用PyTorch实现MNIST手写数字识别

使用PyTorch实现MNIST手写数字识别是一个常见的深度学习入门示例，它通常涉及几个步骤：

1. **导入库**：

   import torch
   from torchvision import datasets, transforms
   import torch.nn as nn
   import torch.optim as optim

2. **数据预处理**：

   transform = transforms.Compose([
       transforms.ToTensor(),
       transforms.Normalize((0.5,), (0.5,))
   ])

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

3. **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)

4. **定义模型结构**，这里我们用经典的卷积神经网络(CNN)作为例子：

   class Net(nn.Module):
       def __init__(self):
           super(Net, self).__init__()
           self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
           self.pool = nn.MaxPool2d(2, 2)
           self.fc1 = nn.Linear(10 * 14 * 14, 128)
           self.fc2 = nn.Linear(128, 10)

       def forward(self, x):
           x = self.pool(F.relu(self.conv1(x)))
           x = x.view(-1, 10 * 14 * 14)
           x = F.relu(self.fc1(x))
           x = self.fc2(x)
           return x

   model = Net()

5. **选择损失函数和优化器**：

   criterion = nn.CrossEntropyLoss()
   optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

6. **训练循环**：

   for epoch in range(num_epochs):
       for i, (images, labels) in enumerate(train_loader):
           # ... 进行前向传播、计算loss、反向传播以及优化操作
       # 记录和可视化训练过程的指标（如准确率）

7. **评估模型**：

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

       accuracy = 100 * correct / total