2.1 Hyperparameters

In [7]:
# Hyperparameters
training_epochs = 30 # Total number of training epochs
learning_rate = 0.01 # The learning rate

2.2 Creating a model

In [8]:
# create a model
def create_model():
    model = Sequential()
    # Input layer
    model.add(Dense(64, input_dim=64, kernel_initializer='normal',
        kernel_regularizer= tf.keras.regularizers.l2(0.01),activation='tanh'))
    # Output layer
    model.add(Dense(10, activation='softmax'))

    # Compile a model
    model.compile(loss='categorical_crossentropy', 
                  optimizer=Adam(learning_rate), metrics=['accuracy'])
    return model
model = create_model()
model.summary()

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense (Dense)                (None, 64)                4160      
_________________________________________________________________
dense_1 (Dense)              (None, 10)                650       
=================================================================
Total params: 4,810
Trainable params: 4,810
Non-trainable params: 0
_________________________________________________________________

2.3 Train the model

In [9]:
results = model.fit(
    X_train, y_train,
    epochs= training_epochs,
    batch_size = 516,
    validation_data = (X_test, y_test),
    verbose = 0
)

2.4 Test the model

Model can generate output predictions for the input samples.

In [10]:
prediction_values = model.predict_classes(X_test)

2.5 Evaluate the model to see the accuracy

In [11]:
print("Evaluating on training set...")
(loss, accuracy) = model.evaluate(X_train,y_train, verbose=0)
print("loss={:.4f}, accuracy: {:.4f}%".format(loss,accuracy * 100))


print("Evaluating on testing set...")
(loss, accuracy) = model.evaluate(X_test, y_test, verbose=0)
print("loss={:.4f}, accuracy: {:.4f}%".format(loss,accuracy * 100))

Evaluating on training set...
loss=0.1054, accuracy: 99.8338%
Evaluating on testing set...
loss=0.1842, accuracy: 97.1380%

2.6 Summarize history for accuracy

In [12]:
# summarize history for accuracy
plt.plot(results.history['accuracy'])
plt.plot(results.history['val_accuracy'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'])
Out[12]:
<matplotlib.legend.Legend at 0x221922776d8>

2.7 Summarize history for loss

In [13]:
plt.plot(results.history['loss'])
plt.plot(results.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'])

max_loss = np.max(results.history['loss'])
min_loss = np.min(results.history['loss'])
print("Maximum Loss : {:.4f}".format(max_loss))
print("")
print("Minimum Loss : {:.4f}".format(min_loss))
print("")
print("Loss difference : {:.4f}".format((max_loss - min_loss)))

Maximum Loss : 2.9333

Minimum Loss : 0.1097

Loss difference : 2.8236