How do I train a machine learning model to identify objects in images?

Hi,

I am trying to develop an application, that would be able to identify objects that are usually found on the rooftops of buildings (like exhaust fans, pipes, etc.) using machine learning (Or should I use deep learning as the type of data is not tabular and consists of images). I needed help as to how do I start coding for this purpose? I have a set of images of coomonly found objects on the rooftops to train my model from but don't exactly know how to go about this task (I don't know how to train the model). I was wondering if anyone could guide me through.

Thanks.