李宏毅2023机器学习作业1--homework1——模型创建

一、导入包

import torch              # pytorch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader, random_split

二、配置项

方便更新超参数，对模型进行参数调整

device = 'cuda' if torch.cuda.is_available() else 'cpu'
config = {
    'seed': 5201314,      # Your seed number, you can pick your lucky number. :)
    'select_all': False,   # Whether to use all features.
    'valid_ratio': 0.2,   # validation_size = train_size * valid_ratio
    'n_epochs': 5000,     # Number of epochs.
    'batch_size': 256,
    'learning_rate': 1e-5,
    'early_stop': 600,    # If model has not improved for this many consecutive epochs, stop training.
    'save_path': './models/model.ckpt'  # Your model will be saved here.
}

三、创建神经网络模型

class My_Model(nn.Module):                # 搭建的神经网络 Model继承了 Module类（父类）    
    def __init__(self, input_dim):        # 初始化函数
        super(My_Model, self).__init__()  # 必须要这一步，调用父类的初始化函数
        # TODO: modify model's structure, be aware of dimensions.
        self.layers = nn.Sequential(
            nn.Linear(input_dim, 16),
            nn.ReLU(),
            nn.Linear(16, 8),
            nn.ReLU(),
            nn.Linear(8, 1)
        )
 
    def forward(self, x):                  # 前向传播（为输入和输出中间的处理过程），x为输入
        x = self.layers(x)
        x = x.squeeze(1) # (B, 1) -> (B)
        return x

四、模型训练过程

def trainer(train_loader, valid_loader, model, config, device):
 
    criterion = nn.MSELoss(reduction='mean') # Define your loss function, do not modify this.
 
    # Define your optimization algorithm.
    # TODO: Please check https://pytorch.org/docs/stable/optim.html to get more available algorithms.
    # TODO: L2 regularization (optimizer(weight decay...) or implement by your self).
    optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.9)
 
    # math.inf为无限大
    n_epochs, best_loss, step, early_stop_count = config['n_epochs'], math.inf, 0, 0
 
    for epoch in range(n_epochs):
        model.train() # Set your model to train mode.
        loss_record = []    # 记录损失
 
        for x, y in train_loader:
            optimizer.zero_grad()               # Set gradient to zero. 梯度清0
            x, y = x.to(device), y.to(device)   # Move your data to device.
            pred = model(x)                     # 数据传入模型model，生成预测值pred
            loss = criterion(pred, y)           # 预测值pred和真实值y计算损失loss  
            loss.backward()                     # Compute gradient(backpropagation).
            optimizer.step()                    # Update parameters.
            step += 1
            loss_record.append(loss.detach().item())   # 当前步骤的loss加到loss_record[]
 
            # Display current epoch number and loss on tqdm progress bar.
            train_pbar.set_description(f'Epoch [{epoch+1}/{n_epochs}]')
            train_pbar.set_postfix({'loss': loss.detach().item()})
 
        mean_train_loss = sum(loss_record)/len(loss_record)      # 计算训练集上平均损失
        writer.add_scalar('Loss/train', mean_train_loss, step)   
 
        model.eval() # Set your model to evaluation mode.
        loss_record = []
        for x, y in valid_loader:
            x, y = x.to(device), y.to(device)
            with torch.no_grad():
                pred = model(x)
                loss = criterion(pred, y)
 
            loss_record.append(loss.item())
 
        mean_valid_loss = sum(loss_record)/len(loss_record)      # 计算验证集上平均损失     
        print(f'Epoch [{epoch+1}/{n_epochs}]: Train loss: {mean_train_loss:.4f}, Valid loss: {mean_valid_loss:.4f}')
        writer.add_scalar('Loss/valid', mean_valid_loss, step)
 
        # 保存验证集上平均损失最小的模型
        if mean_valid_loss < best_loss:         
            best_loss = mean_valid_loss
            torch.save(model.state_dict(), config['save_path']) # Save your best model
            print('Saving model with loss {:.3f}...'.format(best_loss))
            early_stop_count = 0
        else:
            early_stop_count += 1
        
        # 设置早停early_stop_count
        # 如果early_stop_count次数，验证集上的平均损失没有变化，模型性能没有提升，停止训练
        if early_stop_count >= config['early_stop']:   
            print('\nModel is not improving, so we halt the training session.')
            return

五、训练模型

# 创建模型model，将模型和数据放到相同的计算设备上
model = My_Model(input_dim=x_train.shape[1]).to(device) 
 
# 开始训练
trainer(train_loader, valid_loader, model, config, device)

六、模型测试过程

# 测试数据集的预测
def predict(test_loader, model, device):
    model.eval() # Set your model to evaluation mode.
    preds = []
    for x in tqdm(test_loader):
        x = x.to(device)
        with torch.no_grad():   # 关闭梯度
            pred = model(x)
            preds.append(pred.detach().cpu())
    preds = torch.cat(preds, dim=0).numpy()
    return preds

七、测试模型

def save_pred(preds, file):
    ''' Save predictions to specified file '''
    with open(file, 'w') as fp:
        writer = csv.writer(fp)
        writer.writerow(['id', 'tested_positive'])
        for i, p in enumerate(preds):
            writer.writerow([i, p])
 
model = My_Model(input_dim=x_train.shape[1]).to(device)
model.load_state_dict(torch.load(config['save_path']))    # 加载模型
preds = predict(test_loader, model, device)               # 生成预测结果preds
save_pred(preds, 'pred.csv')                              # 保存preds到pred.csv