build based on 6d8e6c0
This commit is contained in:
parent
8681c63a9e
commit
cda8897d94
@ -6,7 +6,23 @@ m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
|
||||
|
||||
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://fonts.googleapis.com/css?family=Lato|Roboto+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="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/default.min.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="../siteinfo.js"></script><script src="../../versions.js"></script><link href="../assets/documenter.css" rel="stylesheet" type="text/css"/><link href="../../flux.css" rel="stylesheet" type="text/css"/></head><body><nav class="toc"><h1>Flux</h1><select id="version-selector" onChange="window.location.href=this.value" style="visibility: hidden"></select><form class="search" id="search-form" action="../search.html"><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="../models/basics.html">Basics</a></li><li><a class="toctext" href="../models/recurrence.html">Recurrence</a></li><li><a class="toctext" href="../models/regularisation.html">Regularisation</a></li><li><a class="toctext" href="../models/layers.html">Model Reference</a></li></ul></li><li><span class="toctext">Training Models</span><ul><li><a class="toctext" href="../training/optimisers.html">Optimisers</a></li><li><a class="toctext" href="../training/training.html">Training</a></li></ul></li><li><a class="toctext" href="../data/onehot.html">One-Hot Encoding</a></li><li><a class="toctext" href="../gpu.html">GPU Support</a></li><li><a class="toctext" href="../saving.html">Saving & Loading</a></li><li><span class="toctext">Internals</span><ul><li class="current"><a class="toctext" href="tracker.html">Backpropagation</a><ul class="internal"><li><a class="toctext" href="#Internals-1">Internals</a></li><li><a class="toctext" href="#Custom-Gradients-1">Custom Gradients</a></li><li><a class="toctext" href="#Notes-1">Notes</a></li></ul></li></ul></li><li><a class="toctext" href="../community.html">Community</a></li></ul></nav><article id="docs"><header><nav><ul><li>Internals</li><li><a href="tracker.html">Backpropagation</a></li></ul><a class="edit-page" href="https://github.com/FluxML/Flux.jl/blob/master/docs/src/internals/tracker.md"><span class="fa"></span> Edit on GitHub</a></nav><hr/><div id="topbar"><span>Backpropagation</span><a class="fa fa-bars" href="#"></a></div></header><h1><a class="nav-anchor" id="Flux.Tracker-1" href="#Flux.Tracker-1">Flux.Tracker</a></h1><p>Backpropagation, or reverse-mode automatic differentiation, is handled by the <code>Flux.Tracker</code> module.</p><pre><code class="language-julia">julia> using Flux.Tracker</code></pre><p>The <code>param</code> function converts a normal Julia array into a new object that, while behaving like an array, tracks extra information that allows us to calculate derivatives. For example, say we multiply two parameters:</p><pre><code class="language-julia">julia> W = param([1 2; 3 4])
|
||||
</script><link href="https://cdnjs.cloudflare.com/ajax/libs/normalize/4.2.0/normalize.min.css" rel="stylesheet" type="text/css"/><link href="https://fonts.googleapis.com/css?family=Lato|Roboto+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="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/default.min.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="../siteinfo.js"></script><script src="../../versions.js"></script><link href="../assets/documenter.css" rel="stylesheet" type="text/css"/><link href="../../flux.css" rel="stylesheet" type="text/css"/></head><body><nav class="toc"><h1>Flux</h1><select id="version-selector" onChange="window.location.href=this.value" style="visibility: hidden"></select><form class="search" id="search-form" action="../search.html"><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="../models/basics.html">Basics</a></li><li><a class="toctext" href="../models/recurrence.html">Recurrence</a></li><li><a class="toctext" href="../models/regularisation.html">Regularisation</a></li><li><a class="toctext" href="../models/layers.html">Model Reference</a></li></ul></li><li><span class="toctext">Training Models</span><ul><li><a class="toctext" href="../training/optimisers.html">Optimisers</a></li><li><a class="toctext" href="../training/training.html">Training</a></li></ul></li><li><a class="toctext" href="../data/onehot.html">One-Hot Encoding</a></li><li><a class="toctext" href="../gpu.html">GPU Support</a></li><li><a class="toctext" href="../saving.html">Saving & Loading</a></li><li><span class="toctext">Internals</span><ul><li class="current"><a class="toctext" href="tracker.html">Backpropagation</a><ul class="internal"><li><a class="toctext" href="#Taking-Gradients-1">Taking Gradients</a></li><li><a class="toctext" href="#Tracked-Arrays-1">Tracked Arrays</a></li><li><a class="toctext" href="#Custom-Gradients-1">Custom Gradients</a></li><li><a class="toctext" href="#Tracked-Internals-1">Tracked Internals</a></li></ul></li></ul></li><li><a class="toctext" href="../community.html">Community</a></li></ul></nav><article id="docs"><header><nav><ul><li>Internals</li><li><a href="tracker.html">Backpropagation</a></li></ul><a class="edit-page" href="https://github.com/FluxML/Flux.jl/blob/master/docs/src/internals/tracker.md"><span class="fa"></span> Edit on GitHub</a></nav><hr/><div id="topbar"><span>Backpropagation</span><a class="fa fa-bars" href="#"></a></div></header><h1><a class="nav-anchor" id="Flux.Tracker-1" href="#Flux.Tracker-1">Flux.Tracker</a></h1><p>Backpropagation, or reverse-mode automatic differentiation, is handled by the <code>Flux.Tracker</code> module.</p><pre><code class="language-julia">julia> using Flux.Tracker</code></pre><p>Here we discuss some more advanced uses of this module, as well as covering its internals.</p><h2><a class="nav-anchor" id="Taking-Gradients-1" href="#Taking-Gradients-1">Taking Gradients</a></h2><p>In the <a href="../models/basics.html">basics section</a> we covered basic usage of the <code>gradient</code> function.</p><pre><code class="language-julia">using Flux.Tracker
|
||||
|
||||
Tracker.gradient((a, b) -> a*b, 2, 3) # (3.0 (tracked), 2.0 (tracked))</code></pre><p><code>gradient</code> is actually just a thin wrapper around the backpropagator-based interface, <code>forward</code>.</p><pre><code class="language-julia">using Flux.Tracker: forward
|
||||
|
||||
y, back = forward((a, b) -> a*b, 2, 3) # (6.0 (tracked), Flux.Tracker.#9)
|
||||
|
||||
