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10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

以下是使用PyTorch实现的代码，使用了pytorch_geometric库来加载和处理Cora数据集，并使用GCNConv实现了10层图卷积神经网络，并在每一层之间添加了Res残差连接：

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

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

# Define graph convolutional neural network
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = GCNConv(dataset.num_features, 16)
        self.conv2 = GCNConv(16, 16)
        self.conv3 = GCNConv(16, 16)
        self.conv4 = GCNConv(16, 16)
        self.conv5 = GCNConv(16, 16)
        self.conv6 = GCNConv(16, 16)
        self.conv7 = GCNConv(16, 16)
        self.conv8 = GCNConv(16, 16)
        self.conv9 = GCNConv(16, 16)
        self.conv10 = GCNConv(16, dataset.num_classes)

    def forward(self, x, edge_index):
        # Apply first convolutional layer
        x1 = F.relu(self.conv1(x, edge_index))
        # Apply second convolutional layer and add Res connection
        x2 = F.relu(self.conv2(x1, edge_index) + x1)
        # Apply third convolutional layer and add Res connection
        x3 = F.relu(self.conv3(x2, edge_index) + x2)
        # Apply fourth convolutional layer and add Res connection
        x4 = F.relu(self.conv4(x3, edge_index) + x3)
        # Apply fifth convolutional layer and add Res connection
        x5 = F.relu(self.conv5(x4, edge_index) + x4)
        # Apply sixth convolutional layer and add Res connection
        x6 = F.relu(self.conv6(x5, edge_index) + x5)
        # Apply seventh convolutional layer and add Res connection
        x7 = F.relu(self.conv7(x6, edge_index) + x6)
        # Apply eighth convolutional layer and add Res connection
        x8 = F.relu(self.conv8(x7, edge_index) + x7)
        # Apply ninth convolutional layer and add Res connection
        x9 = F.relu(self.conv9(x8, edge_index) + x8)
        # Apply final convolutional layer and return output
        x10 = self.conv10(x9, edge_index)
        return F.log_softmax(x10, dim=1)

# Train and test the model
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = Net().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)

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])
    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)
    correct = float(pred[data.test_mask].eq(data.y[data.test_mask]).sum().item())
    acc = correct / data.test_mask.sum().item()
    return acc

for epoch in range(1, 201):
    loss = train()
    acc = test()
    print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}, Test Acc: {acc:.4f}')

请注意，对于Res连接，我们在每一层中将输出与上一层的输入相加。在这个例子中，我们使用了ReLU作为激活函数，并使用Adam优化器进行训练。