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 = Truetorch.backends.cudnn.benchmark = Falsenp.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CPUpreds = 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_sizetrain_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, 0for 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 += 1loss_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_losstorch.save(model.state_dict(), config['save_path']) # 模型保存print('Saving model with loss {:.3f}...'.format(best_loss))early_stop_count = 0else: early_stop_count += 1if 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')