Comparing activation functions II
What you coded in the previous exercise has been executed to obtain theactivation_results
variable, this time 100 epochs were used instead of 20. This way you will have more epochs to further compare how the training evolves per activation function.
For every h_callback
of each activation function in activation_results
:
- The
h_callback.history['val_loss']
has been extracted. - The
h_callback.history['val_accuracy']
has been extracted.
Both are saved into two dictionaries: val_loss_per_function
and val_acc_per_function
.
Pandas is also loaded as pd
for you to use. Let's plot some quick validation loss and accuracy charts!
This exercise is part of the course
Introduction to Deep Learning with Keras
Exercise instructions
- Use
pd.DataFrame()
to create a new DataFrame from theval_loss_per_function
dictionary. - Call
plot()
on the DataFrame. - Create another pandas DataFrame from
val_acc_per_function
. - Once again, plot the DataFrame.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Create a dataframe from val_loss_per_function
val_loss= ____.____(____)
# Call plot on the dataframe
____
plt.show()
# Create a dataframe from val_acc_per_function
val_acc = _____
# Call plot on the dataframe
____
plt.show()