As artificial intelligence (AI) technology continues to advance, developers aim to rapidly deploy machine learning models onto embedded systems. However, the significant differences between traditional AI development environments and resource-constrained microcontroller unit (MCU) platforms make model deployment complex and time-consuming. To lower development barriers, Nuvoton has introduced the NuML Toolkit, a Microsoft Windows® tool specifically designed for the NuMicro® M55M1 series microcontrollers. This toolkit enables quick conversion of pre-trained AI models into executable code compatible with Arm® Keil®, simplifying the deployment process.

The NuML Toolkit is optimized for the NuMicro® M55M1 microcontroller, which features an Arm® Cortex®-M55 core and integrates the Ethos™-U55 neural processing unit (NPU), significantly enhancing AI inference performance. Additionally, the M55M1 is equipped with 1.5 MB of SRAM and 2 MB of flash memory, providing ample computational and storage resources for AI applications.

The NuML Toolkit integrates Keil µVision®5 / Arm Compiler 6 (armc6), Make / GCC, and can convert fully INT8-quantized AI models into Keil example code. Developers no longer need to worry about converting PC-trained models into MCU-executable formats; they can directly integrate AI models into MCU development projects and focus on writing peripheral control code, such as for cameras, audio processing, and display outputs.

For instance, if a developer has trained an object detection model to recognize specific objects, designed a keyword spotting (KWS) model for voice control, or created an anomaly detection model to monitor abnormal behavior, the NuML Toolkit allows seamless deployment of these AI models onto the M55M1 platform for real-time execution on the MCU. This conversion process enables developers to concentrate on application development, thereby enhancing project development efficiency.

The NuML Toolkit makes AI deployment more intuitive, particularly for developers seeking to quickly integrate AI applications into embedded systems. With this tool, you can effortlessly complete AI model conversion and focus on implementing MCU functionalities and hardware integration.

If you are interested in this tool, please contact the Nuvoton team through Nuvoton AI webpage www.nuvoton.com/ai "Contact Us" form for more information.