BrainChip AKD1500 树莓派 5 开发套件发布,快速体验事件驱动类脑 AIBrainchip AKD1500 Raspberry Pi 5 Dev Kit enables event-based neuromorphic AI experiments


AI free token/AI免费积分
BrainChip AKD1500 树莓派 5 开发套件发布,快速体验事件驱动类脑 AI

CNX Software 报道,BrainChip 推出 AKD1500 树莓派 5 开发套件,让开发者能快速体验其低功耗、低延迟的事件驱动(event-based)类脑 AI 技术。

套件将树莓派 5 8GB、官方 M.2 HAT+ 扩展卡与 Akida AKD1500 M.2 加速卡集成于一个金属外壳中,除供电 USB-C 外,千兆网口、四个 USB、双 HDMI 等接口均外露。

预装 Ubuntu Server 20.04、Python 3.7 与 MetaTF 开发环境。接上 USB 摄像头并连网后,在浏览器输入开发板 IP 即可本地运行 Visual Wake-Word 人检、YOLO 目标检测、MobileNet 边缘与人脸等演示,全程无需云端。

开发者可使用 MetaTF 框架训练自定义模型,官方还提到支持 Edge Impulse;芯片支持片上训练,模型可在设备端直接学习新类别而无需云端重训。

价格方面,该开发套件售价 1295 美元(非成本优化定位);若自行采购树莓派 5 8GB、M.2 HAT+、Akida 卡与外壳组装,硬件成本约 350 美元。

本文来源:https://www.cnx-software.com/2026/11/02/brainchip-akd1500-raspberry-pi-5-dev-kit-enables-users-to-quickly-experiment-with-event-based-neuromorphic-ai/
若有版权问题,请来信告知:13951431913#139.com 或在右方提交评论。

A few weeks ago, we noted that the Brainchip AKD1500 M.2 module could work with the Raspberry Pi 5 using a compatible M.2 HAT+ expansion card to evaluate the solution or develop applications using the company’s low-power, low-latency neuromorphic AI technology.

To make things even easier, they’ve now introduced the AKD1500 Raspberry Pi 5 Dev Kit that packs a Raspberry Pi 5 8GB, an official M.2 HAT+, and an Akida AKD1500 M.2 B+M-Key card into a metal case.

Most ports from the Raspberry Pi 5 are exposed, namely the Gigabit Ethernet port, the four USB connectors, the two HDMI video outputs,  and the USB-C port for power. The Raspberry Pi 5 power button and an LED on the M.2 HAT+ are also visible through openings in the metal case. The kit requires a camera for operation, but instead of relying on a MIPI CSI-based Raspberry Pi Camera module, users are asked to connect a USB camera.

The kit also ships with a 32GB SD card preinstalled with Ubuntu Server 20.04 LTS (TBC), Python 3.7, and the MetaTF Development Environment. Users just need to connect a USB camera and the Raspberry Pi 5 to their local network over Ethernet or WiFi. You can then type the IP address (e.g., 10.42.0.1 over WiFi) of the development kit in a web browser to access the Akikda Demo Dev Kit launcher for the Visual Wake-Word (VWW) person presence demo, object detection demo (YOLO), edge demo (MobileNet), and Face demo (MobileNet). Everything runs locally on the device without cloud needed.

Once you are done with the demos, you can work on your own custom models with the MetaTF ML Framework. The company also mentions Edge Impulse support, but it’s only mentioned in the product brief, not the user manual. Other features include on-chip training, where models can learn new classes directly on the device without cloud retraining.

It looks good until we look at the price: $1,295 . I understand it’s a development kit and not cost-optimized, but you could reproduce something similar with a Raspberry Pi 5 8GB ($175 MSRP), an M.2 HAT+ ($12), the Akida AKD1500 M.2 card ($129), a metal case like Geekworm P579 ( $10.99 ), and a 32GB class A1/A2 microSD card ($10-$20). That’s about $350 plus taxes and shipping for the hardware, and you’ll probably need two hours for hardware assembly and software installation. If you make more than ~$400 per hour, then buying the kit may make sense…

Additional information may be found in the press release .

Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.

Brainchip AKD1500 Raspberry Pi 5 Dev Kit enables event-based neuromorphic AI experiments

Support CNX Software! Donate via cryptocurrencies , become a Patron on Patreon, or purchase goods on Amazon or Aliexpress . We also use affiliate links in articles to earn commissions if you make a purchase after clicking on those links.

BrainChip AKD1000 SNN AI SoC gets Raspberry Pi and x86 development kits

SECO launches Mediatek Genio 510 and 700 SMARC SoMs built for industrial and edge AI applications

Pironman 5 Pro Max Raspberry Pi 5 case gains 4.3-inch touchscreen, camera mount, speakers, microphone, and more

Radxa AICore DX-M1M M.2 2242 low-power AI module delivers 25 TOPS of edge AI performance for just 3W of power

Renesas RZ/V2H Robotics Development Kit handles AI vision, motor control, and power management with a single board

暂无评论,快来发表第一条评论吧!No comments yet. Be the first!

📮 需求咨询📮 Inquiry