mmdeploy/tests/test_codebase/test_mmdet3d/data/model_cfg.py

# Copyright (c) OpenMMLab. All rights reserved.
voxel_size = [0.16, 0.16, 4]

model = dict(
    type='VoxelNet',
    voxel_layer=dict(
        max_num_points=32,  # max_points_per_voxel
        point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1],
        voxel_size=voxel_size,
        max_voxels=(16000, 40000)  # (training, testing) max_voxels
    ),
    voxel_encoder=dict(
        type='PillarFeatureNet',
        in_channels=4,
        feat_channels=[64],
        with_distance=False,
        voxel_size=voxel_size,
        point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]),
    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]),
    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),
    bbox_head=dict(
        type='Anchor3DHead',
        num_classes=3,
        in_channels=384,
        feat_channels=384,
        use_direction_classifier=True,
        anchor_generator=dict(
            type='AlignedAnchor3DRangeGenerator',
            ranges=[
                [0, -39.68, -0.6, 69.12, 39.68, -0.6],
                [0, -39.68, -0.6, 69.12, 39.68, -0.6],
                [0, -39.68, -1.78, 69.12, 39.68, -1.78],
            ],
            sizes=[[0.6, 0.8, 1.73], [0.6, 1.76, 1.73], [1.6, 3.9, 1.56]],
            rotations=[0, 1.57],
            reshape_out=False),
        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)))
point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1]
# dataset settings
data_root = 'tests/test_codebase/test_mmdet3d/data/kitti/'
dataset_type = 'KittiDataset'
class_names = ['Pedestrian', 'Cyclist', 'Car']
input_modality = dict(use_lidar=True, use_camera=False)
# PointPillars adopted a different sampling strategies among classes
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=10, Cyclist=10)),
    classes=class_names,
    sample_groups=dict(Car=15, Pedestrian=10, Cyclist=10))
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='ObjectNoise',
        num_try=100,
        translation_std=[0.25, 0.25, 0.25],
        global_rot_range=[0.0, 0.0],
        rot_range=[-0.15707963267, 0.15707963267]),
    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='DefaultFormatBundle3D', class_names=class_names),
    dict(type='Collect3D', 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='DefaultFormatBundle3D',
                class_names=class_names,
                with_label=False),
            dict(type='Collect3D', keys=['points'])
        ])
]
data = dict(
    train=dict(
        dataset=dict(
            pipeline=train_pipeline, classes=class_names,
            box_type_3d='LiDAR')),
    val=dict(pipeline=test_pipeline, classes=class_names, box_type_3d='LiDAR'),
    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,
        box_type_3d='LiDAR'))

