pytorch 单机单卡的脚本怎么修改为单机多卡？

要将 PyTorch 单机单卡的脚本修改为单机多卡，需要执行以下步骤：

1. 导入必要的库和设定参数

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

# 设定参数
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
batch_size = 64
epochs = 10
learning_rate = 0.01

2. 加载数据集并进行数据增广

# 加载数据集
train_dataset = datasets.CIFAR10(root='./data', train=True, download=True, transform=transforms.ToTensor())
test_dataset = datasets.CIFAR10(root='./data', train=False, download=True, transform=transforms.ToTensor())

# 数据增广
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=4, pin_memory=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False, num_workers=4, pin_memory=True)

3. 定义模型和损失函数

# 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(nn.functional.relu(self.conv1(x)))
        x = self.pool(nn.functional.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = nn.functional.relu(self.fc1(x))
        x = nn.functional.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# 定义损失函数
criterion = nn.CrossEntropyLoss()

4. 初始化模型和优化器

# 初始化模型和优化器
model = Net().to(device)
if torch.cuda.device_count() > 1:
    model = nn.DataParallel(model)
optimizer = optim.SGD(model.parameters(), lr=learning_rate, momentum=0.9)

5. 训练模型

# 训练模型
for epoch in range(epochs):
    model.train()
    train_loss = 0.0
    for i, (inputs, labels) in enumerate(train_loader):
        inputs, labels = inputs.to(device), labels.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        train_loss += loss.item() * inputs.size(0)
    train_loss /= len(train_loader.dataset)
    print('Epoch: {} \tTraining Loss: {:.6f}'.format(epoch+1, train_loss))

6. 测试模型

# 测试模型
model.eval()
correct = 0
total = 0
with torch.no_grad():
    for inputs, labels in test_loader:
        inputs, labels = inputs.to(device), labels.to(device)
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
accuracy = 100 * correct / total
print('Accuracy: %.2f%%' % accuracy)

在第四步中，我们使用了 `nn.DataParallel` 函数来将模型在多个 GPU 上并行计算。当有多个 GPU 时，PyTorch 会自动将 batch 拆分到不同的 GPU 上进行计算，然后将结果合并。在使用 `nn.DataParallel` 时，需要将模型包装在 `nn.DataParallel` 中，然后将其移到 GPU 上。如果只有一个 GPU，则不需要使用 `nn.DataParallel`。