20220509Pytorch安装torch-geometric, torch-sparse, torch-scatter, torch-cluster, torch-spline-conv

第一步：在Pytorch中下载需要的版本

链接：https://pytorch.org/get-started/previous-versions/
e.g. torch == 1.7.1

# CUDA 11.0
pip install torch==1.7.1+cu110 torchvision==0.8.2+cu110 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html

# CUDA 10.2
pip install torch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2

# CUDA 10.1
pip install torch==1.7.1+cu101 torchvision==0.8.2+cu101 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html

# CUDA 9.2
pip install torch==1.7.1+cu92 torchvision==0.8.2+cu92 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html

# CPU only
pip install torch==1.7.1+cpu torchvision==0.8.2+cpu torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html

第二步：根据自己下载的Torch、cuda、python版本，下载对应的torch-geometric, torch-sparse, torch-scatter, torch-cluster, torch-spline-conv。

链接：https://data.pyg.org/whl/
e.g.

# 如果在第一步下载了torch==1.7.1+cu110，python=3.7，那么就在上述链接中选择对应版本的torch，然后再选择对应的包下载
# 下载之后尽可以进行安装
pip install torch_cluster-1.5.8-cp37-cp37m-linux_x86_64.whl
pip install torch_scatter-2.0.5-cp37-cp37m-linux_x86_64.whl
pip install torch_sparse-0.6.8-cp37-cp37m-linux_x86_64.whl
pip install torch_spline_conv-1.2.0-cp37-cp37m-linux_x86_64.whl
pip install torch_geometric==1.7.0

完成！