Image: Raspberry Pi
“AI” applications are so specialized that they need dedicated neural processing units to work. Apparently, anyway — what benefits these NPUs can actually offer for typical users isn’t exactly clear. But if you’d like to experiment with some very specific AI applications on your Raspberry Pi, that’s now an option with an official hardware module.
The comes with a Hailo-8L accelerator module with an M.2 interface, plus the PCIe 3.0 breakout board needed to use it and install it onto a Pi 5. The module can handle 13 teraflops of data per second over an 8Gbps connection.
That’s some great alphabet soup, but what can this thing actually do? Well don’t expect it to run a chatbot or spit out some LMM text. The Hailo-8L is designed for use with camera modules to process images and video, specifically for things like object detection and pose estimation. Like this admittedly neat little demo posted on the blog post:
That’s the kind of thing that could let you build a cheap motion capture setup in a garage, letting a little phone camera module stand in for thousands of dollars of expensive equipment. It’s pretty dang cool…and if I sound skeptical, it’s only because calling this amalgamation of machine learning “AI” rankles the sci-fi fan in me.
Rasperry Pi is selling the AI kit for $70 on its official web store. That’s a lot for Pi hardware — almost as much as the Pi 5 itself, and it doesn’t include a camera necessary to actually do some of this cool stuff. But considering what makers could build with it, it might be worth the asking price.
Further reading: 10 surprisingly practical Raspberry Pi projects anybody can do
Author: Michael Crider, Staff Writer, PCWorld
Michael is a 10-year veteran of technology journalism, covering everything from Apple to ZTE. On PCWorld he’s the resident keyboard nut, always using a new one for a review and building a new mechanical board or expanding his desktop “battlestation” in his off hours. Michael’s previous bylines include Android Police, Digital Trends, Wired, Lifehacker, and How-To Geek, and he’s covered events like CES and Mobile World Congress live. Michael lives in Pennsylvania where he’s always looking forward to his next kayaking trip.