Define LSTM class model

Step 5: Creating Data Loader for batch training

Now, we defined a PyTorch network using LSTM architecture. The class consist of LSTM layer and linear layer. In LSTMModel class, we initialized parameters-

input_size : number of features in the input data at each time step
hidden_size : hidden units in LSTM layer
num_layers : number of LSTM layers
batch_first= True: input data will have the batch size as the first dimension

The function super(LSTMModel, self).__init__() initializes the parent class for building the neural network.

The forward method defines the forward pass of the model, where the input x is processed through the layers of the model to produce an output.

Python3

class LSTMModel(nn.Module):
      # input_size : number of features in input at each time step
      # hidden_size : Number of LSTM units 
      # num_layers : number of LSTM layers 
    def __init__(self, input_size, hidden_size, num_layers): 
        super(LSTMModel, self).__init__() #initializes the parent class nn.Module
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.linear = nn.Linear(hidden_size, 1)
 
    def forward(self, x): # defines forward pass of the neural network
        out, _ = self.lstm(x)
        out = self.linear(out)
        return out

Check Hardware Availability

For the PyTorch code, we need to check the hardware resources.

Python3

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(device)

Output:

cuda

Defining the model

Now, we define the model, loss function and optimizer for the forecasting. We have adjusted the hyperparameters of the model and set the loss fuction to mean squared error. To optimize the parameters during the training, we have considered Adam optimizer.

Python3

input_size = 1
num_layers = 2
hidden_size = 64
output_size = 1
 
# Define the model, loss function, and optimizer
model = LSTMModel(input_size, hidden_size, num_layers).to(device)
 
loss_fn = torch.nn.MSELoss(reduction='mean')
 
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
print(model)

Output:

LSTMModel(
  (lstm): LSTM(1, 32, num_layers=2, batch_first=True)
  (linear): Linear(in_features=32, out_features=1, bias=True)
)

Time Series Forecasting using Pytorch

Time series forecasting plays a major role in data analysis, with applications ranging from anticipating stock market trends to forecasting weather patterns. In this article, we’ll dive into the field of time series forecasting using PyTorch and LSTM (Long Short-Term Memory) neural networks. We’ll uncover the critical preprocessing procedures that underpin the accuracy of our forecasts along the way.

Table of Content

Time Series Forecasting
Implementation of Time Series Forecasting:
Step 1: Import the necessary libraries
Step2: Loading the Dataset
Step 3: Data Preprocessing
Step 4: Define LSTM class model
Step 5: Creating Data Loader for batch training
Step 6: Model Training & Evaluations
Step 7: Forecasting

Define LSTM class model

Python3

Check Hardware Availability

Python3

Defining the model

Python3

Time Series Forecasting using Pytorch

Table of Content

Similar Reads