API REFERENCE/omnibias-torch

omnibias.torch.training

0.5.0rc1Release candidatePython >=3.10Apache-2.0

PyTorch activation derivatives, trainable operator layers, network jets, and direct differential-operator contractions.

import omnibias.torch.training

Module contract & mathematical conventions

Training-loop helpers for omnibias.

Currently exports:

• KGrowthScheduler: plateau-triggered K-growth callback for GrowableOperatorMultiBiasUnit modules.

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 →

k_schedulerModule ↗

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
AnchorProvider	omnibias.torch.training.AnchorProvider
GrowthEvent	omnibias.torch.training.GrowthEvent
KGrowthScheduler	omnibias.torch.training.KGrowthScheduler

← Package overviewRunnable learning examples →