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 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_detector(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)
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_show_result_meshlab():
pcd = 'tests/data/nuscenes/samples/LIDAR_TOP/n015-2018-08-02-17-16-37+' \
'0800__LIDAR_TOP__1533201470948018.pcd.bin'
box_3d = LiDARInstance3DBoxes(
torch.tensor(
[[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]]))
labels_3d = torch.tensor([0])
scores_3d = torch.tensor([0.5])
points = np.random.rand(100, 4)
img_meta = dict(
pts_filename=pcd, boxes_3d=box_3d, box_mode_3d=Box3DMode.LIDAR)
data = dict(points=[[torch.tensor(points)]], img_metas=[[img_meta]])
result = [
dict(
pts_bbox=dict(
boxes_3d=box_3d, labels_3d=labels_3d, scores_3d=scores_3d))
]
temp_out_dir = tempfile.mkdtemp()
out_dir, file_name = show_result_meshlab(data, result, temp_out_dir)
expected_outfile_ply = file_name + '_pred.ply'
expected_outfile_obj = file_name + '_points.obj'
expected_outfile_ply_path = os.path.join(out_dir, file_name,
expected_outfile_ply)
expected_outfile_obj_path = os.path.join(out_dir, file_name,
expected_outfile_obj)
assert os.path.exists(expected_outfile_ply_path)
assert os.path.exists(expected_outfile_obj_path)
os.remove(expected_outfile_obj_path)
os.remove(expected_outfile_ply_path)
os.removedirs(os.path.join(temp_out_dir, file_name))
def execution(idx):
global dataset, model, cfg, args
print()
# Select and infer a sample
sample = dataset.__getitem__(idx)
if isinstance(sample['img_metas'], list):
filename = sample['img_metas'][0].data['pts_filename']
else:
filename = sample['img_metas'].data['pts_filename']
pcd_file = os.path.join(dataset.root_split, dataset.pts_prefix, filename)
print("Selected pcd_file:", pcd_file)
result, data = inference_detector(model, pcd_file)
print("Number of detected bboxes:", len(result['labels_3d']))
# Convert to MeshLab
os.makedirs(args.outdir, exist_ok=True)
show_result_meshlab(data, result, args.outdir)
print("Visualization result is saved in \'{}\'. "
"Please use MeshLab to visualize it.".format(
os.path.join(args.outdir,
os.path.basename(pcd_file).split('.')[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('--score-thr',
type=float,
default=0.6,
help='bbox score threshold')
parser.add_argument('--out-dir',
type=str,
default='demo',
help='dir to save results')
args = parser.parse_args()
# build the model from a config file and a checkpoint file
model = init_detector(args.config, args.checkpoint, device=args.device)
# test a single image
result, data = inference_detector(model, args.pcd)
# show the results
show_result_meshlab(data, result, args.out_dir)
def test_show_result_meshlab():
pcd = 'tests/data/nuscenes/samples/LIDAR_TOP/n015-2018-08-02-17-16-37+' \
'0800__LIDAR_TOP__1533201470948018.pcd.bin'
box_3d = LiDARInstance3DBoxes(
torch.tensor(
[[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]]))
labels_3d = torch.tensor([0])
scores_3d = torch.tensor([0.5])
points = np.random.rand(100, 4)
img_meta = dict(pts_filename=pcd,
boxes_3d=box_3d,
box_mode_3d=Box3DMode.LIDAR)
data = dict(points=[[torch.tensor(points)]], img_metas=[[img_meta]])
result = [
dict(pts_bbox=dict(
boxes_3d=box_3d, labels_3d=labels_3d, scores_3d=scores_3d))
]
tmp_dir = tempfile.TemporaryDirectory()
temp_out_dir = tmp_dir.name
out_dir, file_name = show_result_meshlab(data, result, temp_out_dir)
expected_outfile_pred = file_name + '_pred.obj'
expected_outfile_pts = file_name + '_points.obj'
expected_outfile_pred_path = os.path.join(out_dir, file_name,
expected_outfile_pred)
expected_outfile_pts_path = os.path.join(out_dir, file_name,
expected_outfile_pts)
assert os.path.exists(expected_outfile_pred_path)
assert os.path.exists(expected_outfile_pts_path)
tmp_dir.cleanup()
# test multi-modality show
# indoor scene
pcd = 'tests/data/sunrgbd/points/000001.bin'
filename = 'tests/data/sunrgbd/sunrgbd_trainval/image/000001.jpg'
box_3d = DepthInstance3DBoxes(
torch.tensor(
[[-1.1580, 3.3041, -0.9961, 0.3829, 0.4647, 0.5574, 1.1213]]))
img = np.random.randn(1, 3, 608, 832)
k_mat = np.array([[529.5000, 0.0000, 365.0000],
