Closed samvanstroud closed 2 months ago
All modified and coverable lines are covered by tests :white_check_mark:
Project coverage is 94.17%. Comparing base (
9e0c6d1
) to head (1275a81
). Report is 1 commits behind head on main.
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
@samvanstroud looks good to me
Question: do we want another variable-ghost-default-cut.yaml with the track selection if we want to separate the transition from dR to ghost and then to loose tracks? Or do you think we could just implement the track selection in salt?
Question: do we want another variable-ghost-default-cut.yaml with the track selection if we want to separate the transition from dR to ghost and then to loose tracks? Or do you think we could just implement the track selection in salt?
Good point @WeiShengL! For full flexibility I thought we should go with the loose track selection in the preprocessed inputs and then apply the selections during training. If this looks good could you approve? thanks!
Changes:
@WeiShengL could you take a quick look here?