scannet_seg-3d-20class.py

# dataset settings
dataset_type = 'ScanNetSegDataset'
data_root = './data/scannet/'
class_names = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table',
               'door', 'window', 'bookshelf', 'picture', 'counter', 'desk',
               'curtain', 'refrigerator', 'showercurtrain', 'toilet', 'sink',
               'bathtub', 'otherfurniture')
num_points = 8192
train_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='DEPTH',
        shift_height=False,
        use_color=True,
        load_dim=6,
        use_dim=[0, 1, 2, 3, 4, 5]),
    dict(
        type='LoadAnnotations3D',
        with_bbox_3d=False,
        with_label_3d=False,
        with_mask_3d=False,
        with_seg_3d=True),
    dict(
        type='PointSegClassMapping',
        valid_cat_ids=(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28,
                       33, 34, 36, 39)),
    dict(
        type='IndoorPatchPointSample',
        num_points=num_points,
        block_size=1.5,
        sample_rate=1.0,
        ignore_index=len(class_names),
        use_normalized_coord=True),
    dict(type='NormalizePointsColor', color_mean=None),
    dict(type='DefaultFormatBundle3D', class_names=class_names),
    dict(type='Collect3D', keys=['points', 'pts_semantic_mask'])
]
test_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='DEPTH',
        shift_height=False,
        use_color=True,
        load_dim=6,
        use_dim=[0, 1, 2, 3, 4, 5]),
    dict(type='NormalizePointsColor', color_mean=None),
    dict(type='DefaultFormatBundle3D', class_names=class_names),
    dict(type='Collect3D', 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)
# we need to load gt seg_mask!
eval_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='DEPTH',
        shift_height=False,
        use_color=True,
        load_dim=6,
        use_dim=[0, 1, 2, 3, 4, 5]),
    dict(
        type='LoadAnnotations3D',
        with_bbox_3d=False,
        with_label_3d=False,
        with_mask_3d=False,
        with_seg_3d=True),
    dict(
        type='PointSegClassMapping',
        valid_cat_ids=(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28,
                       33, 34, 36, 39)),
    dict(
        type='DefaultFormatBundle3D',
        with_label=False,
        class_names=class_names),
    dict(type='Collect3D', keys=['points', 'pts_semantic_mask'])
]

data = dict(
    samples_per_gpu=8,
    workers_per_gpu=4,
    train=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=data_root + 'scannet_infos_train.pkl',
        pipeline=train_pipeline,
        classes=class_names,
        test_mode=False,
        ignore_index=len(class_names),
        scene_idxs=data_root + 'seg_info/train_resampled_scene_idxs.npy',
        label_weight=data_root + 'seg_info/train_label_weight.npy'),
    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,
        ignore_index=len(class_names)),
    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,
        ignore_index=len(class_names)))

evaluation = dict(pipeline=eval_pipeline)