def main():
args = parse_args()
mmcv.check_file_exist(args.prediction_path)
cfg = Config.fromfile(args.config)
# update data root according to MMDET_DATASETS
update_data_root(cfg)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
cfg.data.test.test_mode = True
cfg.data.test.pop('samples_per_gpu', 0)
cfg.data.test.pipeline = get_loading_pipeline(cfg.data.train.pipeline)
dataset = build_dataset(cfg.data.test)
outputs = mmcv.load(args.prediction_path)
result_visualizer = ResultVisualizer(args.show, args.wait_time,
args.show_score_thr)
result_visualizer.evaluate_and_show(dataset,
outputs,
topk=args.topk,
show_dir=args.show_dir)
def _load_semantic_seg_3d(self, results):
"""Private function to load 3D semantic segmentation annotations.
Args:
results (dict): Result dict from :obj:`mmdet3d.CustomDataset`.
Returns:
dict: The dict containing the semantic segmentation annotations.
"""
pts_semantic_mask_path = results['ann_info']['pts_semantic_mask_path']
if self.file_client is None:
self.file_client = mmcv.FileClient(**self.file_client_args)
try:
mask_bytes = self.file_client.get(pts_semantic_mask_path)
# add .copy() to fix read-only bug
pts_semantic_mask = np.frombuffer(mask_bytes,
dtype=self.seg_3d_dtype).copy()
except ConnectionError:
mmcv.check_file_exist(pts_semantic_mask_path)
pts_semantic_mask = np.fromfile(pts_semantic_mask_path,
dtype=np.long)
results['pts_semantic_mask'] = pts_semantic_mask
results['pts_seg_fields'].append('pts_semantic_mask')
return results
def evaluate(self, runner, results):
tmp_file = osp.join(runner.work_dir, 'temp_0')
result_files = results2json(self.dataset, results, tmp_file)
if result_files is None:
print('Nothing to evaluate.')
return
for res_type in self.iou_type:
if res_type not in ['bbox', 'segm']:
raise KeyError(
'invalid iou_type: {} for evaluation'.format(res_type))
if res_type == 'segm':
assert runner.model.module.with_mask
try:
mmcv.check_file_exist(result_files[res_type])
except IndexError:
print('No prediction found.')
break
lvis_eval = LVISEval(
self.dataset.lvis, result_files[res_type], iou_type=res_type)
lvis_eval.run()
lvis_eval.print_results()
eval_results = lvis_eval.get_results()
metrics = eval_results.keys()
for i, metric in enumerate(metrics):
if metric.find('AP') == -1:
continue
key = 'AP_{}/{}'.format(res_type, metric)
val = float('{:.3f}'.format(eval_results[metric]))
runner.log_buffer.output[key] = val
runner.log_buffer.ready = True
for res_type in self.iou_type:
os.remove(result_files[res_type])
def main():
args = parse_args()
mmcv.check_file_exist(args.prediction_path)
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
cfg.data.test.test_mode = True
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
cfg.data.test.pop('samples_per_gpu', 0)
cfg.data.test.pipeline = get_loading_pipeline(cfg.data.train.pipeline)
dataset = build_dataset(cfg.data.test)
outputs = mmcv.load(args.prediction_path)
result_visualizer = ResultVisualizer(args.show, args.wait_time,
args.show_score_thr)
result_visualizer.evaluate_and_show(dataset,
outputs,
topk=args.topk,
show_dir=args.show_dir)
def test_seg_format_results():
import mmcv
from os import path as osp
root_path = './tests/data/scannet'
ann_file = './tests/data/scannet/scannet_infos.pkl'
scannet_dataset = ScanNetSegDataset(data_root=root_path,
ann_file=ann_file,
test_mode=True)
results = []
pred_sem_mask = dict(semantic_mask=torch.tensor([
13, 5, 1, 2, 6, 2, 13, 1, 14, 2, 0, 0, 5, 5, 3, 0, 1, 14, 0, 0, 0, 18,
6, 15, 13, 0, 2, 4, 0, 3, 16, 6, 13, 5, 13, 0, 0, 0, 0, 1, 7, 3, 19,
12, 8, 0, 11, 0, 0, 1, 2, 13, 17, 1, 1, 1, 6, 2, 13, 19, 4, 17, 0, 14,
1, 7, 2, 1, 7, 2, 0, 5, 17, 5, 0, 0, 3, 6, 5, 11, 1, 13, 13, 2, 3, 1,
0, 13, 19, 1, 14, 5, 3, 1, 13, 1, 2, 3, 2, 1
]).long())
results.append(pred_sem_mask)
result_files, tmp_dir = scannet_dataset.format_results(results)
expected_label = np.array([
16, 6, 2, 3, 7, 3, 16, 2, 24, 3, 1, 1, 6, 6, 4, 1, 2, 24, 1, 1, 1, 36,
7, 28, 16, 1, 3, 5, 1, 4, 33, 7, 16, 6, 16, 1, 1, 1, 1, 2, 8, 4, 39,
14, 9, 1, 12, 1, 1, 2, 3, 16, 34, 2, 2, 2, 7, 3, 16, 39, 5, 34, 1, 24,
2, 8, 3, 2, 8, 3, 1, 6, 34, 6, 1, 1, 4, 7, 6, 12, 2, 16, 16, 3, 4, 2,
1, 16, 39, 2, 24, 6, 4, 2, 16, 2, 3, 4, 3, 2
])
expected_txt_path = osp.join(tmp_dir.name, 'results', 'scene0000_00.txt')
assert np.all(result_files[0]['seg_mask'] == expected_label)
mmcv.check_file_exist(expected_txt_path)
def main():
parser = ArgumentParser(description='LVIS Evaluation')
parser.add_argument('config', help='config')
parser.add_argument('result', help='result file path')
parser.add_argument(
'--types',
type=str,
nargs='+',
choices=['proposal_fast', 'proposal', 'bbox', 'segm', 'keypoint'],
default=['segm'],
help='result types')
parser.add_argument(
'--max_dets',
type=int,
default=100,
help='proposal numbers, only used for recall evaluation')
args = parser.parse_args()
cfg = mmcv.Config.fromfile(args.config)
dataset = build_dataset(cfg.data.test)
print('loading result file: {}'.format(args.result))
result_files = dict()
for eval_type in args.types:
result_json_path = args.result + '.{}.json'.format(eval_type)
mmcv.check_file_exist(result_json_path)
result_files[eval_type] = result_json_path
lvis_eval(result_files, args.types, dataset.lvis, args.max_dets)
def main():
args = parse_args()
mmcv.check_file_exist(args.prediction_path)
cfg = Config.fromfile(args.config)
