scannet-3d-18class.py

# dataset settings
dataset_type = 'ScanNetDataset'
data_root = './data/scannet/'
class_names = ('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
               'bookshelf', 'picture', 'counter', 'desk', 'curtain',
               'refrigerator', 'showercurtrain', 'toilet', 'sink', 'bathtub',
               'garbagebin')
train_pipeline = [
    dict(
        type='LoadPointsFromFile',
        shift_height=True,
        load_dim=6,
        use_dim=[0, 1, 2]),
    dict(
        type='LoadAnnotations3D',
        with_bbox_3d=True,
        with_label_3d=True,
        with_mask_3d=True,
        with_seg_3d=True),
    dict(
        type='PointSegClassMapping',
        valid_cat_ids=(3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34,
                       36, 39)),
    dict(type='IndoorPointSample', num_points=40000),
    dict(type='IndoorFlipData', flip_ratio_yz=0.5, flip_ratio_xz=0.5),
    dict(
        type='IndoorGlobalRotScaleTrans',
        shift_height=True,
        rot_range=[-1 / 36, 1 / 36],
        scale_range=None),
    dict(type='DefaultFormatBundle3D', class_names=class_names),
    dict(
        type='Collect3D',
        keys=[
            'points', 'gt_bboxes_3d', 'gt_labels_3d', 'pts_semantic_mask',
            'pts_instance_mask'
        ])
]
test_pipeline = [
    dict(
        type='LoadPointsFromFile',
        shift_height=True,
        load_dim=6,
        use_dim=[0, 1, 2]),
    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='IndoorPointSample', num_points=40000),
            dict(
                type='DefaultFormatBundle3D',
                class_names=class_names,
                with_label=False),
            dict(type='Collect3D', keys=['points'])
        ])
]

data = dict(
    samples_per_gpu=8,
    workers_per_gpu=4,
    train=dict(
        type='RepeatDataset',
        times=5,
        dataset=dict(
            type=dataset_type,
            data_root=data_root,
            ann_file=data_root + 'scannet_infos_train.pkl',
            pipeline=train_pipeline,
            filter_empty_gt=False,
            classes=class_names)),
    val=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'scannet_infos_val.pkl',
        pipeline=test_pipeline,
        classes=class_names,
        test_mode=True),
    test=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'scannet_infos_val.pkl',
        pipeline=test_pipeline,
        classes=class_names,
        test_mode=True))