cancel
Showing results for 
Search instead for 
Did you mean: 

Unanle to run tensorflow lite micro on stm32769 eval board

hadi81
Associate II

I am trying to run tflm with stm32f769 eval. I build the tflm as a static library and included it in my project. My app  is crashing whille calling allocatetensors() function.  Anyone having any luck with it? Also I couldn' find any official demo for running tflm with stm32.

I am struggling to run my basic model on stm32f769 board. It is failing in allocate tensors step.
My program crashes on the 9th iteration.
"AllocateTensors()->StartModelAllocation()->AllocateTfLiteEvalTensors()->InitializeTfLiteEvalTensorFromFlatbuffer()."
Any help here will be appreciated.
I couldn’t find any official documentation or tutorial which I could follow.

 
 
 
 
 
 
1 ACCEPTED SOLUTION

Accepted Solutions
Julian E.
ST Employee

Hello @hadi81,

 

We do not support TFLM anymore, 

You can find our documentation regarding support of NN here:

https://stedgeai-dc.st.com/assets/embedded-docs/index.html

 

Have a good day,

Julian


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.

View solution in original post

3 REPLIES 3
Julian E.
ST Employee

Hello @hadi81,

 

We do not support TFLM anymore, 

You can find our documentation regarding support of NN here:

https://stedgeai-dc.st.com/assets/embedded-docs/index.html

 

Have a good day,

Julian


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.
hadi81
Associate II

Issue seemed to be related to the boars. Changed my board and it started working fine.

Hello @hadi81,

 

Thanks for the update.

Could you share what materials you are using related to TFLM.

 

I pretty sure it is not supported by ST anymore, meaning that for future issue, we will not be able to help you.

Almost all AI on STM32 is now provided by the ST Edge AI Core.

 

Have a good day,

Julian


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.