# replace the ${key} with the value of cfg.key
cfg = replace_cfg_vals(cfg)
# update data root according to MMDET_DATASETS
update_data_root(cfg)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
cfg.data.test.test_mode = True
cfg.data.test.pop('samples_per_gpu', 0)
if cfg.data.train.type in ('MultiImageMixDataset', 'ClassBalancedDataset',
'RepeatDataset', 'ConcatDataset'):
cfg.data.test.pipeline = get_loading_pipeline(
cfg.data.train.dataset.pipeline)
else:
cfg.data.test.pipeline = get_loading_pipeline(cfg.data.train.pipeline)
dataset = build_dataset(cfg.data.test)
outputs = mmcv.load(args.prediction_path)
result_visualizer = ResultVisualizer(args.show, args.wait_time,
args.show_score_thr,
args.overlay_gt_pred)
result_visualizer.evaluate_and_show(dataset,
outputs,
topk=args.topk,
show_dir=args.show_dir)
def _load_points(self, pts_filename):
if self.file_client is None:
self.file_client = mmcv.FileClient(**self.file_client_args)
try:
pts_bytes = self.file_client.get(pts_filename)
points = np.frombuffer(pts_bytes, dtype=np.float32)
except ConnectionError:
mmcv.check_file_exist(pts_filename)
if pts_filename.endswith('.npy'):
points = np.load(pts_filename)
else:
points = np.fromfile(pts_filename, dtype=np.float32)
return points
def lvis_eval(result_files, result_types, lvis, max_dets=100):
if result_files is None:
print('Nothing to evaluate.')
return
for res_type in result_types:
if res_type not in ['bbox', 'segm']:
raise KeyError(
'invalid iou_type: {} for evaluation'.format(res_type))
try:
mmcv.check_file_exist(result_files[res_type])
except IndexError:
print('No prediction found.')
break
lvis_eval = LVISEval(lvis, result_files[res_type], iou_type=res_type)
lvis_eval.params.max_dets = max_dets
lvis_eval.run()
lvis_eval.print_results()
# Compute per-category AP
# from https://github.com/facebookresearch/detectron2/blob/03064eb5bafe4a3e5750cc7a16672daf5afe8435/detectron2/evaluation/coco_evaluation.py#L259-L283 # noqa
if False:
precisions = lvis_eval.eval['precision']
catIds = lvis.get_cat_ids()
# precision has dims (iou, recall, cls, area range, max dets)
assert len(catIds) == precisions.shape[2]
results_per_category = []
for idx, catId in enumerate(catIds):
# area range index 0: all area ranges
# max dets index -1: typically 100 per image
nm = lvis.load_cats([catId])[0]
precision = precisions[:, :, idx, :]
precision = precision[precision > -1]
ap = np.mean(precision) if precision.size else float('nan')
results_per_category.append(
('{}'.format(nm['name']),
'{:0.3f}'.format(float(ap * 100))))
N_COLS = min(6, len(results_per_category) * 2)
results_flatten = list(itertools.chain(*results_per_category))
headers = ['category', 'AP'] * (N_COLS // 2)
results_2d = itertools.zip_longest(
*[results_flatten[i::N_COLS] for i in range(N_COLS)])
table_data = [headers]
table_data += [result for result in results_2d]
table = AsciiTable(table_data)
print(table.table)
mmcv.dump(results_per_category, 'interp_classwise_ap.pkl')
def _load_points(self, pts_filename):
"""Private function to load point clouds data.
Args:
pts_filename (str): Filename of point clouds data.
Returns:
np.ndarray: An array containing point clouds data.
"""
if self.file_client is None:
self.file_client = mmcv.FileClient(**self.file_client_args)
try:
pts_bytes = self.file_client.get(pts_filename)
points = np.frombuffer(pts_bytes, dtype=np.float32)
except ConnectionError:
mmcv.check_file_exist(pts_filename)
if pts_filename.endswith('.npy'):
points = np.load(pts_filename)
else:
points = np.fromfile(pts_filename, dtype=np.float32)
return points
def test_show():
import mmcv
import tempfile
from os import path as osp
from mmdet3d.core.bbox import LiDARInstance3DBoxes
temp_dir = tempfile.mkdtemp()
data_root, ann_file, classes, pts_prefix,\
pipeline, modality, split = _generate_kitti_dataset_config()
kitti_dataset = KittiDataset(data_root,
ann_file,
split=split,
modality=modality,
pipeline=pipeline)
boxes_3d = LiDARInstance3DBoxes(
torch.tensor(
[[46.1218, -4.6496, -0.9275, 0.5316, 1.4442, 1.7450, 1.1749],
[33.3189, 0.1981, 0.3136, 0.5656, 1.2301, 1.7985, 1.5723],
[46.1366, -4.6404, -0.9510, 0.5162, 1.6501, 1.7540, 1.3778],
[33.2646, 0.2297, 0.3446, 0.5746, 1.3365, 1.7947, 1.5430],
[58.9079, 16.6272, -1.5829, 1.5656, 3.9313, 1.4899, 1.5505]]))
scores_3d = torch.tensor([0.1815, 0.1663, 0.5792, 0.2194, 0.2780])
labels_3d = torch.tensor([0, 0, 1, 1, 2])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [result]
kitti_dataset.show(results, temp_dir)
pts_file_path = osp.join(temp_dir, '000000', '000000_points.obj')
gt_file_path = osp.join(temp_dir, '000000', '000000_gt.ply')
pred_file_path = osp.join(temp_dir, '000000', '000000_pred.ply')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
def test_seg_show():
import mmcv
import tempfile
from os import path as osp
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path = './tests/data/s3dis'
ann_file = './tests/data/s3dis/s3dis_infos.pkl'
s3dis_dataset = S3DISSegDataset(data_root=root_path,
ann_files=ann_file,
scene_idxs=[0])
result = dict(semantic_mask=torch.tensor([
2, 2, 1, 2, 2, 5, 1, 0, 1, 1, 9, 12, 3, 0, 2, 0, 2, 0, 8, 2, 0, 2, 0,
2, 1, 7, 2, 10, 2, 0, 0, 0, 2, 2, 2, 2, 2, 1, 2, 2, 0, 0, 4, 6, 7, 2,
1, 2, 0, 1, 7, 0, 2, 2, 2, 0, 2, 2, 1, 12, 0, 2, 2, 2, 2, 7, 2, 2, 0,
2, 6, 2, 12, 6, 2, 12, 2, 1, 6, 1, 2, 6, 8, 2, 10, 1, 10, 0, 6, 9, 4,
