def test_inference_multi_modality_detector():
# these two multi-modality models both only have GPU implementations
if not torch.cuda.is_available():
pytest.skip('test requires GPU and torch+cuda')
# indoor scene
pcd = 'tests/data/sunrgbd/points/000001.bin'
img = 'tests/data/sunrgbd/sunrgbd_trainval/image/000001.jpg'
ann_file = 'tests/data/sunrgbd/sunrgbd_infos.pkl'
detector_cfg = 'configs/imvotenet/imvotenet_stage2_'\
'16x8_sunrgbd-3d-10class.py'
detector = init_model(detector_cfg, device='cuda:0')
results = inference_multi_modality_detector(detector, pcd, img, ann_file)
bboxes_3d = results[0][0]['boxes_3d']
scores_3d = results[0][0]['scores_3d']
labels_3d = results[0][0]['labels_3d']
assert bboxes_3d.tensor.shape[0] >= 0
assert bboxes_3d.tensor.shape[1] == 7
assert scores_3d.shape[0] >= 0
assert labels_3d.shape[0] >= 0
# outdoor scene
pcd = 'tests/data/kitti/training/velodyne_reduced/000000.bin'
img = 'tests/data/kitti/training/image_2/000000.png'
ann_file = 'tests/data/kitti/kitti_infos_train.pkl'
detector_cfg = 'configs/mvxnet/dv_mvx-fpn_second_secfpn_adamw_' \
'2x8_80e_kitti-3d-3class.py'
detector = init_model(detector_cfg, device='cuda:0')
results = inference_multi_modality_detector(detector, pcd, img, ann_file)
bboxes_3d = results[0][0]['pts_bbox']['boxes_3d']
scores_3d = results[0][0]['pts_bbox']['scores_3d']
labels_3d = results[0][0]['pts_bbox']['labels_3d']
assert bboxes_3d.tensor.shape[0] >= 0
assert bboxes_3d.tensor.shape[1] == 7
assert scores_3d.shape[0] >= 0
assert labels_3d.shape[0] >= 0
def main():
parser = ArgumentParser()
parser.add_argument('pcd', help='Point cloud file')
parser.add_argument('config', help='Config file')
parser.add_argument('checkpoint', help='Checkpoint file')
parser.add_argument('--device',
default='cuda:0',
help='Device used for inference')
parser.add_argument('--out-dir',
type=str,
default='demo',
help='dir to save results')
parser.add_argument('--show',
action='store_true',
help='show online visuliaztion results')
parser.add_argument('--snapshot',
action='store_true',
help='whether to save online visuliaztion results')
args = parser.parse_args()
# build the model from a config file and a checkpoint file
model = init_model(args.config, args.checkpoint, device=args.device)
# test a single image
result, data = inference_segmentor(model, args.pcd)
# show the results
show_result_meshlab(data,
result,
args.out_dir,
show=args.show,
snapshot=args.snapshot,
task='seg',
palette=model.PALETTE)
def test_inference_segmentor():
# PN2 only has GPU implementations
if not torch.cuda.is_available():
pytest.skip('test requires GPU and torch+cuda')
pcd = 'tests/data/scannet/points/scene0000_00.bin'
segmentor_cfg = 'configs/pointnet2/pointnet2_ssg_' \
'16x2_cosine_200e_scannet_seg-3d-20class.py'
segmentor = init_model(segmentor_cfg, device='cuda:0')
results = inference_segmentor(segmentor, pcd)
seg_3d = results[0][0]['semantic_mask']
assert seg_3d.shape == torch.Size([100])
assert seg_3d.min() >= 0
assert seg_3d.max() <= 19
def test_inference_detector():
pcd = 'tests/data/kitti/training/velodyne_reduced/000000.bin'
detector_cfg = 'configs/pointpillars/hv_pointpillars_secfpn_' \
'6x8_160e_kitti-3d-3class.py'
detector = init_model(detector_cfg, device='cpu')
results = inference_detector(detector, pcd)
bboxes_3d = results[0][0]['boxes_3d']
scores_3d = results[0][0]['scores_3d']
labels_3d = results[0][0]['labels_3d']
assert bboxes_3d.tensor.shape[0] >= 0
assert bboxes_3d.tensor.shape[1] == 7
assert scores_3d.shape[0] >= 0
assert labels_3d.shape[0] >= 0
def test_inference_detector():
if not torch.cuda.is_available():
pytest.skip('test requires GPU and torch+cuda')
pcd = 'tests/data/kitti/training/velodyne_reduced/000000.bin'
detector_cfg = 'configs/pointpillars/hv_pointpillars_secfpn_' \
'6x8_160e_kitti-3d-3class.py'
detector = init_model(detector_cfg, device='cuda:0')
results = inference_detector(detector, pcd)
bboxes_3d = results[0][0]['boxes_3d']
scores_3d = results[0][0]['scores_3d']
labels_3d = results[0][0]['labels_3d']
assert bboxes_3d.tensor.shape[0] >= 0
assert bboxes_3d.tensor.shape[1] == 7
assert scores_3d.shape[0] >= 0
assert labels_3d.shape[0] >= 0
def test_inference_mono_3d_detector():
# FCOS3D only has GPU implementations
if not torch.cuda.is_available():
pytest.skip('test requires GPU and torch+cuda')
img = 'tests/data/nuscenes/samples/CAM_BACK_LEFT/' \
'n015-2018-07-18-11-07-57+0800__CAM_BACK_LEFT__1531883530447423.jpg'
ann_file = 'tests/data/nuscenes/nus_infos_mono3d.coco.json'
detector_cfg = 'configs/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_' \
'2x8_1x_nus-mono3d.py'
detector = init_model(detector_cfg, device='cuda:0')
results = inference_mono_3d_detector(detector, img, ann_file)
bboxes_3d = results[0][0]['img_bbox']['boxes_3d']
scores_3d = results[0][0]['img_bbox']['scores_3d']
labels_3d = results[0][0]['img_bbox']['labels_3d']
assert bboxes_3d.tensor.shape[0] >= 0
assert bboxes_3d.tensor.shape[1] == 9
assert scores_3d.shape[0] >= 0
assert labels_3d.shape[0] >= 0
def main():
parser = ArgumentParser()
parser.add_argument('pcd', help='Point cloud file')
parser.add_argument('image', help='image file')
parser.add_argument('ann', help='ann file')
parser.add_argument('config', help='Config file')
parser.add_argument('checkpoint', help='Checkpoint file')
parser.add_argument('--device',
default='cuda:0',
help='Device used for inference')
parser.add_argument('--score-thr',
type=float,
default=0.0,
help='bbox score threshold')
parser.add_argument('--out-dir',
type=str,
default='demo',
help='dir to save results')
parser.add_argument('--show',
action='store_true',
help='show online visualization results')
parser.add_argument('--snapshot',
action='store_true',
help='whether to save online visualization results')
args = parser.parse_args()
# build the model from a config file and a checkpoint file
model = init_model(args.config, args.checkpoint, device=args.device)
# test a single image
result, data = inference_multi_modality_detector(model, args.pcd,
args.image, args.ann)
# show the results
show_result_meshlab(data,
result,
args.out_dir,
args.score_thr,
show=args.show,
snapshot=args.snapshot,
task='multi_modality-det')
