wearepal/hyaline

Stars
2
Language
Python
License
MIT License
Created almost 2 years ago
Updated over 1 year ago

wearepal/hyaline

wearepal

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

A repo with the straightforward goal of evaluating and comparing various domain-generalisation, group-robust, and distributionally-robust algorithms on common benchmarks in an attempt to gauge what progress (if any) has been made and thereby identify future avenues of research.

data-science-types

Mypy stubs, i.e., type information, for numpy, pandas and matplotlib

EthicML

Package for evaluating the performance of methods which aim to increase fairness, accountability and/or transparency

conduit

Lightweight framework for data-loading with PyTorch and harvesting the power of (PyTorch) lightning

nifr

Null-sampling for Interpretable and Fair Representations

Jupyter Notebook

UniversalGP

Generic implementation of GP model

qBOLD-VI

A Bayesian inference package for qBOLD MRI data

okapi

[NeurIPS 2022] Okapi: Generalising Better by Making Statistical Matches Match

Data-Domain-Fairness

denoising

Fully-convolutional image denoiser incorporating camera ISO values as conditional information.

ranzen

A python toolkit facilitating machine-learning experimentation.

ecoacoustics

Jupyter Notebook

datasheet_generation

Jupyter Notebook

fescher

A foray into the world of performative prediction

acre-cascade

biomassters

teext

Typing extensions extensions

compression-subgroup

[EMNLP 2023] Are Compressed Language Models Less Subgroup Robust?

RealPatch

presentations

View presentations here: https://wearepal.ai/presentations/

landscapes

ethicml-models

Models for EthicML

Jupyter Notebook

missing-sources

Jupyter Notebook

neoconfigen

configen-fork with extended type-support

topocluster

landscapes-ml

Models and training routines for the 'landscapes' projects

rhyolite

Simple creation of data classes from dictionaries.

support-matching

Jupyter Notebook