Raspberry Pi releases new AI kit

4th June 2024
Sheryl Miles

The Raspberry Pi Foundation, in collaboration with Hailo, announces the release of the Raspberry Pi AI Kit.

The kit is designed to empower users to experiment with neural networks, artificial intelligence, and machine learning on the new Raspberry Pi 5, and it features Raspberry Pi’s M.2 HAT+ preassembled with a Hailo-8L AI accelerator module, offering an accessible way to integrate local, high-performance, power-efficient inferencing into a variety of applications.

Speaking on the collaboration, CEO and Co-Founder, Orr Danon commented: "We are thrilled to support Raspberry Pi and empower its vibrant community of professional engineers and creative makers with cutting-edge AI capabilities, Our partnership with the world’s leading single-board computer provider will inspire a new era of computing, enhanced by our high-performance AI processing capacity.”

Comments Raspberry Pi CEO, Eben Upton: "Our collaboration with Hailo enables Raspberry Pi’s industrial customers to integrate AI into high-performance solutions that are extremely cost-effective and power-efficient. For enthusiasts, the AI Kit provides an accessible way to enhance their creative projects with AI,” Eben Upton, Raspberry Pi CEO, said. “Hailo’s combination of high compute power and low power consumption make it an incredibly attractive AI solution for professionals and enthusiasts alike."

Hailo is also introducing an online developer community to support its growing developer community and new Raspberry Pi users. The community aims to support members through tutorials, FAQs, and other resources.

“Our new online community will serve as a collaborative environment for AI lovers to share their experiences and discuss new ways to innovate. We fully expect the introduction of Raspberry Pi’s AI-enabled board to set forth a new path for innovation – and we look forward to collaborating with makers to support them as they experiment and leverage Hailo’s AI capabilities.”  Danon concludes.

Key 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
  • Extensive model zoo with a variety of pre-trained neural network models ready to deploy

Software highlights

Creating real-world AI-based vision applications often presents significant software complexity.

The Raspberry Pi Foundation has simplified this process:

  • The rpicam-apps suite now includes a post-processing template for integrating neural network inferencing in the camera pipeline.
  • Hailo Tappas post-processing libraries allow advanced AI-based applications to be created with only a few hundred lines of C++ code.
  • Simple software installation steps: Install a few packages through apt, reboot, and users can try out AI demos in minutes.
  • API integration in the GStreamer framework and native Python or C/C++ applications, including non-camera use cases, such as running inference on pre-recorded video files.

Some of the demos that can be run through rpicam-apps are:

  • Object recognition
  • Pose estimation

Kit contents

The Raspberry Pi AI kit includes:

  • Hailo AI module with a Neural Processing Unit (NPU)
  • Raspberry Pi M.2 HAT+ for connecting the AI module to the Raspberry Pi 5
  • Thermal pad pre-fitted between the module and the M.2 HAT+
  • Mounting hardware kit
  • 16mm stacking GPIO header

Installation requirements

To use the AI kit, users will need a Raspberry Pi 5.

Each AI Kit comes with:

  • Pre-installed AI module
  • Ribbon cable
  • GPIO stacking header
  • Mounting hardware

The kit is available now for $70.

Featured products

Product Spotlight

Upcoming Events

View all events
Latest global electronics news
© Copyright 2024 Electronic Specifier