The Coral is fantastic for use cases that don’t need large models. Object recognition for security cameras (using Blue Iris or Frigate) is a common use case, but you can also do things like object tracking (track where individual objects move in a video), pose estimation, keyphrase detection, sound classification, and more.
It runs Tensorflow Lite, so you can also build your own models.
Pretty good for a $25 device!
This is something a lot of people don’t seem to understand. Even if code is self-explanatory, I want to know why it was designed that way.
I’ve fixed bugs where the fix was only a one line change, but it was extremely difficult to figure out, so I left a 10ish line comment above it explaining why it has to be done that way.