back(1) # (3.0 (tracked), 2.0 (tracked))</code></pre><p>The <code>forward</code> function returns two results. The first, <code>y</code>, is the original value of the function (perhaps with tracking applied). The second, <code>back</code>, is a new function which, given a sensitivity, returns the sensitivity of the inputs to <code>forward</code> (we call this a "backpropagator"). One use of this interface is to provide custom sensitivities when outputs are not scalar.</p><pre><code class="language-julia">julia> y, back = forward((a, b) -> a.*b, [1,2,3],[4,5,6])
|
||||
(param([4.0, 10.0, 18.0]), Flux.Tracker.#9)
|
||||
|
||||
julia> back([1,1,1])
|
||||
(param([4.0, 5.0, 6.0]), param([1.0, 2.0, 3.0]))</code></pre><p>We can also take gradients in-place. This can be useful if you only care about first-order gradients.</p><pre><code class="language-julia">a, b = param(2), param(3)
|
||||
|
||||
c = a*b # 6.0 (tracked)
|
||||
|
||||
Tracker.back!(c)
|
||||
|
||||
Tracker.grad(a), Tracker.grad(b) # (3.0, 2.0)</code></pre><h2><a class="nav-anchor" id="Tracked-Arrays-1" href="#Tracked-Arrays-1">Tracked Arrays</a></h2><p>The <code>param</code> function converts a normal Julia array into a new object that, while behaving like an array, tracks extra information that allows us to calculate derivatives. For example, say we multiply two parameters:</p><pre><code class="language-julia">julia> W = param([1 2; 3 4])
|
||||
Tracked 2×2 Array{Float64,2}:
|
||||
1.0 2.0
|
||||
3.0 4.0
|
||||
@ -29,40 +45,15 @@ julia> W.grad
|
||||
julia> x.grad
|
||||
2-element Array{Float64,1}:
|
||||
-2.0
|
||||
-2.0</code></pre><h2><a class="nav-anchor" id="Internals-1" href="#Internals-1">Internals</a></h2><p>All <code>Tracked*</code> objects (<code>TrackedArray</code>, <code>TrackedReal</code>) are light wrappers around the <code>Tracked</code> type, which you can access via the <code>.tracker</code> field.</p><pre><code class="language-julia">julia> x.tracker
|
||||
Flux.Tracker.Tracked{Array{Float64,1}}(0x00000000, Flux.Tracker.Call{Void,Tuple{}}(nothing, ()), true, [5.0, 6.0], [-2.0, -2.0])</code></pre><p>The <code>Tracker</code> stores the value and gradient of a given object, which we've seen before.</p><pre><code class="language-julia">julia> x.tracker.data
|
||||
2-element Array{Float64,1}:
|
||||
5.0
|
||||
6.0
|
||||
-2.0</code></pre><p>You may sometimes want to drop derivative information and just get the plain value back. You can do this by calling <code>Tracker.data(W)</code>.</p><h2><a class="nav-anchor" id="Custom-Gradients-1" href="#Custom-Gradients-1">Custom Gradients</a></h2><p>We can hook in to the processes above to implement custom gradients for a function or kernel. For a toy example, imagine a custom implementation of <code>minus</code>:</p><pre><code class="language-julia">minus(a, b) = a - b</code></pre><p>Firstly, we must tell the tracker system to stop when it sees a call to <code>minus</code>, and record it. We can do this using dispatch:</p><pre><code class="language-julia">using Flux.Tracker: TrackedReal, track, @grad
|
||||
|
||||
julia> x.tracker.grad
|
||||
minus(a::TrackedArray, b::TrackedArray) = Tracker.track(minus, a, b)</code></pre><p><code>track</code> takes care of building a new <code>Tracked</code> object and recording the operation on the tape. We just need to provide a gradient definition.</p><pre><code class="language-julia">@grad function minus(a, b)
|
||||
return minus(data(a),data(b)), Δ -> (Δ, -Δ)
|
||||
end</code></pre><p>This is essentially just a way of overloading the <code>forward</code> function we saw above. We strip tracking from <code>a</code> and <code>b</code> so that we are calling the original definition of <code>minus</code> (otherwise, we'd just try to track the call again and hit an infinite regress).</p><p>Note that in the backpropagator we don't call <code>data(a)</code>; we <em>do</em> in fact want to track this, since nest AD will take a derivative through the backpropagator itself. For example, the gradient of <code>*</code> might look like this.</p><pre><code class="language-julia">@grad a * b = data(a)*data(b), Δ -> (Δ*b, a*Δ)</code></pre><p>For multi-argument functions with custom gradients, you likely want to catch not just <code>minus(::TrackedArray, ::TrackedArray)</code> but also <code>minus(::Array, TrackedArray)</code> and so on. To do so, just define those extra signatures as needed:</p><pre><code class="language-julia">minus(a::AbstractArray, b::TrackedArray) = Tracker.track(minus, a, b)
|
||||
minus(a::TrackedArray, b::AbstractArray) = Tracker.track(minus, a, b)</code></pre><h2><a class="nav-anchor" id="Tracked-Internals-1" href="#Tracked-Internals-1">Tracked Internals</a></h2><p>All <code>Tracked*</code> objects (<code>TrackedArray</code>, <code>TrackedReal</code>) are light wrappers around the <code>Tracked</code> type, which you can access via the <code>.tracker</code> field.</p><pre><code class="language-julia">julia> x.tracker
|
||||
Flux.Tracker.Tracked{Array{Float64,1}}(0x00000000, Flux.Tracker.Call{Void,Tuple{}}(nothing, ()), true, [5.0, 6.0], [-2.0, -2.0])</code></pre><p>The <code>Tracker</code> stores the gradient of a given object, which we've seen before.</p><pre><code class="language-julia">julia> x.tracker.grad
|
||||
2-element Array{Float64,1}:
|
||||
-2.0
|
||||
-2.0</code></pre><p>The tracker also contains a <code>Call</code> object, which simply represents a function call that was made at some point during the forward pass. For example, the <code>+</code> call would look like this:</p><pre><code class="language-julia">julia> Tracker.Call(+, 1, 2)
|
||||
Flux.Tracker.Call{Base.#+,Tuple{Int64,Int64}}(+, (1, 2))</code></pre><p>In the case of the <code>y</code> we produced above, we can see that it stores the call that produced it – that is, <code>W*x</code>.</p><pre><code class="language-julia">julia> y.tracker.f
|
||||
Flux.Tracker.Call{...}(*, (param([1.0 2.0; 3.0 4.0]), param([5.0, 6.0])))</code></pre><p>Notice that because the arguments to the call may also be tracked arrays, storing their own calls, this means that <code>Tracker</code> ends up forming a data structure that records everything that happened during the forward pass (often known as a <em>tape</em>).</p><p>When we call <code>back!(y, [1, -1])</code>, the sensitivities <code>[1, -1]</code> simply get forwarded to <code>y</code>'s call (<code>*</code>), effectively calling</p><pre><code class="language-julia">Tracker.back(*, [1, -1], W, x)</code></pre><p>which in turn calculates the sensitivities of the arguments (<code>W</code> and <code>x</code>) and backpropagates through their calls. This is recursive, so it will walk the entire program graph and propagate gradients to the original model parameters.</p><h2><a class="nav-anchor" id="Custom-Gradients-1" href="#Custom-Gradients-1">Custom Gradients</a></h2><p>We can hook in to the processes above to implement custom gradients for a function or kernel. For a toy example, imagine a custom implementation of <code>minus</code>:</p><pre><code class="language-julia">julia> minus(a, b) = a - b</code></pre><p>Firstly, we must tell the tracker system to stop when it sees a call to <code>minus</code>, and record it. We can do this using dispatch:</p><pre><code class="language-julia">julia> minus(a::TrackedArray, b::TrackedArray) = Tracker.track(minus, a, b)
