hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car.py

_base_ = './hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py'

point_cloud_range = [0, -40, -3, 70.4, 40, 1]  # velodyne coordinates, x, y, z

model = dict(
    rpn_head=dict(
        type='PartA2RPNHead',
        num_classes=1,
        anchor_generator=dict(
            _delete_=True,
            type='Anchor3DRangeGenerator',
            ranges=[[0, -40.0, -1.78, 70.4, 40.0, -1.78]],
            sizes=[[1.6, 3.9, 1.56]],
            rotations=[0, 1.57],
            reshape_out=False)),
    roi_head=dict(
        num_classes=1,
        semantic_head=dict(num_classes=1),
        bbox_head=dict(num_classes=1)),
    # model training and testing settings
    train_cfg=dict(
        _delete_=True,
        rpn=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),
        rpn_proposal=dict(
            nms_pre=9000,
            nms_post=512,
            max_num=512,
            nms_thr=0.8,
            score_thr=0,
            use_rotate_nms=False),
        rcnn=dict(
            assigner=dict(  # for Car
                type='MaxIoUAssigner',
                iou_calculator=dict(type='BboxOverlaps3D', coordinate='lidar'),
                pos_iou_thr=0.55,
                neg_iou_thr=0.55,
                min_pos_iou=0.55,
                ignore_iof_thr=-1),
            sampler=dict(
                type='IoUNegPiecewiseSampler',
                num=128,
                pos_fraction=0.55,
                neg_piece_fractions=[0.8, 0.2],
                neg_iou_piece_thrs=[0.55, 0.1],
                neg_pos_ub=-1,
                add_gt_as_proposals=False,
                return_iou=True),
            cls_pos_thr=0.75,
            cls_neg_thr=0.25)),
    test_cfg=dict(
        rpn=dict(
            nms_pre=1024,
            nms_post=100,
            max_num=100,
            nms_thr=0.7,
            score_thr=0,
            use_rotate_nms=True),
        rcnn=dict(
            use_rotate_nms=True,
            use_raw_score=True,
            nms_thr=0.01,
            score_thr=0.1)))

# 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,
    prepare=dict(filter_by_difficulty=[-1], filter_by_min_points=dict(Car=5)),
    classes=class_names,
    sample_groups=dict(Car=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='ObjectNoise',
        num_try=100,
        translation_std=[1.0, 1.0, 0.5],
        global_rot_range=[0.0, 0.0],
        rot_range=[-0.78539816, 0.78539816]),
    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='ObjectNameFilter', classes=class_names),
    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)),
    val=dict(pipeline=test_pipeline, classes=class_names),
    test=dict(pipeline=test_pipeline, classes=class_names))

find_unused_parameters = True