加速训练 - 在 PyTorch 中使用 LSTM 的 RNN

Speeding up the trainning - RNN with LSTM in PyTorch

我正在尝试训练用于能源需求预测的 LSTM,但它花费的时间太长。我不明白为什么,因为模型看起来“简单”并且没有太多数据。可能是因为我没有使用 DataLoader?我有一个序列,如何将它与 RNN 一起使用?

完整代码在 Colab 中:https://colab.research.google.com/drive/130rG8_j1Lf8RQoVRrfXCeo5h_CcC5NU6?usp=sharing

需要改进的有趣部分可能是:

for seq, y_train in train_data:
    optimizer.zero_grad()
    model.hidden = (torch.zeros(1,1,model.hidden_size),
                    torch.zeros(1,1,model.hidden_size))
    y_pred = model(seq)
    loss = criterion(y_pred, y_train)
    loss.backward()
    optimizer.step()

提前感谢任何帮助我的人。

如果您想加快训练过程,每次训练必须向模型提供更多数据。就我而言,我只提供了一批。简单解决此问题的最佳方法是使用 DataLoader。

完整的 Colab 和解决方案可以在这个 link 中找到:https://colab.research.google.com/drive/1QgtshCFETZ9oTvIYWy1Bdre-614kbwRX?usp=sharing

# This is to create the Dataset
from torch.utils.data import Dataset, DataLoader

class DemandDataset(Dataset):
    def __init__(self, X_train, y_train):
        self.X_train = X_train
        self.y_train = y_train

    def __len__(self):
        return len(self.y_train)

    def __getitem__(self, idx):
        data = self.X_train[idx]
        labels = self.y_train[idx]
        return data, labels

#This is to convert from typical RNN sequences
sq_0 =[]
y_0 =[]
for seq, y_train in train_data:
  sq_0.append(seq)
  y_0.append(y_train)

dataset=DemandDataset(sq_0,y_0)
dataloader = DataLoader(dataset, batch_size=20)

epochs = 30
t = 50

for i in range(epochs):
    print("New epoch")    
  
    for data,label in dataloader:
         
        optimizer.zero_grad()
        model.hidden = (torch.zeros(1,1,model.hidden_size),
                        torch.zeros(1,1,model.hidden_size))
        
        y_pred = model(seq)
        
        loss = criterion(y_pred, label)
        loss.backward()
        optimizer.step()
        
   
    print(f'Epoch: {i+1:2} Loss: {loss.item():10.8f}')
    
   
    preds = train_set[-window_size:].tolist()

    for f in range(t):  
        seq = torch.FloatTensor(preds[-window_size:])
        with torch.no_grad():
            model.hidden = (torch.zeros(1,1,model.hidden_size),
                            torch.zeros(1,1,model.hidden_size))
            preds.append(model(seq).item())
            
    loss = criterion(torch.tensor(preds[-window_size:]),y[-t:])