KumaraswamyNumericalConverter#

class sdm.prior.KumaraswamyNumericalConverter(a: HP[float] | Correlated[float] | float, b: HP[float] | Correlated[float] | float)#

Bases: NumericalConverter

Apply Kumaraswamy warping after min-max scaling each column.

Parameters:
forward(slices: Tensor, generator: Generator | None = None) → tuple[Tensor, Tensor]#

Return numerical column values and slices passed to child nodes.

Parameters:
  • slices (Tensor) – Node-channel slices per column with shape [C, H, R] for columns, channels, and rows. The channel count H may be ragged across columns.

  • generator (Generator | None) – Pseudorandom generator.

Returns:

Column values with shape [C, R] and updated node-channel slices with the input shape for use by child nodes.

Return type:

tuple[Tensor, Tensor]