import os import pandas as pd import torch import torch.nn as nn from torch_geometric.data import Data, DataLoader from torch_geometric.nn import GCNConv import torch.nn.functional as F from sklearn.model_selection import train_test_split

加载数据并创建PyG数据集类：

class MyDataset(torch.utils.data.Dataset): def init(self, root, transform=None, pre_transform=None): self.edges = pd.read_csv(os.path.join(root, 'edges_L.csv')) self.transform = transform self.pre_transform = pre_transform self.num_classes = 8 # 修改成8类标签 self.features = [] self.labels = []

    for i in range(1, 43):
        for j in range(37):
            feature_path = os.path.join(root, 'images_block', f'{i}.png_{j}.png')
            label_path = os.path.join(root, 'labels', f'{i}_{j}.txt')  # 修改标签文件名
            
            features = pd.read_csv(feature_path, header=None, sep=' ')
            labels = pd.read_csv(label_path, header=None, sep=' ', encoding='ansi')
            
            self.features.append(torch.tensor(features.values, dtype=torch.float))
            self.labels.append(torch.tensor(labels.values.squeeze(), dtype=torch.long))  # 修改标签数据类型为long型

def __len__(self):
    return len(self.features)

def __getitem__(self, idx):
    edge_index = torch.tensor(self.edges.values, dtype=torch.long).t().contiguous()
    x = self.features[idx]
    y = self.labels[idx]
    
    # 定义图数据的train_mask和val_mask
    train_mask = torch.zeros(y.size(0), dtype=torch.bool)
    val_mask = torch.zeros(y.size(0), dtype=torch.bool)
    train_mask[:30] = 1
    val_mask[30:] = 1
    
    data = Data(x=x, edge_index=edge_index, y=y, train_mask=train_mask, val_mask=val_mask)
    
    if self.transform is not None:
        data = self.transform(data)
    
    return data

定义GCN模型：

class GCN(torch.nn.Module): def init(self, num_node_features, num_classes): super(GCN, self).init() self.conv1 = GCNConv(num_node_features, 8) self.conv2 = GCNConv(8, 16) self.conv3 = GCNConv(16, num_classes)

def forward(self, data):
    x, edge_index = data.x, data.edge_index
    x = self.conv1(x, edge_index)
    x = F.relu(x)
    x = self.conv2(x, edge_index)
    x = F.relu(x)
    x = F.dropout(x, training=self.training)
    x = self.conv3(x, edge_index)
    return x

创建训练和验证模型：

def train_model(dataset, model, optimizer, device): model.train() total_loss = 0.0

for data in dataset:
    data = data.to(device)
    optimizer.zero_grad()
    output = model(data)
    loss = F.cross_entropy(output[data.train_mask], data.y[data.train_mask])
    loss.backward()
    optimizer.step()
    total_loss += loss.item()

return total_loss / len(dataset)

def validate_model(dataset, model, device): model.eval() correct = 0 total = 0

for data in dataset:
    data = data.to(device)
    output = model(data)
    _, predicted = torch.max(output[data.val_mask], 1)
    total += data.val_mask.sum().item()
    correct += (predicted == data.y[data.val_mask]).sum().item()

return correct / total

加载数据集、创建模型、定义优化器和训练循环，以及验证模型：

if name == 'main': dataset = MyDataset(root="C:\Users\jh\Desktop\data\input") device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

model = GCN(num_node_features=1600, num_classes=8).to(device)  # 修改num_classes为8
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)

train_dataset, val_dataset = train_test_split(dataset, test_size=0.1)
train_loader = DataLoader(train_dataset, batch_size=1, shuffle=False)
val_loader = DataLoader(val_dataset, batch_size=1, shuffle=False)

epochs = 2
for epoch in range(epochs):
    train_loss = train_model(train_loader, model, optimizer, device)
    print(f'Epoch {epoch + 1}/{epochs}, Train Loss: {train_loss:.4f}')

val_accuracy = validate_model(val_loader, model, device)
print(f'Val_Acc: {val_accuracy:.4f}')