Linux CUDA11.6 Python3.8 安装pytorch-geometric

最近在学习图神经网络，需要安装pytorch-geometric。

pytorch-geometric安装教程

Pytorch-gemetric适配 python3.8-3.11版本

1. 首先创建python3.8环境

conda create --name PyG python=3.8
conda activate PyG

2. 安装PyTorch

conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.6 -c pytorch -c nvidia

3. 安装pytorch-geometric

pip install torch-geometric

4. 安装测试

import torch
print(torch.cuda.is_available())
print(torch.cuda.device_count())
print(torch.version.cuda)

from torch_geometric.nn import GCNConv
class GCN(torch.nn.Module):
    def __init__(self, hidden_channels):
        super().__init__()
        torch.manual_seed(1234567)
        self.conv1 = GCNConv(1433, hidden_channels)
        self.conv2 = GCNConv(hidden_channels, 7)

    def forward(self, x, edge_index):
        x = self.conv1(x, edge_index)
        x = x.relu()
        x = F.dropout(x, p=0.5, training=self.training)
        x = self.conv2(x, edge_index)
        return x

model = GCN(hidden_channels=16)
print(model)

>>
True
8
11.6
GCN(
  (conv1): GCNConv(1433, 16)
  (conv2): GCNConv(16, 7)
)