Dynamic number of pedestrians

Hi, I'd like to listen your opinion on the following issues related to human trajectory prediction on training real datasets.

1. What if the number of people changes at each timestamps? e.g., the number of people per scene may varies(5⇒5⇒6⇒8⇒1⇒...)
2. Even if the number of people is fixed for each timestamp, what if the people who make up the scene change? e.g. at t=1, human id=1,2,3,4,5 ⇒ t=2, human id=2,3,4,6,7(human 1,5 are missing but human 6,7 are pop in). The above problems may not occur in the simulation using a synthetic dataset in which the number of people is unchanged, but it may be happen on the train with real datasets. Does this code can deal with the problems? I wish to hear your opinion on this.

Regards,

@mincheulkim first of all, this simulation does not support loading real datasets. Secondly, the algorithm is invariant of the number of people present in the scene, although drastically changing number of humans might cause the algorithm's learning to be unstable.

So yeah, you will need a way to figure out a way in the simulation to load varying number of humans. But I think with some proper coding, this can be easily taken care of and added to this framework. One thing that I can think of is: you probably need to supply the id of humans to the algorithm too since currently we assume the id is fixed.