mnist手写数字识别

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
import torch.nn.functional as F

# 1. 加载 MNIST 数据集
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)

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

# 2. 定义卷积神经网络
class SimpleCNN(nn.Module):
    def __init__(self):
        super(SimpleCNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, padding=1)  # 卷积层
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)  # 卷积层
        self.fc1 = nn.Linear(64 * 7 * 7, 128)  # 全连接层
        self.fc2 = nn.Linear(128, 10)  # 输出层

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2)  # 池化

        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2)  # 池化

        x = x.view(-1, 64 * 7 * 7)  # 展平
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

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

# 3. 设置损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 4. 训练模型
num_epochs = 5
losses = []
accuracies = []

for epoch in range(num_epochs):
    model.train()  # Set model to training mode
    epoch_loss = 0
    for images, labels in train_loader:
        images, labels = images.to(device), labels.to(device)  # 将数据移动到 GPU
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        epoch_loss += loss.item()

    avg_loss = epoch_loss / len(train_loader)
    losses.append(avg_loss)
    print(f'Epoch [{epoch + 1}/{num_epochs}], Loss: {avg_loss:.4f}')

    # 计算准确率
    model.eval()  # Set model to evaluation mode
    correct = 0
    total = 0
    with torch.no_grad():
        for images, labels in test_loader:
            images, labels = images.to(device), labels.to(device)  # 将数据移动到 GPU
            outputs = model(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    accuracy = 100 * correct / total
    accuracies.append(accuracy)
    print(f'Accuracy: {accuracy:.2f}%')

# 5. 可视化损失和准确率
plt.figure(figsize=(12, 5))

# 绘制损失
plt.subplot(1, 2, 1)
plt.plot(range(1, num_epochs + 1), losses, marker='o')
plt.title('Training Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')

# 绘制准确率
plt.subplot(1, 2, 2)
plt.plot(range(1, num_epochs + 1), accuracies, marker='o', color='orange')
plt.title('Test Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy (%)')

plt.tight_layout()
plt.show()