Model Training & Evaluations

Step 5: Creating Data Loader for batch training

Now, we built a training loop for 50 epochs. In the provided code snippet, the model processes mini batches of training data and compute loss and update the parameters.

Python3

num_epochs = 50
train_hist =[]
test_hist =[]
# Training loop
for epoch in range(num_epochs):
    total_loss = 0.0
 
    # Training
    model.train()
    for batch_X, batch_y in train_loader:
        batch_X, batch_y = batch_X.to(device), batch_y.to(device)
        predictions = model(batch_X)
        loss = loss_fn(predictions, batch_y)
 
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
 
        total_loss += loss.item()
 
    # Calculate average training loss and accuracy
    average_loss = total_loss / len(train_loader)
    train_hist.append(average_loss)
 
    # Validation on test data
    model.eval()
    with torch.no_grad():
        total_test_loss = 0.0
 
        for batch_X_test, batch_y_test in test_loader:
            batch_X_test, batch_y_test = batch_X_test.to(device), batch_y_test.to(device)
            predictions_test = model(batch_X_test)
            test_loss = loss_fn(predictions_test, batch_y_test)
 
            total_test_loss += test_loss.item()
 
        # Calculate average test loss and accuracy
        average_test_loss = total_test_loss / len(test_loader)
        test_hist.append(average_test_loss)
    if (epoch+1)%10==0:
        print(f'Epoch [{epoch+1}/{num_epochs}] - Training Loss: {average_loss:.4f}, Test Loss: {average_test_loss:.4f}')

Output:

Epoch [10/50] - Training Loss: 0.0000, Test Loss: 0.0002
Epoch [20/50] - Training Loss: 0.0000, Test Loss: 0.0002
Epoch [30/50] - Training Loss: 0.0000, Test Loss: 0.0002
Epoch [40/50] - Training Loss: 0.0000, Test Loss: 0.0002
Epoch [50/50] - Training Loss: 0.0000, Test Loss: 0.0002

Plotting the Learning Curve

We have plotted the learning curve to track the progress and give us an idea, how much time time and training is required by the model to understand the patterns.

Python3

x = np.linspace(1,num_epochs,num_epochs)
plt.plot(x,train_hist,scalex=True, label="Training loss")
plt.plot(x, test_hist, label="Test loss")
plt.legend()
plt.show()

Output:

Learning Curve for Training Loss and Test Loss

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

Model Training & Evaluations

Python3

Plotting the Learning Curve

Python3

Time Series Forecasting using Pytorch

Table of Content

Similar Reads