Closed jpata closed 1 month ago
Training works and gives losses that are expected with the PR
before and after this PR, LorentzNet has equivalent performance
while ParticleTransformer is now better (probably due to removing the SequenceTrimmer):
for SimpleDNN, we now revert back to the cand_ParT_features (in #62, the default was changed to kinematics+ParT+lifetimes), which is better:
use_lifetime
cand_features
->cand_ParT_features
for clarity, this is the default feature set as in https://arxiv.org/abs/2407.06788