Deploying neural networks.Tflite on N657X0 Nucleo

[HANITALY]

Hi,

I have been trying to deploy simple neural networks.tflite on the STM32 N657X0 board, by applying the XCUBEAI, running under NPU.

While, I have not made it work yet. 

If anyone has such project or docs to share, It would be highly appreciated.

Best,

Han

[Julian E. · Accepted solution]

Hello @HANITALY,

We are finalizing a document to explain how to start a project in cubeMX and add a model inference with random inputs for the DK and Nucleo N6 boards.

I will update you when this is ready.

Alternatively, you should find all the AI demo on N6 (compatible with both boards) here: 

GitHub - STMicroelectronics/STM32AI_Overall_Offer: This repo is the entry point to all other STM32 MCU/MPU AI-related GitHub repos.

These are complete application with camera pipeline, AI inference and display.

Have a good day,

Julian

[Julian E.]

Hello @HANITALY,

I answered another thread of yours with the same content.

I include the links also here, for potential readers, as I mentioned it on my last message.

You can find the article here:

Nucleo N6:  How to build an AI application from scratch on the... - STMicroelectronics Community

DK N6: How to build an AI application from scratch on the... - STMicroelectronics Community

Have a good day,

Julian

[HANITALY]

Dear Julian,

I am having an issue running the project. For me, I can run until  LL_ATON_RT_Init_Network(&NN_Instance_Default); // Initialize network instance.

I do not know why after the LL_ATON_RT_Init_Network(&NN_Instance_Default);, there is no any print from APPLI on Serial monitor, while the codes can print everything(input buffer infos and so on) normally before this function.

If it is convenient for you, would you mind sharing the Zip file of the project with me? Maybe I missed some programming parts somewhere that I am not noticing.

Thank you very much!

-----------------------------------------------------------------------------------------------------------------------------------------------

I have solved the Issue!