classification recognition result

[LinXiaoj]

Hello, may I ask how to extract the coordinate information of the key points of the human body and hand it over to the neural network for training, so as to classify and predict the actions of the human body through the actions represented by the key points?In other words, is it necessary to perform classification training on the detected key point skeleton diagram, and how to return the classification result to yolopose so that the detection result has both the key point skeleton diagram and the classification recognition result?