Intro to Python for Computer Science and Data Science: Learning to Program with AI, Big Data and The Cloud

16.7 Visualizing Neural Network Training with TensorBoard

With deep learning networks, there’s so much complexity and so much going on internally that’s hidden from you that it’s difficult to know and fully understand all the details. This creates challenges in testing, debugging and updating models and algorithms. Deep learning learns the features but there may be enormous numbers of them, and they may not be apparent to you.

Google provides the TensorBoard⁶⁶,⁶⁷ tool for visualizing neural networks implemented in TensorFlow and Keras. Just as a car’s dashboard visualizes data from your car’s sensors, such as your speed, engine temperature and the amount of gas remaining, a TensorBoard dashboard visualizes data from a deep learning model that ...