13

Visualizing Networks with TensorFlow 2.x and TensorBoard

In this chapter, we are going to take a peek inside a machine's "mind" while it's "thinking" through the layers of a deep learning neural network. The number of lines of code required to build a sequential classifier for a convolutional neural network (CNN) has been drastically reduced with TensorFlow 2. Running the classifier only takes a click. However, to understand the program when something goes wrong is a more difficult task, and visualizing the outputs of the layers can be very productive.

Visualizing the output of the layers of a CNN can provide an in-depth knowledge of each individual step comprising the whole process.

In this chapter, as in several of the preceding chapters, ...

Get Artificial Intelligence By Example - Second Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.