Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
nus_mono3d.py 4.56 KB
Newer Older
Jingwei Zhang's avatar
[Feature] Support new config type (#2608)  
Jingwei Zhang committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132 
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.transforms.processing import Resize
from mmengine.dataset.sampler import DefaultSampler
from mmengine.visualization.vis_backend import LocalVisBackend

from mmdet3d.datasets.nuscenes_dataset import NuScenesDataset
from mmdet3d.datasets.transforms.formating import Pack3DDetInputs
from mmdet3d.datasets.transforms.loading import (LoadAnnotations3D,
                                                 LoadImageFromFileMono3D)
from mmdet3d.datasets.transforms.transforms_3d import RandomFlip3D
from mmdet3d.evaluation.metrics.nuscenes_metric import NuScenesMetric
from mmdet3d.visualization.local_visualizer import Det3DLocalVisualizer

dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
class_names = [
    'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
    'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
metainfo = dict(classes=class_names)
# Input modality for nuScenes dataset, this is consistent with the submission
# format which requires the information in input_modality.
input_modality = dict(use_lidar=False, use_camera=True)

# 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/nuscenes/'

# 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

train_pipeline = [
    dict(type=LoadImageFromFileMono3D, backend_args=backend_args),
    dict(
        type=LoadAnnotations3D,
        with_bbox=True,
        with_label=True,
        with_attr_label=True,
        with_bbox_3d=True,
        with_label_3d=True,
        with_bbox_depth=True),
    dict(type=Resize, scale=(1600, 900), keep_ratio=True),
    dict(type=RandomFlip3D, flip_ratio_bev_horizontal=0.5),
    dict(
        type=Pack3DDetInputs,
        keys=[
            'img', 'gt_bboxes', 'gt_bboxes_labels', 'attr_labels',
            'gt_bboxes_3d', 'gt_labels_3d', 'centers_2d', 'depths'
        ]),
]

test_pipeline = [
    dict(type=LoadImageFromFileMono3D, backend_args=backend_args),
    dict(type=Resize, scale=(1600, 900), keep_ratio=True),
    dict(type=Pack3DDetInputs, keys=['img'])
]

train_dataloader = dict(
    batch_size=2,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type=DefaultSampler, shuffle=True),
    dataset=dict(
        type=NuScenesDataset,
        data_root=data_root,
        data_prefix=dict(
            pts='',
            CAM_FRONT='samples/CAM_FRONT',
            CAM_FRONT_LEFT='samples/CAM_FRONT_LEFT',
            CAM_FRONT_RIGHT='samples/CAM_FRONT_RIGHT',
            CAM_BACK='samples/CAM_BACK',
            CAM_BACK_RIGHT='samples/CAM_BACK_RIGHT',
            CAM_BACK_LEFT='samples/CAM_BACK_LEFT'),
        ann_file='nuscenes_infos_train.pkl',
        load_type='mv_image_based',
        pipeline=train_pipeline,
        metainfo=metainfo,
        modality=input_modality,
        test_mode=False,
        # we use box_type_3d='Camera' in monocular 3d
        # detection task
        box_type_3d='Camera',
        use_valid_flag=True,
        backend_args=backend_args))
val_dataloader = dict(
    batch_size=1,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type=DefaultSampler, shuffle=False),
    dataset=dict(
        type=NuScenesDataset,
        data_root=data_root,
        data_prefix=dict(
            pts='',
            CAM_FRONT='samples/CAM_FRONT',
            CAM_FRONT_LEFT='samples/CAM_FRONT_LEFT',
            CAM_FRONT_RIGHT='samples/CAM_FRONT_RIGHT',
            CAM_BACK='samples/CAM_BACK',
            CAM_BACK_RIGHT='samples/CAM_BACK_RIGHT',
            CAM_BACK_LEFT='samples/CAM_BACK_LEFT'),
        ann_file='nuscenes_infos_val.pkl',
        load_type='mv_image_based',
        pipeline=test_pipeline,
        modality=input_modality,
        metainfo=metainfo,
        test_mode=True,
        box_type_3d='Camera',
        use_valid_flag=True,
        backend_args=backend_args))
test_dataloader = val_dataloader

val_evaluator = dict(
    type=NuScenesMetric,
    data_root=data_root,
    ann_file=data_root + 'nuscenes_infos_val.pkl',
    metric='bbox',
    backend_args=backend_args)

test_evaluator = val_evaluator

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