configs/parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py

_base_ = [
    '../_base_/schedules/cyclic-40e.py', '../_base_/default_runtime.py',
    '../_base_/models/parta2.py'
]

point_cloud_range = [0, -40, -3, 70.4, 40, 1]

# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
input_modality = dict(use_lidar=True, use_camera=False)
backend_args = None
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=12, Pedestrian=6, Cyclist=6),
    points_loader=dict(
        type='LoadPointsFromFile',
        coord_type='LIDAR',
        load_dim=4,
        use_dim=4,
        backend_args=backend_args),
    backend_args=backend_args)
train_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='LIDAR',
        load_dim=4,
        use_dim=4,
        backend_args=backend_args),
    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='Pack3DDetInputs',
        keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='LIDAR',
        load_dim=4,
        use_dim=4,
        backend_args=backend_args),
    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,
        backend_args=backend_args),
    dict(type='Pack3DDetInputs', keys=['points'])
]
train_dataloader = dict(
    batch_size=2,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type='RepeatDataset',
        times=2,
        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,
            metainfo=dict(classes=class_names),
            box_type_3d='LiDAR',
            test_mode=False,
            backend_args=backend_args)))
test_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,
        ann_file='kitti_infos_val.pkl',
        data_prefix=dict(pts='training/velodyne_reduced'),
        pipeline=test_pipeline,
        modality=input_modality,
        metainfo=dict(classes=class_names),
        box_type_3d='LiDAR',
        test_mode=True,
        backend_args=backend_args))
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,
        ann_file='kitti_infos_val.pkl',
        data_prefix=dict(pts='training/velodyne_reduced'),
        pipeline=eval_pipeline,
        modality=input_modality,
        metainfo=dict(classes=class_names),
        box_type_3d='LiDAR',
        test_mode=True,
        backend_args=backend_args))
val_evaluator = dict(
    type='KittiMetric',
    ann_file=data_root + 'kitti_infos_val.pkl',
    metric='bbox',
    backend_args=backend_args)
test_evaluator = val_evaluator
# Part-A2 uses a different learning rate from what SECOND uses.
optim_wrapper = dict(optimizer=dict(lr=0.001))
find_unused_parameters = True

# Default setting for scaling LR automatically
#   - `enable` means enable scaling LR automatically
#       or not by default.
#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=16)