API REFERENCE/omnibias-partition

omnibias.partition.keras

0.1.0a2AlphaPython >=3.10AGPL / commercial

Trainable soft partitions of unity, regional experts, temperature hardening, and scoped membership bounds.

import omnibias.partition.keras

Module contract & mathematical conventions

Keras 3 weight twin for omnibias.partition (needs the keras extra).

Shared formulas do not imply universal floating-point identity. Verify dtype, shape, derivative-order support, and the stated numerical assumptions for the path you use.

Module source ↗Source revision 9a2d73df0573Running reference examples →

weightsModule ↗

Imports & aliases

These names share a definition with another public module. Follow a name for its full contract, parameters, and examples.

Import from this module	Canonical reference
combine	omnibias.partition.keras.combine
partition_weights	omnibias.partition.keras.partition_weights
partition_weights_arrays	omnibias.partition.keras.partition_weights_arrays
prod_last_axis	omnibias.partition.keras.prod_last_axis

← Package overviewRunnable learning examples →