An Issue related to running the furthest_point_sampling function

[NeilCui6]

Dear Author,

Hope you are well.

I got an issue related to the pointnet2_utils.py and setup.py files. When I stalled setup.py the file, I got a warning below related to the GCC version.

Then when I was running the highlighted part within the setup.py below, I got an error of "Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)".

Just wondering if you happen to know what's the issue? Does it related to the g++version?

Our PyTorch version is 1.2.0.

Many thanks! @hehefan

[hehefan]

Hi @NeilCui6,

Did you successfully compile the PointNet++ operations?

[NeilCui6]

Hi @NeilCui6,

Did you successfully compile the PointNet++ operations?

Many thanks for your reply, @hehefan ! All good now. It was the GCC version issue, which has been solved.

May I ask you another question? when running the MSRAction dataset, do I need to do any conversion with the original bin type data(like using the codes provided by the dataset to load and display depth map )？ Also, do I need to convert it to cloud points like what needs to be done for the NTU data by using your depth2point4ntu.py code？

Thanks again!

[hehefan]

Hi, you do need to convert the MSRAction dataset. The MeteorNet work provides a way to do that.

[NeilCui6]

All good now. Thanks a lot for your help! : ) @hehefan