|
||||
minus (generic function with 2 methods)</code></pre><p><code>Tracker.track</code> does two things: (1) it makes sure <code>minus</code> is called with <em>normal</em> array, not tracked ones (you can use <code>@show</code> inside <code>minus</code> to verify this), and (2) it uses the result to add a <code>minus</code> node to the tape. Look inside the result of calling <code>minus</code> to see what happened:</p><pre><code class="language-julia">julia> a, b = param([6,5,4]), param([1,2,3])
|
||||
(param([6.0, 5.0, 4.0]), param([1.0, 2.0, 3.0]))
|
||||
|
||||
julia> c = minus(a, b)
|
||||
Tracked 3-element Array{Float64,1}:
|
||||
5.0
|
||||
3.0
|
||||
1.0
|
||||
|
||||
julia> c.tracker.f
|
||||
Flux.Tracker.Call{...}(minus, (param([6.0, 5.0, 4.0]), param([1.0, 2.0, 3.0])))</code></pre><p>Finally, we have to specify the gradient of <code>minus</code>.</p><pre><code class="language-julia">julia> Tracker.back(::typeof(minus), Δ, a, b) =
|
||||
(Tracker.@back(a, Δ); Tracker.@back(b, -Δ))</code></pre><p><code>@back(x, Δ)</code> tells the tracker to continue propagating the sensitivity <code>Δ</code> through <code>x</code>. Now, AD will work with any program that calls <code>minus</code>.</p><pre><code class="language-julia">julia> Flux.back!(c, 1)
|
||||
|
||||
julia> a.grad
|
||||
3-element Array{Float64,1}:
|
||||
1.0
|
||||
1.0
|
||||
1.0
|
||||
|
||||
julia> b.grad
|
||||
3-element Array{Float64,1}:
|
||||
-1.0
|
||||
-1.0
|
||||
-1.0</code></pre><h2><a class="nav-anchor" id="Notes-1" href="#Notes-1">Notes</a></h2><p>For multi-argument functions with custom gradients, you likely want to catch not just <code>minus(::TrackedArray, ::TrackedArray)</code> but also <code>minus(::Array, TrackedArray)</code> and so on. To do so, just define those extra signatures as needed:</p><pre><code class="language-julia">minus(a::AbstractArray, b::TrackedArray) = Tracker.track(minus, a, b)
|
||||
minus(a::TrackedArray, b::AbstractArray) = Tracker.track(minus, a, b)</code></pre><p><code>@back</code> <em>must</em> be called exactly once on each tracked input argument. You do not need to do any special handling if one of the arguments is not tracked, as <code>@back</code> will just become a no-op.</p><footer><hr/><a class="previous" href="../saving.html"><span class="direction">Previous</span><span class="title">Saving & Loading</span></a><a class="next" href="../community.html"><span class="direction">Next</span><span class="title">Community</span></a></footer></article></body></html>
|
||||
Flux.Tracker.Call{...}(*, (param([1.0 2.0; 3.0 4.0]), param([5.0, 6.0])))</code></pre><p>Notice that because the arguments to the call may also be tracked arrays, storing their own calls, this means that <code>Tracker</code> ends up forming a data structure that records everything that happened during the forward pass (often known as a <em>tape</em>).</p><p>When we call <code>back!(y, [1, -1])</code>, the sensitivities <code>[1, -1]</code> simply get forwarded to <code>y</code>'s call (<code>*</code>), effectively calling</p><pre><code class="language-julia">Tracker.back(*, [1, -1], W, x)</code></pre><p>which in turn calculates the sensitivities of the arguments (<code>W</code> and <code>x</code>) and back-propagates through their calls. This is recursive, so it will walk the entire program graph and propagate gradients to the original model parameters.</p><footer><hr/><a class="previous" href="../saving.html"><span class="direction">Previous</span><span class="title">Saving & Loading</span></a><a class="next" href="../community.html"><span class="direction">Next</span><span class="title">Community</span></a></footer></article></body></html>
|
||||
|
@ -6,28 +6,54 @@ m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
|
||||
|
||||
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://fonts.googleapis.com/css?family=Lato|Roboto+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="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/default.min.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="../siteinfo.js"></script><script src="../../versions.js"></script><link href="../assets/documenter.css" rel="stylesheet" type="text/css"/><link href="../../flux.css" rel="stylesheet" type="text/css"/></head><body><nav class="toc"><h1>Flux</h1><select id="version-selector" onChange="window.location.href=this.value" style="visibility: hidden"></select><form class="search" id="search-form" action="../search.html"><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 class="current"><a class="toctext" href="basics.html">Basics</a><ul class="internal"><li><a class="toctext" href="#Taking-Gradients-1">Taking Gradients</a></li><li><a class="toctext" href="#Building-Layers-1">Building Layers</a></li><li><a class="toctext" href="#Stacking-It-Up-1">Stacking It Up</a></li><li><a class="toctext" href="#Layer-helpers-1">Layer helpers</a></li></ul></li><li><a class="toctext" href="recurrence.html">Recurrence</a></li><li><a class="toctext" href="regularisation.html">Regularisation</a></li><li><a class="toctext" href="layers.html">Model Reference</a></li></ul></li><li><span class="toctext">Training Models</span><ul><li><a class="toctext" href="../training/optimisers.html">Optimisers</a></li><li><a class="toctext" href="../training/training.html">Training</a></li></ul></li><li><a class="toctext" href="../data/onehot.html">One-Hot Encoding</a></li><li><a class="toctext" href="../gpu.html">GPU Support</a></li><li><a class="toctext" href="../saving.html">Saving & Loading</a></li><li><span class="toctext">Internals</span><ul><li><a class="toctext" href="../internals/tracker.html">Backpropagation</a></li></ul></li><li><a class="toctext" href="../community.html">Community</a></li></ul></nav><article id="docs"><header><nav><ul><li>Building Models</li><li><a href="basics.html">Basics</a></li></ul><a class="edit-page" href="https://github.com/FluxML/Flux.jl/blob/master/docs/src/models/basics.md"><span class="fa"></span> Edit on GitHub</a></nav><hr/><div id="topbar"><span>Basics</span><a class="fa fa-bars" href="#"></a></div></header><h1><a class="nav-anchor" id="Model-Building-Basics-1" href="#Model-Building-Basics-1">Model-Building Basics</a></h1><h2><a class="nav-anchor" id="Taking-Gradients-1" href="#Taking-Gradients-1">Taking Gradients</a></h2><p>Consider a simple linear regression, which tries to predict an output array <code>y</code> from an input <code>x</code>. (It's a good idea to follow this example in the Julia repl.)</p><pre><code class="language-julia">W = rand(2, 5)
