torchfilter.data._split_trajectories

Private module; avoid importing from directly.

Module Contents

Functions

split_trajectories(trajectories: List[types.TrajectoryNumpy], subsequence_length: int) → List[types.TrajectoryNumpy]

Helper for splitting a list of trajectories into a list of overlapping
torchfilter.data._split_trajectories.split_trajectories(trajectories: List[types.TrajectoryNumpy], subsequence_length: int) → List[types.TrajectoryNumpy][source]

Helper for splitting a list of trajectories into a list of overlapping subsequences.

For each trajectory, assuming a subsequence length of 10, this function includes in its output overlapping subsequences corresponding to timesteps…

[0:10], [10:20], [20:30], ...

as well as…

[5:15], [15:25], [25:30], ...
Parameters:

  • trajectories (List[torchfilter.base.TrajectoryNumpy]) – List of trajectories.

  • subsequence_length (int) – # of timesteps per subsequence.

Returns:

List[torchfilter.base.TrajectoryNumpy] – List of subsequences.