ytm.tm.config.RegressionConfig

class ytm.tm.config.RegressionConfig

Bases: TMConfig

Settings for the discrete regression TM. Also takes every parameter of TMConfig.

y_range: tuple[float, float] = (0.0, 1.0)

Range (lo, hi) of the targets, lo < hi. Targets are scaled linearly from this range to [0, T_max]. Every target must lie inside it.

prepare_Y(Y: ndarray) → ndarray

Check Y, and convert any type of provided Y to multihot/onehot.