|
||||
</script><link href="https://cdnjs.cloudflare.com/ajax/libs/normalize/4.2.0/normalize.min.css" rel="stylesheet" type="text/css"/><link href="https://fonts.googleapis.com/css?family=Lato|Roboto+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="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/default.min.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="../siteinfo.js"></script><script src="../../versions.js"></script><link href="../assets/documenter.css" rel="stylesheet" type="text/css"/><link href="../../flux.css" rel="stylesheet" type="text/css"/></head><body><nav class="toc"><h1>Flux</h1><select id="version-selector" onChange="window.location.href=this.value" style="visibility: hidden"></select><form class="search" id="search-form" action="../search.html"><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 class="current"><a class="toctext" href="basics.html">Basics</a><ul class="internal"><li><a class="toctext" href="#Taking-Gradients-1">Taking Gradients</a></li><li><a class="toctext" href="#Simple-Models-1">Simple Models</a></li><li><a class="toctext" href="#Building-Layers-1">Building Layers</a></li><li><a class="toctext" href="#Stacking-It-Up-1">Stacking It Up</a></li><li><a class="toctext" href="#Layer-helpers-1">Layer helpers</a></li></ul></li><li><a class="toctext" href="recurrence.html">Recurrence</a></li><li><a class="toctext" href="regularisation.html">Regularisation</a></li><li><a class="toctext" href="layers.html">Model Reference</a></li></ul></li><li><span class="toctext">Training Models</span><ul><li><a class="toctext" href="../training/optimisers.html">Optimisers</a></li><li><a class="toctext" href="../training/training.html">Training</a></li></ul></li><li><a class="toctext" href="../data/onehot.html">One-Hot Encoding</a></li><li><a class="toctext" href="../gpu.html">GPU Support</a></li><li><a class="toctext" href="../saving.html">Saving & Loading</a></li><li><span class="toctext">Internals</span><ul><li><a class="toctext" href="../internals/tracker.html">Backpropagation</a></li></ul></li><li><a class="toctext" href="../community.html">Community</a></li></ul></nav><article id="docs"><header><nav><ul><li>Building Models</li><li><a href="basics.html">Basics</a></li></ul><a class="edit-page" href="https://github.com/FluxML/Flux.jl/blob/master/docs/src/models/basics.md"><span class="fa"></span> Edit on GitHub</a></nav><hr/><div id="topbar"><span>Basics</span><a class="fa fa-bars" href="#"></a></div></header><h1><a class="nav-anchor" id="Model-Building-Basics-1" href="#Model-Building-Basics-1">Model-Building Basics</a></h1><h2><a class="nav-anchor" id="Taking-Gradients-1" href="#Taking-Gradients-1">Taking Gradients</a></h2><p>Flux's core feature is taking gradients of Julia code. The <code>gradient</code> function takes another Julia function <code>f</code> and a set of arguments, and returns the gradient with respect to each argument. (It's a good idea to try pasting these examples in the Julia terminal.)</p><pre><code class="language-julia">using Flux.Tracker
|
||||
|
||||
f(x) = 3x^2 + 2x + 1
|
||||
|
||||
# df/dx = 6x + 2
|
||||
f′(x) = Tracker.gradient(f, x)[1]
|
||||
|
||||
f′(2) # 14.0 (tracked)
|
||||
|
||||
# d²f/dx² = 6
|
||||
f′′(x) = Tracker.gradient(f′, x)[1]
|
||||
|
||||
f′′(2) # 6.0 (tracked)</code></pre><p>(We'll learn more about why these numbers show up as <code>(tracked)</code> below.)</p><p>When a function has many parameters, we can pass them all in explicitly:</p><pre><code class="language-julia">f(W, b, x) = W * x + b
|
||||
|
||||
Tracker.gradient(f, 2, 3, 4)
|
||||
(4.0 (tracked), 1.0, 2.0 (tracked))</code></pre><p>But machine learning models can have <em>hundreds</em> of parameters! Flux offers a nice way to handle this. We can tell Flux to treat something as a parameter via <code>param</code>. Then we can collect these together and tell <code>gradient</code> to collect the gradients of all of them at once.</p><pre><code class="language-julia">W = param(2) # 2.0 (tracked)
|
||||
b = param(3) # 3.0 (tracked)
|
||||
|
||||
f(x) = W * x + b
|
||||
|
||||
params = Params([W, b])
|
||||
grads = Tracker.gradient(() -> f(4), params)
|
||||
|
||||
grads[W] # 4.0
|
||||
grads[b] # 1.0</code></pre><p>There are a few things to notice here. Firstly, <code>W</code> and <code>b</code> now show up as <em>tracked</em>. Tracked things behave like normal numbers or arrays, but keep records of everything you do with them, allowing Flux to calculate their gradients. <code>gradient</code> takes a zero-argument function; no arguments are necessary because the <code>Params</code> tell it what to differentiate.</p><p>This will come in really handy when dealing with big, complicated models. For now, though, let's start with something simple.</p><h2><a class="nav-anchor" id="Simple-Models-1" href="#Simple-Models-1">Simple Models</a></h2><p>Consider a simple linear regression, which tries to predict an output array <code>y</code> from an input <code>x</code>.</p><pre><code class="language-julia">W = rand(2, 5)
|
||||
b = rand(2)
|
||||
|
||||
predict(x) = W*x .+ b
|
||||
loss(x, y) = sum((predict(x) .- y).^2)
|
||||
|
||||
function loss(x, y)
|
||||
ŷ = predict(x)
|
||||
sum((y .- ŷ).^2)
|
||||
end
|
||||
|
||||
x, y = rand(5), rand(2) # Dummy data
|
||||
loss(x, y) # ~ 3</code></pre><p>To improve the prediction we can take the gradients of <code>W</code> and <code>b</code> with respect to the loss function and perform gradient descent. We could calculate gradients by hand, but Flux will do it for us if we tell it that <code>W</code> and <code>b</code> are trainable <em>parameters</em>.</p><pre><code class="language-julia">using Flux.Tracker
|
||||
loss(x, y) # ~ 3</code></pre><p>To improve the prediction we can take the gradients of <code>W</code> and <code>b</code> with respect to the loss and perform gradient descent. Let's tell Flux that <code>W</code> and <code>b</code> are parameters, just like we did above.</p><pre><code class="language-julia">using Flux.Tracker
|
||||
|
||||
W = param(W)
|
||||
b = param(b)
|
||||
|
||||
l = loss(x, y)
|
||||
gs = Tracker.gradient(() -> loss(x, y), Params([W, b]))</code></pre><p>Now that we have gradients, we can pull them out and update <code>W</code> to train the model. The <code>update!(W, Δ)</code> function applies <code>W = W + Δ</code>, which we can use for gradient descent.</p><pre><code class="language-julia">using Flux.Tracker: update!
