TypeError: float() argument must be a string or a number, not 'open3d.open3d.geometry.PointCloud'

[Chunsheng13]

when I run predict.py and predict_ros.py it comes the same error:

root@xiufeij-System-Product-Name:/home/se3_tracknet# python predict.py ckpt_dir: weights/YCB_weights/bleach_cleanser/model_best_val.pth.tar dataset_info_path ./dataset_info.yml YCBInEOAT/bleach0 self.object_cloud loaded and downsampled Traceback (most recent call last): File "predict.py", line 663, in predictSequenceMyData() File "predict.py", line 566, in predictSequenceMyData tracker = Tracker(dataset_info, images_mean, images_std,ckpt_dir, trans_normalizer=0.03, rot_normalizer=30np.pi/180) File "predict.py", line 136, in init object_max_width = compute_obj_max_width(self.object_cloud) File "/home/se3_tracknet/Utils.py", line 450, in compute_obj_max_width return compute_cloud_diameter(model_cloud) 1000 File "/home/se3_tracknet/Utils.py", line 102, in compute_cloud_diameter hull = ConvexHull(points) File "qhull.pyx", line 2421, in scipy.spatial.qhull.ConvexHull.init File "/usr/local/lib/python3.6/dist-packages/numpy/core/_asarray.py", line 177, in ascontiguousarray return array(a, dtype, copy=False, order='C', ndmin=1) TypeError: float() argument must be a string or a number, not 'open3d.open3d.geometry.PointCloud'

is it numpy version problem or something else? hope you can help me figure out what happent,thanks very much

[wenbowen123]

I fixed the bug. Can you please try again?

[Chunsheng13]

Thank you very much for your helping, should I re download the docker image or something else?

[wenbowen123]

No need. You can directly run.