3, 0, 0, 12, 1, 1, 5, 2, 2
]).long())
results = [result]
s3dis_dataset.show(results, temp_dir, show=False)
pts_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_points.obj')
gt_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_gt.obj')
pred_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def test_show():
import mmcv
import tempfile
from os import path as osp
from mmdet3d.core.bbox import LiDARInstance3DBoxes
temp_dir = tempfile.mkdtemp()
data_root = 'tests/data/kitti'
ann_file = 'tests/data/kitti/kitti_infos_train.pkl'
modality = {'use_lidar': True, 'use_camera': False}
split = 'training'
file_client_args = dict(backend='disk')
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
class_names = ['Pedestrian', 'Cyclist', 'Car']
pipeline = [
dict(type='LoadPointsFromFile',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(type='PointsRangeFilter',
point_cloud_range=point_cloud_range),
dict(type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
kitti_dataset = KittiDataset(data_root,
ann_file,
split=split,
modality=modality,
pipeline=pipeline)
boxes_3d = LiDARInstance3DBoxes(
torch.tensor(
[[46.1218, -4.6496, -0.9275, 0.5316, 1.4442, 1.7450, 1.1749],
[33.3189, 0.1981, 0.3136, 0.5656, 1.2301, 1.7985, 1.5723],
[46.1366, -4.6404, -0.9510, 0.5162, 1.6501, 1.7540, 1.3778],
[33.2646, 0.2297, 0.3446, 0.5746, 1.3365, 1.7947, 1.5430],
[58.9079, 16.6272, -1.5829, 1.5656, 3.9313, 1.4899, 1.5505]]))
scores_3d = torch.tensor([0.1815, 0.1663, 0.5792, 0.2194, 0.2780])
labels_3d = torch.tensor([0, 0, 1, 1, 2])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [result]
kitti_dataset.show(results, temp_dir)
pts_file_path = osp.join(temp_dir, '000000', '000000_points.obj')
gt_file_path = osp.join(temp_dir, '000000', '000000_gt.ply')
pred_file_path = osp.join(temp_dir, '000000', '000000_pred.ply')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
def test_show():
root_path = 'tests/data/nuscenes/'
ann_file = 'tests/data/nuscenes/nus_infos_mono3d.coco.json'
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
eval_pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['img'])
]
nus_dataset = NuScenesMonoDataset(data_root=root_path,
ann_file=ann_file,
img_prefix='tests/data/nuscenes/',
test_mode=True,
pipeline=eval_pipeline)
results = mmcv.load('tests/data/nuscenes/mono3d_sample_results.pkl')
results = [results[0]]
# show with eval_pipeline
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
nus_dataset.show(results, temp_dir, show=False)
file_name = 'n015-2018-07-18-11-07-57+0800__' \
'CAM_BACK_LEFT__1531883530447423'
img_file_path = osp.join(temp_dir, file_name, f'{file_name}_img.png')
gt_file_path = osp.join(temp_dir, file_name, f'{file_name}_gt.png')
pred_file_path = osp.join(temp_dir, file_name, f'{file_name}_pred.png')
mmcv.check_file_exist(img_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def test_show():
import mmcv
import tempfile
from os import path as osp
from mmdet3d.core.bbox import DepthInstance3DBoxes
temp_dir = tempfile.mkdtemp()
root_path = './tests/data/sunrgbd'
ann_file = './tests/data/sunrgbd/sunrgbd_infos.pkl'
sunrgbd_dataset = SUNRGBDDataset(root_path, ann_file)
boxes_3d = DepthInstance3DBoxes(
torch.tensor(
[[1.1500, 4.2614, -1.0669, 1.3219, 2.1593, 1.0267, 1.6473],
[-0.9583, 2.1916, -1.0881, 0.6213, 1.3022, 1.6275, -3.0720],
[2.5697, 4.8152, -1.1157, 0.5421, 0.7019, 0.7896, 1.6712],
[0.7283, 2.5448, -1.0356, 0.7691, 0.9056, 0.5771, 1.7121],
[-0.9860, 3.2413, -1.2349, 0.5110, 0.9940, 1.1245, 0.3295]]))
scores_3d = torch.tensor(
[1.5280e-01, 1.6682e-03, 6.2811e-04, 1.2860e-03, 9.4229e-06])
labels_3d = torch.tensor([0, 0, 0, 0, 0])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [result]
sunrgbd_dataset.show(results, temp_dir, show=False)
pts_file_path = osp.join(temp_dir, '000001', '000001_points.obj')
gt_file_path = osp.join(temp_dir, '000001', '000001_gt.ply')
pred_file_path = osp.join(temp_dir, '000001', '000001_pred.ply')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
def test_seg_show():
import mmcv
import tempfile
from os import path as osp
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path = './tests/data/scannet'
ann_file = './tests/data/scannet/scannet_infos.pkl'
scannet_dataset = ScanNetSegDataset(
data_root=root_path, ann_file=ann_file, scene_idxs=[0])
result = dict(
semantic_mask=torch.tensor([
13, 5, 1, 2, 6, 2, 13, 1, 14, 2, 0, 0, 5, 5, 3, 0, 1, 14, 0, 0, 0,
18, 6, 15, 13, 0, 2, 4, 0, 3, 16, 6, 13, 5, 13, 0, 0, 0, 0, 1, 7,
3, 19, 12, 8, 0, 11, 0, 0, 1, 2, 13, 17, 1, 1, 1, 6, 2, 13, 19, 4,
17, 0, 14, 1, 7, 2, 1, 7, 2, 0, 5, 17, 5, 0, 0, 3, 6, 5, 11, 1, 13,
13, 2, 3, 1, 0, 13, 19, 1, 14, 5, 3, 1, 13, 1, 2, 3, 2, 1
]).long())
results = [result]
scannet_dataset.show(results, temp_dir, show=False)
pts_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_points.obj')
gt_file_path = osp.join(temp_dir, 'scene0000_00', 'scene0000_00_gt.obj')
pred_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def test_check_file_exist():
mmcv.check_file_exist(__file__)
if sys.version_info > (3, 3):
with pytest.raises(FileNotFoundError): # noqa
mmcv.check_file_exist('no_such_file.txt')
else:
with pytest.raises(IOError):
mmcv.check_file_exist('no_such_file.txt')
def _load_points(self, pts_filename):
"""Private function to load point clouds data.
