« first day (791 days earlier)      last day (1610 days later) » 

Ivo Flipse
Ivo Flipse
10:39
I can determine it for my test set, because I have a manually annotated data to evaluate the algorithm with. But with new data, I don't know beforehand which of the different trackings gives the best result and some make the same kind of error, so they would agree on the wrong thing
But I'm definitely going to look into running multiple at the same time and compare the results and see what I can come up with

« first day (791 days earlier)      last day (1610 days later) »