File size: 16,804 Bytes
34d1f8b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 |
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
from os import path as osp
from mmengine import print_log
from tools.dataset_converters import indoor_converter as indoor
from tools.dataset_converters import kitti_converter as kitti
from tools.dataset_converters import lyft_converter as lyft_converter
from tools.dataset_converters import nuscenes_converter as nuscenes_converter
from tools.dataset_converters import semantickitti_converter
from tools.dataset_converters.create_gt_database import (
GTDatabaseCreater, create_groundtruth_database)
from tools.dataset_converters.update_infos_to_v2 import update_pkl_infos
def kitti_data_prep(root_path,
info_prefix,
version,
out_dir,
with_plane=False):
"""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.
with_plane (bool, optional): Whether to use plane information.
Default: False.
"""
kitti.create_kitti_info_file(root_path, info_prefix, with_plane)
kitti.create_reduced_point_cloud(root_path, info_prefix)
info_train_path = osp.join(out_dir, f'{info_prefix}_infos_train.pkl')
info_val_path = osp.join(out_dir, f'{info_prefix}_infos_val.pkl')
info_trainval_path = osp.join(out_dir, f'{info_prefix}_infos_trainval.pkl')
info_test_path = osp.join(out_dir, f'{info_prefix}_infos_test.pkl')
update_pkl_infos('kitti', out_dir=out_dir, pkl_path=info_train_path)
update_pkl_infos('kitti', out_dir=out_dir, pkl_path=info_val_path)
update_pkl_infos('kitti', out_dir=out_dir, pkl_path=info_trainval_path)
update_pkl_infos('kitti', out_dir=out_dir, pkl_path=info_test_path)
create_groundtruth_database(
'KittiDataset',
root_path,
info_prefix,
f'{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, optional): 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(out_dir, f'{info_prefix}_infos_test.pkl')
update_pkl_infos('nuscenes', out_dir=out_dir, pkl_path=info_test_path)
return
info_train_path = osp.join(out_dir, f'{info_prefix}_infos_train.pkl')
info_val_path = osp.join(out_dir, f'{info_prefix}_infos_val.pkl')
update_pkl_infos('nuscenes', out_dir=out_dir, pkl_path=info_train_path)
update_pkl_infos('nuscenes', out_dir=out_dir, pkl_path=info_val_path)
create_groundtruth_database(dataset_name, root_path, info_prefix,
f'{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)
if version == 'v1.01-test':
info_test_path = osp.join(root_path, f'{info_prefix}_infos_test.pkl')
update_pkl_infos('lyft', out_dir=root_path, pkl_path=info_test_path)
elif version == 'v1.01-train':
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')
update_pkl_infos('lyft', out_dir=root_path, pkl_path=info_train_path)
update_pkl_infos('lyft', out_dir=root_path, pkl_path=info_val_path)
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)
info_train_path = osp.join(out_dir, f'{info_prefix}_infos_train.pkl')
info_val_path = osp.join(out_dir, f'{info_prefix}_infos_val.pkl')
info_test_path = osp.join(out_dir, f'{info_prefix}_infos_test.pkl')
update_pkl_infos('scannet', out_dir=out_dir, pkl_path=info_train_path)
update_pkl_infos('scannet', out_dir=out_dir, pkl_path=info_val_path)
update_pkl_infos('scannet', out_dir=out_dir, pkl_path=info_test_path)
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)
splits = [f'Area_{i}' for i in [1, 2, 3, 4, 5, 6]]
for split in splits:
filename = osp.join(out_dir, f'{info_prefix}_infos_{split}.pkl')
update_pkl_infos('s3dis', out_dir=out_dir, pkl_path=filename)
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)
info_train_path = osp.join(out_dir, f'{info_prefix}_infos_train.pkl')
info_val_path = osp.join(out_dir, f'{info_prefix}_infos_val.pkl')
update_pkl_infos('sunrgbd', out_dir=out_dir, pkl_path=info_train_path)
update_pkl_infos('sunrgbd', out_dir=out_dir, pkl_path=info_val_path)
def waymo_data_prep(root_path,
info_prefix,
version,
out_dir,
workers,
max_sweeps=10,
only_gt_database=False,
save_senor_data=False,
skip_cam_instances_infos=False):
"""Prepare waymo dataset. There are 3 steps as follows:
Step 1. Extract camera images and lidar point clouds from waymo raw
data in '*.tfreord' and save as kitti format.
Step 2. Generate waymo train/val/test infos and save as pickle file.
