The Raspberry Pi 5, the small-but-mighty laptop that has turn into fairly widespread with tech hobbyists and industrial corporations, is now additionally an AI laptop. The corporate simply launched the AI Package, a $70 extension equipment with a neural community inference accelerator that can be utilized for native inferencing.
For this new extension module, Raspberry Pi is profiting from its HAT+ extension card. HAT stands for “{Hardware} Hooked up on High”. It’s a cute acronym that the corporate has been utilizing for extension playing cards that you would be able to match on prime of a daily Raspberry Pi.
Raspberry Pi’s HAT+ extension card provides an M.2 slot, which is an ordinary extension slot that’s generally used for PC elements. (this slot is related to the Raspberry Pi by a single-lane PCIe 3.0 interface working at 8Gbps for our readers who care concerning the advantageous prints).
And the corporate has partnered with Hailo, an AI chip startup that not too long ago raised $120 million and desires to problem Nvidia. Hailo focuses on chips which can be designed to run AI workloads on edge gadgets, comparable to automobiles, good cameras, robotics and now Raspberry Pi gadgets.
The accelerator module that Raspberry Pi is utilizing for the AI Package is the Hailo-8L. It’s an entry-level module in an M.2 for issue, which implies that it will probably simply be fitted on the HAT+.
As soon as every thing is put in, what you get is a Raspberry Pi 5 with 13 tera-operations per second (TOPS) of inferencing efficiency. It’s not a lot in comparison with the efficiency of an Nvidia GPU. However it’s cost-effective and works with the Raspberry Pi’s default 27W energy provide.
On the software program entrance, the newest launch of the Raspberry Pi OS robotically detects the Hailo module. The neural processing unit turns into obtainable for the OS and functions that make the most of it.
Raspberry Pi has additionally up to date its suite of digicam functions in order that they help neural community inferencing as a part of the digicam pipeline. For example, it may be used for object detection (“this can be a banana”), semantic segmentation (“these three issues are shifting automobiles”), occasion segmentation (“these three shifting automobiles are a truck, a purple automotive and a blue automotive”), pose estimation and facial landmarking.
These are simply examples of what you are able to do with a Raspberry Pi outfitted with the AI equipment and a first-party or third-party digicam. However the Hailo chip may be leveraged for non-camera use instances.
It’s going to be fascinating to see new use instances emerge from the Raspberry Pi neighborhood. This AI extension equipment is a instrument. Now, it’s as much as Raspberry Pi’s clients to determine what they wish to do with it.