2017-05-02 13:01:23 +00:00
<!DOCTYPE html>
< html lang = "en" >
< head >
< meta charset = "UTF-8" / >
< meta name = "viewport" content = "width=device-width, initial-scale=1.0" / >
< title >
Home · Flux
< / title >
< script >
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-36890222-9', 'auto');
ga('send', 'pageview');
< / script >
< link href = "https://cdnjs.cloudflare.com/ajax/libs/normalize/4.2.0/normalize.min.css" rel = "stylesheet" type = "text/css" / >
< link href = "https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.5.0/styles/default.min.css" rel = "stylesheet" type = "text/css" / >
< link href = "https://fonts.googleapis.com/css?family=Lato|Ubuntu+Mono" rel = "stylesheet" type = "text/css" / >
< link href = "https://cdnjs.cloudflare.com/ajax/libs/font-awesome/4.6.3/css/font-awesome.min.css" rel = "stylesheet" type = "text/css" / >
< link href = "assets/documenter.css" rel = "stylesheet" type = "text/css" / >
< script >
documenterBaseURL="."
< / script >
< script src = "https://cdnjs.cloudflare.com/ajax/libs/require.js/2.2.0/require.min.js" data-main = "assets/documenter.js" > < / script >
< script src = "../versions.js" > < / script >
< link href = "../flux.css" rel = "stylesheet" type = "text/css" / >
< / head >
< body >
< nav class = "toc" >
< h1 >
Flux
< / h1 >
< form class = "search" action = "search.html" >
< select id = "version-selector" onChange = "window.location.href=this.value" >
< option value = "#" selected = "selected" disabled = "disabled" >
Version
< / option >
< / select >
< input id = "search-query" name = "q" type = "text" placeholder = "Search docs" / >
< / form >
< ul >
< li class = "current" >
< a class = "toctext" href = "index.html" >
Home
< / a >
< ul class = "internal" >
< li >
< a class = "toctext" href = "#Where-do-I-start?-1" >
Where do I start?
< / a >
< / li >
< li >
< a class = "toctext" href = "#Installation-1" >
Installation
< / a >
< / li >
< / ul >
< / li >
< li >
< span class = "toctext" >
Building Models
< / span >
< ul >
< li >
< a class = "toctext" href = "models/basics.html" >
Model Building Basics
< / a >
< / li >
< li >
< a class = "toctext" href = "models/templates.html" >
Model Templates
< / a >
< / li >
< li >
< a class = "toctext" href = "models/recurrent.html" >
Recurrence
< / a >
< / li >
< li >
< a class = "toctext" href = "models/debugging.html" >
Debugging
< / a >
< / li >
< / ul >
< / li >
< li >
< span class = "toctext" >
Other APIs
< / span >
< ul >
< li >
< a class = "toctext" href = "apis/batching.html" >
Batching
< / a >
< / li >
< li >
< a class = "toctext" href = "apis/backends.html" >
Backends
< / a >
< / li >
< li >
< a class = "toctext" href = "apis/storage.html" >
Storing Models
< / a >
< / li >
< / ul >
< / li >
< li >
< span class = "toctext" >
In Action
< / span >
< ul >
< li >
< a class = "toctext" href = "examples/logreg.html" >
Simple MNIST
< / a >
< / li >
< li >
< a class = "toctext" href = "examples/char-rnn.html" >
Char RNN
< / a >
< / li >
< / ul >
< / li >
< li >
< a class = "toctext" href = "contributing.html" >
Contributing & Help
< / a >
< / li >
< li >
< a class = "toctext" href = "internals.html" >
Internals
< / a >
< / li >
< / ul >
< / nav >
< article id = "docs" >
< header >
< nav >
< ul >
< li >
< a href = "index.html" >
Home
< / a >
< / li >
< / ul >
2017-05-04 16:25:27 +00:00
< a class = "edit-page" href = "https://github.com/MikeInnes/Flux.jl/tree/7a85eff370b7c68d587b49699fa3f71e44993397/docs/src/index.md" >
2017-05-02 13:01:23 +00:00
< span class = "fa" >
< / span >
Edit on GitHub
< / a >
< / nav >
< hr / >
< / header >
< h1 >
< a class = "nav-anchor" id = "Flux-1" href = "#Flux-1" >
Flux
< / a >
< / h1 >
< p >
2017-05-04 16:25:27 +00:00
< em >
... Initialising Photon Beams ...
