Raspberry Pi gets Hailo AI co-processor accelerator

Thinking of dabbling in the world of AI, whether trying to master machine learning or noodling around with neural networks? Well, the Raspberry Pi team have announced its official Hailo-based Raspberry Pi AI Kit to help you.

For use with its most powerful variant – the Raspberry Pi 5 board – the kit comprises the Raspberry Pi M.2 HAT+ preassembled with a Hailo-8L AI accelerator module.

This enables 13 tera-operations per second (TOPS) and the neural network inference accelerator is built around the Hailo-8L chip. You can get an official overview of that here.

(If the Pi M.2 HAT+ sounds familiar, we covered it going on sale last month. As well as AI accelerators it can hold high-speed NVMe drives for extra storage.)

Hailo

Raspberry Pi writes:

“The AI Kit allows you to rapidly build complex AI vision applications, running in real time, with low latency and low power requirements. State-of-the-art neural networks for object detection, semantic and instance segmentation, pose estimation, and facial landmarking (to name just a few) run entirely on the Hailo-8L co-processor, leaving the Raspberry Pi 5 CPU free to perform other tasks.”

Highlighted features of the Raspberry Pi AI Kit include:

13 tera-operations per second (TOPS) of inferencing performance
Single-lane PCIe 3.0 connection running at 8Gbps
Full integration with the Raspberry Pi image software subsystem
Compatibility with first-party or third-party cameras
Efficient scheduling of the accelerator hardware: run multiple neural networks on a single camera, or single/multiple neural networks with two cameras concurrently

On the AI, software side of things, Hailo has created what it terms a “zoo” of models – a variety of pre-trained neural network models that are ready to run on the AI Kit. We’re talking, depth estimation, face recognition and object detection…

And to help with the software complexity of integrating the Pi’s camera subsystem with the AI framework, Raspberry Pi writes:

“Our rpicam-apps suite of camera applications now has a post-processing template for integrating neural network inferencing running real-time in the camera pipeline. By using the pre-installed Hailo Tappas post-processing libraries, we are able to create advanced AI-based applications in only a few hundred lines of C++ code. Similar levels of integration into our Picamera2 framework will follow soon.”

Impressive.

How much does the kit cost? Seventy online dollars.

Please note, you also can read our Technology Editor’s news story about the AI kit.