pytorch使用gpu

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms

# 定义简单的 CNN 模型
class SimpleCNN(nn.Module):
    def __init__(self):
        super(SimpleCNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.fc1 = nn.Linear(64 * 5 * 5, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = nn.functional.relu(self.conv1(x))
        x = nn.functional.relu(self.conv2(x))
        x = x.view(x.size(0), -1)
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return nn.functional.log_softmax(x, dim=1)

# 数据预处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

# 加载 MNIST 数据集
train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True, num_workers=4)

# 检查 GPU 可用性并设置设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 初始化模型、损失函数和优化器
model = SimpleCNN().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
for epoch in range(10):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 100 == 0:
            print(f'Epoch {epoch+1}, Batch {batch_idx}, Loss {loss.item()}')