|
||||
|
||||
back!(l)</code></pre><p><code>loss(x, y)</code> returns the same number, but it's now a <em>tracked</em> value that records gradients as it goes along. Calling <code>back!</code> then accumulates the gradient of <code>W</code> and <code>b</code>. We can see what this gradient is, and modify <code>W</code> to train the model.</p><pre><code class="language-julia">using Flux.Tracker: grad, update!
|
||||
|
||||
Δ = grad(W)
|
||||
Δ = gs[W]
|
||||
|
||||
# Update the parameter and reset the gradient
|
||||
update!(W, -0.1Δ)
|
||||
|
||||
loss(x, y) # ~ 2.5</code></pre><p>The loss has decreased a little, meaning that our prediction <code>x</code> is closer to the target <code>y</code>. If we have some data we can already try <a href="../training/training.html">training the model</a>.</p><p>All deep learning in Flux, however complex, is a simple generalisation of this example. Of course, models can <em>look</em> very different – they might have millions of parameters or complex control flow, and there are ways to manage this complexity. Let's see what that looks like.</p><h2><a class="nav-anchor" id="Building-Layers-1" href="#Building-Layers-1">Building Layers</a></h2><p>It's common to create more complex models than the linear regression above. For example, we might want to have two linear layers with a nonlinearity like <a href="https://en.wikipedia.org/wiki/Sigmoid_function">sigmoid</a> (<code>σ</code>) in between them. In the above style we could write this as:</p><pre><code class="language-julia">W1 = param(rand(3, 5))
|
||||
loss(x, y) # ~ 2.5</code></pre><p>The loss has decreased a little, meaning that our prediction <code>x</code> is closer to the target <code>y</code>. If we have some data we can already try <a href="../training/training.html">training the model</a>.</p><p>All deep learning in Flux, however complex, is a simple generalisation of this example. Of course, models can <em>look</em> very different – they might have millions of parameters or complex control flow. Let's see how Flux handles more complex models.</p><h2><a class="nav-anchor" id="Building-Layers-1" href="#Building-Layers-1">Building Layers</a></h2><p>It's common to create more complex models than the linear regression above. For example, we might want to have two linear layers with a nonlinearity like <a href="https://en.wikipedia.org/wiki/Sigmoid_function">sigmoid</a> (<code>σ</code>) in between them. In the above style we could write this as:</p><pre><code class="language-julia">W1 = param(rand(3, 5))
|
||||
b1 = param(rand(3))
|
||||
layer1(x) = W1 * x .+ b1
|
||||
|
||||
|
@ -11,26 +11,26 @@ m(5) == 26
|
||||
|
||||
m = Chain(Dense(10, 5), Dense(5, 2))
|
||||
x = rand(10)
|
||||
m(x) == m[2](m[1](x))</code></pre><p><code>Chain</code> also supports indexing and slicing, e.g. <code>m[2]</code> or <code>m[1:end-1]</code>. <code>m[1:3](x)</code> will calculate the output of the first three layers.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/basic.jl#L1-L18">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Dense" href="#Flux.Dense"><code>Flux.Dense</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">Dense(in::Integer, out::Integer, σ = identity)</code></pre><p>Creates a traditional <code>Dense</code> layer with parameters <code>W</code> and <code>b</code>.</p><pre><code class="language-none">y = σ.(W * x .+ b)</code></pre><p>The input <code>x</code> must be a vector of length <code>in</code>, or a batch of vectors represented as an <code>in × N</code> matrix. The out <code>y</code> will be a vector or batch of length <code>out</code>.</p><pre><code class="language-julia">julia> d = Dense(5, 2)
|
||||
m(x) == m[2](m[1](x))</code></pre><p><code>Chain</code> also supports indexing and slicing, e.g. <code>m[2]</code> or <code>m[1:end-1]</code>. <code>m[1:3](x)</code> will calculate the output of the first three layers.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/basic.jl#L1-L18">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Dense" href="#Flux.Dense"><code>Flux.Dense</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">Dense(in::Integer, out::Integer, σ = identity)</code></pre><p>Creates a traditional <code>Dense</code> layer with parameters <code>W</code> and <code>b</code>.</p><pre><code class="language-none">y = σ.(W * x .+ b)</code></pre><p>The input <code>x</code> must be a vector of length <code>in</code>, or a batch of vectors represented as an <code>in × N</code> matrix. The out <code>y</code> will be a vector or batch of length <code>out</code>.</p><pre><code class="language-julia">julia> d = Dense(5, 2)
|
||||
Dense(5, 2)
|
||||
|
||||
julia> d(rand(5))
|
||||
Tracked 2-element Array{Float64,1}:
|
||||
0.00257447
|
||||
-0.00449443</code></pre></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/basic.jl#L46-L65">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Conv" href="#Flux.Conv"><code>Flux.Conv</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">Conv(size, in=>out)
|
||||
Conv(size, in=>out, relu)</code></pre><p>Standard convolutional layer. <code>size</code> should be a tuple like <code>(2, 2)</code>. <code>in</code> and <code>out</code> specify the number of input and output channels respectively.</p><p>Data should be stored in WHCN order. In other words, a 100×100 RGB image would be a <code>100×100×3</code> array, and a batch of 50 would be a <code>100×100×3×50</code> array.</p><p>Takes the keyword arguments <code>pad</code>, <code>stride</code> and <code>dilation</code>.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/conv.jl#L8-L19">source</a></section><h2><a class="nav-anchor" id="Recurrent-Layers-1" href="#Recurrent-Layers-1">Recurrent Layers</a></h2><p>Much like the core layers above, but can be used to process sequence data (as well as other kinds of structured data).</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.RNN" href="#Flux.RNN"><code>Flux.RNN</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">RNN(in::Integer, out::Integer, σ = tanh)</code></pre><p>The most basic recurrent layer; essentially acts as a <code>Dense</code> layer, but with the output fed back into the input each time step.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/recurrent.jl#L105-L110">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.LSTM" href="#Flux.LSTM"><code>Flux.LSTM</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">LSTM(in::Integer, out::Integer, σ = tanh)</code></pre><p>Long Short Term Memory recurrent layer. Behaves like an RNN but generally exhibits a longer memory span over sequences.</p><p>See <a href="http://colah.github.io/posts/2015-08-Understanding-LSTMs/">this article</a> for a good overview of the internals.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/recurrent.jl#L151-L159">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.GRU" href="#Flux.GRU"><code>Flux.GRU</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">GRU(in::Integer, out::Integer, σ = tanh)</code></pre><p>Gated Recurrent Unit layer. Behaves like an RNN but generally exhibits a longer memory span over sequences.</p><p>See <a href="http://colah.github.io/posts/2015-08-Understanding-LSTMs/">this article</a> for a good overview of the internals.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/recurrent.jl#L192-L200">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Recur" href="#Flux.Recur"><code>Flux.Recur</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">Recur(cell)</code></pre><p><code>Recur</code> takes a recurrent cell and makes it stateful, managing the hidden state in the background. <code>cell</code> should be a model of the form:</p><pre><code class="language-none">h, y = cell(h, x...)</code></pre><p>For example, here's a recurrent network that keeps a running total of its inputs.</p><pre><code class="language-julia">accum(h, x) = (h+x, x)