Args:
pts_filename (str): Filename of point clouds data.
Returns:
np.ndarray: An array containing point clouds data.
"""
if self._file_client is None:
self._file_client = mmcv.FileClient(**self._file_client_args)
try:
pts_bytes = self._file_client.get(pts_filename)
points = np.frombuffer(pts_bytes, dtype=np.float32)
except ConnectionError:
mmcv.check_file_exist(pts_filename)
if pts_filename.endswith(".npy"):
points = np.load(pts_filename)
else:
points = np.fromfile(pts_filename, dtype=np.float32)
points = points.reshape(-1, self._load_dim)
points = points[:, self._use_dim]
attribute_dims = None
# TODO attributes
if self.shift_height:
floor_height = np.percentile(points[:, 2], 0.99)
height = points[:, 2] - floor_height
points = np.concatenate([points, np.expand_dims(height, 1)], 1)
attribute_dims = dict(height=3)
points_class = get_points_type(self._coord_type)
points = points_class(points,
points_dim=points.shape[-1],
attribute_dims=attribute_dims)
return points
def __init__(self, root_path, split='train'):
self.root_dir = root_path
self.split = split
self.split_dir = osp.join(root_path)
self.classes = [
'cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
'bookshelf', 'picture', 'counter', 'desk', 'curtain',
'refrigerator', 'showercurtrain', 'toilet', 'sink', 'bathtub',
'garbagebin'
]
self.cat2label = {cat: self.classes.index(cat) for cat in self.classes}
self.label2cat = {self.cat2label[t]: t for t in self.cat2label}
self.cat_ids = np.array(
[3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34, 36, 39])
self.cat_ids2class = {
nyu40id: i
for i, nyu40id in enumerate(list(self.cat_ids))
}
assert split in ['train', 'val', 'test']
split_file = osp.join(self.root_dir, 'meta_data',
f'scannetv2_{split}.txt')
mmcv.check_file_exist(split_file)
self.sample_id_list = mmcv.list_from_file(split_file)
def __init__(self, root_path, split='train', use_v1=False):
self.root_dir = root_path
self.split = split
self.split_dir = osp.join(root_path, 'sunrgbd_trainval')
self.classes = [
'bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
'night_stand', 'bookshelf', 'bathtub'
]
self.cat2label = {cat: self.classes.index(cat) for cat in self.classes}
self.label2cat = {
label: self.classes[label]
for label in range(len(self.classes))
}
assert split in ['train', 'val', 'test']
split_file = osp.join(self.split_dir, f'{split}_data_idx.txt')
mmcv.check_file_exist(split_file)
self.sample_id_list = map(int, mmcv.list_from_file(split_file))
self.image_dir = osp.join(self.split_dir, 'image')
self.calib_dir = osp.join(self.split_dir, 'calib')
self.depth_dir = osp.join(self.split_dir, 'depth')
if use_v1:
self.label_dir = osp.join(self.split_dir, 'label_v1')
else:
self.label_dir = osp.join(self.split_dir, 'label')
def _load_masks_3d(self, results):
"""Private function to load 3D mask annotations.
Args:
results (dict): Result dict from :obj:`mmdet3d.CustomDataset`.
Returns:
dict: The dict containing loaded 3D mask annotations.
