New Raspberry Pi AI Kit for Edge Applications Developed with Hailo
June 05, 2024
News
Raspberry Pi is now making AI accessible on its platform, tailored specifically for low-power edge applications. The new Raspberry Pi AI Kit is available now for $70 and is ready to help developers experiment and implement with neural networks, artificial intelligence and machine learning on Raspberry Pi 5.
This AI Kit was developed in collaboration with Hailo, and the partners say that it is designed to offer an accessible way to integrate local, high-performance, power-efficient inferencing into a wide variety of applications, and allows rapid builds of complex AI vision applications, running in real time, with low latency and low power requirements. Neural networks for object detection, semantic and instance segmentation, pose estimation, and facial landmarking can all reportedly run entirely on the built-in Hailo-8L co-processor.
This kit can perform 13 TOPS of inferencing performance, and has single-lane PCIe 3.0 connection running at 8Gbps. It’s of course fully integrated with the Raspberry Pi image software subsystem, and is compatible with first- or third-party cameras, according to the documentation. If you don’t want to build your own neural net, Hailo is offering a variety of pre-trained neural network models that are ready to deploy.
The focus for the software was in making AI-vision applications possible on the platform. To that end it’s compatible with first- and third-party cameras, and the rpicam-apps suite of camera applications includes a post-processing template for integrating neural network inferencing running real-time in the camera pipeline. Users can tap into pre-installed Hailo Tappas post-processing libraries to create AI apps with only a few hundred lines of C++ code.
There are hundreds of possible applications, of course, but Raspberry Pi has created several previews. Check them them out here:
The partners didn’t even limit users to only rpicam-apps or Picamera2. They’ve also created an API integrated in the GStreamer framework and native Python or C/C++ applications, even for non-camera use cases, such as running inference on pre-recorded video files.
For more information, check out the documentation for the AI Kit and the full technical specifications for the Hailo-8L AI accelerator module on Hailo’s product web page.
Ken Briodagh is a writer and editor with two decades of experience under his belt. He is in love with technology and if he had his druthers, he would beta test everything from shoe phones to flying cars. In previous lives, he’s been a short order cook, telemarketer, medical supply technician, mover of the bodies at a funeral home, pirate, poet, partial alliterist, parent, partner and pretender to various thrones. Most of his exploits are either exaggerated or blatantly false.
