p66页实验题

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

# ===================== 1. 数据加载与预处理 =====================
transform = transforms.Compose([
    transforms.ToTensor(),  # 转换为张量并归一化到[0,1]
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))  # 标准化到[-1,1]
])

# 加载训练集和测试集
trainset = torchvision.datasets.CIFAR10(
    root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(
    trainset, batch_size=128, shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(
    root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(
    testset, batch_size=100, shuffle=False, num_workers=2)

# 类别标签
classes = ('飞机', '汽车', '鸟', '猫', '鹿', '狗', '青蛙', '马', '船', '卡车')

# 可视化样本
def imshow(img):
    img = img / 2 + 0.5  # 反标准化
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

# 获取一批训练样本并可视化
dataiter = iter(trainloader)
images, labels = next(dataiter)
imshow(torchvision.utils.make_grid(images[:4]))
print(' '.join(f'{classes[labels[j]]:5s}' for j in range(4)))

# ===================== 2. 构建卷积神经网络 =====================
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        # 卷积层+池化层
        self.conv1 = nn.Conv2d(3, 32, 3, padding=1)
        self.relu1 = nn.ReLU()
        self.pool1 = nn.MaxPool2d(2, 2)
        
        self.conv2 = nn.Conv2d(32, 64, 3, padding=1)
        self.relu2 = nn.ReLU()
        self.pool2 = nn.MaxPool2d(2, 2)
        
        self.conv3 = nn.Conv2d(64, 128, 3, padding=1)
        self.relu3 = nn.ReLU()
        self.pool3 = nn.MaxPool2d(2, 2)
        
        # 全连接层
        self.fc1 = nn.Linear(128 * 4 * 4, 512)
        self.relu4 = nn.ReLU()
        self.fc2 = nn.Linear(512, 10)  # 10个类别
        
    def forward(self, x):
        x = self.pool1(self.relu1(self.conv1(x)))
        x = self.pool2(self.relu2(self.conv2(x)))
        x = self.pool3(self.relu3(self.conv3(x)))
        x = x.view(-1, 128 * 4 * 4)  # 展平
        x = self.relu4(self.fc1(x))
        x = self.fc2(x)
        return x

net = Net()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
net.to(device)  # 移动到GPU（如果可用）

# ===================== 3. 定义损失函数和优化器 =====================
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)

# ===================== 4. 训练网络 =====================
epochs = 5
train_losses = []
for epoch in range(epochs):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data[0].to(device), data[1].to(device)
        
        # 梯度清零
        optimizer.zero_grad()
        
        # 前向传播 + 反向传播 + 优化
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item()
        if i % 100 == 99:  # 每100个mini-batch打印一次
            print(f' epoch: {epoch + 1},  batch: {i + 1},  loss: {running_loss / 100:.3f}')
            train_losses.append(running_loss / 100)
            running_loss = 0.0

print('训练完成')

# 保存模型
torch.save(net.state_dict(), './cifar10_net.pth')

# ===================== 5. 测试网络 =====================
# 加载模型（如果需要）
# net.load_state_dict(torch.load('./cifar10_net.pth'))

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data[0].to(device), data[1].to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print(f'测试集准确率: {100 * correct / total:.2f}%')

# 按类别评估准确率
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data[0].to(device), data[1].to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(len(labels)):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1

for i in range(10):
    print(f'类别 {classes[i]} 的准确率: {100 * class_correct[i] / class_total[i]:.2f}%')

# 绘制训练损失曲线
plt.plot(train_losses)
plt.xlabel('Mini-batch (×100)')
plt.ylabel('Loss')
plt.title('Training Loss')
plt.show()