简单的方式，设置pytorch框架上，使用两个GPU进行加速

使用PyTorch框架进行多GPU加速非常简单，只需要遵循以下步骤：

1. 导入必要的PyTorch库

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader

2. 定义模型

class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.fc1 = nn.Linear(784, 512)
        self.fc2 = nn.Linear(512, 10)
        self.relu = nn.ReLU()

    def forward(self, x):
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        return x

model = MyModel()

3. 定义数据集

train_dataset = torchvision.datasets.MNIST(root='./data', train=True, transform=transforms.ToTensor(), download=True)
test_dataset = torchvision.datasets.MNIST(root='./data', train=False, transform=transforms.ToTensor(), download=True)

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True, num_workers=2)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False, num_workers=2)

4. 设置GPU设备

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)

5. 将模型放到GPU上

model = model.to(device)

6. 定义损失函数和优化器

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

7. 训练模型

for epoch in range(10):
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        inputs, labels = inputs.to(device), labels.to(device)

        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 100 == 99:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))
            running_loss = 0.0

8. 在测试集上测试模型

correct = 0
total = 0
with torch.no_grad():
    for data in test_loader:
        images, labels = data
        images, labels = images.to(device), labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))

可以看到，只需要在适当的地方添加一些代码，就可以轻松地将PyTorch模型放在多个GPU上进行加速运算。