"""
pts_instance_mask_path = results['ann_info']['pts_instance_mask_path']
if self.file_client is None:
self.file_client = mmcv.FileClient(**self.file_client_args)
try:
mask_bytes = self.file_client.get(pts_instance_mask_path)
pts_instance_mask = np.frombuffer(mask_bytes, dtype=np.int)
except ConnectionError:
mmcv.check_file_exist(pts_instance_mask_path)
pts_instance_mask = np.fromfile(pts_instance_mask_path,
dtype=np.long)
results['pts_instance_mask'] = pts_instance_mask
results['pts_mask_fields'].append('pts_instance_mask')
return results
def test_show():
import mmcv
from os import path as osp
from mmdet3d.core.bbox import LiDARInstance3DBoxes
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
nus_dataset = NuScenesDataset('tests/data/nuscenes/nus_info.pkl', None,
'tests/data/nuscenes')
boxes_3d = LiDARInstance3DBoxes(
torch.tensor(
[[46.1218, -4.6496, -0.9275, 0.5316, 1.4442, 1.7450, 1.1749],
[33.3189, 0.1981, 0.3136, 0.5656, 1.2301, 1.7985, 1.5723],
[46.1366, -4.6404, -0.9510, 0.5162, 1.6501, 1.7540, 1.3778],
[33.2646, 0.2297, 0.3446, 0.5746, 1.3365, 1.7947, 1.5430],
[58.9079, 16.6272, -1.5829, 1.5656, 3.9313, 1.4899, 1.5505]]))
scores_3d = torch.tensor([0.1815, 0.1663, 0.5792, 0.2194, 0.2780])
labels_3d = torch.tensor([0, 0, 1, 1, 2])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [dict(pts_bbox=result)]
nus_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
file_name = 'n015-2018-08-02-17-16-37+0800__LIDAR_TOP__1533201470948018'
pts_file_path = osp.join(temp_dir, file_name, f'{file_name}_points.obj')
gt_file_path = osp.join(temp_dir, file_name, f'{file_name}_gt.obj')
pred_file_path = osp.join(temp_dir, file_name, f'{file_name}_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def test_show():
import mmcv
import tempfile
from os import path as osp
from mmdet3d.core.bbox import DepthInstance3DBoxes
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path = './tests/data/scannet'
ann_file = './tests/data/scannet/scannet_infos.pkl'
scannet_dataset = ScanNetDataset(root_path, ann_file)
boxes_3d = DepthInstance3DBoxes(
torch.tensor([[
-2.4053e+00, 9.2295e-01, 8.0661e-02, 2.4054e+00, 2.1468e+00,
8.5990e-01, 0.0000e+00
],
[
-1.9341e+00, -2.0741e+00, 3.0698e-03, 3.2206e-01,
2.5322e-01, 3.5144e-01, 0.0000e+00
],
[
-3.6908e+00, 8.0684e-03, 2.6201e-01, 4.1515e-01,
7.6489e-01, 5.3585e-01, 0.0000e+00
],
[
2.6332e+00, 8.5143e-01, -4.9964e-03, 3.0367e-01,
1.3448e+00, 1.8329e+00, 0.0000e+00
],
[
2.0221e-02, 2.6153e+00, 1.5109e-02, 7.3335e-01,
1.0429e+00, 1.0251e+00, 0.0000e+00
]]))
scores_3d = torch.tensor(
[1.2058e-04, 2.3012e-03, 6.2324e-06, 6.6139e-06, 6.7965e-05])
labels_3d = torch.tensor([0, 0, 0, 0, 0])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [result]
scannet_dataset.show(results, temp_dir, show=False)
pts_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_points.obj')
gt_file_path = osp.join(temp_dir, 'scene0000_00', 'scene0000_00_gt.obj')
pred_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def test_show():
import mmcv
from os import path as osp
from mmdet3d.core.bbox import LiDARInstance3DBoxes
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path = './tests/data/lyft'
ann_file = './tests/data/lyft/lyft_infos.pkl'
class_names = ('car', 'truck', 'bus', 'emergency_vehicle', 'other_vehicle',
'motorcycle', 'bicycle', 'pedestrian', 'animal')
eval_pipeline = [
dict(type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
kitti_dataset = LyftDataset(ann_file, None, root_path)
boxes_3d = LiDARInstance3DBoxes(
torch.tensor(
[[46.1218, -4.6496, -0.9275, 0.5316, 1.4442, 1.7450, 1.1749],
[33.3189, 0.1981, 0.3136, 0.5656, 1.2301, 1.7985, 1.5723],
[46.1366, -4.6404, -0.9510, 0.5162, 1.6501, 1.7540, 1.3778],
[33.2646, 0.2297, 0.3446, 0.5746, 1.3365, 1.7947, 1.5430],
[58.9079, 16.6272, -1.5829, 1.5656, 3.9313, 1.4899, 1.5505]]))
scores_3d = torch.tensor([0.1815, 0.1663, 0.5792, 0.2194, 0.2780])
labels_3d = torch.tensor([0, 0, 1, 1, 2])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [dict(pts_bbox=result)]
kitti_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
file_name = 'host-a017_lidar1_1236118886901125926'
pts_file_path = osp.join(temp_dir, file_name, f'{file_name}_points.obj')
gt_file_path = osp.join(temp_dir, file_name, f'{file_name}_gt.obj')
pred_file_path = osp.join(temp_dir, file_name, f'{file_name}_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def _fill_trainval_infos(nusc,
split_names,
out_dir,
keyword=None,
keyword_action=None,
subset_name=None,
location=None,
test=False,
max_sweeps=10):
import tools.data_converter.xmuda_splits as splits
pkl_dict = {}
for split_name in split_names:
pkl_dict[split_name] = []
for sample in mmcv.track_iter_progress(nusc.sample):
curr_scene_name = nusc.get(
'scene', sample['scene_token'])['name'] # 'scene-0061'
# get if the current scene is in train, val or test
curr_split = None
for split_name in split_names:
if curr_scene_name in getattr(splits, split_name):
curr_split = split_name
break
if curr_split is None:
continue
if subset_name == 'night':
if curr_split == 'train':
if curr_scene_name in splits.val_night:
curr_split = 'val'
if subset_name == 'singapore':
if curr_split == 'train':
if curr_scene_name in splits.val_singapore:
curr_split = 'val'
# filter for day/night
if keyword:
scene_description = nusc.get("scene",
sample["scene_token"])["description"]
if keyword.lower() in scene_description.lower():
if keyword_action == 'exclude':
# skip sample
continue
else:
if keyword_action == 'filter':
# skip sample
continue
if location:
scene = nusc.get("scene", sample["scene_token"])
if location not in nusc.get("log", scene['log_token'])['location']:
continue
lidar_token = sample['data']['LIDAR_TOP']
cam_token = sample['data']['CAM_FRONT']
sd_rec = nusc.get('sample_data', sample['data']['LIDAR_TOP'])
cs_record = nusc.get('calibrated_sensor',
sd_rec['calibrated_sensor_token'])
pose_record = nusc.get('ego_pose', sd_rec['ego_pose_token'])
