30 Packages since 2015
User Packages
-
Flux.jl4122Relax! Flux is the ML library that doesn't make you tensor
-
Zygote.jl135321st century AD
-
FastAI.jl557Repository of best practices for deep learning in Julia, inspired by fastai
-
GeometricFlux.jl330Geometric Deep Learning for Flux
-
Metalhead.jl297Computer vision models for Flux
-
MacroTools.jl281MacroTools provides a library of tools for working with Julia code and expressions.
-
Torch.jl183Sensible extensions for exposing torch in Julia.
-
NNlib.jl165Neural Network primitives with multiple backends
-
ONNX.jl122Read ONNX graphs in Julia
-
MLJFlux.jl115Wrapping deep learning models from the package Flux.jl for use in the MLJ.jl toolbox
-
IRTools.jl101Mike's Little Intermediate Representation
-
Functors.jl96Parameterise all the things
-
FluxTraining.jl95A flexible neural net training library inspired by fast.ai
-
Flux3D.jl913D computer vision library in Julia
-
Mjolnir.jl86A little less conversation, a little more abstraction
-
DaggerFlux.jl58Distributed computation of differentiation pipelines to use multiple workers, devices, GPU, etc. since Julia wasn't fast enough already
-
Optimisers.jl56Optimisers.jl defines many standard optimisers and utilities for learning loops.
-
XLATools.jl48"Maybe we have our own magic."
-
FluxJS.jl43I heard you like compile times
-
DataAugmentation.jl37Flexible data augmentation library for machine and deep learning
-
Tracker.jl36Flux's ex AD
-
HuggingFaceApi.jl27-
-
ParameterSchedulers.jl26Common hyperparameter scheduling for ML
-
Trebuchet.jl21Throw stuff
-
ZygoteRules.jl15-
-
DiffImages.jl14Differentiable Computer Vision using pure Julia
-
NNlibCUDA.jl13CUDA integration for the NNlib API
-
FluxBench.jl13Benchmarks for the FluxML ecosystem for deep learning, scientific machine learning, differentiable programming etc including AD and CUDA accelerated workloads
-
OneHotArrays.jl10Memory efficient one-hot array encodings
-
Fluxperimental.jl10Experimental features for Flux.jl
View all packages