Aan de slagGa gratis aan de slag

Plot the learning curves

During learning, the model will store the loss function evaluated in each epoch. Looking at the learning curves can tell us quite a bit about the learning process. In this exercise, you will plot the learning and validation loss curves for a model that you will train.

Deze oefening maakt deel uit van de cursus

Image Modeling with Keras

Cursus bekijken

Oefeninstructies

  • Fit the model to the training data (train_data).
  • Use a validation split of 20%, 3 epochs and batch size of 10.
  • Plot the training loss.
  • Plot the validation loss.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

import matplotlib.pyplot as plt

# Train the model and store the training object
training = ____

# Extract the history from the training object
history = training.____

# Plot the training loss 
plt.plot(history[____])
# Plot the validation loss
plt.plot(history[____])

# Show the figure
plt.show()
Code bewerken en uitvoeren