In this chapter, you learned how to develop and optimize a convolutional neural network model on the farthest edge of the network. At its core, a neural network requires lots of data to train, but in the end, it comes out with a model that is able to complete a task without human intervention. In the previous chapters, we learned about the necessary theory and implemented models, but we never did any practical exercises. In practice, a camera can be used for surveillance, to monitor machine performance, or to evaluate a surgical procedure. In each of these cases, embedded vision is used for real time on-device data processing, which requires a smaller and more efficient model to be deployed on edge devices.
In this chapter, you learned about the performance of various single-board computers and accelerators, thus enabling you to make an informed decision regarding what...
