Yang7879/3D-BoNet

ModuleNotFoundError: No module named 'open3d.linux.open3d'

fxy2012 opened this issue · 5 comments

Thank you for your sharing of the codes. And I would like to ask can I use open3d for windows to visualize the results. I faced the problem below. I only use python for windows to visualize the results because it seems my server can't show the images, just see the second picture.
OL)RHKV~ML)@3%I {GDP31E

{1T{CBFZBVX@@UFB82J{BZ4

Hi @fxy2012 , tbh, I don't know how to make it work on a windows machine. If you need to visualize the pc, I suggest you use Matlab in windows OS.

@Yang7879 Thank you for your reply. I have solved this problem. But the codes for visualization in main_eval.py always show that sem_gt_all is empty. Does there something wrong with the array sem_gt_all ?
And I would like to know how I could get the segmentation of the object ,which will show the boxes around the object.

@fxy2012 , (1) Plz check whether the sem gt labels are well loaded from your datasets. (2) After obtaining the instance segmentation results, you may compute the bounding box by checking the min-max vertex.

@Yang7879 Thank you for your help! I have solved the problems above. Then could you please tell me how you compute the mPrec on dataset S3DIS ? Prec = The boxes whose IoU >0.5 / The number of total boxes( In one scene). Is this right? Then the mean Prec is the average of all scenes. Is it right?

@fxy2012, For each category, the Prec is computed after gathering predicted results from all scenes. The mPrec is the average score from all categories. Plz check the code below carefully.

pre_all = []