2025-08-25 11:15 PM
Hello ,
I am trying to use a text detection model on STM32N6 . This is a CNN model
The command used is :
stedgeai generate --model custom_model.onnx --target stm32n6 --st-neural-art default@user_neuralart_STM32N6570-DK.json --input-data-type float32
The error I get is : INTERNAL ERROR: Order of dimensions of input cannot be interpreted
The model is using the following operators :
Conv
Relu
BatchNormalization
MaxPool
Concat
Resize
It was using Transpose operator , but I removed it from the model
Could you provide the possible reasons behind the error.
Regards,
Sandeep
2025-08-26 12:51 AM
Hello @sandeepchawla74,
I cannot say without the model.
Could you share it in a zip file?
Also, please try to use the option --use-onnx-simplifier, sometimes it helps.
Make sure to use the latest version of the st edge ai core (2.2)
Have a good day,
Julian
2025-08-26 12:55 AM