Error Neural-ART Accelerator MCU: "INTERNAL ERROR: Scale, zero-point, and quantizer must be set simultaneously"

[Fra_]

This ONNX model is compiled with a standard MCU and runs on it (both with and without quantization). However, I encounter the following error when using the Neural-ART Accelerator NPU (both with and without quantization):

INTERNAL ERROR: Scale, zero-point, and quantizer must be set simultaneously.

 

It seems to me that all the model's onnx operations are supported (https://stedgeai-dc.st.com/assets/embedded-docs/stneuralart_operator_support.html)

[Julian E.]

Hello @Fra_,

 

Can you share the model in a .zip file?

 

Have a good day,

Julian

[Fra_]

Here the zip file

[Julian E.]

Hello @Fra_ ,

 

After investigation, the issue is caused by the equal layer. We opened a ticket internally to fix it.

 

Have a good day,

Julian