机器学习复习（1）——任务整理流程

目录

固定的随机数种子

定义predict功能

拆分数据集

定义trainer

超参数设置

数据集载入

固定的随机数种子

在大量的机器学习与深度学习实验中，如果不进行特殊设置，我们的结果将不可复现，固定的随机数种子将会解决这个问题

def same_seed(seed): 
    '''
    设置随机种子(便于复现)
    '''
    torch.backends.cudnn.deterministic = True
    torch.backends.cudnn.benchmark = False
    np.random.seed(seed)
    torch.manual_seed(seed)
    if torch.cuda.is_available():
        torch.cuda.manual_seed_all(seed)
    print(f'Set Seed = {seed}')

定义predict功能

在自己进行完整的训练框架搭建时，对于结果的预测功能搭建，需要分离被预测对象，否则预测的对象的梯度会回传，扰乱模型backbone

def predict(test_loader, model, device):
    model.eval() # 设置成eval模式.
    preds = []
    for x in tqdm(test_loader):
        x = x.to(device)                        
        with torch.no_grad():
            pred = model(x)         
            preds.append(pred.detach().cpu())   
#detach()从GPU分离tensor, cpu()将tensor从GPU转到CPU
    preds = torch.cat(preds, dim=0).numpy()  
# 将预测结果拼接成一个numpy矩阵
    return preds

拆分数据集

对于原始数据集（分类）的拆分函数

def train_valid_split(data_set, valid_ratio, seed):
    '''
    数据集拆分成训练集（training set）和 验证集（validation set）
    '''
    valid_set_size = int(valid_ratio * len(data_set)) 
    train_set_size = len(data_set) - valid_set_size
    train_set, valid_set = random_split(data_set, [train_set_size, valid_set_size],
                                        generator=torch.Generator().manual_seed(seed))
    return np.array(train_set), np.array(valid_set)

定义trainer

def trainer(train_loader, valid_loader, model, config, device):

    criterion = nn.MSELoss(reduction='mean') # 损失函数的定义

    # 定义优化器
    optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.9) 
    
    # tensorboard 的记录器
    writer = SummaryWriter()

    if not os.path.isdir('./models'):
        # 创建文件夹-用于存储模型
        os.mkdir('./models')

    n_epochs, best_loss, step, early_stop_count = config['n_epochs'], math.inf, 0, 0

    for epoch in range(n_epochs):
        model.train() # 训练模式
        loss_record = []

        # tqdm可以帮助我们显示训练的进度  
        train_pbar = tqdm(train_loader, position=0, leave=True)
        # 设置进度条的左边 ： 显示第几个Epoch了
        train_pbar.set_description(f'Epoch [{epoch+1}/{n_epochs}]')
        for x, y in train_pbar:
            optimizer.zero_grad()               # 将梯度置0.
            x, y = x.to(device), y.to(device)   # 将数据一到相应的存储位置(CPU/GPU)
            pred = model(x)             
            loss = criterion(pred, y)
            loss.backward()                     # 反向传播 计算梯度.
            optimizer.step()                    # 更新网络参数
            step += 1
            loss_record.append(loss.detach().item())
            
            # 训练完一个batch的数据，将loss 显示在进度条的右边
            train_pbar.set_postfix({'loss': loss.detach().item()})

        mean_train_loss = sum(loss_record)/len(loss_record)
        # 每个epoch,在tensorboard 中记录训练的损失（后面可以展示出来）
        writer.add_scalar('Loss/train', mean_train_loss, step)

        model.eval() # 将模型设置成 evaluation 模式.
        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)
        print(f'Epoch [{epoch+1}/{n_epochs}]: Train loss: {mean_train_loss:.4f}, Valid loss: {mean_valid_loss:.4f}')
        # 每个epoch,在tensorboard 中记录验证的损失（后面可以展示出来）
        writer.add_scalar('Loss/valid', mean_valid_loss, step)

        if mean_valid_loss < best_loss:
            best_loss = mean_valid_loss
            torch.save(model.state_dict(), config['save_path']) # 模型保存
            print('Saving model with loss {:.3f}...'.format(best_loss))
            early_stop_count = 0
        else: 
            early_stop_count += 1

        if early_stop_count >= config['early_stop']:
            print('\nModel is not improving, so we halt the training session.')
            return

超参数设置

device = 'cuda' if torch.cuda.is_available() else 'cpu'
config = {
    'seed': 5201314,      # 随机种子，可以自己填写. :)
    'select_all': True,   # 是否选择全部的特征
    'valid_ratio': 0.2,   # 验证集大小(validation_size) = 训练集大小(train_size) * 验证数据占比(valid_ratio)
    'n_epochs': 3000,     # 数据遍历训练次数           
    'batch_size': 256, 
    'learning_rate': 1e-5,              
    'early_stop': 400,    # 如果early_stop轮损失没有下降就停止训练.     
    'save_path': './models/model.ckpt'  # 模型存储的位置
}

数据集载入

# 使用Pytorch中Dataloader类按照Batch将数据集加载
train_loader = DataLoader(train_dataset, batch_size=config['batch_size'], 
                          shuffle=True, pin_memory=True)
valid_loader = DataLoader(valid_dataset, batch_size=config['batch_size'], 
                          shuffle=True, pin_memory=True)
test_loader = DataLoader(test_dataset, batch_size=config['batch_size'], 
                         shuffle=False, pin_memory=True)

 模型训练

model = My_Model(input_dim=x_train.shape[1]).to(device) 
# 将模型和训练数据放在相同的存储位置(CPU/GPU)
trainer(train_loader, valid_loader, model, config, device)

模型测试

def save_pred(preds, file):
    ''' 将模型保存到指定位置'''
    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']))
preds = predict(test_loader, model, device) 
save_pred(preds, 'pred.csv')