torch-points-kernels 0.6.5

PyTorch kernels for spatial operations on point clouds

3D Point Cloud Kernels

Pytorch CPU and CUDA kernels for spatial search and interpolation for 3D point clouds.

Installation

Requires torch version 1.0 or higher to be installed before proceeding. Once this is done, simply run

pip install torch-points-kernels

or with poetry:

poetry add torch-points-kernels

Usage

import torch
import torch_points_kernels.points_cuda

Build and test

python setup.py build_ext --inplace
python -m unittest

Troubleshooting

Ensure that at least PyTorch 1.4.0 is installed and verify that cuda/bin and cuda/include are in your $PATH and $CPATH respectively, e.g.:

$ python -c "import torch; print(torch.__version__)"
>>> 1.4.0

$ python -c "import torch; print(torch.__version__)"
>>> 1.1.0

$ echo $PATH
>>> /usr/local/cuda/bin:...

$ echo $CPATH
>>> /usr/local/cuda/include:...

Projects using those kernels.

Pytorch Point Cloud Benchmark

Credit

• Pointnet2_Tensorflow by Charles R. Qi

• Pointnet2_PyTorch by Erik Wijmans