spvcnn_w32_8xb2-amp-laser-polar-mix-3x_semantickitti.py

_base_ = [
    '../_base_/datasets/semantickitti.py', '../_base_/models/spvcnn.py',
    '../_base_/schedules/schedule-3x.py', '../_base_/default_runtime.py'
]

model = dict(data_preprocessor=dict(max_voxels=None))

train_pipeline = [
    dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4),
    dict(
        type='LoadAnnotations3D',
        with_bbox_3d=False,
        with_label_3d=False,
        with_seg_3d=True,
        seg_3d_dtype='np.int32',
        seg_offset=2**16,
        dataset_type='semantickitti'),
    dict(type='PointSegClassMapping'),
    dict(
        type='RandomChoice',
        transforms=[
            [
                dict(
                    type='LaserMix',
                    num_areas=[3, 4, 5, 6],
                    pitch_angles=[-25, 3],
                    pre_transform=[
                        dict(
                            type='LoadPointsFromFile',
                            coord_type='LIDAR',
                            load_dim=4,
                            use_dim=4),
                        dict(
                            type='LoadAnnotations3D',
                            with_bbox_3d=False,
                            with_label_3d=False,
                            with_seg_3d=True,
                            seg_3d_dtype='np.int32',
                            seg_offset=2**16,
                            dataset_type='semantickitti'),
                        dict(type='PointSegClassMapping')
                    ],
                    prob=1)
            ],
            [
                dict(
                    type='PolarMix',
                    instance_classes=[0, 1, 2, 3, 4, 5, 6, 7],
                    swap_ratio=0.5,
                    rotate_paste_ratio=1.0,
                    pre_transform=[
                        dict(
                            type='LoadPointsFromFile',
                            coord_type='LIDAR',
                            load_dim=4,
                            use_dim=4),
                        dict(
                            type='LoadAnnotations3D',
                            with_bbox_3d=False,
                            with_label_3d=False,
                            with_seg_3d=True,
                            seg_3d_dtype='np.int32',
                            seg_offset=2**16,
                            dataset_type='semantickitti'),
                        dict(type='PointSegClassMapping')
                    ],
                    prob=1)
            ],
        ],
        prob=[0.5, 0.5]),
    dict(
        type='GlobalRotScaleTrans',
        rot_range=[0., 6.28318531],
        scale_ratio_range=[0.95, 1.05],
        translation_std=[0, 0, 0],
    ),
    dict(type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask'])
]

train_dataloader = dict(dataset=dict(pipeline=train_pipeline))

optim_wrapper = dict(type='AmpOptimWrapper', loss_scale='dynamic')

default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=1))
randomness = dict(seed=0, deterministic=False, diff_rank_seed=True)
env_cfg = dict(cudnn_benchmark=True)