Open xiaolinhan opened 3 years ago
We partition the temporal dimension into slots and the trips falling into one slot share a common T.C.
We partition the temporal dimension into slots and the trips falling into one slot share a common T.C.
Thanks. So the dimension of T.C in one slot of temporal dimension is (the number of grids in the width of the map * the number of grids in the height of the map). Am I correct?
The dimension of T.C is fixed for all trips. The preprocessing code is the same as my previous work.
The dimension of T.C is fixed for all trips. The preprocessing code is the same as my previous work.
Thank you for your help.
I would like to know is the input of CNN a N N(or N M) matrix that covers the traffic condition of ALL trips of ONE (S,D) pair, or is T.C a 1*N(the number of roads in one trip T) vector that only covers the traffic condition of ONE specific trip T.
Many thanks for your help.