Skip to content

Inference

Jump to bottom
Dan Marley edited this page Sep 20, 2018 · 2 revisions

This page describes the steps necessary to include the goldilocks top tagger in an analysis workflow to identify semi-merged top quarks.

Python

Using Keras, it is possible to reload the model used in the training to do inference. You can predict outputs using this function in the Asimov class Foundation.

C++

LWTNN: Deep learning in C++ (use models generated from python tools in C++)

  • deepLearning.cxx

A std::map<std::string,double> is created where the keys represent the different variables used in the training. For each AK8, the map is filled with new values and the lwtnn tool predicts the DNN score.

Clone this wiki locally