|
||||
-0.00449443</code></pre></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/basic.jl#L46-L65">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Conv" href="#Flux.Conv"><code>Flux.Conv</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">Conv(size, in=>out)
|
||||
Conv(size, in=>out, relu)</code></pre><p>Standard convolutional layer. <code>size</code> should be a tuple like <code>(2, 2)</code>. <code>in</code> and <code>out</code> specify the number of input and output channels respectively.</p><p>Data should be stored in WHCN order. In other words, a 100×100 RGB image would be a <code>100×100×3</code> array, and a batch of 50 would be a <code>100×100×3×50</code> array.</p><p>Takes the keyword arguments <code>pad</code>, <code>stride</code> and <code>dilation</code>.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/conv.jl#L8-L19">source</a></section><h2><a class="nav-anchor" id="Recurrent-Layers-1" href="#Recurrent-Layers-1">Recurrent Layers</a></h2><p>Much like the core layers above, but can be used to process sequence data (as well as other kinds of structured data).</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.RNN" href="#Flux.RNN"><code>Flux.RNN</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">RNN(in::Integer, out::Integer, σ = tanh)</code></pre><p>The most basic recurrent layer; essentially acts as a <code>Dense</code> layer, but with the output fed back into the input each time step.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/recurrent.jl#L105-L110">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.LSTM" href="#Flux.LSTM"><code>Flux.LSTM</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">LSTM(in::Integer, out::Integer, σ = tanh)</code></pre><p>Long Short Term Memory recurrent layer. Behaves like an RNN but generally exhibits a longer memory span over sequences.</p><p>See <a href="http://colah.github.io/posts/2015-08-Understanding-LSTMs/">this article</a> for a good overview of the internals.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/recurrent.jl#L151-L159">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.GRU" href="#Flux.GRU"><code>Flux.GRU</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">GRU(in::Integer, out::Integer, σ = tanh)</code></pre><p>Gated Recurrent Unit layer. Behaves like an RNN but generally exhibits a longer memory span over sequences.</p><p>See <a href="http://colah.github.io/posts/2015-08-Understanding-LSTMs/">this article</a> for a good overview of the internals.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/recurrent.jl#L192-L200">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Recur" href="#Flux.Recur"><code>Flux.Recur</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">Recur(cell)</code></pre><p><code>Recur</code> takes a recurrent cell and makes it stateful, managing the hidden state in the background. <code>cell</code> should be a model of the form:</p><pre><code class="language-none">h, y = cell(h, x...)</code></pre><p>For example, here's a recurrent network that keeps a running total of its inputs.</p><pre><code class="language-julia">accum(h, x) = (h+x, x)
|
||||
rnn = Flux.Recur(accum, 0)
|
||||
rnn(2) # 2
|
||||
rnn(3) # 3
|
||||
rnn.state # 5
|
||||
rnn.(1:10) # apply to a sequence
|
||||
rnn.state # 60</code></pre></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/recurrent.jl#L7-L26">source</a></section><h2><a class="nav-anchor" id="Activation-Functions-1" href="#Activation-Functions-1">Activation Functions</a></h2><p>Non-linearities that go between layers of your model. Most of these functions are defined in <a href="https://github.com/FluxML/NNlib.jl">NNlib</a> but are available by default in Flux.</p><p>Note that, unless otherwise stated, activation functions operate on scalars. To apply them to an array you can call <code>σ.(xs)</code>, <code>relu.(xs)</code> and so on.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.σ" href="#NNlib.σ"><code>NNlib.σ</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">σ(x) = 1 / (1 + exp(-x))</code></pre><p>Classic <a href="https://en.wikipedia.org/wiki/Sigmoid_function">sigmoid</a> activation function.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/NNlib.jl/blob/5b4c5e2bf228a56f92e2fc75069e9e5e79fa563d/src/activation.jl#L1-L6">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.relu" href="#NNlib.relu"><code>NNlib.relu</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">relu(x) = max(0, x)</code></pre><p><a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">Rectified Linear Unit</a> activation function.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/NNlib.jl/blob/5b4c5e2bf228a56f92e2fc75069e9e5e79fa563d/src/activation.jl#L42-L47">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.leakyrelu" href="#NNlib.leakyrelu"><code>NNlib.leakyrelu</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">leakyrelu(x) = max(0.01x, x)</code></pre><p>Leaky <a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">Rectified Linear Unit</a> activation function. You can also specify the coefficient explicitly, e.g. <code>leakyrelu(x, 0.01)</code>.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/NNlib.jl/blob/5b4c5e2bf228a56f92e2fc75069e9e5e79fa563d/src/activation.jl#L51-L57">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.elu" href="#NNlib.elu"><code>NNlib.elu</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">elu(x, α = 1) =
|
||||
