
    val=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'kitti_infos_val.pkl',
        split='training',
        pts_prefix='velodyne_reduced',
        pipeline=test_pipeline,
        modality=input_modality,
        classes=class_names,
        test_mode=True),
    test=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'kitti_infos_val.pkl',
        split='training',
        pts_prefix='velodyne_reduced',
        pipeline=test_pipeline,
        modality=input_modality,
        classes=class_names,
        test_mode=True))
# optimizer
lr = 0.001  # max learning rate
optimizer = dict(
    type='AdamW',
    lr=lr,
    betas=(0.95, 0.99),  # the momentum is change during training
    weight_decay=0.01)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='cyclic',
    target_ratio=(10, 1e-4),
    cyclic_times=1,
    step_ratio_up=0.4)
momentum_config = dict(
    policy='cyclic',
    target_ratio=(0.85 / 0.95, 1),
    cyclic_times=1,
    step_ratio_up=0.4)
checkpoint_config = dict(interval=1)
evaluation = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 80
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/pp_secfpn_80e'
load_from = None
resume_from = None
workflow = [('train', 1)]