图卷积神经网络要求每一层之间都加入Res残差连接，要求有12层图卷积层，并且完成对cora数据集的训练与测试，写一段python代码

好的，下面是一份使用PyTorch实现12层ResGCN对cora数据集进行训练和测试的代码：

首先，需要引入必要的库和包：

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch_geometric.nn import GCNConv
from torch_geometric.datasets import Planetoid

然后，定义ResGCN模型，包括ResGCN层和一个全连接层：

class ResGCN(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(ResGCN, self).__init__()
        self.conv1 = GCNConv(in_channels, out_channels)
        self.conv2 = GCNConv(out_channels, out_channels)
        self.res_conv = GCNConv(in_channels, out_channels)
        self.fc = nn.Linear(out_channels, 7)

    def forward(self, x, edge_index):
        res = self.res_conv(x, edge_index)
        x = self.conv1(x, edge_index)
        x = F.relu(x)
        x = self.conv2(x, edge_index)
        x = x + res
        x = F.relu(x)
        x = self.fc(x)
        return F.log_softmax(x, dim=1)

接着，加载cora数据集：

dataset = Planetoid(root='/tmp/Cora', name='Cora')
data = dataset[0]

然后，定义模型和优化器：

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = ResGCN(dataset.num_features, 64).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)

接下来，定义训练函数和测试函数：

def train():
    model.train()
    optimizer.zero_grad()
    out = model(data.x.to(device), data.edge_index.to(device))
    loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask].to(device))
    loss.backward()
    optimizer.step()
    return loss.item()

def test():
    model.eval()
    out = model(data.x.to(device), data.edge_index.to(device))
    pred = out.argmax(dim=1)
    test_correct = pred[data.test_mask] == data.y[data.test_mask].to(device)
    test_acc = int(test_correct.sum()) / int(data.test_mask.sum())
    return test_acc

最后，进行训练和测试，并输出测试准确率：

for epoch in range(1, 101):
    loss = train()
    test_acc = test()
    print('Epoch: {:03d}, Loss: {:.4f}, Test Acc: {:.4f}'.format(epoch, loss, test_acc))

完整代码如下：