AI Runner: LOAD ERROR: STM32 - read timeout 50047.0ms/50000ms

[Krip]

I have followed the instructions mentioned in :Getting started - How to evaluate a model on STM32N6 development board for a quick profiling of my model.

Board: STM32N6 Nucleo board

I, however , get a timeout message "LOAD ERROR: STM32 - read timeout 50047.0ms/50000ms" when running the Ai runner. 

I have done the following.

1. In Dev Mode(BOOT0 and BOOT1 set) , n6_loader.py is executed and the log is attached as n6_loader.log

2. The image Post_programming.png shows the output in TerraTerm after loading the Software.

3. After setting the relevant python paths, and running the validate command as below, I see the load error. Attached is the screenshot Ai_runner_log.png.

$ stedgeai validate -m <model_path> --target stm32 --mode target -d file:st_ai_ws

The generated report on the model resources are Flash : 1.1 MB and RAM: 3.1 MB.

Could you please let me know how can I do a quick validation without encountering such an error ?

 

[Julian E.]

Hi @Krip,

 

I think your issue is that you did not generate the model.

 

You need to:

• do a generate of your model to get the /st_ai_output and /st_ai_ws folders.
• What I personally do is that I copy these 2 folders in the /n6_loader folder (I delete previous one if any to be sure that I will flash the right model)
• In config_n6l.json, make sure that the path to your network.c is pointing to your /st_ai_output/network.c
• Then use the n6_loader.py 
• finally run the validate command with the same options that you used in the generate (datatypes, channels etc)

 

Please also check the troubleshooting part:

https://stedgeai-dc.st.com/assets/embedded-docs/stneuralart_getting_started.html#ref_troubleshoot 

 

Let me know if this helped.

 

Have a good day,

Julian