Confused about OpenCL & dnn backends

Hi, this is my first post and I’m very new to OpenCV and Python.

Im getting confused about if/how I could use my container hosts Intel iGPU (Core i5 14500) in my code which is all about face detection and recognition from rtsp streams.

I can build a docker container using python:slim, install the intel-opencl-icd drivers and clinfo does see the devices in /dev/dri.

My code is very young and an almost copy-paste of the YuNet Face Detection model found opencv_zoo. I’ve read and have some basic comprehension of the T-API and the need to use cv::UMat. However I don’t understand enough to know where to go next. I would really appreicate any help here in terms of solid articles to consult, example code with good comments and/or any pre-reading I may have skipped over as I’m tackling this alone.

I appreicate time is precious but in case anyone wants to take a closer look my code is here.