把你上述写的代码，整合成一个py文件的代码

好的，以下是整合后的代码：

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision.transforms as transforms
from torchvision.datasets import MNIST

# 定义数据转换
transform = transforms.Compose([
    transforms.ToTensor(),  # 将图像转换为PyTorch张量
    transforms.Normalize((0.1307,), (0.3081,))  # 对张量进行标准化
])

# 下载和加载MNIST数据集
train_dataset = MNIST(root='./data', train=True, transform=transform, download=True)
test_dataset = MNIST(root='./data', train=False, transform=transform, download=True)

# 创建数据加载器
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=False)


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)  # 输入通道数为1，输出通道数为32，卷积核大小为3*3，步长为1
        self.conv2 = nn.Conv2d(32, 64, 3, 1)  # 输入通道数为32，输出通道数为64，卷积核大小为3*3，步长为1
        self.dropout1 = nn.Dropout2d(0.25)  # Dropout层，丢弃概率为0.25
        self.dropout2 = nn.Dropout2d(0.5)  # Dropout层，丢弃概率为0.5
        self.fc1 = nn.Linear(9216, 128)  # 全连接层，输入大小为9216，输出大小为128
        self.fc2 = nn.Linear(128, 10)  # 全连接层，输入大小为128，输出大小为10

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output


# 定义超参数
learning_rate = 0.001
momentum = 0.9
epochs = 10

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

# 网络训练
for epoch in range(epochs):
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        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

# 网络性能测试
correct = 0
total = 0
with torch.no_grad():
    for data in test_loader:
        images, labels = data
        outputs = net(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))