point_cloud_range = [-51.2, -51.2, -5.0, 51.2, 51.2, 3.0]
centerpoint_model = dict(
    pts_voxel_layer=dict(
        max_num_points=20,
        voxel_size=voxel_size,
        max_voxels=(30000, 40000),
        point_cloud_range=point_cloud_range),
    pts_voxel_encoder=dict(
        type='PillarFeatureNet',
        in_channels=4,
        feat_channels=[64],
        with_distance=False,
        voxel_size=(0.2, 0.2, 8),
        norm_cfg=dict(type='BN1d', eps=1e-3, momentum=0.01),
        legacy=False),
    pts_middle_encoder=dict(
        type='PointPillarsScatter', in_channels=64, output_shape=(512, 512)),
    pts_backbone=dict(
        type='SECOND',
        in_channels=64,
        out_channels=[64, 128, 256],
        layer_nums=[3, 5, 5],
        layer_strides=[2, 2, 2],
        norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
        conv_cfg=dict(type='Conv2d', bias=False)),
    pts_neck=dict(
        type='SECONDFPN',
        in_channels=[64, 128, 256],
        out_channels=[128, 128, 128],
        upsample_strides=[0.5, 1, 2],
        norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
        upsample_cfg=dict(type='deconv', bias=False),
        use_conv_for_no_stride=True),
    pts_bbox_head=dict(
        type='CenterHead',
        in_channels=sum([128, 128, 128]),
        tasks=[
            dict(num_class=1, class_names=['car']),
            dict(num_class=2, class_names=['truck', 'construction_vehicle']),
            dict(num_class=2, class_names=['bus', 'trailer']),
            dict(num_class=1, class_names=['barrier']),
            dict(num_class=2, class_names=['motorcycle', 'bicycle']),
            dict(num_class=2, class_names=['pedestrian', 'traffic_cone']),
        ],
        common_heads=dict(
            reg=(2, 2), height=(1, 2), dim=(3, 2), rot=(2, 2), vel=(2, 2)),
        share_conv_channel=64,
        bbox_coder=dict(
            type='CenterPointBBoxCoder',
            post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
            pc_range=point_cloud_range[:2],
            max_num=500,
            score_threshold=0.1,
            out_size_factor=4,
            voxel_size=voxel_size[:2],
            code_size=9),
        separate_head=dict(
            type='SeparateHead', init_bias=-2.19, final_kernel=3),
        loss_cls=dict(type='GaussianFocalLoss', reduction='mean'),
        loss_bbox=dict(type='L1Loss', reduction='mean', loss_weight=0.25),
        norm_bbox=True),
    # model training and testing settings
    train_cfg=dict(
        pts=dict(
            grid_size=[512, 512, 1],
            voxel_size=voxel_size,
            out_size_factor=4,
            dense_reg=1,
            gaussian_overlap=0.1,
            max_objs=500,
            min_radius=2,
            code_weights=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2])),
    test_cfg=dict(
        pts=dict(
            post_center_limit_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
            max_per_img=500,
            max_pool_nms=False,
            min_radius=[4, 12, 10, 1, 0.85, 0.175],
            pc_range=point_cloud_range[:2],
            score_threshold=0.1,
            out_size_factor=4,
            voxel_size=voxel_size[:2],
            nms_type='circle',
            pre_max_size=1000,
            post_max_size=83,
            nms_thr=0.2)))
voxel_size = [0.25, 0.25, 8]
pointpillars_nus_model = dict(
    pts_voxel_layer=dict(
        max_num_points=64,
        point_cloud_range=[-50, -50, -5, 50, 50, 3],
        voxel_size=voxel_size,
        max_voxels=(30000, 40000)),
    pts_voxel_encoder=dict(
        type='HardVFE',
        in_channels=4,
        feat_channels=[64, 64],
        with_distance=False,
        voxel_size=voxel_size,
        with_cluster_center=True,
        with_voxel_center=True,
        point_cloud_range=[-50, -50, -5, 50, 50, 3],
        norm_cfg=dict(type='naiveSyncBN1d', eps=1e-3, momentum=0.01)),
    pts_middle_encoder=dict(
        type='PointPillarsScatter', in_channels=64, output_shape=[400, 400]),
    pts_backbone=dict(
        type='SECOND',
        in_channels=64,
        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
        layer_nums=[3, 5, 5],
        layer_strides=[2, 2, 2],
        out_channels=[64, 128, 256]),
    pts_neck=dict(
        type='FPN',
        norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
        act_cfg=dict(type='ReLU'),
        in_channels=[64, 128, 256],
        out_channels=256,
        start_level=0,
        num_outs=3),
    pts_bbox_head=dict(
        type='Anchor3DHead',
        num_classes=10,
        in_channels=256,
        feat_channels=256,
        use_direction_classifier=True,
        anchor_generator=dict(
            type='AlignedAnchor3DRangeGenerator',
            ranges=[[-50, -50, -1.8, 50, 50, -1.8]],
            scales=[1, 2, 4],
            sizes=[
                [2.5981, 0.8660, 1.],  # 1.5 / sqrt(3)
                [1.7321, 0.5774, 1.],  # 1 / sqrt(3)
                [1., 1., 1.],
                [0.4, 0.4, 1],
            ],
            custom_values=[0, 0],
            rotations=[0, 1.57],
            reshape_out=True),
        assigner_per_size=False,
        diff_rad_by_sin=True,
        dir_offset=-0.7854,  # -pi / 4
        bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=9),
        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=1.0),
        loss_dir=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)),
    # model training and testing settings
    train_cfg=dict(
        pts=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                iou_calculator=dict(type='BboxOverlapsNearest3D'),
                pos_iou_thr=0.6,
                neg_iou_thr=0.3,
                min_pos_iou=0.3,
                ignore_iof_thr=-1),
            allowed_border=0,
            code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2],
            pos_weight=-1,
            debug=False)),
    test_cfg=dict(
        pts=dict(
            use_rotate_nms=True,
            nms_across_levels=False,
            nms_pre=1000,
            nms_thr=0.2,
            score_thr=0.05,
            min_bbox_size=0,
            max_num=500)))