Skip to content

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

License

Notifications You must be signed in to change notification settings

skyleaworlder/Flux.jl

This branch is 7 commits ahead of, 357 commits behind FluxML/Flux.jl:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

b8415dd · Feb 13, 2023
Feb 28, 2022
Jan 28, 2021
Feb 2, 2023
Feb 8, 2023
Apr 25, 2019
Mar 25, 2022
Feb 13, 2023
Feb 11, 2023
Sep 8, 2019
Oct 10, 2021
Mar 7, 2021
Jul 10, 2020
Jan 22, 2022
Apr 15, 2019
Feb 4, 2023
Feb 5, 2023
Dec 15, 2022

Repository files navigation

DOI Flux Downloads
ColPrac: Contributor's Guide on Collaborative Practices for Community Packages

Flux is an elegant approach to machine learning. It's a 100% pure-Julia stack, and provides lightweight abstractions on top of Julia's native GPU and AD support. Flux makes the easy things easy while remaining fully hackable.

Works best with Julia 1.8 or later. Here's a very short example to try it out:

using Flux, Plots
data = [([x], 2x-x^3) for x in -2:0.1f0:2]

model = Chain(Dense(1 => 23, tanh), Dense(23 => 1, bias=false), only)

optim = Flux.setup(Adam(), model)
for epoch in 1:1000
  Flux.train!((m,x,y) -> (m(x) - y)^2, model, data, optim)
end

plot(x -> 2x-x^3, -2, 2, legend=false)
scatter!(-2:0.1:2, [model([x]) for x in -2:0.1:2])

The quickstart page has a longer example. See the documentation for details, or the model zoo for examples. Ask questions on the Julia discourse or slack.

If you use Flux in your research, please cite our work.

About

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

Resources

License

Citation

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Julia 100.0%