-
Notifications
You must be signed in to change notification settings - Fork 16
/
Copy pathcreate_data.py
287 lines (254 loc) · 10.4 KB
/
create_data.py
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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
from os import path as osp
from tools.data_converter import indoor_converter as indoor
from tools.data_converter import kitti_converter as kitti
from tools.data_converter import lyft_converter as lyft_converter
from tools.data_converter import nuscenes_converter as nuscenes_converter
from tools.data_converter.create_gt_database import create_groundtruth_database
def kitti_data_prep(root_path, info_prefix, version, out_dir):
"""Prepare data related to Kitti dataset.
Related data consists of '.pkl' files recording basic infos,
2D annotations and groundtruth database.
Args:
root_path (str): Path of dataset root.
info_prefix (str): The prefix of info filenames.
version (str): Dataset version.
out_dir (str): Output directory of the groundtruth database info.
"""
kitti.create_kitti_info_file(root_path, info_prefix)
kitti.create_reduced_point_cloud(root_path, info_prefix)
info_train_path = osp.join(root_path, f'{info_prefix}_infos_train.pkl')
info_val_path = osp.join(root_path, f'{info_prefix}_infos_val.pkl')
info_trainval_path = osp.join(root_path,
f'{info_prefix}_infos_trainval.pkl')
info_test_path = osp.join(root_path, f'{info_prefix}_infos_test.pkl')
kitti.export_2d_annotation(root_path, info_train_path)
kitti.export_2d_annotation(root_path, info_val_path)
kitti.export_2d_annotation(root_path, info_trainval_path)
kitti.export_2d_annotation(root_path, info_test_path)
create_groundtruth_database(
'KittiDataset',
root_path,
info_prefix,
f'{out_dir}/{info_prefix}_infos_train.pkl',
relative_path=False,
mask_anno_path='instances_train.json',
with_mask=(version == 'mask'))
def nuscenes_data_prep(root_path,
info_prefix,
version,
dataset_name,
out_dir,
max_sweeps=10):
"""Prepare data related to nuScenes dataset.
Related data consists of '.pkl' files recording basic infos,
2D annotations and groundtruth database.
Args:
root_path (str): Path of dataset root.
info_prefix (str): The prefix of info filenames.
version (str): Dataset version.
dataset_name (str): The dataset class name.
out_dir (str): Output directory of the groundtruth database info.
max_sweeps (int): Number of input consecutive frames. Default: 10
"""
nuscenes_converter.create_nuscenes_infos(
root_path, info_prefix, version=version, max_sweeps=max_sweeps)
if version == 'v1.0-test':
info_test_path = osp.join(root_path, f'{info_prefix}_infos_test.pkl')
nuscenes_converter.export_2d_annotation(
root_path, info_test_path, version=version)
return
info_train_path = osp.join(root_path, f'{info_prefix}_infos_train.pkl')
info_val_path = osp.join(root_path, f'{info_prefix}_infos_val.pkl')
nuscenes_converter.export_2d_annotation(
root_path, info_train_path, version=version)
nuscenes_converter.export_2d_annotation(
root_path, info_val_path, version=version)
create_groundtruth_database(dataset_name, root_path, info_prefix,
f'{out_dir}/{info_prefix}_infos_train.pkl')
def lyft_data_prep(root_path, info_prefix, version, max_sweeps=10):
"""Prepare data related to Lyft dataset.
Related data consists of '.pkl' files recording basic infos.
Although the ground truth database and 2D annotations are not used in
Lyft, it can also be generated like nuScenes.
Args:
root_path (str): Path of dataset root.
info_prefix (str): The prefix of info filenames.
version (str): Dataset version.
max_sweeps (int, optional): Number of input consecutive frames.
Defaults to 10.
"""
lyft_converter.create_lyft_infos(
root_path, info_prefix, version=version, max_sweeps=max_sweeps)
def scannet_data_prep(root_path, info_prefix, out_dir, workers):
"""Prepare the info file for scannet dataset.
Args:
root_path (str): Path of dataset root.
info_prefix (str): The prefix of info filenames.
out_dir (str): Output directory of the generated info file.
workers (int): Number of threads to be used.
"""
indoor.create_indoor_info_file(
root_path, info_prefix, out_dir, workers=workers)
def s3dis_data_prep(root_path, info_prefix, out_dir, workers):
"""Prepare the info file for s3dis dataset.
Args:
root_path (str): Path of dataset root.
info_prefix (str): The prefix of info filenames.
out_dir (str): Output directory of the generated info file.
workers (int): Number of threads to be used.
