Model from visual wake word does not work for Harvard tinyMLx course arduino code

I am trying to modify the benchmark training code to create a custom model for person detection.

Just to check for sanity, I was trying to see whether I can port the already generated model to arduino code.

I have used the vww_model.cc file and the corresponding settings file to replace the model files in the arduino code developed for the course https://www.edx.org/professional-certificate/harvardx-tiny-machine-learning

I have used the board from here: https://store-usa.arduino.cc/products/arduino-tiny-machine-learning-kit

We have arduino code already available for this course.
This code already has model file. So I replace it with the model file available in this repo and also change the settings files.
The output of the code always shows no person, even when I change the position of the camera.

Can anybody let me know whether this model can be directly used to replace the model files in other repo.

Start by comparing vww_model.cc and its corresponding settings file with the model files used by the Harvard tinyMLx Arduino course code. Check whether the generated model and settings are intended to be interchangeable; done means determining whether direct replacement is supported and identifying the compatibility issue if it is not.