Is there an easy way to make it so that track IDs are also unique across classes?
Also, does this model work well if the dataset is very large so tid_num dict is like {0:500000, 1: 800000}, and is there a more appropriate loss function to select in this case?
Is there an easy way to make it so that track IDs are also unique across classes?
Also, does this model work well if the dataset is very large so
tid_num
dict is like{0:500000, 1: 800000}
, and is there a more appropriate loss function to select in this case?