Training with Keras

Introduction to TensorFlow in Python

Isaiah Hull

Visiting Associate Professor of Finance, BI Norwegian Business School

Overview of training and evaluation

# Import tensorflow
import tensorflow as tf

# Define a sequential model
model = tf.keras.Sequential()

# Define the hidden layer
model.add(tf.keras.layers.Dense(16, activation='relu', input_shape=(784,)))

# Define the output layer
model.add(tf.keras.layers.Dense(4, activation='softmax'))

# Compile model
model.compile('adam', loss='categorical_crossentropy')

# Train model
model.fit(image_features, image_labels)

The diagram illustrates how a dataset is divided into batches and the combination of those batches equals one epoch.

The image shows a dataset being split into a training and validation sample.

# Train model with validation split
model.fit(features, labels, epochs=10, validation_split=0.20)

The image shows 10 epochs of training and validation results.

# Recomile the model with the accuracy metric
model.compile('adam', loss='categorical_crossentropy', metrics=['accuracy'])

# Train model with validation split
model.fit(features, labels, epochs=10, validation_split=0.20)

The image shows 10 epochs of training and validation results.

The image shows a dataset being split into a training, validation, and test sample.

# Evaluate the test set
model.evaluate(test)

Introduction to TensorFlow in Python