lidar_path, boxes_lidar, _ = nusc.get_sample_data(lidar_token)
_, boxes_cam, _ = nusc.get_sample_data(cam_token)
lidarseg = nusc.get('lidarseg', lidar_token)
lidarseg_path = os.path.join(nusc.dataroot, lidarseg['filename'])
mmcv.check_file_exist(lidar_path)
info = {
'lidar_path': lidar_path,
'lidarseg_path': lidarseg_path,
'token': sample['token'],
'sweeps': [],
'cams': dict(),
'lidar2ego_translation': cs_record['translation'],
'lidar2ego_rotation': cs_record['rotation'],
'ego2global_translation': pose_record['translation'],
'ego2global_rotation': pose_record['rotation'],
'timestamp': sample['timestamp'],
}
l2e_r = info['lidar2ego_rotation']
l2e_t = info['lidar2ego_translation']
e2g_r = info['ego2global_rotation']
e2g_t = info['ego2global_translation']
l2e_r_mat = Quaternion(l2e_r).rotation_matrix
e2g_r_mat = Quaternion(e2g_r).rotation_matrix
# obtain 6 image's information per frame
camera_types = [
'CAM_FRONT',
'CAM_FRONT_RIGHT',
'CAM_FRONT_LEFT',
'CAM_BACK',
'CAM_BACK_LEFT',
'CAM_BACK_RIGHT',
]
for cam in camera_types:
cam_token = sample['data'][cam]
cam_path, _, cam_intrinsic = nusc.get_sample_data(cam_token)
cam_info = obtain_sensor2top(nusc, cam_token, l2e_t, l2e_r_mat,
e2g_t, e2g_r_mat, cam)
cam_info.update(cam_intrinsic=cam_intrinsic)
info['cams'].update({cam: cam_info})
# obtain sweeps for a single key-frame
sd_rec = nusc.get('sample_data', sample['data']['LIDAR_TOP'])
sweeps = []
while len(sweeps) < max_sweeps:
if not sd_rec['prev'] == '':
sweep = obtain_sensor2top(nusc, sd_rec['prev'], l2e_t,
l2e_r_mat, e2g_t, e2g_r_mat, 'lidar')
sweeps.append(sweep)
sd_rec = nusc.get('sample_data', sd_rec['prev'])
else:
break
info['sweeps'] = sweeps
# obtain annotation
if not test:
# full range
# annotations = [
# nusc.get('sample_annotation', token)
# for token in sample['anns']
# ]
# inside camera
valid_box_tokens = [box.token for box in boxes_cam]
boxes_lidar_filter = [
box for box in boxes_lidar if box.token in valid_box_tokens
]
annotations = [
nusc.get('sample_annotation', token)
for token in valid_box_tokens
]
locs = np.array([b.center
for b in boxes_lidar_filter]).reshape(-1, 3)
dims = np.array([b.wlh for b in boxes_lidar_filter]).reshape(-1, 3)
rots = np.array([
b.orientation.yaw_pitch_roll[0] for b in boxes_lidar_filter
]).reshape(-1, 1)
# velocity = np.array(
# [nusc.box_velocity(token)[:2] for token in sample['anns']])
velocity = np.array(
[nusc.box_velocity(token)[:2] for token in valid_box_tokens])
valid_flag = np.array(
[(anno['num_lidar_pts'] + anno['num_radar_pts']) > 0
for anno in annotations],
dtype=bool).reshape(-1)
# convert velo from global to lidar
for i in range(len(boxes_lidar_filter)):
velo = np.array([*velocity[i], 0.0])
velo = velo @ np.linalg.inv(e2g_r_mat).T @ np.linalg.inv(
l2e_r_mat).T
velocity[i] = velo[:2]
names = [b.name for b in boxes_lidar_filter]
for i in range(len(names)):
if names[i] in NuScenesDataset.NameMapping:
names[i] = NuScenesDataset.NameMapping[names[i]]
names = np.array(names)
# we need to convert rot to SECOND format.
gt_boxes = np.concatenate([locs, dims, -rots - np.pi / 2], axis=1)
assert len(gt_boxes) == len(
annotations), f'{len(gt_boxes)}, {len(annotations)}'
info['gt_boxes'] = gt_boxes
info['gt_names'] = names
info['gt_velocity'] = velocity.reshape(-1, 2)
info['num_lidar_pts'] = np.array(
[a['num_lidar_pts'] for a in annotations])
info['num_radar_pts'] = np.array(
[a['num_radar_pts'] for a in annotations])
info['valid_flag'] = valid_flag
pkl_dict[curr_split].append(info)
save_dir = osp.join(out_dir, 'mmda_xmuda_split')
os.makedirs(save_dir, exist_ok=True)
for split_name in split_names:
metadata = split_name + '_' + subset_name
# save_path = osp.join(save_dir, '{}{}.pkl'.format(split_name, '_' + subset_name if subset_name else ''))
save_path = osp.join(save_dir, '{}.pkl'.format(metadata))
res = dict(infos=pkl_dict[split_name], metadata=metadata)
mmcv.dump(res, save_path)
print('Wrote preprocessed data to ' + save_path)
def test_show():
import mmcv
import tempfile
from os import path as osp
from mmdet3d.core.bbox import DepthInstance3DBoxes
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path = './tests/data/scannet'
ann_file = './tests/data/scannet/scannet_infos.pkl'
scannet_dataset = ScanNetDataset(root_path, ann_file)
boxes_3d = DepthInstance3DBoxes(
torch.tensor([[
-2.4053e+00, 9.2295e-01, 8.0661e-02, 2.4054e+00, 2.1468e+00,
8.5990e-01, 0.0000e+00
],
[
-1.9341e+00, -2.0741e+00, 3.0698e-03, 3.2206e-01,
2.5322e-01, 3.5144e-01, 0.0000e+00
],
[
-3.6908e+00, 8.0684e-03, 2.6201e-01, 4.1515e-01,
7.6489e-01, 5.3585e-01, 0.0000e+00
],
[
2.6332e+00, 8.5143e-01, -4.9964e-03, 3.0367e-01,
1.3448e+00, 1.8329e+00, 0.0000e+00
],
[
2.0221e-02, 2.6153e+00, 1.5109e-02, 7.3335e-01,
1.0429e+00, 1.0251e+00, 0.0000e+00
]]))
scores_3d = torch.tensor(
[1.2058e-04, 2.3012e-03, 6.2324e-06, 6.6139e-06, 6.7965e-05])
labels_3d = torch.tensor([0, 0, 0, 0, 0])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [result]
scannet_dataset.show(results, temp_dir, show=False)
pts_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_points.obj')
gt_file_path = osp.join(temp_dir, 'scene0000_00', 'scene0000_00_gt.obj')
pred_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
# show function with pipeline
class_names = ('cabinet', 'bed', 'chair', 'sofa', 'table', 'door',
'window', 'bookshelf', 'picture', 'counter', 'desk',
'curtain', 'refrigerator', 'showercurtrain', 'toilet',
'sink', 'bathtub', 'garbagebin')
eval_pipeline = [
dict(type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
load_dim=6,
use_dim=[0, 1, 2]),
dict(type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
scannet_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
pts_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_points.obj')
gt_file_path = osp.join(temp_dir, 'scene0000_00', 'scene0000_00_gt.obj')
pred_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def test_seg_show():
