Dependency Packages
-
Flux.jl4122Relax! Flux is the ML library that doesn't make you tensor
-
AlphaZero.jl1131A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.
-
DiffEqFlux.jl771Universal neural differential equations with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
-
NeuralPDE.jl755Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
-
NeuralNetDiffEq.jl755Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
-
FastAI.jl557Repository of best practices for deep learning in Julia, inspired by fastai
-
Transformers.jl420Julia Implementation of Transformer models
-
GeometricFlux.jl330Geometric Deep Learning for Flux
-
Metalhead.jl297Computer vision models for Flux
-
Omega.jl155Causal, Higher-Order, Probabilistic Programming
-
GraphNeuralNetworks.jl153Graph Neural Networks in Julia
-
NeuralOperators.jl151DeepONets, (Fourier) Neural Operators, Physics-Informed Neural Operators, and more in Julia
-
TopOpt.jl141A beautifully Julian topology optimization package.
-
SeaPearl.jl141Julia hybrid constraint programming solver enhanced by a reinforcement learning driven search.
-
RayTracer.jl141Differentiable RayTracing in Julia
-
MLJFlux.jl115Wrapping deep learning models from the package Flux.jl for use in the MLJ.jl toolbox
-
FluxArchitectures.jl113Complex neural network examples for Flux.jl
-
InvertibleNetworks.jl101A Julia framework for invertible neural networks
-
Kinetic.jl96Universal modeling and simulation of fluid mechanics upon machine learning. From the Boltzmann equation, heading towards multiscale and multiphysics flows.
-
FluxTraining.jl95A flexible neural net training library inspired by fast.ai
-
Flux3D.jl913D computer vision library in Julia
-
ObjectDetector.jl82Pure Julia implementations of single-pass object detection neural networks.
-
ExplainableAI.jl77XAI in Julia using Flux.
-
CounterfactualExplanations.jl75A package for Counterfactual Explanations and Algorithmic Recourse in Julia.
-
Mill.jl74Multiple Instance Learning Library is build on top of Flux.jl aimed to prototype flexible multi-instance learning models.
-
DeepQLearning.jl65Implementation of the Deep Q-learning algorithm to solve MDPs
-
HighDimPDE.jl60A Julia package that breaks down the curse of dimensionality in solving PDEs.
-
AtomicGraphNets.jl58Atomic graph models for molecules and crystals in Julia
-
FluxOptTools.jl54Use Optim to train Flux models and visualize loss landscapes
-
EasyML.jl52A foolproof way of doing ML with GUI elements.
-
FluxMPI.jl48Distributed Data Parallel Training of Deep Neural Networks
-
FluxJS.jl43I heard you like compile times
-
ChainPlots.jl42Visualization for Flux.Chain neural networks
-
UNet.jl40Generic UNet implementation written in pure Julia, based on Flux.jl
-
ChemistryFeaturization.jl39Interface package for featurizing atomic structures
-
NaiveGAflux.jl38Evolve Flux networks from scratch!
-
OperatorLearning.jl37No need to train, he's a smooth operator
-
JsonGrinder.jl37Towards more automatic processing of structured data
-
Sophon.jl36Neural networks and neural operators for physics-informed machine learning
-
FMIFlux.jl33FMIFlux.jl is a free-to-use software library for the Julia programming language, which offers the ability to set up NeuralFMUs just like NeuralODEs: You can place FMUs (fmi-standard.org) simply inside any feed-forward ANN topology and keep the resulting hybrid model trainable with a standard (or custom) FluxML training process.
Loading more...