TinyML

Chapter 10. Person Detection: Training a Model

In Chapter 9, we showed how you can deploy a pretrained model for recognizing people in images, but we didn’t explain where that model came from. If your product has different requirements, you’ll want to be able to train your own version, and this chapter explains how to do that.

Picking a Machine

Training this image model takes a lot more compute power than our previous examples, so if you want your training to complete in a reasonable amount of time, you’ll need to use a machine with a high-end graphics processing unit (GPU). Unless you expect to be running a lot of training jobs, we recommend starting off by renting a cloud instance rather than buying a special machine. Unfortunately the free Colaboratory service from Google that we’ve used in previous chapters for smaller models won’t work, and you will need to pay for access to a machine. There are many great providers available, but our instructions will assume you’re using Google Cloud Platform because that’s the service we’re most familiar with. If you are already using Amazon Web Services (AWS) or Microsoft Azure, they also have TensorFlow support and the training instructions should be the same, but you’ll need to follow their tutorials for setting up a machine.

Setting Up a Google Cloud Platform Instance

You can rent a virtual machine with TensorFlow and NVIDIA drivers preinstalled from Google Cloud Platform, and with support for a Jupyter Notebook web interface, which ...