Adding fast forward to dl1
This MR adds the option for DL1 models to repeat some of the input variables in the last layer of the tagger. The idea is to repeat global variables (such as pT and eta) to help the taggers.
This MR adds the option for DL1 models to repeat some of the input variables in the last layer of the tagger. The idea is to repeat global variables (such as pT and eta) to help the taggers.