scannet_seg.py

# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.transforms.processing import TestTimeAug
from mmengine.dataset.sampler import DefaultSampler
from mmengine.visualization.vis_backend import LocalVisBackend

from mmdet3d.datasets.scannet_dataset import ScanNetSegDataset
from mmdet3d.datasets.transforms.formating import Pack3DDetInputs
from mmdet3d.datasets.transforms.loading import (LoadAnnotations3D,
                                                 LoadPointsFromFile,
                                                 NormalizePointsColor,
                                                 PointSegClassMapping)
from mmdet3d.datasets.transforms.transforms_3d import (IndoorPatchPointSample,
                                                       RandomFlip3D)
from mmdet3d.evaluation.metrics.seg_metric import SegMetric
from mmdet3d.models.segmentors.seg3d_tta import Seg3DTTAModel
from mmdet3d.visualization.local_visualizer import Det3DLocalVisualizer

# For ScanNet seg we usually do 20-class segmentation
class_names = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table',
               'door', 'window', 'bookshelf', 'picture', 'counter', 'desk',
               'curtain', 'refrigerator', 'showercurtrain', 'toilet', 'sink',
               'bathtub', 'otherfurniture')
metainfo = dict(classes=class_names)
dataset_type = 'ScanNetSegDataset'
data_root = 'data/scannet/'
input_modality = dict(use_lidar=True, use_camera=False)
data_prefix = dict(
    pts='points',
    pts_instance_mask='instance_mask',
    pts_semantic_mask='semantic_mask')

# Example to use different file client
# Method 1: simply set the data root and let the file I/O module
# automatically infer from prefix (not support LMDB and Memcache yet)

# data_root = 's3://openmmlab/datasets/detection3d/scannet/'

# Method 2: Use backend_args, file_client_args in versions before 1.1.0
# backend_args = dict(
#     backend='petrel',
#     path_mapping=dict({
#         './data/': 's3://openmmlab/datasets/detection3d/',
#          'data/': 's3://openmmlab/datasets/detection3d/'
#      }))
backend_args = None

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],
        backend_args=backend_args),
    dict(
        type=LoadAnnotations3D,
        with_bbox_3d=False,
        with_label_3d=False,
        with_mask_3d=False,
        with_seg_3d=True,
        backend_args=backend_args),
    dict(type=PointSegClassMapping),
    dict(
        type=IndoorPatchPointSample,
        num_points=num_points,
        block_size=1.5,
        ignore_index=len(class_names),
        use_normalized_coord=False,
        enlarge_size=0.2,
        min_unique_num=None),
    dict(type=NormalizePointsColor, color_mean=None),
    dict(type=Pack3DDetInputs, 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],
        backend_args=backend_args),
    dict(
        type=LoadAnnotations3D,
        with_bbox_3d=False,
        with_label_3d=False,
        with_mask_3d=False,
        with_seg_3d=True,
        backend_args=backend_args),
    dict(type=NormalizePointsColor, color_mean=None),
    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)
# 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],
        backend_args=backend_args),
    dict(type=NormalizePointsColor, color_mean=None),
    dict(type=Pack3DDetInputs, keys=['points'])
]
tta_pipeline = [
    dict(
        type=LoadPointsFromFile,
        coord_type='DEPTH',
        shift_height=False,
        use_color=True,
        load_dim=6,
        use_dim=[0, 1, 2, 3, 4, 5],
        backend_args=backend_args),
    dict(
        type=LoadAnnotations3D,
        with_bbox_3d=False,
        with_label_3d=False,
        with_mask_3d=False,
        with_seg_3d=True,
        backend_args=backend_args),
    dict(type=NormalizePointsColor, color_mean=None),
    dict(
        type=TestTimeAug,
        transforms=[[
            dict(
                type=RandomFlip3D,
                sync_2d=False,
                flip_ratio_bev_horizontal=0.,
                flip_ratio_bev_vertical=0.)
        ], [dict(type=Pack3DDetInputs, keys=['points'])]])
]

train_dataloader = dict(
    batch_size=8,
    num_workers=4,
    persistent_workers=True,
    sampler=dict(type=DefaultSampler, shuffle=True),
    dataset=dict(
        type=ScanNetSegDataset,
        data_root=data_root,
        ann_file='scannet_infos_train.pkl',
        metainfo=metainfo,
        data_prefix=data_prefix,
        pipeline=train_pipeline,
        modality=input_modality,
        ignore_index=len(class_names),
        scene_idxs=data_root + 'seg_info/train_resampled_scene_idxs.npy',
        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=ScanNetSegDataset,
        data_root=data_root,
        ann_file='scannet_infos_val.pkl',
        metainfo=metainfo,
        data_prefix=data_prefix,
        pipeline=test_pipeline,
        modality=input_modality,
        ignore_index=len(class_names),
        test_mode=True,
        backend_args=backend_args))
val_dataloader = test_dataloader

val_evaluator = dict(type=SegMetric)
test_evaluator = val_evaluator

vis_backends = [dict(type=LocalVisBackend)]
visualizer = dict(
    type=Det3DLocalVisualizer, vis_backends=vis_backends, name='visualizer')

tta_model = dict(type=Seg3DTTAModel)