Hi, I’m trying to work 3D semantic segmentation with Intel RealSense camera(D455).
“vis_pred.py” is correctly working and I’m modifying the sample source code.
I referred to the following article and set the label of my point cloud to zero.
However, the following error message is displayed when “results_r = pipeline_r.run_inference(data)” is executed.
File “/home/makoto/.local/lib/python3.8/site-packages/open3d/_ml3d/datasets/samplers/semseg_spatially_regular.py”, line 86, in _random_centered_gen
idxs = list(idxs) + list(random.choices(idxs, k=diff))
NameError: name ‘diff’ is not defined
SemanticKITTI dataset is no problem. This problem only happens when I use my point cloud data from Intel RealSense and the labels (all zero).
What I would like to do is to correctly work 3D semantic segmentation by using Intel RealSense (D455) in real time.
Could you please let me know what I should do, anyone?