请写一个CNN识别MNIST，用pytorch，用GPU

当然可以！以下是一个使用PyTorch和GPU训练CNN来识别MNIST数据集的示例代码：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

# 设置GPU设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 加载MNIST数据集
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])
trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True, num_workers=2)

testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False, num_workers=2)

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

    def forward(self, x):
        x = self.conv1(x)
        x = nn.ReLU()(x)
        x = nn.MaxPool2d(2)(x)
        x = self.conv2(x)
        x = nn.ReLU()(x)
        x = nn.MaxPool2d(2)(x)
        x = x.view(-1, 64 * 5 * 5)
        x = self.fc1(x)
        x = nn.ReLU()(x)
        x = self.fc2(x)
        return x

net = Net().to(device)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

# 训练网络
for epoch in range(10):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data[0].to(device), data[1].to(device)
        optimizer.zero_grad()
        outputs = net(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

print('Finished training')

# 在测试集上评估网络
correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data[0].to(device), data[1].to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy on the test set: %d %%' % (100 * correct / total))

这段代码首先加载MNIST数据集，然后定义了一个简单的CNN模型。接下来，我们将模型移动到可用的GPU设备上，并定义了损失函数和优化器。在训练过程中，我们将数据传递给模型并进行前向传播、计算损失、反向传播和参数更新。最后，在测试集上评估网络的准确率。

请确保你的环境中已经安装了PyTorch和CUDA，并且你的GPU支持CUDA计算。