ShapeNet.Points error at ShapeNetCore.v2

[dkasuga]

I tried to apply examples/ImageRecon/Image_Mesh_Recon_Direct/train.py to ShapeNetCore.v2 Dataset, but I encountered this error:

File "train_Core.py", line 104, in
train = True, split = .7, num_points=3000 )
File "/kaolin/lib/python3.6/site-packages/kaolin-0.1.0-py3.6-linux-x86_64.egg/kaolin/datasets/shapenet.py", line 563, in init
File "/kaolin/lib/python3.6/site-packages/kaolin-0.1.0-py3.6-linux-x86_64.egg/kaolin/datasets/shapenet.py", line 443, in init
File "/kaolin/lib/python3.6/site-packages/kaolin-0.1.0-py3.6-linux-x86_64.egg/kaolin/datasets/shapenet.py", line 368, in init
File "/kaolin/lib/python3.6/site-packages/kaolin-0.1.0-py3.6-linux-x86_64.egg/kaolin/transforms/transforms.py", line 98, in call
File "/kaolin/lib/python3.6/site-packages/kaolin-0.1.0-py3.6-linux-x86_64.egg/kaolin/transforms/transforms.py", line 54, in call
File "/kaolin/lib/python3.6/site-packages/kaolin-0.1.0-py3.6-linux-x86_64.egg/kaolin/transforms/transforms.py", line 694, in call
File "~/kaolin/lib/python3.6/site-packages/kaolin-0.1.0-py3.6-linux-x86_64.egg/kaolin/conversions/meshconversions.py", line 141, in trianglemesh_to_voxelgrid
IndexError: index 101 is out of bounds for dimension 0 with size 100

Does anybody have the same problem?

In the first place, the original code has some bugs and can solve it easily(#25).

[GeronimoRoeder1]

same problem here, also with ShapeNetCore.v2, is there a solution yet? @dkasuga

[realptkkit]

Have you found a way to fix this @dkasuga @GeronimoRoeder1 ?
I already tried something like #292, but it just gave me a SIGKILL error which I couldn't figure out yet.

[kosuke55]

@realptkkit
Can you share the error when using #292 ?
What will happen to the result of running a simple script on a mesh that causes an error?

# mesh is your mesh that causes an error
voxels = kal.conversions.trianglemesh_to_voxelgrid(mesh, 32, normalize=False, vertex_offset=0.5, voxel_range=1.08)

[Caenorst]

Hi, thank you for using Kaolin! The library went through a major rewrite with the version 0.9.0, and only the core library components we can thoroughly test and maintain are now part of this repository. Please refer to our latest documentation:
https://kaolin.readthedocs.io/en/latest/

Closing the bug as it is no longer relevant to this repo.