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

AntonOresten/Flux.jl

 
 

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 1.10 or later. Here's a very short example to try it out:

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

model = let
  w, b, v = (randn(Float32, 23) for _ in 1:3)  # parameters
  x -> sum(v .* tanh.(w*x .+ b))               # callable
end
# model = Chain(vcat, Dense(1 => 23, tanh), Dense(23 => 1, bias=false), only)

opt_state = Flux.setup(Adam(), model)
for epoch in 1:100
  Flux.train!((m,x,y) -> (m(x) - y)^2, model, data, opt_state)
end

using Plots
plot(x -> 2x-x^3, -2, 2, label="truth")
scatter!(model, -2:0.1f0:2, label="learned")

In Flux 0.15, almost any parameterised function in Julia is a valid Flux model -- such as this closure over w, b, v. The same function can also be implemented with built-in layers as shown.

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

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Julia 100.0%