pytorch_geometric + MinkowskiEng

pytroch_geometric
cuda用的是10.1
cuda版本不对会出现问题。

• cuda version

$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Wed_Apr_24_19:10:27_PDT_2019
Cuda compilation tools, release 10.1, V10.1.168

• pytroch 安装（先卸载了老版本

pip install torch==1.5.1+cu101 torchvision==0.6.1+cu101 -f https://download.pytorch.org/whl/torch_stable.html

• MinkowskiEngine安装(按照官网的教程安装的
  注意MinkowskiEngine一定要在pytorch安装完毕之后再安装

git clone https://github.com/StanfordVL/MinkowskiEngine.git
cd MinkowskiEngine
python setup.py install

• pytroch_geometric 安装

$ pip install torch-scatter==latest+cu101 -f https://pytorch-geometric.com/whl/torch-1.5.0.html
$ pip install torch-sparse==latest+cu101 -f https://pytorch-geometric.com/whl/torch-1.5.0.html
$ pip install torch-cluster==latest+cu101 -f https://pytorch-geometric.com/whl/torch-1.5.0.html
$ pip install torch-spline-conv==latest+cu101 -f https://pytorch-geometric.com/whl/torch-1.5.0.html
$ pip install torch-geometric

验证安装结果

$ python 
Python 3.8.3 (default, May 19 2020, 18:47:26) 
[GCC 7.3.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> import torchvision
>>> import MinkowskiEngine
>>> import torch_geometric
>>> torch.cuda.is_available()
True

$ pip list
MinkowskiEngine       0.4.3
torch                 1.5.1+cu101
torch-cluster         1.5.5
torch-geometric       1.6.0
torch-scatter         2.0.5
torch-sparse          0.6.6
torch-spline-conv     1.2.0
torchvision           0.6.1+cu101