[0.0000, 529.5000, 265.0000], [0.0000, 0.0000, 1.0000]])
rt_mat = np.array([[0.9980, 0.0058, -0.0634], [0.0058, 0.9835, 0.1808],
[0.0634, -0.1808, 0.9815]])
rt_mat = np.array([[1, 0, 0], [0, 0, -1], [0, 1, 0]]) @ rt_mat.transpose(
1, 0)
depth2img = k_mat @ rt_mat
img_meta = dict(filename=filename,
depth2img=depth2img,
pcd_horizontal_flip=False,
pcd_vertical_flip=False,
box_mode_3d=Box3DMode.DEPTH,
box_type_3d=DepthInstance3DBoxes,
pcd_trans=np.array([0., 0., 0.]),
pcd_scale_factor=1.0,
pts_filename=pcd,
transformation_3d_flow=['R', 'S', 'T'])
data = dict(points=[[torch.tensor(points)]],
img_metas=[[img_meta]],
img=[img])
result = [dict(boxes_3d=box_3d, labels_3d=labels_3d, scores_3d=scores_3d)]
tmp_dir = tempfile.TemporaryDirectory()
temp_out_dir = tmp_dir.name
out_dir, file_name = show_result_meshlab(data,
result,
temp_out_dir,
0.3,
task='multi_modality-det')
expected_outfile_pred = file_name + '_pred.obj'
expected_outfile_pts = file_name + '_points.obj'
expected_outfile_png = file_name + '_img.png'
expected_outfile_proj = file_name + '_pred.png'
expected_outfile_pred_path = os.path.join(out_dir, file_name,
expected_outfile_pred)
expected_outfile_pts_path = os.path.join(out_dir, file_name,
expected_outfile_pts)
expected_outfile_png_path = os.path.join(out_dir, file_name,
expected_outfile_png)
expected_outfile_proj_path = os.path.join(out_dir, file_name,
expected_outfile_proj)
assert os.path.exists(expected_outfile_pred_path)
assert os.path.exists(expected_outfile_pts_path)
assert os.path.exists(expected_outfile_png_path)
assert os.path.exists(expected_outfile_proj_path)
tmp_dir.cleanup()
# outdoor scene
pcd = 'tests/data/kitti/training/velodyne_reduced/000000.bin'
filename = 'tests/data/kitti/training/image_2/000000.png'
box_3d = LiDARInstance3DBoxes(
torch.tensor(
[[6.4495, -3.9097, -1.7409, 1.5063, 3.1819, 1.4716, 1.8782]]))
img = np.random.randn(1, 3, 384, 1280)
lidar2img = np.array(
[[6.09695435e+02, -7.21421631e+02, -1.25125790e+00, -1.23041824e+02],
[1.80384201e+02, 7.64479828e+00, -7.19651550e+02, -1.01016693e+02],
[9.99945343e-01, 1.24365499e-04, 1.04513029e-02, -2.69386917e-01],
[0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 1.00000000e+00]])
img_meta = dict(filename=filename,
pcd_horizontal_flip=False,
pcd_vertical_flip=False,
box_mode_3d=Box3DMode.LIDAR,
box_type_3d=LiDARInstance3DBoxes,
pcd_trans=np.array([0., 0., 0.]),
pcd_scale_factor=1.0,
pts_filename=pcd,
lidar2img=lidar2img)
data = dict(points=[[torch.tensor(points)]],
img_metas=[[img_meta]],
img=[img])
result = [
dict(pts_bbox=dict(
boxes_3d=box_3d, labels_3d=labels_3d, scores_3d=scores_3d))
]
out_dir, file_name = show_result_meshlab(data,
result,
temp_out_dir,
0.1,
task='multi_modality-det')
tmp_dir = tempfile.TemporaryDirectory()
temp_out_dir = tmp_dir.name
expected_outfile_pred = file_name + '_pred.obj'
expected_outfile_pts = file_name + '_points.obj'
expected_outfile_png = file_name + '_img.png'
expected_outfile_proj = file_name + '_pred.png'
expected_outfile_pred_path = os.path.join(out_dir, file_name,
expected_outfile_pred)
expected_outfile_pts_path = os.path.join(out_dir, file_name,
expected_outfile_pts)
expected_outfile_png_path = os.path.join(out_dir, file_name,
expected_outfile_png)
expected_outfile_proj_path = os.path.join(out_dir, file_name,
expected_outfile_proj)
assert os.path.exists(expected_outfile_pred_path)
assert os.path.exists(expected_outfile_pts_path)
assert os.path.exists(expected_outfile_png_path)
assert os.path.exists(expected_outfile_proj_path)
tmp_dir.cleanup()
# test mono-3d show
filename = 'tests/data/nuscenes/samples/CAM_BACK_LEFT/n015-2018-' \
'07-18-11-07-57+0800__CAM_BACK_LEFT__1531883530447423.jpg'
box_3d = CameraInstance3DBoxes(
torch.tensor(
[[6.4495, -3.9097, -1.7409, 1.5063, 3.1819, 1.4716, 1.8782]]))
img = np.random.randn(1, 3, 384, 1280)
cam2img = np.array([[100.0, 0.0, 50.0], [0.0, 100.0, 50.0],
[0.0, 0.0, 1.0]])
img_meta = dict(filename=filename,
pcd_horizontal_flip=False,
pcd_vertical_flip=False,
box_mode_3d=Box3DMode.CAM,
box_type_3d=CameraInstance3DBoxes,
pcd_trans=np.array([0., 0., 0.]),
pcd_scale_factor=1.0,
cam2img=cam2img)
data = dict(points=[[torch.tensor(points)]],
