cancel
Showing results for 
Search instead for 
Did you mean: 

E801(HwIOError): Invalid firmware - COM2:115200

Pitt_Engineer
Associate

I am currently having an issue with flashing my neural network (saved as a .tflite model) to my Nucleo-L476RG board. I am able to analyze the model successfully, but when I select, "Validate on Target", I receive the error message below: E200(ValidationError): stm32: Unable to bind the STM AI runtime with "network" c-model: [] 
 connection to "serial:115200"/"115200" run-time fails 
 E801(HwIOError): Invalid firmware - COM2:115200 

I have the following screenshots to show my STMCubeIDE as I attempt to validate on target: 

Pitt_Engineer_0-1708994417414.pngPitt_Engineer_1-1708994428211.png

If someone knows how to fix this issue, please let me know. 

5 REPLIES 5
changwen
Associate

I have the same problem.My board is STM32L496G-DISCO.

fauvarque.daniel
ST Employee

I see that you have not selected to compile and flash the project. 

It is ok if you already have on the board the validation firmware with that network flashed. But in your case the desktop application could not communicate with the application on the board, so I guess the program has not been flashed.

You need to check the "Automatic compilation" checkbox so that the validation project with that network is generated, compiled, and flashed on the board.

 


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 have solved my problem.After compiling and flashing the project to the board, you should reconnect the board with the computer.Then select "Validate on Target" again.

MMary.11
Associate II

Hello,

Did you find a solution to your problem?

I encountered a similar issue:

 

MMary11_1-1718802885795.png

Running the Keras model...
Running the STM AI c-model (AI RUNNER)...(name=model, mode=TARGET)
INTERNAL ERROR: E801(HwIOError): Invalid firmware - /dev/ttyACM0:115200
Validation ended

 

Do you have any idea what's wrong?

Thank you.

 

You can see if the project starts correctly by just opening a virtual tty on the port at the correct speed and verify that when you reset the board you have some messages printed like

-------------------------------------------
| READY to receive a CMD from the HOST... |
-------------------------------------------

# Note: At this point, default ASCII-base terminal should be closed
# and a serial COM interface should be used
# (i.e. Python ai_runner module). Protocol version = 3.1

If you have unreadable messages your baud rate is probably wrong

If you don't have any messages, verify that the software is correctly flash, you can check the Automatic compilation and download checkbox

Regards


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.