Aan de slagGa gratis aan de slag

Plot losses

Once we've fit a model, we usually check the training loss curve to make sure it's flattened out. The history returned from model.fit() is a dictionary that has an entry, 'loss', which is the training loss. We want to ensure this has more or less flattened out at the end of our training.

Deze oefening maakt deel uit van de cursus

Machine Learning for Finance in Python

Cursus bekijken

Oefeninstructies

  • Plot the losses ('loss') from history.history.
  • Set the title of the plot as the last loss from history.history, and round it to 6 digits.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Plot the losses from the fit
plt.plot(____)

# Use the last loss as the title
plt.title('loss:' + str(round(____, 6)))
plt.show()
Code bewerken en uitvoeren