Building on the success of the Raspberry Pi AI Kit and AI Camera, Raspberry Pi today announced the new Raspberry Pi AI HAT+ as part of its AI product lineup. The latest AI HAT+ features the same Hailo AI accelerator technology as the Raspberry Pi AI Kit.
The AI HAT+ comes in two variants offering different performance capabilities. The 13 TOPS model will cost $70 and features the same Hailo-8L accelerator available in the recently released Raspberry Pi AI Kit. The 26 TOPS model will cost $110 and is powered by the Hailo-8 accelerator.
While the Raspberry Pi AI Kit uses an M.2 connector, the Hailo accelerator chip is directly integrated into the main PCB in the AI HAT+ for improved thermal dissipation. Also, the AI HAT+ uses PCIe Gen 3.0 mode to deliver 26 TOPS AI performance. With 26 TOPS of performance, developers will be able to perform object detection, pose estimation, and subject segmentation simultaneously on a live camera feed.
Raspberry Pi confirmed that both versions of the AI HAT+ are backward compatible with the AI Kit and are fully integrated into Raspberry Pi’s camera software stack. This allows developers to run post-processing tasks, including object detection, image segmentation, and pose estimation. All models built for the Hailo-8L accelerator can be used with the Hailo-8.
Since the Raspberry Pi AI HAT+ supports popular frameworks like TensorFlow and PyTorch, developers can easily build different AI-powered applications.
Naush Patuck from Raspberry Pi wrote the following regarding the AI HAT+ launch:
After an exciting few months of AI product releases, we now offer an extensive range of options for running inferencing workloads on Raspberry Pi. Many such workloads – particularly those that are sparse, quantised, or intermittent – run natively on Raspberry Pi platforms; for more demanding workloads, we aim to be the best possible embedded host for accelerator hardware such as our AI Camera and today’s new Raspberry Pi AI HAT+.
You can order the new Raspberry Pi AI HAT+ here.
5 Comments - Add comment