cancel
Showing results for 
Search instead for 
Did you mean: 

configuring STM32N647X0H3Q using STM32CUBE AI STUDIO

jungle_bert
Associate II

屏幕截图 2026-03-19 111839.png

As shown in the figure, I have equipped the MCU with an external FLASH connected via XSPI2. However, it seems that AI Studio is not aware that there is an external FLASH. How should I configure it to solve this problem?

112303.png112403.png

As shown in the two pictures above, after I connected the development board via ST-link, I wanted to run it on the target, but it prompted "failed to start running". Why is this happening?

1 ACCEPTED SOLUTION

Accepted Solutions
hamitiya
ST Employee

Hello @jungle_bert 

You are right, STM32Cube AI Studio is not able to detect and setup XSPI2 for a user-defined flash.

If your platform is similar to STM32N6570-DK, I would suggest you try from this board instead.

Else, I would suggest you generate a default STM32N6 project from STM32CubeMX, configure XSPI2 and your startup, and integrate AI on it.

Sadly, for STM32N6 Series, it is quite difficult to create a working project out-of-the-box for a custom design.

 

Best regards,

Yanis


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

View solution in original post

3 REPLIES 3
hamitiya
ST Employee

Hello @jungle_bert 

You are right, STM32Cube AI Studio is not able to detect and setup XSPI2 for a user-defined flash.

If your platform is similar to STM32N6570-DK, I would suggest you try from this board instead.

Else, I would suggest you generate a default STM32N6 project from STM32CubeMX, configure XSPI2 and your startup, and integrate AI on it.

Sadly, for STM32N6 Series, it is quite difficult to create a working project out-of-the-box for a custom design.

 

Best regards,

Yanis


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

I would like to know if you will carry out any development in this area in the future. Also, you can add some customizable permissions to enable the AI studio to analyze the models. Additionally, I discovered that this issue only occurred during the model analysis process. I was still able to generate the project and by determining in the network.c file that the code had placed the weights in the external flash.

Hi @jungle_bert,

 

There are definitely a lot of things that we are working on to add to STM32Cube AI Studio.
The ability to perform only an analysis is one of them, since running the whole process takes a lot of time and may not always be what you want to do.

 

Have a good day,

Julian


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.