Neural Network Workshop – Lab 6 Training

 

Visualize The Model

Output the Model to the Console

  1. Call the Summary method on the model to display it

Reference Material

https://keras.io/models/about-keras-models/

Hint 1

call to retrieve the model:

model.summary()

[collapse]
Full Solution

To output the model to the console:

# summary to console
print (model.summary())

[collapse]

[collapse]

 

Train The Model

Fit the Model

  1. Fit the model with the following parameters:
    • the inputs (X)
    • the outpus (y)
    • validation_split=.20
    • batch_size=64
    • epochs =25

Reference Material

https://keras.io/models/sequential/

Hint 1

call:

model.fit(???)

[collapse]
Hint 2

The entire model.fit command:

model.fit(X, y, validation_split = .20, batch_size = 64, epochs = 25)

[collapse]
Full Solution 
#Fit the ANN to the training set
history = model.fit(X, y, validation_split = .20, batch_size = 64, epochs = 25)

[collapse]

[collapse]

 

Visualize The Training

Visual the Training Accuracy

  1. Visualize the training model accuracy with pyplot from matplotlib using the following parameters:
    • the inputs = history.history[‘acc’] and history.history[‘val_acc’]
    • the title = model accuracy
    • ylabel = accuracy
    • xlabel = epoch
    • legend containing = train and test

Reference Material

https://matplotlib.org/api/pyplot_api.html

Hint 1

Import the library:

import matplotlib.pyplot as plt

[collapse]
Full Solution

Use the following to display the graph:

import matplotlib.pyplot as plt

# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

[collapse]

[collapse]
Visual the Training Model Loss

  1. Visualize the training model loss with pyplot from matplotlib using the following parameters:
    • the inputs = history.history[‘loss’] and history.history[‘val_loss]
    • the title = model accuracy
    • ylabel = loss
    • xlabel = epoch
    • legend containing = train and test

Reference Material

https://matplotlib.org/api/pyplot_api.html

Full Solution

Use the following to display the graph:

# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

[collapse]

[collapse]

 

Lab Complete!

 

Extra Credit – Understand Tensorboard

Interpret the Graphs

http://cs231n.github.io/neural-networks-3/#baby

[collapse]