第三十七天打卡

1. 过拟合的判断：测试集和训练集同步打印指标
2. 模型的保存和加载
   1. 仅保存权重
   2. 保存权重和模型
   3. 保存全部信息checkpoint，还包含训练状态
3. 早停策略

过拟合判断

import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import time
import matplotlib.pyplot as plt
from tqdm import tqdm  # 导入tqdm库用于进度条显示
import warnings
warnings.filterwarnings("ignore")  # 忽略警告信息# 设置GPU设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f"使用设备: {device}")# 加载鸢尾花数据集
iris = load_iris()
X = iris.data  # 特征数据
y = iris.target  # 标签数据# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)# 归一化数据
scaler = MinMaxScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)# 将数据转换为PyTorch张量并移至GPU
X_train = torch.FloatTensor(X_train).to(device)
y_train = torch.LongTensor(y_train).to(device)
X_test = torch.FloatTensor(X_test).to(device)
y_test = torch.LongTensor(y_test).to(device)class MLP(nn.Module):def __init__(self):super(MLP, self).__init__()self.fc1 = nn.Linear(4, 10)  # 输入层到隐藏层self.relu = nn.ReLU()self.fc2 = nn.Linear(10, 3)  # 隐藏层到输出层def forward(self, x):out = self.fc1(x)out = self.relu(out)out = self.fc2(out)return out# 实例化模型并移至GPU
model = MLP().to(device)# 分类问题使用交叉熵损失函数
criterion = nn.CrossEntropyLoss()# 使用随机梯度下降优化器
optimizer = optim.SGD(model.parameters(), lr=0.01)# 训练模型
num_epochs = 20000  # 训练的轮数# 用于存储每200个epoch的损失值和对应的epoch数
train_losses = [] # 存储训练集损失
test_losses = [] # 新增：存储测试集损失
epochs = []start_time = time.time()  # 记录开始时间# 创建tqdm进度条
with tqdm(total=num_epochs, desc="训练进度", unit="epoch") as pbar:# 训练模型for epoch in range(num_epochs):# 前向传播outputs = model(X_train)  # 隐式调用forward函数train_loss = criterion(outputs, y_train)# 反向传播和优化optimizer.zero_grad()train_loss.backward()optimizer.step()# 记录损失值并更新进度条if (epoch + 1) % 200 == 0:# 计算测试集损失，新增代码model.eval()with torch.no_grad():test_outputs = model(X_test)test_loss = criterion(test_outputs, y_test)model.train()train_losses.append(train_loss.item())test_losses.append(test_loss.item())epochs.append(epoch + 1)# 更新进度条的描述信息pbar.set_postfix({'Train Loss': f'{train_loss.item():.4f}', 'Test Loss': f'{test_loss.item():.4f}'})# 每1000个epoch更新一次进度条if (epoch + 1) % 1000 == 0:pbar.update(1000)  # 更新进度条# 确保进度条达到100%if pbar.n < num_epochs:pbar.update(num_epochs - pbar.n)  # 计算剩余的进度并更新time_all = time.time() - start_time  # 计算训练时间
print(f'Training time: {time_all:.2f} seconds')# 可视化损失曲线
plt.figure(figsize=(10, 6))
plt.plot(epochs, train_losses, label='Train Loss') # 原始代码已有
plt.plot(epochs, test_losses, label='Test Loss')  # 新增：测试集损失曲线
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.title('Training and Test Loss over Epochs')
plt.legend() # 新增：显示图例
plt.grid(True)
plt.show()# 在测试集上评估模型，此时model内部已经是训练好的参数了
# 评估模型
model.eval() # 设置模型为评估模式
with torch.no_grad(): # torch.no_grad()的作用是禁用梯度计算，可以提高模型推理速度outputs = model(X_test)  # 对测试数据进行前向传播，获得预测结果_, predicted = torch.max(outputs, 1) # torch.max(outputs, 1)返回每行的最大值和对应的索引correct = (predicted == y_test).sum().item() # 计算预测正确的样本数accuracy = correct / y_test.size(0)print(f'测试集准确率: {accuracy * 100:.2f}%')  

