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

In-memory tabular data in Julia

21st century AD

CUDA programming in Julia.

Forward Mode Automatic Differentiation for Julia

Statically sized arrays for Julia

Julia implementation of Data structures

Formatted output of timed sections in Julia

HTTP for Julia

⅀

Physical quantities with arbitrary units

Basic statistics for Julia

HDF5-compatible file format in pure Julia

Utility library for working with CSV and other delimited files in the Julia programming language

An optimized graphs package for the Julia programming language

Forward and reverse mode automatic differentiation primitives for Julia Base + StdLibs

A Julia package for evaluating distances (metrics) between vectors.

High performance nearest neighbor data structures (KDTree and BallTree) and algorithms for Julia.

Print data in formatted tables.

Julia functional programming infrastructures and metaprogramming facilities

Save and load data in the HDF5 file format from Julia

MPI wrappers for Julia

Heterogeneous programming in Julia

Special mathematical functions in Julia

Geometric Deep Learning for Flux

Efficient implementation of struct arrays in Julia

Reusable array functionality for Julia's various GPU backends.

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

An interface for tables in Julia

Julia module for reading MATLAB files

Julia bindings to the FFTW library for fast Fourier transforms

AD-backend agnostic system defining custom forward and reverse mode rules. This is the light weight core to allow you to define rules for your functions in your packages, without depending on any particular AD system.

Utility package for accessing common Machine Learning datasets in Julia

Main Package for IO, loading all different kind of files

-

Convenient input and display of LaTeX equation strings for the Julia language

Color manipulation utilities for Julia

Reduce time-to-first-execution of Julia code

Neural Network primitives with multiple backends

Fortran-like arrays with arbitrary, zero or negative starting indices.