Regularization Python Packages

networks

Library which can be used to build feed forward NN, Convolutional Nets, Linear Regression, and Logistic Regression Models.

neural-structured-learning

Training neural models with structured signals.

dropblock

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

scproject

Transfer Learning of Gene Expression Signatures in Python.

l1tv

Denoising/reconstruction of piecewise constant signals using the L1TV model

pyunfold

Iterative unfolding for Python

l0learn

Efficient Algorithms for L0 Regularized Learning

condat-tv

Python wrapper for the fast TV denoising algorithm by Laurent Condat

tomobar

TOmographic MOdel-BAsed Reconstruction (ToMoBAR) software

early-stopping-pytorch

Early stopping for PyTorch

egora

EgoRA — Entropy-Governed Orthogonality Regularization for Adaptation. Dynamic information-theoretic regularization for fine-tuning neural networks.

mlektic

A simple machine learning python library.

pytmpinv

Tabular Matrix Problems via Pseudoinverse Estimation

mumfordshah2d

Algorithms for edge preserving smoothing based on the Mumford-Shah model

pyclsp

A modular two-step convex optimization estimator for ill-posed problems

ear-transformers

Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"

pylppinv

Linear Programming via Regularized Least Squares

torch-layer-normalization

Layer normalization in PyTorch

egora-diagnostics

EgoRA — Entropy-Governed Orthogonality Regularization for Adaptation. Dynamic information-theoretic regularization for fine-tuning neural networks.

egora-rrl

EgoRA — Entropy-Governed Orthogonality Regularization for Adaptation. Dynamic information-theoretic regularization for fine-tuning neural networks.

ccpi-regularisation-cupy

The set of CPU/GPU optimised regularisation modules for iterative image reconstruction and other image processing tasks

lppinv

Linear Programming via Regularized Least Squares

label-relaxation

Supplementary material and code for "From Label Smoothing to Label Relaxation" as published at AAAI 2021.

libnmf

Optimization and Regularization variants of Non-negative Matrix Factorization (NMF)