2017-02-02 07:48:56 +00:00
<!DOCTYPE html>
< html lang = "en" >
< head >
< meta charset = "UTF-8" / >
< meta name = "viewport" content = "width=device-width, initial-scale=1.0" / >
< title >
Model Templates · 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 >
< a class = "toctext" href = "../index.html" >
Home
< / a >
< / li >
< li >
< span class = "toctext" >
Building Models
< / span >
< ul >
< li >
< a class = "toctext" href = "basics.html" >
Model Building Basics
< / a >
< / li >
< li class = "current" >
< a class = "toctext" href = "templates.html" >
Model Templates
< / a >
< ul class = "internal" >
< li >
< a class = "toctext" href = "#Models-in-templates-1" >
Models in templates
< / a >
< / li >
< li >
< a class = "toctext" href = "#Supported-syntax-1" >
Supported syntax
< / a >
< / li >
< / ul >
< / li >
< li >
< a class = "toctext" href = "recurrent.html" >
Recurrence
< / a >
< / li >
< li >
< a class = "toctext" href = "debugging.html" >
Debugging
< / a >
< / li >
< / ul >
< / li >
2017-02-18 15:11:53 +00:00
< li >
2017-02-20 10:53:09 +00:00
< span class = "toctext" >
Other APIs
< / span >
< ul >
< li >
2017-02-20 11:05:06 +00:00
< a class = "toctext" href = "../apis/batching.html" >
2017-02-18 15:11:53 +00:00
Batching
2017-02-20 10:53:09 +00:00
< / a >
< / li >
< li >
2017-02-20 11:05:06 +00:00
< a class = "toctext" href = "../apis/backends.html" >
2017-02-18 15:11:53 +00:00
Backends
2017-02-20 10:53:09 +00:00
< / a >
< / li >
2017-02-28 16:50:27 +00:00
< li >
< a class = "toctext" href = "../apis/storage.html" >
Storing Models
< / a >
< / li >
2017-02-20 10:53:09 +00:00
< / ul >
2017-02-18 15:11:53 +00:00
< / li >
2017-02-02 07:48:56 +00:00
< li >
< span class = "toctext" >
In Action
< / span >
< ul >
< li >
< a class = "toctext" href = "../examples/logreg.html" >
2017-03-09 00:26:06 +00:00
Simple MNIST
2017-02-02 07:48:56 +00:00
< / a >
< / li >
2017-02-28 16:21:45 +00:00
< li >
< a class = "toctext" href = "../examples/char-rnn.html" >
Char RNN
< / a >
< / li >
2017-02-02 07:48:56 +00:00
< / 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 >
Building Models
< / li >
< li >
< a href = "templates.html" >
Model Templates
< / a >
< / li >
< / ul >
2017-06-02 15:26:51 +00:00
< a class = "edit-page" href = "https://github.com/MikeInnes/Flux.jl/tree/5232a3300c80a35ad1839fc6f163cf97459bbec8/docs/src/models/templates.md" >
2017-02-02 07:48:56 +00:00
< span class = "fa" >
< / span >
Edit on GitHub
< / a >
< / nav >
< hr / >
< / header >
< h1 >
< a class = "nav-anchor" id = "Model-Templates-1" href = "#Model-Templates-1" >
Model Templates
< / a >
< / h1 >
< p >
2017-05-04 16:19:01 +00:00
We mentioned that we could factor out the repetition of defining affine layers with something like:
2017-02-02 07:48:56 +00:00
< / p >
2017-05-04 16:19:01 +00:00
< pre > < code class = "language-julia" > function create_affine(in, out)
W = param(randn(out,in))
b = param(randn(out))
@net x -> W * x + b
end< / code > < / pre >
2017-02-02 07:48:56 +00:00
< p >
2017-05-04 16:19:01 +00:00
< code > @net type< / code >
syntax provides a shortcut for this:
2017-02-02 07:48:56 +00:00
< / p >
2017-05-04 16:19:01 +00:00
< pre > < code class = "language-julia" > @net type MyAffine
2017-02-02 07:48:56 +00:00
W
b
2017-05-04 16:19:01 +00:00
x -> x * W + b
2017-02-02 07:48:56 +00:00
end
# Convenience constructor
MyAffine(in::Integer, out::Integer) =
