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

21st century AD

Repository of best practices for deep learning in Julia, inspired by fastai

Geometric Deep Learning for Flux

Computer vision models for Flux

MacroTools provides a library of tools for working with Julia code and expressions.

Sensible extensions for exposing torch in Julia.

Neural Network primitives with multiple backends

Wrapping deep learning models from the package Flux.jl for use in the MLJ.jl toolbox

Read ONNX graphs in Julia

A flexible neural net training library inspired by fast.ai

Parameterise all the things

Mike's Little Intermediate Representation

3D computer vision library in Julia

A little less conversation, a little more abstraction

Optimisers.jl defines many standard optimisers and utilities for learning loops.

Distributed computation of differentiation pipelines to use multiple workers, devices, GPU, etc. since Julia wasn't fast enough already

Flux's ex AD

"Maybe we have our own magic."

I heard you like compile times

Flexible data augmentation library for machine and deep learning

-

Common hyperparameter scheduling for ML

Throw stuff

Memory efficient one-hot array encodings

Differentiable Computer Vision using pure Julia

-

CUDA integration for the NNlib API

Experimental features for Flux.jl

-

A benchmarking suite for the FluxML org