nestordemeure

iced

A cross-platform GUI library for Rust, inspired by Elm

ThreadPool

A simple C++11 Thread Pool implementation

flax

Flax is a neural network library for JAX that is designed for flexibility.

rust

Rust language bindings for TensorFlow

corpora

A collection of small corpuses of interesting data for the creation of bots and similar stuff.

Flux.jl

Relax! Flux is the ML library that doesn't make you tensor

gpytorch

A highly efficient implementation of Gaussian Processes in PyTorch

rust-bert

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

Zygote.jl

21st century AD

awesome-jax

JAX - A curated list of resources https://github.com/google/jax

Enzyme

High-performance automatic differentiation of LLVM and MLIR.

juice

The Hacker's Machine Learning Engine

objax

trueskill

An implementation of the TrueSkill rating system for Python

Gradient-Centralization

A New Optimization Technique for Deep Neural Networks

rust-autograd

Tensors and differentiable operations (like TensorFlow) in Rust

mpi4jax

Zero-copy MPI communication of JAX arrays, for turbo-charged HPC applications in Python :zap:

pyhpc-benchmarks

A suite of benchmarks for CPU and GPU performance of the most popular high-performance libraries for Python :rocket:

adahessian

ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning

jpeg2dct

uncertainty-deep-learning

hypergradient-descent

Hypergradient descent

Better_LSTM_PyTorch

An LSTM in PyTorch with best practices (weight dropout, forget bias, etc.) built-in. Fully compatible with PyTorch LSTM.

fast_tabnet

TabNet for fastai

batchup

Python library for extracting mini-batches of data from a data source for the purpose of training neural networks

verrou

floating-point errors checker

cxxtimer

A timer for modern C++

ManifoldMixup

ManifoldMixup with support for Interpolated Adversarial training

oxide-enzyme

Experimental usage of https://github.com/wsmoses/Enzyme with Rust

LibNT

C++ and MATLAB library for dense and sparse numeric tensor arithmetic