Python Deep Learning Projects

Plot training and validation loss

With loss_lst and val_loss_lst containing the train and validation MSE loss at intervals of 40 batches, let's plot this and see how the learning has progressed:

plt.style.use('ggplot')plt.figure(figsize=(10, 6))plt.plot(count_lst, loss_lst, marker='D', label = 'training_loss')plt.plot(count_lst, val_loss_lst, marker='o', label = 'validation_loss')plt.ylabel('Mean Squared Error')plt.title('Plot of MSE over time')plt.legend(loc = 'upper right')plt.show()

Following is the output:

Figure 12.18: Plot of train and validation loss 

A smoother train validation loss plot can be obtained by reducing the store hyperparameter. ...