Skip to main content
API REFERENCE/omnibias-torch

omnibias.torch.blocks

0.5.0rc1Release candidatePython >=3.10Apache-2.0

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

import omnibias.torch.blocks
Module contract & mathematical conventions

Operator-typed composite blocks built on OperatorMultiBiasUnit.

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 →
convModule ↗linearModule ↗operatorModule ↗

Imports & aliases​

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

Import from this moduleCanonical reference
AnalyticGaussianConv1domnibias.torch.AnalyticGaussianConv1d
AnalyticGaussianConv2domnibias.torch.AnalyticGaussianConv2d
OperatorBlockomnibias.torch.OperatorBlock
analytic_gaussian_tapsomnibias.torch.analytic_gaussian_taps
cmbConv1domnibias.torch.cmbConv1d
cmbConv2domnibias.torch.cmbConv2d
cmbLinearomnibias.torch.cmbLinear
← Package overviewRunnable learning examples →