转载请注明出处:小锋学长生活大爆炸[xfxuezhang.cn]
本教程以DGL版本的GCN为例,其他也相似。
1、安装cython、gcc:
sudo apt install cython gcc -y
2、安装DGL、PyTorch:
pip3 install torch torchvision torchaudio
pip install dgl -f https://data.dgl.ai/wheels/cu117/repo.html
pip install dglgo -f https://data.dgl.ai/wheels-test/repo.html
3、编写gcn.py。注意添加# cython: language_level=3,不然默认用的是python2:
# cython: language_level=3import torch
import torch.nn as nn
import torch.nn.functional as F
import dgl
from dgl.data import CoraGraphDataset
from dgl.nn import GraphConv# 定义 GCN 模型
class GCN(nn.Module):def __init__(self, in_feats, h_feats, num_classes):super(GCN, self).__init__()self.conv1 = GraphConv(in_feats, h_feats)self.conv2 = GraphConv(h_feats, num_classes)def forward(self, g, in_feat):h = self.conv1(g, in_feat)h = F.relu(h)h = self.conv2(g, h)return hif __name__ == "__main__":# 加载数据集dataset = CoraGraphDataset()g = dataset[0]# 创建模型实例model = GCN(g.ndata['feat'].shape[1], 16, dataset.num_classes)# 定义损失函数和优化器optimizer = torch.optim.Adam(model.parameters(), lr=0.01)criterion = nn.CrossEntropyLoss()# 训练模型for epoch in range(200):logits = model(g, g.ndata['feat'])loss = criterion(logits[g.ndata['train_mask']], g.ndata['label'][g.ndata['train_mask']])optimizer.zero_grad()loss.backward()optimizer.step()if epoch % 10 == 0:print(f'Epoch {epoch}, Loss: {loss.item()}')# 测试模型model.eval()with torch.no_grad():logits = model(g, g.ndata['feat'])_, predicted = torch.max(logits[g.ndata['test_mask']], 1)correct = (predicted == g.ndata['label'][g.ndata['test_mask']]).sum().item()acc = correct / len(predicted)print(f'Accuracy: {acc:.4f}')
4、使用cython将Python转为C语言,此时会生成一个gcn.c文件。注意要加--embed:
cython gcn.py --embed
5、然后使用 C 编译器来编译gcn.c文件,此时会生成一个gcn.o文件:
gcc -c gcn.c `python3-config --includes` `python3-config --ldflags` -o gcn.o
6、链接生成可执行文件,此时会生成一个gcn可执行文件。注意这里-L后面改成你的路径:
gcc gcn.o -L/home/sxf/anaconda3/envs/dgl/lib -lpython3.9 -o gcn
7、运行二进制可执行文件:
./gcn
8、如果报错:error while loading shared libraries: libpython3.9.so.1.0: cannot open shared object file: No such file or directory。就把这个so文件的路径包含进来,再重新执行步骤7。注意这里后面改成你的路径:
export LD_LIBRARY_PATH=/home/sxf/anaconda3/envs/dgl/lib/:$LD_LIBRARY_PATH
9、最终效果:
注意:如果你有多个自定义的py文件要import进来,那么自定义的几个py文件需要转为so库文件,来被主文件调用。而如果只有一个py文件,就没有这个问题了。