Chapter 15 Understand Model Behavior During Training By Plotting History

Question 1

History is a Keras callback. True/False? P 108

Answer 1

True. Keras provides the capability to register callbacks when training a deep learning model. One of the default callbacks that is registered when training all deep learning models is the History callback

Question 2

What does History do, in Keras? P 108

Answer 2

It records training metrics for each epoch. This includes the loss and the accuracy (for classification problems) as well as the loss and accuracy for the validation dataset, if one is set.

Question 3

How can we visualize the history of learning based on each epoch and evaluation metric? P 109

Answer 3

# Checkpoint the weights when validation accuracy improves
from keras.models import Sequential
from keras.layers import Dense
from keras.callbacks import ModelCheckpoint
import matplotlib.pyplot as plt
import numpy
from sklearn.datasets import load_breast_cancer, load_iris,load_diabetes

dataset =  load_breast_cancer(as_frame=True)
X = dataset.data
Y = dataset.target
model = Sequential()
model.add(Dense(12, input_dim=30,activation= "relu" ))
model.add(Dense(8, activation= "relu" ))
model.add(Dense(1, activation= "sigmoid" ))
# Compile model
model.compile(loss= "binary_crossentropy" , optimizer= "adam" , metrics=[ "accuracy" ])
# Fit the model
history=model.fit(X, Y, validation_split=0.2, epochs=15, batch_size=10,  verbose=0)
# summarize history for accuracy
plt.plot(history.history[ "accuracy" ])
plt.plot(history.history[ "val_accuracy" ])
plt.title( "model accuracy" )
plt.ylabel( "accuracy" )
plt.xlabel( "epoch" )
plt.legend([ "train" , "test" ], loc= "best" )
plt.show()
# 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= "best" )
plt.show()

Question 4

What does history.history.keys() do? P 109

Answer 4

List the metrics collected in a history object. for example, in classification it returns the below dict keys:
dict_keys([‘loss’, ‘accuracy’, ‘val_loss’, ‘val_accuracy’])

Question 5

The “history_” attribute in SciKeras, works only when the model is fitted first. True/False? External

Answer 5

True

USE OF FIT IS A MUST BEFORE USING ANY ATTRIBUTE OF SCIKERAS MODELS

Using Cross_val_score DOES NOT fit the model to data it just creates a replica of the model to calculate the scores, so this attribute would NOT work after using cross_val_score on the data.