Charl-AI

keyd

A key remapping daemon for linux.

uv

An extremely fast Python package installer and resolver, written in Rust.

phd_thesis

PhD Thesis

stochastic-caching

A tiny library for stochastic dataset caching in PyTorch.

algostability

Code for the Pre-print 'I don't need u'

snake-fury

a challenge for Haskell beginners

datathon

causal-gen

(ICML 2023) High Fidelity Image Counterfactuals with Probabilistic Causal Models

subgroup-separability

[MICCAI 2023] "The Role of Subgroup Separability in Group-Fair Medical Image Classification"

poop

Performance Optimizer Observation Platform

lazygit

simple terminal UI for git commands

atuin

✨ Magical shell history

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

design-patterns-for-humans

An ultra-simplified explanation to design patterns

Python

All Algorithms implemented in Python

eqxvision

A Python package of computer vision models for the Equinox ecosystem.

sos-vae

Official Code for "Structured Uncertainty in the Observation Space of Variational Autoencoders"

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

quartz

🌱 a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites

MEDFAIR

[ICLR 2023 spotlight] MEDFAIR: Benchmarking Fairness for Medical Imaging

kickstart.nvim

A launch point for your personal nvim configuration

autodidact

A pedagogical implementation of Autograd

the-art-of-command-line

Master the command line, in one page

CommonLoopUtils

CLU lets you write beautiful training loops in JAX.

ViT-CIFAR

PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 with small number of parameters (= 6.3M, originally ViT-B has 86M).

optax

Optax is a gradient processing and optimization library for JAX.

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

dm-haiku

JAX-based neural network library

jaxtyping

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

mkdocstrings

:blue_book: Automatic documentation from sources, for MkDocs.