"""
indoor.create_indoor_info_file(
root_path, info_prefix, out_dir, workers=workers)
def sunrgbd_data_prep(root_path, info_prefix, out_dir, workers):
"""Prepare the info file for sunrgbd dataset.
Args:
root_path (str): Path of dataset root.
info_prefix (str): The prefix of info filenames.
out_dir (str): Output directory of the generated info file.
workers (int): Number of threads to be used.
"""
indoor.create_indoor_info_file(
root_path, info_prefix, out_dir, workers=workers)
def waymo_data_prep(root_path,
info_prefix,
version,
out_dir,
workers,
max_sweeps=5):
"""Prepare the info file for waymo dataset.
Args:
root_path (str): Path of dataset root.
info_prefix (str): The prefix of info filenames.
out_dir (str): Output directory of the generated info file.
workers (int): Number of threads to be used.
max_sweeps (int): Number of input consecutive frames. Default: 5 \
Here we store pose information of these frames for later use.
"""
from tools.data_converter import waymo_converter as waymo
splits = ['training', 'validation', 'testing']
for i, split in enumerate(splits):
load_dir = osp.join(root_path, 'waymo_format', split)
if split == 'validation':
save_dir = osp.join(out_dir, 'kitti_format', 'training')
else:
save_dir = osp.join(out_dir, 'kitti_format', split)
converter = waymo.Waymo2KITTI(
load_dir,
save_dir,
prefix=str(i),
workers=workers,
test_mode=(split == 'test'))
converter.convert()
# Generate waymo infos
out_dir = osp.join(out_dir, 'kitti_format')
kitti.create_waymo_info_file(out_dir, info_prefix, max_sweeps=max_sweeps)
create_groundtruth_database(
'WaymoDataset',
out_dir,
info_prefix,
f'{out_dir}/{info_prefix}_infos_train.pkl',
relative_path=False,
with_mask=False)
parser = argparse.ArgumentParser(description='Data converter arg parser')
parser.add_argument('dataset', metavar='kitti', help='name of the dataset')
parser.add_argument(
'--root-path',
type=str,
default='./data/kitti',
help='specify the root path of dataset')
parser.add_argument(
'--version',
type=str,
default='v1.0',
required=False,
help='specify the dataset version, no need for kitti')
parser.add_argument(
'--max-sweeps',
type=int,
default=10,
required=False,
help='specify sweeps of lidar per example')
parser.add_argument(
'--out-dir',
type=str,
default='./data/kitti',
required='False',
help='name of info pkl')
parser.add_argument('--extra-tag', type=str, default='kitti')
parser.add_argument(
'--workers', type=int, default=4, help='number of threads to be used')
args = parser.parse_args()
if __name__ == '__main__':
if args.dataset == 'kitti':
kitti_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
version=args.version,
out_dir=args.out_dir)
elif args.dataset == 'nuscenes' and args.version != 'v1.0-mini':
# train_version = f'{args.version}-trainval'
# nuscenes_data_prep(
# root_path=args.root_path,
# info_prefix=args.extra_tag,
# version=train_version,
# dataset_name='NuScenesDataset',
# out_dir=args.out_dir,
# max_sweeps=args.max_sweeps)
test_version = f'{args.version}-test'
nuscenes_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
version=test_version,
dataset_name='NuScenesDataset',
out_dir=args.out_dir,
max_sweeps=args.max_sweeps)
elif args.dataset == 'nuscenes' and args.version == 'v1.0-mini':
train_version = f'{args.version}'
nuscenes_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
version=train_version,
dataset_name='NuScenesDataset',
out_dir=args.out_dir,
max_sweeps=args.max_sweeps)
elif args.dataset == 'lyft':
train_version = f'{args.version}-train'
lyft_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
version=train_version,
max_sweeps=args.max_sweeps)
test_version = f'{args.version}-test'
lyft_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
version=test_version,
max_sweeps=args.max_sweeps)
elif args.dataset == 'waymo':
waymo_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
version=args.version,
out_dir=args.out_dir,
workers=args.workers,
max_sweeps=args.max_sweeps)
elif args.dataset == 'scannet':
scannet_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
out_dir=args.out_dir,
workers=args.workers)
elif args.dataset == 's3dis':
s3dis_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
out_dir=args.out_dir,
workers=args.workers)
elif args.dataset == 'sunrgbd':
sunrgbd_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
out_dir=args.out_dir,
workers=args.workers)