Step 3. Generate waymo ground truth database (point clouds within
each 3D bounding box) for data augmentation in training.
Steps 1 and 2 will be done in Waymo2KITTI, and step 3 will be done in
GTDatabaseCreater.
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, optional): Number of input consecutive frames.
Default to 10. Here we store ego2global information of these
frames for later use.
only_gt_database (bool, optional): Whether to only generate ground
truth database. Default to False.
save_senor_data (bool, optional): Whether to skip saving
image and lidar. Default to False.
skip_cam_instances_infos (bool, optional): Whether to skip
gathering cam_instances infos in Step 2. Default to False.
"""
from tools.dataset_converters import waymo_converter as waymo
if version == 'v1.4':
splits = [
'training', 'validation', 'testing',
'testing_3d_camera_only_detection'
]
elif version == 'v1.4-mini':
splits = ['training', 'validation']
else:
raise NotImplementedError(f'Unsupported Waymo version {version}!')
out_dir = osp.join(out_dir, 'kitti_format')
if not only_gt_database:
for i, split in enumerate(splits):
load_dir = osp.join(root_path, 'waymo_format', split)
if split == 'validation':
save_dir = osp.join(out_dir, 'training')
else:
save_dir = osp.join(out_dir, split)
converter = waymo.Waymo2KITTI(
load_dir,
save_dir,
prefix=str(i),
workers=workers,
test_mode=(split
in ['testing', 'testing_3d_camera_only_detection']),
info_prefix=info_prefix,
max_sweeps=max_sweeps,
split=split,
save_senor_data=save_senor_data,
save_cam_instances=not skip_cam_instances_infos)
converter.convert()
if split == 'validation':
converter.merge_trainval_infos()
from tools.dataset_converters.waymo_converter import \
create_ImageSets_img_ids
create_ImageSets_img_ids(out_dir, splits)
GTDatabaseCreater(
'WaymoDataset',
out_dir,
info_prefix,
f'{info_prefix}_infos_train.pkl',
relative_path=False,
with_mask=False,
num_worker=workers).create()
print_log('Successfully preparing Waymo Open Dataset')
def semantickitti_data_prep(info_prefix, out_dir):
"""Prepare the info file for SemanticKITTI dataset.
Args:
info_prefix (str): The prefix of info filenames.
out_dir (str): Output directory of the generated info file.
"""
semantickitti_converter.create_semantickitti_info_file(
info_prefix, out_dir)
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(
'--with-plane',
action='store_true',
help='Whether to use plane information for kitti.')
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')
parser.add_argument(
'--only-gt-database',
action='store_true',
help='''Whether to only generate ground truth database.
Only used when dataset is NuScenes or Waymo!''')
parser.add_argument(
'--skip-cam_instances-infos',
action='store_true',
help='''Whether to skip gathering cam_instances infos.
Only used when dataset is Waymo!''')
parser.add_argument(
'--skip-saving-sensor-data',
action='store_true',
help='''Whether to skip saving image and lidar.
Only used when dataset is Waymo!''')
args = parser.parse_args()
if __name__ == '__main__':
from mmengine.registry import init_default_scope
init_default_scope('mmdet3d')
if args.dataset == 'kitti':
if args.only_gt_database:
create_groundtruth_database(
'KittiDataset',
args.root_path,
args.extra_tag,
f'{args.extra_tag}_infos_train.pkl',
relative_path=False,
mask_anno_path='instances_train.json',
with_mask=(args.version == 'mask'))
else:
kitti_data_prep(
root_path=args.root_path,
info_prefix=args.extra_tag,
version=args.version,
out_dir=args.out_dir,
with_plane=args.with_plane)
elif args.dataset == 'nuscenes' and args.version != 'v1.0-mini':
if args.only_gt_database:
create_groundtruth_database('NuScenesDataset', args.root_path,
args.extra_tag,
f'{args.extra_tag}_infos_train.pkl')
else:
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':
if args.only_gt_database:
create_groundtruth_database('NuScenesDataset', args.root_path,
args.extra_tag,
f'{args.extra_tag}_infos_train.pkl')
else:
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 == '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,
only_gt_database=args.only_gt_database,
save_senor_data=not args.skip_saving_sensor_data,
skip_cam_instances_infos=args.skip_cam_instances_infos)
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 == '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)
elif args.dataset == 'semantickitti':
semantickitti_data_prep(
info_prefix=args.extra_tag, out_dir=args.out_dir)
else:
raise NotImplementedError(f'Don\'t support {args.dataset} dataset.')
|