Most machine learning platforms are focused toward scientists and practitioners in academic or industrial settings. Accordingly, while quite powerful, they are often rough around the edges and have few user-experience features.

Quite a bit of effort goes into peeking at the model at various stages and viewing and aggregating performance across models and runs. Even viewing the neural network can involve far more effort than expected.

While this was acceptable when neural networks were simple and only a few layers deep, today's networks are far deeper. In 2015, Microsoft won the annual ImageNet competition using a deep network with 152 layers. Visualizing such networks can be difficult, and peeking at weights and biases can be overwhelming.

Practitioners started using home-built visualizers and bootstrapped tools to analyze their networks and run performance. TensorFlow changed this by releasing TensorBoard directly alongside their overall platform release. TensorBoard runs out of the box with no additional installations or setup.

Users just need to instrument their code according to what they wish to capture. It features plotting of events, learning rate, and loss over time; histograms, for weights and biases; and images. The Graph Explorer allows interactive reviews of the neural network.

In this chapter, we will focus on several areas, which are as follows:

• We will start with the instrumentation required to feed TensorBoard using four common models and datasets as examples, highlighting the required changes.
• We will then review the data captured and ways to interpret it.
• Finally, we will review common graphs as visualized by Graph Explorer. This will help you visualize common neural network setups, which will be introduced in later chapters and projects. It will also be a visual introduction to common networks.