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 from PIL import Image

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.img_dir = os.path.join(root, 'images') self.label_dir = os.path.join(root, 'labels') self.edge_file = os.path.join(root, 'edges_L.csv') self.transform = transform self.pre_transform = pre_transform self.dataset, self.edges = self.create_dataset()

    # 将train_mask和val_mask定义在__init__函数中
    self.train_mask = torch.zeros(len(self.dataset), dtype=torch.bool)
    self.val_mask = torch.zeros(len(self.dataset), dtype=torch.bool)
    self.train_mask[:30] = 1
    self.val_mask[30:] = 1
    
def create_dataset(self):
    dataset = []
    edges = None
    edge_index, num_nodes = self.read_edges(self.edge_file)
    
    for i in range(1, 43):
        for j in range(37):
            image_path = os.path.join(self.img_dir, f'{i}.png_{j}.png')
            label_path = os.path.join(self.label_dir, f'{i}_{j}.txt')
            features = self.read_image_features(image_path)
            labels = self.read_labels(label_path)
            labels = torch.tensor(labels, dtype=torch.long)
            features = torch.tensor(features).unsqueeze(0)
            features = features.float()
            data = Data(
                x=features, edge_index=edge_index, y=labels,
                train_mask=self.train_mask, val_mask=self.val_mask
            )
            dataset.append(data)
    
    return dataset, edges

def read_edges(self, edge_path):
    edges = []
    with open(edge_path, 'r') as file:
        for line in file:
            src, tgt = line.strip().split(',')
            edges.append((int(src), int(tgt)))

    max_node_idx = max(max(edges, key=lambda x: max(x)))
    num_nodes = max_node_idx + 1
    edge_index = torch.tensor(edges, dtype=torch.long).t().contiguous()

    return edge_index, num_nodes

def read_image_features(self, image_path):
    img = Image.open(image_path)
    img = img.resize((40, 40))
    rgb_img = img.convert('RGB')
    
    features = []
    for i in range(40):
        for j in range(40):
            r, g, b = rgb_img.getpixel((i, j))
            features.append([r, g, b])
    
    return features

def read_labels(self, label_path):
    with open(label_path, 'r') as file:
        labels = [int(label) for label in file.read().strip().split()]
        
    return labels

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

def __getitem__(self, idx):
    data = self.dataset[idx]
    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

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=3, num_classes=8).to(device) 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}')