CUSTOM MODEL RUNNING ISSUE STM32N6570-DK board

[venkatesh_vltk]

Hi,

In STM32N6570-DK_GettingStarted_ObjectDetection project when I add another uint8 model it is stopping at app_postprocess_od_st_yolox_ui.c and it is moving to hard fault 

1. I am unable to start with camera in my new project. So I am using STM32N6570-DK_GettingStarted_ObjectDetection project to deploy customising model. but when I quantise the model using CLI, I am unable to run the code it is going to hard fault. 

[ivan6]

I was having similar issues bringing in custom models onto the board and when I try and run inference, the function moves into a hard fault. How did you train this model? Eventually, I ended up using the model zoo services to bring in my own dataset and run the premade scripts to train evaluate and produce a quantised model using the ssd_mobilenet_v2_fpn as a backbone, which worked on my board without crashing.

For me, I would like to understand the steps I need to take to train my own object detection model (or any model for that matter) without it crashing.