手写数字识别 (MNIST) 实战：你的第一个 PyTorch 图像分类模型

📂 所属阶段：第二阶段 — 深度学习视觉基础（CNN 篇）
🔗 相关章节：经典 CNN 架构剖析 · 数据增强 (Data Augmentation)

1. 数据加载

import torch
import torchvision
from torchvision import transforms
from torch.utils.data import DataLoader

# 数据预处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

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

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

print(f"训练集大小: {len(train_dataset)}")
print(f"测试集大小: {len(test_dataset)}")

2. 定义模型

import torch
import torch.nn as nn

class SimpleCNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(64 * 7 * 7, 128)
        self.fc2 = nn.Linear(128, 10)
        self.dropout = nn.Dropout(0.5)

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 64 * 7 * 7)
        x = torch.relu(self.fc1(x))
        x = self.dropout(x)
        x = self.fc2(x)
        return x

model = SimpleCNN()
print(model)

3. 训练模型

import torch
import torch.nn as nn
import torch.optim as optim

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = SimpleCNN().to(device)

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

# 训练循环
num_epochs = 10
for epoch in range(num_epochs):
    model.train()
    total_loss = 0
    for images, labels in train_loader:
        images, labels = images.to(device), labels.to(device)
        
        # 前向传播
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 反向传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        total_loss += loss.item()
    
    print(f"Epoch {epoch+1}/{num_epochs}, Loss: {total_loss/len(train_loader):.4f}")

4. 评估模型

# 评估
model.eval()
correct = 0
total = 0

with torch.no_grad():
    for images, labels in test_loader:
        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()

accuracy = 100 * correct / total
print(f"测试准确率: {accuracy:.2f}%")

5. 小结

MNIST 完整流程：

1. 数据加载：使用 DataLoader
2. 模型定义：简单 CNN
3. 训练：前向传播 → 计算损失 → 反向传播 → 更新参数
4. 评估：计算准确率

预期结果：
- 简单 CNN：~99% 准确率
- 深度 CNN：~99.5% 准确率

💡 记住：MNIST 是 CV 的"Hello World"。掌握这个流程后，可以迁移到任何图像分类任务。

🔗 扩展阅读