写出pytorch多gpu训练的代码

以下是使用 PyTorch 进行多 GPU 训练的示例代码：

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision.datasets import CIFAR10
from torchvision.transforms import transforms

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# 定义训练函数
def train(model, device, train_loader, optimizer, criterion):
    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()

# 定义测试函数
def test(model, device, test_loader, criterion):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += criterion(output, target).item()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)
    accuracy = 100. * correct / len(test_loader.dataset)
    print('Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)'.format(
        test_loss, correct, len(test_loader.dataset), accuracy))

# 定义主函数
def main():
    # 设置超参数
    batch_size = 128
    epochs = 10
    lr = 0.01
    momentum = 0.9
    num_workers = 4
    num_gpus = torch.cuda.device_count()

    # 加载数据集
    transform = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
    ])
    train_dataset = CIFAR10(root='./data', train=True, download=True, transform=transform)
    test_dataset = CIFAR10(root='./data', train=False, download=True, transform=transform)
    train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=num_workers)
    test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False, num_workers=num_workers)

    # 初始化模型和优化器
    model = Net()
    if num_gpus > 1:
        model = nn.DataParallel(model)
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model.to(device)
    optimizer = optim.SGD(model.parameters(), lr=lr, momentum=momentum)
    criterion = nn.CrossEntropyLoss()

    # 训练和测试
    for epoch in range(1, epochs + 1):
        train(model, device, train_loader, optimizer, criterion)
        test(model, device, test_loader, criterion)

if __name__ == '__main__':
    main()

这个示例代码可以在多个 GPU 上并行训练模型，如果只有一个 GPU，可以将 `num_gpus` 设置为 1。