Software development kit by XMOS addresses AI for the IOT
Tools and resources to accelerate the development of devices that can think for themselves in an intelligent IoT have been collated by XMOS. The software development kit (SDK) for the artificial intelligence of things (AIoT) includes TensorFlowLite for Microcontroller development tools. The SDK is designed to harness xcore.ai and make it easier for engineers to develop connected products that can sense, think, decide and act.
The kit has standardised tools and resources developers can used to create devices that absorb contextual data from their environment, infer meaning from that data, and translate the results into action.
AIoT tools include scripts, tools and libraries to convert TensorFlowLite for Microcontroller models into a format that targets accelerated operations on the xcore.ai platform. There are also libraries to support FreeRTOS operation on xcore.ai, for a standard industry programming environment.
Examples show a variety of operations based on bare-metal and FreeRTOS operation, including smart microphone sensing. There is also documentation (getting started guides, example builds and execution walkthroughs) and access to XMOS’ open-source libraries of interfaces and signal processing algorithms.
The tools are designed to enable developers to rapidly deploy custom or off-the-shelf AI models using a standard framework alongside all of the control, communications, signal and I/O processing required to create a complete and secure application, says XMOS.
“Our AIoT SDK enables developers to create intelligent endpoint-AI solutions for a huge variety of applications,” said Mark Lippett, CEO of XMOS. “The flexibility of the xcore.ai architecture enables our customers to create truly differentiated solutions using standard embedded software techniques like TensorFlowLite for MCU in a fraction of the time required using traditional hardware approaches.”
Early access to the XMOS AIoT SDK will be available on the GitHub open source platform, designed to be used in conjunction with the xcore.ai Explorer Kit, which is available on limited release via xmos.ai.
Future releases will include other xcore.ai hardware platforms, targeting specific use case applications. An example is a smart home platform. This small form factor reference design with additional Wi-Fi capability is designed to demonstrate the capabilities of voice at the edge of networks. It is due to be released in early 2021.