Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
waymoD5-mv3d-3class.py 4.6 KB
Newer Older
lianqing01's avatar
[Features] Support waymo challenge solution (#1716)  
lianqing01 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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148 
# dataset settings
# D3 in the config name means the whole dataset is divided into 3 folds
# We only use one fold for efficient experiments
dataset_type = 'WaymoDataset'
data_root = 'data/waymo/kitti_format/'
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.

class_names = ['Car', 'Pedestrian', 'Cyclist']
input_modality = dict(use_lidar=False, use_camera=True)
point_cloud_range = [-35.0, -75.0, -2, 75.0, 75.0, 4]

train_transforms = [
    dict(type='PhotoMetricDistortion3D'),
    dict(
        type='RandomResize3D',
        scale=(1248, 832),
        ratio_range=(0.95, 1.05),
        keep_ratio=True),
    dict(type='RandomCrop3D', crop_size=(720, 1080)),
    dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5, flip_box3d=False),
]

train_pipeline = [
    dict(type='LoadMultiViewImageFromFiles', to_float32=True),
    dict(
        type='LoadAnnotations3D',
        with_bbox=True,
        with_label=True,
        with_attr_label=False,
        with_bbox_3d=True,
        with_label_3d=True,
        with_bbox_depth=True),
    dict(type='MultiViewWrapper', transforms=train_transforms),
    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
    dict(type='ObjectNameFilter', classes=class_names),
    dict(
        type='Pack3DDetInputs', keys=[
            'img',
            'gt_bboxes_3d',
            'gt_labels_3d',
        ]),
]
test_transforms = [
    dict(
        type='RandomResize3D',
        scale=(1248, 832),
        ratio_range=(1., 1.),
        keep_ratio=True)
]
test_pipeline = [
    dict(type='LoadMultiViewImageFromFiles', to_float32=True),
    dict(type='MultiViewWrapper', transforms=test_transforms),
    dict(type='Pack3DDetInputs', keys=['img'])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
    dict(type='LoadMultiViewImageFromFiles', to_float32=True),
    dict(type='MultiViewWrapper', transforms=test_transforms),
    dict(type='Pack3DDetInputs', keys=['img'])
]
metainfo = dict(CLASSES=class_names)

train_dataloader = dict(
    batch_size=2,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file='waymo_infos_train.pkl',
        data_prefix=dict(
            pts='training/velodyne',
            CAM_FRONT='training/image_0',
            CAM_FRONT_RIGHT='training/image_1',
            CAM_FRONT_LEFT='training/image_2',
            CAM_SIDE_RIGHT='training/image_3',
            CAM_SIDE_LEFT='training/image_4',
        ),
        pipeline=train_pipeline,
        modality=input_modality,
        test_mode=False,
        metainfo=metainfo,
        box_type_3d='Lidar',
        load_interval=5,
    ))

val_dataloader = dict(
    batch_size=1,
    num_workers=1,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file='waymo_infos_val.pkl',
        data_prefix=dict(
            pts='training/velodyne',
            CAM_FRONT='training/image_0',
            CAM_FRONT_RIGHT='training/image_1',
            CAM_FRONT_LEFT='training/image_2',
            CAM_SIDE_RIGHT='training/image_3',
            CAM_SIDE_LEFT='training/image_4',
        ),
        pipeline=eval_pipeline,
        modality=input_modality,
        test_mode=True,
        metainfo=metainfo,
        box_type_3d='Lidar',
    ))

test_dataloader = dict(
    batch_size=1,
    num_workers=1,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file='waymo_infos_val.pkl',
        data_prefix=dict(
            pts='training/velodyne',
            CAM_FRONT='training/image_0',
            CAM_FRONT_RIGHT='training/image_1',
            CAM_FRONT_LEFT='training/image_2',
            CAM_SIDE_RIGHT='training/image_3',
            CAM_SIDE_LEFT='training/image_4',
        ),
        pipeline=eval_pipeline,
        modality=input_modality,
        test_mode=True,
        metainfo=metainfo,
        box_type_3d='Lidar',
    ))
val_evaluator = dict(
    type='WaymoMetric',
    ann_file='./data/waymo/kitti_format/waymo_infos_val.pkl',
    waymo_bin_file='./data/waymo/waymo_format/cam_gt.bin',
    data_root='./data/waymo/waymo_format',
    metric='LET_mAP')

test_evaluator = val_evaluator