I have heard of ensemble methods, such as XGBoost, for binary or categorical machine learning models. However, does this exist for regression? If so, how are the weights for each model in the process of predictions determined?
I am looking to do this manually, as I was planning on training two different models using separate frameworks (YoloV3 aka Darknet and Tensorflow for bounding box regression). Is there a way I can establish a weight for each model in the overall prediction for these boxes?
Or is this a bad idea?