Automatic code generation for fast inference in the CMS tracking software
- Mentors
- Vincenzo Innocente, Felice Pantaleo, Marco Rovere
- Organization
- CERN-HSF
Extracting shape information from simulated CMS events Using Tensorflow to train a DNN based on the shape of the hits, detector information and Montecarlo Truth Measuring efficiency and fake rejection Integrate in the CMS software the trained network