【无标题】

Day51

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np

# 设置随机种子以确保结果可复现
torch.manual_seed(42)

# 定义数据预处理
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 = torch.utils.data.DataLoader(
    train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    test_dataset, batch_size=1000, shuffle=False)

# 定义CNN模型
class SimpleCNN(nn.Module):
    def __init__(self):
        super(SimpleCNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1)
        self.relu1 = nn.ReLU()
        self.pool1 = nn.MaxPool2d(kernel_size=2)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
        self.relu2 = nn.ReLU()
        self.pool2 = nn.MaxPool2d(kernel_size=2)
        self.fc1 = nn.Linear(64 * 7 * 7, 128)
        self.relu3 = nn.ReLU()
        self.fc2 = nn.Linear(128, 10)
        
    def forward(self, x):
        x = self.pool1(self.relu1(self.conv1(x)))
        x = self.pool2(self.relu2(self.conv2(x)))
        x = x.view(-1, 64 * 7 * 7)
        x = self.relu3(self.fc1(x))
        x = self.fc2(x)
        return x

# 初始化模型、损失函数和优化器
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)

# 训练模型
def train(epoch):
    model.train()
    train_loss = 0
    correct = 0
    total = 0
    
    for batch_idx, (inputs, targets) in enumerate(train_loader):
        inputs, targets = inputs.to(device), targets.to(device)
        
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()
        
        train_loss += loss.item()
        _, predicted = outputs.max(1)
        total += targets.size(0)
        correct += predicted.eq(targets).sum().item()
        
        if batch_idx % 100 == 0:
            print(f'Epoch: {epoch} | Batch: {batch_idx} | Loss: {train_loss/(batch_idx+1):.3f} | Acc: {100.*correct/total:.3f}%')
    
    return train_loss / len(train_loader), 100. * correct / total

# 测试模型
def test():
    model.eval()
    test_loss = 0
    correct = 0
    total = 0
    
    with torch.no_grad():
        for batch_idx, (inputs, targets) in enumerate(test_loader):
            inputs, targets = inputs.to(device), targets.to(device)
            outputs = model(inputs)
            loss = criterion(outputs, targets)
            
            test_loss += loss.item()
            _, predicted = outputs.max(1)
            total += targets.size(0)
            correct += predicted.eq(targets).sum().item()
    
    print(f'Test Loss: {test_loss/len(test_loader):.3f} | Test Acc: {100.*correct/total:.3f}%')
    return test_loss / len(test_loader), 100. * correct / total

# 训练和测试模型
epochs = 5
train_losses, train_accs = [], []
test_losses, test_accs = [], []

for epoch in range(1, epochs + 1):
    train_loss, train_acc = train(epoch)
    test_loss, test_acc = test()
    
    train_losses.append(train_loss)
    train_accs.append(train_acc)
    test_losses.append(test_loss)
    test_accs.append(test_acc)

# 绘制训练和测试曲线
plt.figure(figsize=(12, 5))
plt.subplot(1, 2, 1)
plt.plot(train_losses, label='Train Loss')
plt.plot(test_losses, label='Test Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.title('Loss Curves')

plt.subplot(1, 2, 2)
plt.plot(train_accs, label='Train Accuracy')
plt.plot(test_accs, label='Test Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy (%)')
plt.legend()
plt.title('Accuracy Curves')

plt.tight_layout()
plt.savefig('cnn_training_curves.png')
plt.show()

# 可视化一些测试结果
def visualize_results():
    model.eval()
    samples = next(iter(test_loader))
    images, labels = samples[0][:10].to(device), samples[1][:10]
    
    with torch.no_grad():
        outputs = model(images)
        _, predicted = torch.max(outputs, 1)
    
    fig = plt.figure(figsize=(12, 5))
    for i in range(10):
        ax = fig.add_subplot(2, 5, i+1, xticks=[], yticks=[])
        ax.imshow(images[i].cpu().squeeze(), cmap='gray')
        ax.set_title(f'Pred: {predicted[i].item()}, True: {labels[i].item()}',
                    color=("green" if predicted[i] == labels[i] else "red"))
    
    plt.tight_layout()
    plt.savefig('cnn_prediction_examples.png')
    plt.show()

visualize_results()

@浙大疏锦行