rnn.state # 60</code></pre></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/recurrent.jl#L7-L26">source</a></section><h2><a class="nav-anchor" id="Activation-Functions-1" href="#Activation-Functions-1">Activation Functions</a></h2><p>Non-linearities that go between layers of your model. Most of these functions are defined in <a href="https://github.com/FluxML/NNlib.jl">NNlib</a> but are available by default in Flux.</p><p>Note that, unless otherwise stated, activation functions operate on scalars. To apply them to an array you can call <code>σ.(xs)</code>, <code>relu.(xs)</code> and so on.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.σ" href="#NNlib.σ"><code>NNlib.σ</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">σ(x) = 1 / (1 + exp(-x))</code></pre><p>Classic <a href="https://en.wikipedia.org/wiki/Sigmoid_function">sigmoid</a> activation function.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/NNlib.jl/blob/5b4c5e2bf228a56f92e2fc75069e9e5e79fa563d/src/activation.jl#L1-L6">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.relu" href="#NNlib.relu"><code>NNlib.relu</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">relu(x) = max(0, x)</code></pre><p><a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">Rectified Linear Unit</a> activation function.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/NNlib.jl/blob/5b4c5e2bf228a56f92e2fc75069e9e5e79fa563d/src/activation.jl#L42-L47">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.leakyrelu" href="#NNlib.leakyrelu"><code>NNlib.leakyrelu</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">leakyrelu(x) = max(0.01x, x)</code></pre><p>Leaky <a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">Rectified Linear Unit</a> activation function. You can also specify the coefficient explicitly, e.g. <code>leakyrelu(x, 0.01)</code>.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/NNlib.jl/blob/5b4c5e2bf228a56f92e2fc75069e9e5e79fa563d/src/activation.jl#L51-L57">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.elu" href="#NNlib.elu"><code>NNlib.elu</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">elu(x, α = 1) =
|
||||
x > 0 ? x : α * (exp(x) - 1)</code></pre><p>Exponential Linear Unit activation function. See <a href="https://arxiv.org/abs/1511.07289">Fast and Accurate Deep Network Learning by Exponential Linear Units</a>. You can also specify the coefficient explicitly, e.g. <code>elu(x, 1)</code>.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/NNlib.jl/blob/5b4c5e2bf228a56f92e2fc75069e9e5e79fa563d/src/activation.jl#L60-L67">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.swish" href="#NNlib.swish"><code>NNlib.swish</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">swish(x) = x * σ(x)</code></pre><p>Self-gated actvation function. See <a href="https://arxiv.org/pdf/1710.05941.pdf">Swish: a Self-Gated Activation Function</a>.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/NNlib.jl/blob/5b4c5e2bf228a56f92e2fc75069e9e5e79fa563d/src/activation.jl#L70-L75">source</a></section><h2><a class="nav-anchor" id="Normalisation-and-Regularisation-1" href="#Normalisation-and-Regularisation-1">Normalisation & Regularisation</a></h2><p>These layers don't affect the structure of the network but may improve training times or reduce overfitting.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.testmode!" href="#Flux.testmode!"><code>Flux.testmode!</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">testmode!(m)
|
||||
testmode!(m, false)</code></pre><p>Put layers like <a href="layers.html#Flux.Dropout"><code>Dropout</code></a> and <a href="layers.html#Flux.BatchNorm"><code>BatchNorm</code></a> into testing mode (or back to training mode with <code>false</code>).</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/normalise.jl#L1-L7">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.BatchNorm" href="#Flux.BatchNorm"><code>Flux.BatchNorm</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">BatchNorm(channels::Integer, σ = identity;
|
||||
testmode!(m, false)</code></pre><p>Put layers like <a href="layers.html#Flux.Dropout"><code>Dropout</code></a> and <a href="layers.html#Flux.BatchNorm"><code>BatchNorm</code></a> into testing mode (or back to training mode with <code>false</code>).</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/normalise.jl#L1-L7">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.BatchNorm" href="#Flux.BatchNorm"><code>Flux.BatchNorm</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">BatchNorm(channels::Integer, σ = identity;
|
||||
initβ = zeros, initγ = ones,
|
||||
ϵ = 1e-8, momentum = .1)</code></pre><p>Batch Normalization layer. The <code>channels</code> input should be the size of the channel dimension in your data (see below).</p><p>Given an array with <code>N</code> dimensions, call the <code>N-1</code>th the channel dimension. (For a batch of feature vectors this is just the data dimension, for <code>WHCN</code> images it's the usual channel dimension.)</p><p><code>BatchNorm</code> computes the mean and variance for each each <code>W×H×1×N</code> slice and shifts them to have a new mean and variance (corresponding to the learnable, per-channel <code>bias</code> and <code>scale</code> parameters).</p><p>See <a href="https://arxiv.org/pdf/1502.03167.pdf">Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift</a>.</p><p>Example:</p><pre><code class="language-julia">m = Chain(
|
||||
Dense(28^2, 64),
|
||||
BatchNorm(64, relu),
|
||||
Dense(64, 10),
|
||||
BatchNorm(10),
|
||||
softmax)</code></pre></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/normalise.jl#L69-L98">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Dropout" href="#Flux.Dropout"><code>Flux.Dropout</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">Dropout(p)</code></pre><p>A Dropout layer. For each input, either sets that input to <code>0</code> (with probability <code>p</code>) or scales it by <code>1/(1-p)</code>. This is used as a regularisation, i.e. it reduces overfitting during training.</p><p>Does nothing to the input once in <a href="layers.html#Flux.testmode!"><code>testmode!</code></a>.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/normalise.jl#L15-L23">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.LayerNorm" href="#Flux.LayerNorm"><code>Flux.LayerNorm</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">LayerNorm(h::Integer)</code></pre><p>A <a href="https://arxiv.org/pdf/1607.06450.pdf">normalisation layer</a> designed to be used with recurrent hidden states of size <code>h</code>. Normalises the mean/stddev of each input before applying a per-neuron gain/bias.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/layers/normalise.jl#L46-L53">source</a></section><footer><hr/><a class="previous" href="regularisation.html"><span class="direction">Previous</span><span class="title">Regularisation</span></a><a class="next" href="../training/optimisers.html"><span class="direction">Next</span><span class="title">Optimisers</span></a></footer></article></body></html>
|
||||
softmax)</code></pre></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/normalise.jl#L69-L98">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Dropout" href="#Flux.Dropout"><code>Flux.Dropout</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">Dropout(p)</code></pre><p>A Dropout layer. For each input, either sets that input to <code>0</code> (with probability <code>p</code>) or scales it by <code>1/(1-p)</code>. This is used as a regularisation, i.e. it reduces overfitting during training.</p><p>Does nothing to the input once in <a href="layers.html#Flux.testmode!"><code>testmode!</code></a>.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/normalise.jl#L15-L23">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.LayerNorm" href="#Flux.LayerNorm"><code>Flux.LayerNorm</code></a> — <span class="docstring-category">Type</span>.</div><div><pre><code class="language-none">LayerNorm(h::Integer)</code></pre><p>A <a href="https://arxiv.org/pdf/1607.06450.pdf">normalisation layer</a> designed to be used with recurrent hidden states of size <code>h</code>. Normalises the mean/stddev of each input before applying a per-neuron gain/bias.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/layers/normalise.jl#L46-L53">source</a></section><footer><hr/><a class="previous" href="regularisation.html"><span class="direction">Previous</span><span class="title">Regularisation</span></a><a class="next" href="../training/optimisers.html"><span class="direction">Next</span><span class="title">Optimisers</span></a></footer></article></body></html>