import mmcv
import tempfile
from os import path as osp
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path = './tests/data/scannet'
ann_file = './tests/data/scannet/scannet_infos.pkl'
scannet_dataset = ScanNetSegDataset(data_root=root_path,
ann_file=ann_file,
scene_idxs=[0])
result = dict(semantic_mask=torch.tensor([
13, 5, 1, 2, 6, 2, 13, 1, 14, 2, 0, 0, 5, 5, 3, 0, 1, 14, 0, 0, 0, 18,
6, 15, 13, 0, 2, 4, 0, 3, 16, 6, 13, 5, 13, 0, 0, 0, 0, 1, 7, 3, 19,
12, 8, 0, 11, 0, 0, 1, 2, 13, 17, 1, 1, 1, 6, 2, 13, 19, 4, 17, 0, 14,
1, 7, 2, 1, 7, 2, 0, 5, 17, 5, 0, 0, 3, 6, 5, 11, 1, 13, 13, 2, 3, 1,
0, 13, 19, 1, 14, 5, 3, 1, 13, 1, 2, 3, 2, 1
]).long())
results = [result]
scannet_dataset.show(results, temp_dir, show=False)
pts_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_points.obj')
gt_file_path = osp.join(temp_dir, 'scene0000_00', 'scene0000_00_gt.obj')
pred_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
# test show with pipeline
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
class_names = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table',
'door', 'window', 'bookshelf', 'picture', 'counter', 'desk',
'curtain', 'refrigerator', 'showercurtrain', 'toilet',
'sink', 'bathtub', 'otherfurniture')
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]),
dict(type='LoadAnnotations3D',
with_bbox_3d=False,
with_label_3d=False,
with_mask_3d=False,
with_seg_3d=True),
dict(type='PointSegClassMapping',
valid_cat_ids=(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24,
28, 33, 34, 36, 39)),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'pts_semantic_mask'])
]
scannet_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
pts_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_points.obj')
gt_file_path = osp.join(temp_dir, 'scene0000_00', 'scene0000_00_gt.obj')
pred_file_path = osp.join(temp_dir, 'scene0000_00',
'scene0000_00_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def _fill_trainval_infos(nusc,
train_scenes,
val_scenes,
test=False,
max_sweeps=10):
"""Generate the train/val infos from the raw data.
Args:
nusc (:obj:`NuScenes`): Dataset class in the nuScenes dataset.
train_scenes (list[str]): Basic information of training scenes.
val_scenes (list[str]): Basic information of validation scenes.
test (bool): Whether use the test mode. In the test mode, no
annotations can be accessed. Default: False.
max_sweeps (int): Max number of sweeps. Default: 10.
Returns:
tuple[list[dict]]: Information of training set and validation set
that will be saved to the info file.
"""
train_nusc_infos = []
val_nusc_infos = []
for sample in mmcv.track_iter_progress(nusc.sample):
lidar_token = sample['data']['LIDAR_TOP']
cam_token = sample['data']['CAM_FRONT']
sd_rec = nusc.get('sample_data', sample['data']['LIDAR_TOP'])
cs_record = nusc.get('calibrated_sensor',
sd_rec['calibrated_sensor_token'])
pose_record = nusc.get('ego_pose', sd_rec['ego_pose_token'])
lidar_path, boxes_lidar, _ = nusc.get_sample_data(lidar_token)
_, boxes_cam, _ = nusc.get_sample_data(cam_token)
lidarseg = nusc.get('lidarseg', lidar_token)
lidarseg_path = os.path.join(nusc.dataroot, lidarseg['filename'])
mmcv.check_file_exist(lidar_path)
info = {
'lidar_path': lidar_path,
'lidarseg_path': lidarseg_path,
'token': sample['token'],
'sweeps': [],
'cams': dict(),
'lidar2ego_translation': cs_record['translation'],
'lidar2ego_rotation': cs_record['rotation'],
'ego2global_translation': pose_record['translation'],
'ego2global_rotation': pose_record['rotation'],
'timestamp': sample['timestamp'],
}
l2e_r = info['lidar2ego_rotation']
l2e_t = info['lidar2ego_translation']
e2g_r = info['ego2global_rotation']
e2g_t = info['ego2global_translation']
l2e_r_mat = Quaternion(l2e_r).rotation_matrix
e2g_r_mat = Quaternion(e2g_r).rotation_matrix
# obtain 6 image's information per frame
camera_types = [
'CAM_FRONT',
'CAM_FRONT_RIGHT',
'CAM_FRONT_LEFT',
'CAM_BACK',
'CAM_BACK_LEFT',
'CAM_BACK_RIGHT',
]
for cam in camera_types:
cam_token = sample['data'][cam]
cam_path, _, cam_intrinsic = nusc.get_sample_data(cam_token)
cam_info = obtain_sensor2top(nusc, cam_token, l2e_t, l2e_r_mat,
e2g_t, e2g_r_mat, cam)
cam_info.update(cam_intrinsic=cam_intrinsic)
info['cams'].update({cam: cam_info})
# obtain sweeps for a single key-frame
sd_rec = nusc.get('sample_data', sample['data']['LIDAR_TOP'])
sweeps = []
while len(sweeps) < max_sweeps:
if not sd_rec['prev'] == '':
sweep = obtain_sensor2top(nusc, sd_rec['prev'], l2e_t,
l2e_r_mat, e2g_t, e2g_r_mat, 'lidar')
sweeps.append(sweep)
sd_rec = nusc.get('sample_data', sd_rec['prev'])
else:
break
info['sweeps'] = sweeps
# obtain annotation
if not test:
# full range
# annotations = [
# nusc.get('sample_annotation', token)
# for token in sample['anns']
# ]
# inside camera
valid_box_tokens = [box.token for box in boxes_cam]
boxes_lidar_filter = [
box for box in boxes_lidar if box.token in valid_box_tokens
]
annotations = [
nusc.get('sample_annotation', token)
for token in valid_box_tokens
]
locs = np.array([b.center
for b in boxes_lidar_filter]).reshape(-1, 3)
dims = np.array([b.wlh for b in boxes_lidar_filter]).reshape(-1, 3)
rots = np.array([
b.orientation.yaw_pitch_roll[0] for b in boxes_lidar_filter
]).reshape(-1, 1)
# velocity = np.array(
# [nusc.box_velocity(token)[:2] for token in sample['anns']])
velocity = np.array(
[nusc.box_velocity(token)[:2] for token in valid_box_tokens])
valid_flag = np.array(
[(anno['num_lidar_pts'] + anno['num_radar_pts']) > 0
for anno in annotations],
dtype=bool).reshape(-1)
# convert velo from global to lidar
for i in range(len(boxes_lidar_filter)):
velo = np.array([*velocity[i], 0.0])
velo = velo @ np.linalg.inv(e2g_r_mat).T @ np.linalg.inv(
l2e_r_mat).T
velocity[i] = velo[:2]
names = [b.name for b in boxes_lidar_filter]
for i in range(len(names)):
if names[i] in NuScenesDataset.NameMapping:
names[i] = NuScenesDataset.NameMapping[names[i]]
names = np.array(names)
