Recognizing Photo Sizes And Detection Of Specific Classes Only

[furkanaydinoz]

Hello, how important are photo resolutions when preparing my own dataset? So should the size of my photos for yolov3 be 416 x 416? (608 x 608 for Yolov4?) How important is this? What are the important parameters when creating the dataset?

My second question is what kind of way can I follow to recognize only certain objects. For example, I just want to know the "black mercedes cla" class. İt shouldn't know when he sees another car. He only needs to know the trademarks, models and colors I have defined. Like face recognition systems.

Thank you for all your feedbacks.