2025-04-28 9:25 PM - last edited on 2025-04-29 1:31 AM by Andrew Neil
Dear Community,
I am attempting to deploy an .onnx model to STM32F407VET6 via STM32CubeAI 10.0.0.
I have generated the code, completed the compilation and download through MDK5, and also completed the validate on desktop on STM32CubeMX. However, when conducting the validate on target, I encountered the "INTERNAL ERROR: E801(HwIOError): Invalid firmware - COM3:115200" issue. I'm a novice, maybe I haven't done the configuration work well and don't know how to make adjustments.
I have attached my code file in the attachment. If I need to provide more relevant files, please let me know. I would be extremely grateful!
Regards
knight
2025-04-29 1:29 AM
Hello @knight,
To do a validation target with X Cube AI:
Then, to create your own application, use the application template instead of the validation template
Have a good day,
Julian
2025-04-29 7:16 PM
Dear Julian,
Thanks for the guideline! I followed your steps, successfully generated code in STM32CubeMX, built and run project in STM32CubeIDE, but when I tried to validate on target again, there is a "No board connected on the machine with MCU" issue. Do you know how to fix it? Thanks a lot again.
Regards
knight
2025-05-04 11:17 PM
Dear Knight,
In order to perform validation on target you need connection to MCU UART via ST-Link Virtual COM Port (VCP) to exchange validation data with PC e.g. on NUCLEO board such a connection is implemented. I'm not sure what kind of STM32F407 board you are using (proprietary one ?), please make sure you have such a connection and ST-Link is capable to provide VCP profile (>= ST-Link v2.1). As reference you can see NUCLEO-F429 -> USART3 pins PD8, PD9 are connected to on-board ST-Link VCP.
Best regards,
Bartosz