MyAffine(randn(out, in), randn(out))
model = Chain(MyAffine(5, 5), MyAffine(5, 5))
model(x1) # [-1.54458,0.492025,0.88687,1.93834,-4.70062]< / code > < / pre >
< p >
2017-05-04 16:19:01 +00:00
This is almost exactly how
< code > Affine< / code >
is defined in Flux itself. Using
< code > @net type< / code >
gives us some extra conveniences:
2017-02-02 07:48:56 +00:00
< / p >
2017-05-04 16:19:01 +00:00
< ul >
< li >
< p >
It creates default constructor
< code > MyAffine(::AbstractArray, ::AbstractArray)< / code >
which initialises
< code > param< / code >
s for us;
< / p >
< / li >
< li >
< p >
It subtypes
< code > Flux.Model< / code >
to explicitly mark this as a model;
< / p >
< / li >
< li >
< p >
We can easily define custom constructors or instantiate
2017-02-02 07:48:56 +00:00
< code > Affine< / code >
2017-05-04 16:19:01 +00:00
with arbitrary weights of our choosing;
< / p >
< / li >
< li >
< p >
We can dispatch on the
2017-02-02 07:48:56 +00:00
< code > Affine< / code >
2017-05-04 16:19:01 +00:00
type, for example to override how it gets converted to MXNet, or to hook into shape inference.
< / p >
< / li >
< / ul >
2017-02-02 07:48:56 +00:00
< h2 >
< a class = "nav-anchor" id = "Models-in-templates-1" href = "#Models-in-templates-1" >
Models in templates
< / a >
< / h2 >
< p >
< code > @net< / code >
models can contain sub-models as well as just array parameters:
< / p >
< pre > < code class = "language-julia" > @net type TLP
first
second
function (x)
l1 = σ
l2 = softmax(second(l1))
end
end< / code > < / pre >
< p >
Clearly, the
< code > first< / code >
and
< code > second< / code >
parameters are not arrays here, but should be models themselves, and produce a result when called with an input array
< code > x< / code >
. The
< code > Affine< / code >
2017-02-18 15:11:53 +00:00
layer fits the bill, so we can instantiate
2017-02-02 07:48:56 +00:00
< code > TLP< / code >
with two of them:
< / p >
< pre > < code class = "language-julia" > model = TLP(Affine(10, 20),
Affine(20, 15))
x1 = rand(20)
model(x1) # [0.057852,0.0409741,0.0609625,0.0575354 ...< / code > < / pre >
< p >
You may recognise this as being equivalent to
< / p >
< pre > < code class = "language-julia" > Chain(
Affine(10, 20), σ
Affine(20, 15), softmax)< / code > < / pre >
< h2 >
< a class = "nav-anchor" id = "Supported-syntax-1" href = "#Supported-syntax-1" >
Supported syntax
< / a >
< / h2 >
< p >
The syntax used to define a forward pass like
2017-02-18 15:11:53 +00:00
< code > x -> x*W + b< / code >
2017-02-02 07:48:56 +00:00
behaves exactly like Julia code for the most part. However, it' s important to remember that it' s defining a dataflow graph, not a general Julia expression. In practice this means that anything side-effectful, or things like control flow and
< code > println< / code >
2017-02-18 15:11:53 +00:00
s, won' t work as expected. In future we' ll continue to expand support for Julia syntax and features.
2017-02-02 07:48:56 +00:00
< / p >
< footer >
< hr / >
< a class = "previous" href = "basics.html" >
< span class = "direction" >
Previous
< / span >
< span class = "title" >
Model Building Basics
< / span >
< / a >
< a class = "next" href = "recurrent.html" >
< span class = "direction" >
Next
< / span >
< span class = "title" >
Recurrence
< / span >
< / a >
< / footer >
< / article >
< / body >
< / html >