img_metas=[[img_meta]],
img=[img])
result = [
dict(img_bbox=dict(
boxes_3d=box_3d, labels_3d=labels_3d, scores_3d=scores_3d))
]
out_dir, file_name = show_result_meshlab(data,
result,
temp_out_dir,
0.1,
task='mono-det')
tmp_dir = tempfile.TemporaryDirectory()
temp_out_dir = tmp_dir.name
expected_outfile_png = file_name + '_img.png'
expected_outfile_proj = file_name + '_pred.png'
expected_outfile_png_path = os.path.join(out_dir, file_name,
expected_outfile_png)
expected_outfile_proj_path = os.path.join(out_dir, file_name,
expected_outfile_proj)
assert os.path.exists(expected_outfile_png_path)
assert os.path.exists(expected_outfile_proj_path)
tmp_dir.cleanup()
# test seg show
pcd = 'tests/data/scannet/points/scene0000_00.bin'
points = np.random.rand(100, 6)
img_meta = dict(pts_filename=pcd)
data = dict(points=[[torch.tensor(points)]], img_metas=[[img_meta]])
pred_seg = torch.randint(0, 20, (100, ))
result = [dict(semantic_mask=pred_seg)]
tmp_dir = tempfile.TemporaryDirectory()
temp_out_dir = tmp_dir.name
out_dir, file_name = show_result_meshlab(data,
result,
temp_out_dir,
task='seg')
expected_outfile_pred = file_name + '_pred.obj'
expected_outfile_pts = file_name + '_points.obj'
expected_outfile_pred_path = os.path.join(out_dir, file_name,
expected_outfile_pred)
expected_outfile_pts_path = os.path.join(out_dir, file_name,
expected_outfile_pts)
assert os.path.exists(expected_outfile_pred_path)
assert os.path.exists(expected_outfile_pts_path)
tmp_dir.cleanup()
def main():
parser = ArgumentParser()
parser.add_argument(
'--pcd',
type=str,
default='./demo/kitti_000008.bin',
help='Point cloud file'
) #/data/cmpe249-fa21/4c_train5678/training/velodyne/008118.bin
parser.add_argument(
'--config',
type=str,
default=
'./configs/second/myhv_second_secfpn_sbn_2x16_2x_waymoD5-3d-4class.py',
help='Config file')
parser.add_argument(
'--checkpoint',
type=str,
default=
'../modelzoo_mmdetection3d/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth',
help='Checkpoint file')
parser.add_argument('--device',
default='cuda:0',
help='Device used for inference')
parser.add_argument('--score-thr',
type=float,
default=0.6,
help='bbox score threshold')
parser.add_argument('--out-dir',
type=str,
default='demo',
help='dir to save results')
args = parser.parse_args()
# build the model from a config file and a checkpoint file
model = init_detector(args.config, args.checkpoint, device=args.device)
# test a single image
result, data = inference_detector(model, args.pcd)
print(result) # three keys: 'boxes_3d', 'scores_3d', 'labels_3d'
points = data['points'][0][0].cpu().numpy() # points number *4
pts_filename = data['img_metas'][0][0]['pts_filename']
print("pts_filename:", pts_filename)
file_name = osp.split(pts_filename)[-1].split('.')[0] #006767
print(data['img_metas'])
print(data['img_metas'][0][0]['box_mode_3d']) #Box3DMode.LIDAR
print("results len:", len(result[0])) # len=1,
for res in result[0].keys():
print(res)
#boxes_3d, scores_3d, labels_3d
pred_bboxes = result[0]['boxes_3d'].tensor.numpy()
print(
pred_bboxes
) # [11,7], Each row is (x, y, z, x_size, y_size, z_size, yaw) in Box3DMode.LIDAR
print(type(pred_bboxes)) #numpy.ndarray
print("box_mode_3d:",
data['img_metas'][0][0]['box_mode_3d']) #Box3DMode.LIDAR
# show the results (points save to xxx_points.obj file, pred3d box save to xxx_pred.ply, these two files can opend by meshlab)
show_result_meshlab(data, result, args.out_dir)
parser.add_argument("--outdir",
type=str,
default='cache/',
help="Path to the output directory")
args = parser.parse_args()
# Build dataset
cfg = mmcv.Config.fromfile(args.cfg)
dataset = build_dataset(cfg.data.train)
# Select a sample
sample = dataset.__getitem__(args.idx)
# Convert to MeshLab
data = dict(
img_metas=[[sample['img_metas'].data]],
points=[[sample['points'].data]],
)
gts = dict(
boxes_3d=sample['gt_bboxes_3d'].data,
scores_3d=torch.ones([len(sample['gt_labels_3d'].data)]),
labels_3d=sample['gt_labels_3d'].data,
)
os.makedirs(args.outdir, exist_ok=True)
show_result_meshlab(data, gts, args.outdir)
print(
"\nVisualization result is saved in \'{}\'. Please use MeshLab to visualize it."
.format(args.outdir))
