Using CUDA programming for parallel acceleration, efficient K-nearest neighbors (KNN) can be implemented

The testing environment is: pytorch, python3+, CUDA programming

dependency

Tested with cuda 11.7, python 3.7.16, pytorch 1.13.1, gcc 11.2.0

# clone the tool project
git clone https://github.com/upc-ghy/KNN.git
# cd KNN
cd KNN/
# install
sudo python setup.py install

python test.py

Name		Name	Last commit message	Last commit date
Latest commit History 8 Commits
Pytorch_CUDA_KNN		Pytorch_CUDA_KNN
README.md		README.md
knn_modules.py		knn_modules.py
setup.py		setup.py
sub.sh		sub.sh
test.py		test.py