configs/benchmark/hv_second_secfpn_4x8_80e_pcdet_kitti-3d-3class.py

# model settings
voxel_size = [0.05, 0.05, 0.1]
point_cloud_range = [0, -40, -3, 70.4, 40, 1]

model = dict(
    type='VoxelNet',
    data_preprocessor=dict(
        type='Det3DDataPreprocessor',
        voxel=True,
        voxel_layer=dict(
            max_num_points=5,
            point_cloud_range=point_cloud_range,
            voxel_size=voxel_size,
            max_voxels=(16000, 40000))),
    voxel_encoder=dict(type='HardSimpleVFE'),
    middle_encoder=dict(
        type='SparseEncoder',
        in_channels=4,
        sparse_shape=[41, 1600, 1408],
        order=('conv', 'norm', 'act')),
    backbone=dict(
        type='SECOND',
        in_channels=256,
        layer_nums=[5, 5],
        layer_strides=[1, 2],
        out_channels=[128, 256]),
    neck=dict(
        type='SECONDFPN',
        in_channels=[128, 256],
        upsample_strides=[1, 2],
        out_channels=[256, 256]),
    bbox_head=dict(
        type='Anchor3DHead',
        num_classes=3,
        in_channels=512,
        feat_channels=512,
        use_direction_classifier=True,
        anchor_generator=dict(
            type='Anchor3DRangeGenerator',
            ranges=[
                [0, -40.0, -0.6, 70.4, 40.0, -0.6],
                [0, -40.0, -0.6, 70.4, 40.0, -0.6],
                [0, -40.0, -1.78, 70.4, 40.0, -1.78],
            ],
            sizes=[[0.8, 0.6, 1.73], [1.76, 0.6, 1.73], [3.9, 1.6, 1.56]],
            rotations=[0, 1.57],
            reshape_out=False),
        diff_rad_by_sin=True,
        bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
        loss_cls=dict(
            type='mmdet.FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(
            type='mmdet.SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0),
        loss_dir=dict(
            type='mmdet.CrossEntropyLoss', use_sigmoid=False,
            loss_weight=0.2)),
    # model training and testing settings
    train_cfg=dict(
        assigner=[
            dict(  # for Pedestrian
                type='Max3DIoUAssigner',
                iou_calculator=dict(type='BboxOverlapsNearest3D'),
                pos_iou_thr=0.5,
                neg_iou_thr=0.35,
                min_pos_iou=0.35,
                ignore_iof_thr=-1),
            dict(  # for Cyclist
                type='Max3DIoUAssigner',
                iou_calculator=dict(type='BboxOverlapsNearest3D'),
                pos_iou_thr=0.5,
                neg_iou_thr=0.35,
                min_pos_iou=0.35,
                ignore_iof_thr=-1),
            dict(  # for Car
                type='Max3DIoUAssigner',
                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 = ['Pedestrian', 'Cyclist', 'Car']
metainfo = dict(classes=class_names)
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,
    prepare=dict(
        filter_by_difficulty=[-1],
        filter_by_min_points=dict(
            Car=5,
            Pedestrian=5,
            Cyclist=5,
        )),
    classes=class_names,
    sample_groups=dict(
        Car=20,
        Pedestrian=15,
        Cyclist=15,
    ))

train_pipeline = [
    dict(type='LoadPointsFromFile', coord_type='LIDAR', 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='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
    dict(
        type='GlobalRotScaleTrans',
        rot_range=[-0.78539816, 0.78539816],
        scale_ratio_range=[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='Pack3DDetInputs',
        keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
    dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4),
    dict(
        type='MultiScaleFlipAug3D',
        img_scale=(1333, 800),
        pts_scale_ratio=1,
        flip=False,
        transforms=[
            dict(
                type='GlobalRotScaleTrans',
                rot_range=[0, 0],
                scale_ratio_range=[1., 1.],
                translation_std=[0, 0, 0]),
            dict(type='RandomFlip3D'),
            dict(
                type='PointsRangeFilter', point_cloud_range=point_cloud_range)
        ]),
    dict(type='Pack3DDetInputs', keys=['points'])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
    dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4),
    dict(type='Pack3DDetInputs', keys=['points'])
]

train_dataloader = dict(
    batch_size=4,
    num_workers=4,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file='kitti_infos_train.pkl',
        data_prefix=dict(pts='training/velodyne_reduced'),
        pipeline=train_pipeline,
        modality=input_modality,
        test_mode=False,
        metainfo=metainfo,
        # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
        # and box_type_3d='Depth' in sunrgbd and scannet dataset.
        box_type_3d='LiDAR'))
val_dataloader = dict(
    batch_size=1,
    num_workers=1,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        data_prefix=dict(pts='training/velodyne_reduced'),
        ann_file='kitti_infos_val.pkl',
        pipeline=test_pipeline,
        modality=input_modality,
        test_mode=True,
        metainfo=metainfo,
        box_type_3d='LiDAR'))
test_dataloader = val_dataloader

val_evaluator = dict(
    type='KittiMetric',
    ann_file=data_root + 'kitti_infos_val.pkl',
    metric='bbox')
test_evaluator = val_evaluator

# optimizer
lr = 0.0003  # max learning rate
epoch_num = 80
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='AdamW', lr=lr, betas=(0.95, 0.99), weight_decay=0.01),
    clip_grad=dict(max_norm=10, norm_type=2))

# learning policy
param_scheduler = [
    dict(
        type='CosineAnnealingLR',
        T_max=epoch_num * 0.4,
        eta_min=lr * 10,
        begin=0,
        end=epoch_num * 0.4,
        by_epoch=True,
        convert_to_iter_based=True),
    dict(
        type='CosineAnnealingLR',
        T_max=epoch_num * 0.6,
        eta_min=lr * 1e-4,
        begin=epoch_num * 0.4,
        end=epoch_num * 1,
        by_epoch=True,
        convert_to_iter_based=True),
    dict(
        type='CosineAnnealingMomentum',
        T_max=epoch_num * 0.4,
        eta_min=0.85 / 0.95,
        begin=0,
        end=epoch_num * 0.4,
        by_epoch=True,
        convert_to_iter_based=True),
    dict(
        type='CosineAnnealingMomentum',
        T_max=epoch_num * 0.6,
        eta_min=1,
        begin=epoch_num * 0.4,
        end=epoch_num * 1,
        convert_to_iter_based=True)
]

train_cfg = dict(by_epoch=True, max_epochs=epoch_num, val_interval=50)
val_cfg = dict()
test_cfg = dict()
auto_scale_lr = dict(enable=False, base_batch_size=32)

default_scope = 'mmdet3d'

default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=50),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(type='CheckpointHook', interval=1),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    visualization=dict(type='Det3DVisualizationHook'))

custom_hooks = [
    dict(type='BenchmarkHook'),
]

env_cfg = dict(
    cudnn_benchmark=False,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'),
)

vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')
log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)

log_level = 'INFO'
load_from = None
resume = False
work_dir = './work_dirs/pp_secfpn_100e'