Hi, I am currently working on a project which involves giving directions to the user telling them what they should do to frame a given object (also only doing this if sees the object which can be many things, so it needs detection too) so that it can be optimally in view of the camera to be classified. I have figured the classification, but not the real time guidance and detection. I tried training a model that featured all of the different movements ("move up", "move down", etc.). It featured 30 different objects with ten crops per image, and each class featured all 30 images and an even amount per class. It had over 1500 images in total, and I trained using createml and core ml. But, they were very inaccurate in my testing. I also tried using foundation models for this, but it also didn't work. I am quite new to integrating ai/ ml models into a project, and I am unsure of where to go next. If anyone has any suggestions, I would be really appreciative.