AI has become a hot topic again these last few years since the launch of ChatGPT and rival services. Not looking to get left out of this boom, the Raspberry Pi foundation has launched the Raspberry Pi AI Kit in collaboration with Hailo for just $70 at Approved Resellers. The package includes a M.2 HAT+ pre-assembled with a Hailo-8L AI accelerator module atop a Raspberry Pi 5.
If you do decide to buy this piece of kit, you’ll be able to build complex AI vision applications capable of running in real-time with low latency and low power requirements. The Hailo-8L co-processor is able to run neural networks for object detection, semantic and instance segmentation, pose estimation, facial landmarking, and more while leaving the main CPU to process other tasks.
Commenting on the partnership, Hailo CEO and Co-Founder Orr Danon, said:
“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.”
To help users get started, Hailo has created a “model zoo” on GitHub where you can find a whole bunch of pre-trained neural network models ready to deploy, they’ve also been optimised to run on the AI Kit.
Other 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
For those that do decide to pick up the Raspberry Pi AI Kit, a getting started guide has been created to help you set up and begin using AI software on your device quickly so you can move onto building your own projects.
Source: Raspberry Pi and Hailo
5 Comments - Add comment