Interpolation Functionals

physicsnemo.nn.functional.interpolation(

query_points: Tensor,

context_grid: Tensor,

grid: List[Tuple[float, float, int]],

interpolation_type: str = 'smooth_step_2',

mem_speed_trade: bool = True,

) → Tensor

Interpolate values from a grid at query point locations.

Parameters:

• query_points (torch.Tensor) – Points at which interpolation is to be performed.

• context_grid (torch.Tensor) – Source grid from which values are interpolated.

• grid (list[tuple[float, float, int]]) – Describes the grid’s range and resolution.

• interpolation_type (str, optional) – Interpolation method name, by default "smooth_step_2".

• mem_speed_trade (bool, optional) – Trade-off between memory usage and speed.

• implementation ({"warp", "torch"} or None) – Implementation to use. When None, dispatch selects the available implementation.

Notes

TODO: torch is the default dispatch implementation for now. The Warp implementation will be promoted to the default after additional validation and testing.

Benchmarks (ASV)