Hi, I am trying to deploy a Keras NN model that fits in the board STM32F407VG-DISC1.
The model is created and loaded it into the project according to the latest given documentation and latest version of tools is used.
While working with STM32CUBEMX and the AI additional package,
After analyzing the model, and validate it on desktop, they both work fine.
The following error appears while validating on Target,
LOAD ERROR: STM32 - no connected board(s), invalid firmware or the board should be re-started
·In the X-Cube-AI interface I have explicitly choosen the com port (In my case COM3) to use on the PC. Also automatic option is tried
· My last configuration uses USART2 Asynchronous for communications. I'be tried with pins:
· PA2, PA3(USART2)
· PD8, PD9(USART3)
· PA9,PA10 (USART1)
· I've used the validation template on the AI package.
· The clock is set to default Clock configuration.
· Minimum Stack size to 0x2000 on the Project Manager tab.
· The model fits without compression, occupying: 775.53 KBytes Flash, 25.08 KBytes RAM
· I've tried to use several USART ports to enable communications with the board, and I've tested the USART communications with an example project that correctly send the data to my terminal. My configuration seems correct, at least on the board to use the USART.
· Using Windows OS
My questions are:
1. Do I need to perform further configuration to generate the code?
2. Do I have to do any other hardware connections like using, TTL to USB connector from PA2,PA3(USART2).
Best Regards,
Mohan
