cancel
Showing results for 
Search instead for 
Did you mean: 

Help! When I deploy a neural network model to a development board the model fails to initialize!

mc_daydayup
Associate II

I have version 6.7.0 of STM32CUBEMX, version 8.1.0 of X-CUBE-AI, and my stm32 development board model stm32h743iit6. using the Analyze button on STM32CUBEMX works. But when I generate c code for my onnx model and deploy it to the development board, my model fails to initialize. When I traced how the problem happened, I saw the ai_platform_network_create function. It's a black box function and I can't get inside it (it seems to be an officially provided function). I can compile and burn normally using the Keil software, but I can't proceed further when I run into this function. When I use debugging and click on the Stop button while stuck, my Call stack+Locals window prompts an HardFault_handler error. How do I get my model to run properly?

mc_daydayup_1-1701944871635.png

mc_daydayup_2-1701944960749.png

 

O7{76[7RY6I]4WH`UUP%(U2.png

_`67]P]UJOE57MCSV4EKOV1.png

61f5ffe2-b066-4e85-9f07-355ac1631982.png

mc_daydayup_0-1701944803115.png

 

 

1 ACCEPTED SOLUTION

Accepted Solutions
fauvarque.daniel
ST Employee

The STM32Cube.AI library requires to have the CRC IP enabled. 

Normally when the code is generated using STM32CubeMX and X-CUBE-AI the initialization of the CRC is done automatically. You can copy paste that part of the code in your project.

Regards

View solution in original post

2 REPLIES 2
fauvarque.daniel
ST Employee

The STM32Cube.AI library requires to have the CRC IP enabled. 

Normally when the code is generated using STM32CubeMX and X-CUBE-AI the initialization of the CRC is done automatically. You can copy paste that part of the code in your project.

Regards

Thank you for your answer, the problem has been solved!
Thanks again!