For more sophisticated neural networks
Raspberry Pi releases AI HAT+ with up to 26 TOPS
Raspberry Pi continues to expand its AI product portfolio. The new »AI HAT+« offers an AI accelerator with up to 26 TOPS. Unlike the AI Kit, which utilises an M.2 connector, the AI HAT+ integrates the accelerator directly onto the main PCB.
Following the launch of the Raspberry Pi AI Kit and AI Camera, Raspberry Pi introduces the newest addition to its AI product line: the »Raspberry Pi AI HAT+«. The AI HAT+ features the same Hailo AI accelerator technology as the AI Kit, but now with a choice of two performance options: the 13 TOPS model, priced at 70 US-Dollars and featuring the same Hailo-8L accelerator as the AI Kit, and the more powerful 26 TOPS model at 110 USD, equipped with the Hailo-8 accelerator.
Designed to conform to the HAT+ specification, the AI HAT+ automatically switches to PCIe Gen 3.0 mode to maximise the full 26 TOPS of compute power available in the Hailo-8 accelerator. Unlike the AI Kit, which utilises an M.2 connector, the Hailo accelerator chip is directly integrated onto the main PCB. This change not only simplifies setup but also offers improved thermal dissipation, allowing the AI HAT+ to handle demanding AI workloads more efficiently.
The 26 TOPS model allows users to run more sophisticated neural networks in real time, achieving better inference performance. The 26 TOPS model also allows to run multiple networks simultaneously at high frame rates. For instance, object detection, pose estimation, and subject segmentation can be performed simultaneously on a live camera feed using the 26 TOPS AI HAT+.
Both versions of the AI HAT+ are fully backward compatible with the AI Kit. The existing Hailo accelerator integration in the camera software stack works in the same way with the AI HAT+. Any neural network model compiled for the Hailo-8L will run smoothly on the Hailo-8; while models specifically built for the Hailo-8 may not work on the Hailo-8L, alternative versions with lower performance are generally available, ensuring flexibility across different use cases.