# we need to convert rot to SECOND format.
gt_boxes = np.concatenate([locs, dims, -rots - np.pi / 2], axis=1)
assert len(gt_boxes) == len(
annotations), f'{len(gt_boxes)}, {len(annotations)}'
info['gt_boxes'] = gt_boxes
info['gt_names'] = names
info['gt_velocity'] = velocity.reshape(-1, 2)
info['num_lidar_pts'] = np.array(
[a['num_lidar_pts'] for a in annotations])
info['num_radar_pts'] = np.array(
[a['num_radar_pts'] for a in annotations])
info['valid_flag'] = valid_flag
if sample['scene_token'] in train_scenes:
train_nusc_infos.append(info)
else:
val_nusc_infos.append(info)
return train_nusc_infos, val_nusc_infos
def test_check_file_exist():
mmcv.check_file_exist(__file__)
with pytest.raises(FileNotFoundError):
mmcv.check_file_exist('no_such_file.txt')
def test_show():
import mmcv
import tempfile
from os import path as osp
from mmdet3d.core.bbox import DepthInstance3DBoxes
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path, ann_file, class_names, pipelines, modality = \
_generate_sunrgbd_dataset_config()
sunrgbd_dataset = SUNRGBDDataset(root_path,
ann_file,
pipelines,
modality=modality)
boxes_3d = DepthInstance3DBoxes(
torch.tensor(
[[1.1500, 4.2614, -1.0669, 1.3219, 2.1593, 1.0267, 1.6473],
[-0.9583, 2.1916, -1.0881, 0.6213, 1.3022, 1.6275, -3.0720],
[2.5697, 4.8152, -1.1157, 0.5421, 0.7019, 0.7896, 1.6712],
[0.7283, 2.5448, -1.0356, 0.7691, 0.9056, 0.5771, 1.7121],
[-0.9860, 3.2413, -1.2349, 0.5110, 0.9940, 1.1245, 0.3295]]))
scores_3d = torch.tensor(
[1.5280e-01, 1.6682e-03, 6.2811e-04, 1.2860e-03, 9.4229e-06])
labels_3d = torch.tensor([0, 0, 0, 0, 0])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [result]
sunrgbd_dataset.show(results, temp_dir, show=False)
pts_file_path = osp.join(temp_dir, '000001', '000001_points.obj')
gt_file_path = osp.join(temp_dir, '000001', '000001_gt.obj')
pred_file_path = osp.join(temp_dir, '000001', '000001_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
# test show with pipeline
eval_pipeline = [
dict(type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=True,
load_dim=6,
use_dim=[0, 1, 2]),
dict(type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
sunrgbd_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
pts_file_path = osp.join(temp_dir, '000001', '000001_points.obj')
gt_file_path = osp.join(temp_dir, '000001', '000001_gt.obj')
pred_file_path = osp.join(temp_dir, '000001', '000001_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
# test multi-modality show
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path, ann_file, class_names, multi_modality_pipelines, modality = \
_generate_sunrgbd_multi_modality_dataset_config()
sunrgbd_dataset = SUNRGBDDataset(root_path,
ann_file,
multi_modality_pipelines,
modality=modality)
sunrgbd_dataset.show(results, temp_dir, False, multi_modality_pipelines)
pts_file_path = osp.join(temp_dir, '000001', '000001_points.obj')
gt_file_path = osp.join(temp_dir, '000001', '000001_gt.obj')
pred_file_path = osp.join(temp_dir, '000001', '000001_pred.obj')
img_file_path = osp.join(temp_dir, '000001', '000001_img.png')
img_pred_path = osp.join(temp_dir, '000001', '000001_pred.png')
img_gt_file = osp.join(temp_dir, '000001', '000001_gt.png')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
mmcv.check_file_exist(img_file_path)
mmcv.check_file_exist(img_pred_path)
mmcv.check_file_exist(img_gt_file)
tmp_dir.cleanup()
# test multi-modality show with pipeline
eval_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=True,
load_dim=6,
use_dim=[0, 1, 2]),
dict(type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points', 'img'])
]
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
sunrgbd_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
pts_file_path = osp.join(temp_dir, '000001', '000001_points.obj')
gt_file_path = osp.join(temp_dir, '000001', '000001_gt.obj')
pred_file_path = osp.join(temp_dir, '000001', '000001_pred.obj')
img_file_path = osp.join(temp_dir, '000001', '000001_img.png')
img_pred_path = osp.join(temp_dir, '000001', '000001_pred.png')
img_gt_file = osp.join(temp_dir, '000001', '000001_gt.png')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
mmcv.check_file_exist(img_file_path)
mmcv.check_file_exist(img_pred_path)
mmcv.check_file_exist(img_gt_file)
tmp_dir.cleanup()