< / em >
< / p >
< p >
Flux is a library for machine learning, implemented in Julia. In a nutshell, it simply lets you run normal Julia code on a backend like TensorFlow. It also provides many conveniences for doing deep learning.
2017-05-02 13:01:23 +00:00
< / p >
< p >
2017-05-04 16:25:27 +00:00
Flux is very flexible. You can use a convenient Keras-like API if you want something simple, but you can also drop down to straight mathematics, or build your own abstractions. You can even use Flux' s utilities (like optimisers) with a completely different backend (like
< a href = "https://github.com/denizyuret/Knet.jl" >
Knet
< / a >
) or mix and match approaches.
2017-05-02 13:01:23 +00:00
< / p >
< p >
2017-05-04 16:25:27 +00:00
Note that Flux is in alpha. Many things work but the API is still in a state of... well, it might change.
2017-05-02 13:01:23 +00:00
< / p >
< p >
< strong >
Note:
< / strong >
If you' re using Julia v0.5 please see
< a href = "http://mikeinnes.github.io/Flux.jl/v0.1.1/" >
this version
< / a >
of the docs instead.
< / p >
< h2 >
< a class = "nav-anchor" id = "Where-do-I-start?-1" href = "#Where-do-I-start?-1" >
Where do I start?
< / a >
< / h2 >
< p >
2017-05-04 16:25:27 +00:00
< em >
... Charging Ion Capacitors ...
< / em >
< / p >
< p >
2017-05-02 13:01:23 +00:00
The
< a href = "examples/logreg.html" >
examples
< / a >
2017-05-04 16:25:27 +00:00
give a feel for high-level usage.
2017-05-02 13:01:23 +00:00
< / p >
< p >
2017-05-04 16:25:27 +00:00
If you want to know why Flux is unique, or just don' t want to see
2017-05-02 13:01:23 +00:00
< em >
those digits
< / em >
again, check out the
< a href = "models/basics.html" >
model building guide
< / a >
2017-05-04 16:25:27 +00:00
instead.
2017-05-02 13:01:23 +00:00
< / p >
< p >
2017-05-04 16:25:27 +00:00
Flux is meant to be played with. These docs have lots of code snippets; try them out in
< a href = "http://junolab.org" >
Juno
2017-05-02 13:01:23 +00:00
< / a >
2017-05-04 16:25:27 +00:00
!
2017-05-02 13:01:23 +00:00
< / p >
< h2 >
< a class = "nav-anchor" id = "Installation-1" href = "#Installation-1" >
Installation
< / a >
< / h2 >
< p >
< em >
2017-05-04 16:25:27 +00:00
... Inflating Graviton Zeppelins ...
2017-05-02 13:01:23 +00:00
< / em >
< / p >
< pre > < code class = "language-julia" > Pkg.update()
Pkg.add(" Flux.jl" )< / code > < / pre >
< p >
You' ll also need a backend to run real training, if you don' t have one already. Choose from
< a href = "https://github.com/dmlc/MXNet.jl" >
MXNet
< / a >
or
< a href = "https://github.com/malmaud/TensorFlow.jl" >
TensorFlow
< / a >
(MXNet is the recommended option if you' re not sure):
< / p >
< pre > < code class = "language-julia" > Pkg.add(" MXNet" ) # or " TensorFlow"
Pkg.test(" Flux" ) # Make sure everything installed properly< / code > < / pre >
< p >
< strong >
Note:
< / strong >
TensorFlow integration may not work properly on Julia v0.6 yet.
< / p >
< footer >
< hr / >
< a class = "next" href = "models/basics.html" >
< span class = "direction" >
Next
< / span >
< span class = "title" >
Model Building Basics
< / span >
< / a >
< / footer >
< / article >
< / body >
< / html >
