Day43 训练和测试的规范写法

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 numpy as np

# 设置中文字体支持
plt.rcParams["font.family"] = ["SimHei"]
plt.rcParams['axes.unicode_minus'] = False  # 解决负号显示问题

# 1. 数据预处理
transform = transforms.Compose([
    transforms.ToTensor(),  # 转换为张量并归一化到[0,1]
    transforms.Normalize((0.1307,), (0.3081,))  # MNIST数据集的均值和标准差
])

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

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

# 3. 创建数据加载器
batch_size = 64  # 每批处理64个样本
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

# 4. 定义模型、损失函数和优化器
class MLP(nn.Module):
    def __init__(self):
        super(MLP, self).__init__()
        self.flatten = nn.Flatten()  # 将28x28的图像展平为784维向量
        self.layer1 = nn.Linear(784, 128)  # 第一层：784个输入，128个神经元
        self.relu = nn.ReLU()  # 激活函数
        self.layer2 = nn.Linear(128, 10)  # 第二层：128个输入，10个输出（对应10个数字类别）
        
    def forward(self, x):
        x = self.flatten(x)  # 展平图像
        x = self.layer1(x)   # 第一层线性变换
        x = self.relu(x)     # 应用ReLU激活函数
        x = self.layer2(x)   # 第二层线性变换，输出logits
        return x

# 检查GPU是否可用
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 初始化模型
model = MLP()
model = model.to(device)  # 将模型移至GPU（如果可用）

criterion = nn.CrossEntropyLoss()  # 交叉熵损失函数，适用于多分类问题
optimizer = optim.Adam(model.parameters(), lr=0.001)  # Adam优化器

# 5. 训练模型（记录每个 iteration 的损失）
def train(model, train_loader, test_loader, criterion, optimizer, device, epochs):
    model.train()  # 设置为训练模式
    
    # 新增：记录每个 iteration 的损失
    all_iter_losses = []  # 存储所有 batch 的损失
    iter_indices = []     # 存储 iteration 序号（从1开始）
    
    for epoch in range(epochs):
        running_loss = 0.0
        correct = 0
        total = 0
        
        for batch_idx, (data, target) in enumerate(train_loader):
            data, target = data.to(device), target.to(device)  # 移至GPU(如果可用)
            
            optimizer.zero_grad()  # 梯度清零
            output = model(data)  # 前向传播
            loss = criterion(output, target)  # 计算损失
            loss.backward()  # 反向传播
            optimizer.step()  # 更新参数
            
            # 记录当前 iteration 的损失（注意：这里直接使用单 batch 损失，而非累加平均）
            iter_loss = loss.item()
            all_iter_losses.append(iter_loss)
            iter_indices.append(epoch * len(train_loader) + batch_idx + 1)  # iteration 序号从1开始
            
            # 统计准确率和损失（原逻辑保留，用于 epoch 级统计）
            running_loss += iter_loss
            _, predicted = output.max(1)
            total += target.size(0)
            correct += predicted.eq(target).sum().item()
            
            # 每100个批次打印一次训练信息（可选：同时打印单 batch 损失）
            if (batch_idx + 1) % 100 == 0:
                print(f'Epoch: {epoch+1}/{epochs} | Batch: {batch_idx+1}/{len(train_loader)} '
                      f'| 单Batch损失: {iter_loss:.4f} | 累计平均损失: {running_loss/(batch_idx+1):.4f}')
        
        # 原 epoch 级逻辑（测试、打印 epoch 结果）不变
        epoch_train_loss = running_loss / len(train_loader)
        epoch_train_acc = 100. * correct / total
        epoch_test_loss, epoch_test_acc = test(model, test_loader, criterion, device)
        
        print(f'Epoch {epoch+1}/{epochs} 完成 | 训练准确率: {epoch_train_acc:.2f}% | 测试准确率: {epoch_test_acc:.2f}%')
    
    # 绘制所有 iteration 的损失曲线
    plot_iter_losses(all_iter_losses, iter_indices)
    # 保留原 epoch 级曲线（可选）
    # plot_metrics(train_losses, test_losses, train_accuracies, test_accuracies, epochs)
    
    return epoch_test_acc  # 返回最终测试准确率

# 6. 测试模型
def test(model, test_loader, criterion, device):
    model.eval()  # 设置为评估模式
    test_loss = 0
    correct = 0
    total = 0
    
    with torch.no_grad():  # 不计算梯度，节省内存和计算资源
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += criterion(output, target).item()
            
            _, predicted = output.max(1)
            total += target.size(0)
            correct += predicted.eq(target).sum().item()
    
    avg_loss = test_loss / len(test_loader)
    accuracy = 100. * correct / total
    return avg_loss, accuracy  # 返回损失和准确率

# 7.绘制每个 iteration 的损失曲线
def plot_iter_losses(losses, indices):
    plt.figure(figsize=(10, 4))
    plt.plot(indices, losses, 'b-', alpha=0.7, label='Iteration Loss')
    plt.xlabel('Iteration（Batch序号）')
    plt.ylabel('损失值')
    plt.title('每个 Iteration 的训练损失')
    plt.legend()
    plt.grid(True)
    plt.tight_layout()
    plt.show()

# 8. 执行训练和测试（设置 epochs=2 验证效果）
epochs = 2  
print("开始训练模型...")
final_accuracy = train(model, train_loader, test_loader, criterion, optimizer, device, epochs)
print(f"训练完成！最终测试准确率: {final_accuracy:.2f}%")

@浙大疏锦行