早停法

import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import time
import matplotlib.pyplot as plt
from tqdm import tqdm  # 导入tqdm库用于进度条显示
import warnings
warnings.filterwarnings("ignore")  # 忽略警告信息# 设置GPU设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f"使用设备: {device}")# 加载鸢尾花数据集
iris = load_iris()
X = iris.data  # 特征数据
y = iris.target  # 标签数据# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)# 归一化数据
scaler = MinMaxScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)# 将数据转换为PyTorch张量并移至GPU
X_train = torch.FloatTensor(X_train).to(device)
y_train = torch.LongTensor(y_train).to(device)
X_test = torch.FloatTensor(X_test).to(device)
y_test = torch.LongTensor(y_test).to(device)class MLP(nn.Module):def __init__(self):super(MLP, self).__init__()self.fc1 = nn.Linear(4, 10)  # 输入层到隐藏层self.relu = nn.ReLU()self.fc2 = nn.Linear(10, 3)  # 隐藏层到输出层def forward(self, x):out = self.fc1(x)out = self.relu(out)out = self.fc2(out)return out# 实例化模型并移至GPU
model = MLP().to(device)# 分类问题使用交叉熵损失函数
criterion = nn.CrossEntropyLoss()# 使用随机梯度下降优化器
optimizer = optim.SGD(model.parameters(), lr=0.01)# 训练模型
num_epochs = 20000  # 训练的轮数# 用于存储每200个epoch的损失值和对应的epoch数
train_losses = []  # 存储训练集损失
test_losses = []   # 存储测试集损失
epochs = []# ===== 新增早停相关参数 =====
best_test_loss = float('inf')  # 记录最佳测试集损失
best_epoch = 0                 # 记录最佳epoch
patience = 50                # 早停耐心值（连续多少轮测试集损失未改善时停止训练）
counter = 0                    # 早停计数器
early_stopped = False          # 是否早停标志
# ==========================start_time = time.time()  # 记录开始时间# 创建tqdm进度条
with tqdm(total=num_epochs, desc="训练进度", unit="epoch") as pbar:# 训练模型for epoch in range(num_epochs):# 前向传播outputs = model(X_train)  # 隐式调用forward函数train_loss = criterion(outputs, y_train)# 反向传播和优化optimizer.zero_grad()train_loss.backward()optimizer.step()# 记录损失值并更新进度条if (epoch + 1) % 200 == 0:# 计算测试集损失model.eval()with torch.no_grad():test_outputs = model(X_test)test_loss = criterion(test_outputs, y_test)model.train()train_losses.append(train_loss.item())test_losses.append(test_loss.item())epochs.append(epoch + 1)# 更新进度条的描述信息pbar.set_postfix({'Train Loss': f'{train_loss.item():.4f}', 'Test Loss': f'{test_loss.item():.4f}'})# ===== 新增早停逻辑 =====if test_loss.item() < best_test_loss: # 如果当前测试集损失小于最佳损失best_test_loss = test_loss.item() # 更新最佳损失best_epoch = epoch + 1 # 更新最佳epochcounter = 0 # 重置计数器# 保存最佳模型torch.save(model.state_dict(), 'best_model.pth')else:counter += 1if counter >= patience:print(f"早停触发！在第{epoch+1}轮，测试集损失已有{patience}轮未改善。")print(f"最佳测试集损失出现在第{best_epoch}轮，损失值为{best_test_loss:.4f}")early_stopped = Truebreak  # 终止训练循环# ======================# 每1000个epoch更新一次进度条if (epoch + 1) % 1000 == 0:pbar.update(1000)  # 更新进度条# 确保进度条达到100%if pbar.n < num_epochs:pbar.update(num_epochs - pbar.n)  # 计算剩余的进度并更新time_all = time.time() - start_time  # 计算训练时间
print(f'Training time: {time_all:.2f} seconds')# ===== 新增：加载最佳模型用于最终评估 =====
if early_stopped:print(f"加载第{best_epoch}轮的最佳模型进行最终评估...")model.load_state_dict(torch.load('best_model.pth'))
# ================================# 可视化损失曲线
plt.figure(figsize=(10, 6))
plt.plot(epochs, train_losses, label='Train Loss')
plt.plot(epochs, test_losses, label='Test Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.title('Training and Test Loss over Epochs')
plt.legend()
plt.grid(True)
plt.show()# 在测试集上评估模型
model.eval()
with torch.no_grad():outputs = model(X_test)_, predicted = torch.max(outputs, 1)correct = (predicted == y_test).sum().item()accuracy = correct / y_test.size(0)print(f'测试集准确率: {accuracy * 100:.2f}%')    

@浙大疏锦行