How to use the libneai.a lib in MDK?

[Junde]

Hi guys,

These days I already know how to generate the AI model named libneai.a(also including the NanoEdgeAI.h) by NanoEdge AI Studio.

But I don't know how to use it, I try to import it to MDK, but MDK always has a compiler error. Is there some information about "How to do an AI demo from scratch"?

And one more thing, Can I valide the AI model(libneai.a) created by NanoEdgeAI at windows or linux platform?

Thanks!

[Julian E. · Accepted solution]

Hello Junde,

We don't use MDK, but based on what we found, it seems like you need to rename the libneai.a to libneai.lib. Please follow the official documentation: µVision User's Guide (arm.com)

Here is some documentation about NanoEdge's libraries:

• for Anomaly detection: AI:NanoEdge AI Library for anomaly detection (AD) - stm32mcu
• for N class: AI:NanoEdge AI Library for n-class classification (nCC) - stm32mcu
• You can also look for 1 class and extrapolation on the wiki.

Here is a link to a project example, at the end you can find information on how to integrate NanoEdge Ai libraries with cubeIDE, it may help you with MDK: AI:How to create a multi-state vibrations classifier using NanoEdge AI studio - stm32mcu

Finally, about your question to validate the library on windows or linux :

• First, you can validate the library directly in the studio in the emulator step. The emulator simulates the behavior of the library as if in a microcontroller.
• In this same step you can also download an emulator of the lib for window and linux and use it with command line interface. Here is a link for the emulator in Anomaly detection, you can find the documentation for the other emulator in the wiki: AI:NanoEdge AI Emulator for anomaly detection (AD) - stm32mcu

I hope this is helpful,

Have a good day!

[Tesla DeLorean]

Might also need some shim functions for the Linker to get closure.

Getting undefined referencing errors?