|
||||
|
@ -39,4 +39,4 @@ m = Flux.Recur(rnn, h)
|
||||
|
||||
y = m(x)</code></pre><p>The <code>Recur</code> wrapper stores the state between runs in the <code>m.state</code> field.</p><p>If you use the <code>RNN(10, 5)</code> constructor – as opposed to <code>RNNCell</code> – you'll see that it's simply a wrapped cell.</p><pre><code class="language-julia">julia> RNN(10, 5)
|
||||
Recur(RNNCell(Dense(15, 5)))</code></pre><h2><a class="nav-anchor" id="Sequences-1" href="#Sequences-1">Sequences</a></h2><p>Often we want to work with sequences of inputs, rather than individual <code>x</code>s.</p><pre><code class="language-julia">seq = [rand(10) for i = 1:10]</code></pre><p>With <code>Recur</code>, applying our model to each element of a sequence is trivial:</p><pre><code class="language-julia">m.(seq) # returns a list of 5-element vectors</code></pre><p>This works even when we've chain recurrent layers into a larger model.</p><pre><code class="language-julia">m = Chain(LSTM(10, 15), Dense(15, 5))
|
||||
m.(seq)</code></pre><h2><a class="nav-anchor" id="Truncating-Gradients-1" href="#Truncating-Gradients-1">Truncating Gradients</a></h2><p>By default, calculating the gradients in a recurrent layer involves the entire history. For example, if we call the model on 100 inputs, calling <code>back!</code> will calculate the gradient for those 100 calls. If we then calculate another 10 inputs we have to calculate 110 gradients – this accumulates and quickly becomes expensive.</p><p>To avoid this we can <em>truncate</em> the gradient calculation, forgetting the history.</p><pre><code class="language-julia">truncate!(m)</code></pre><p>Calling <code>truncate!</code> wipes the slate clean, so we can call the model with more inputs without building up an expensive gradient computation.</p><p><code>truncate!</code> makes sense when you are working with multiple chunks of a large sequence, but we may also want to work with a set of independent sequences. In this case the hidden state should be completely reset to its original value, throwing away any accumulated information. <code>reset!</code> does this for you.</p><footer><hr/><a class="previous" href="basics.html"><span class="direction">Previous</span><span class="title">Basics</span></a><a class="next" href="regularisation.html"><span class="direction">Next</span><span class="title">Regularisation</span></a></footer></article></body></html>
|
||||
m.(seq)</code></pre><h2><a class="nav-anchor" id="Truncating-Gradients-1" href="#Truncating-Gradients-1">Truncating Gradients</a></h2><p>By default, calculating the gradients in a recurrent layer involves its entire history. For example, if we call the model on 100 inputs, we'll have to calculate the gradient for those 100 calls. If we then calculate another 10 inputs we have to calculate 110 gradients – this accumulates and quickly becomes expensive.</p><p>To avoid this we can <em>truncate</em> the gradient calculation, forgetting the history.</p><pre><code class="language-julia">truncate!(m)</code></pre><p>Calling <code>truncate!</code> wipes the slate clean, so we can call the model with more inputs without building up an expensive gradient computation.</p><p><code>truncate!</code> makes sense when you are working with multiple chunks of a large sequence, but we may also want to work with a set of independent sequences. In this case the hidden state should be completely reset to its original value, throwing away any accumulated information. <code>reset!</code> does this for you.</p><footer><hr/><a class="previous" href="basics.html"><span class="direction">Previous</span><span class="title">Basics</span></a><a class="next" href="regularisation.html"><span class="direction">Next</span><span class="title">Regularisation</span></a></footer></article></body></html>
|
||||
|
@ -45,7 +45,15 @@ var documenterSearchIndex = {"docs": [
|
||||
"page": "Basics",
|
||||
"title": "Taking Gradients",
|
||||
"category": "section",
|
||||
"text": "Consider a simple linear regression, which tries to predict an output array y from an input x. (It\'s a good idea to follow this example in the Julia repl.)W = rand(2, 5)\nb = rand(2)\n\npredict(x) = W*x .+ b\nloss(x, y) = sum((predict(x) .- y).^2)\n\nx, y = rand(5), rand(2) # Dummy data\nloss(x, y) # ~ 3To improve the prediction we can take the gradients of W and b with respect to the loss function and perform gradient descent. We could calculate gradients by hand, but Flux will do it for us if we tell it that W and b are trainable parameters.using Flux.Tracker\n\nW = param(W)\nb = param(b)\n\nl = loss(x, y)\n\nback!(l)loss(x, y) returns the same number, but it\'s now a tracked value that records gradients as it goes along. Calling back! then accumulates the gradient of W and b. We can see what this gradient is, and modify W to train the model.using Flux.Tracker: grad, update!\n\nΔ = grad(W)\n\n# Update the parameter and reset the gradient\nupdate!(W, -0.1Δ)\n\nloss(x, y) # ~ 2.5The loss has decreased a little, meaning that our prediction x is closer to the target y. If we have some data we can already try training the model.All deep learning in Flux, however complex, is a simple generalisation of this example. Of course, models can look very different – they might have millions of parameters or complex control flow, and there are ways to manage this complexity. Let\'s see what that looks like."
|
||||
"text": "Flux\'s core feature is taking gradients of Julia code. The gradient function takes another Julia function f and a set of arguments, and returns the gradient with respect to each argument. (It\'s a good idea to try pasting these examples in the Julia terminal.)using Flux.Tracker\n\nf(x) = 3x^2 + 2x + 1\n\n# df/dx = 6x + 2\nf′(x) = Tracker.gradient(f, x)[1]\n\nf′(2) # 14.0 (tracked)\n\n# d²f/dx² = 6\nf′′(x) = Tracker.gradient(f′, x)[1]\n\nf′′(2) # 6.0 (tracked)(We\'ll learn more about why these numbers show up as (tracked) below.)When a function has many parameters, we can pass them all in explicitly:f(W, b, x) = W * x + b\n\nTracker.gradient(f, 2, 3, 4)\n(4.0 (tracked), 1.0, 2.0 (tracked))But machine learning models can have hundreds of parameters! Flux offers a nice way to handle this. We can tell Flux to treat something as a parameter via param. Then we can collect these together and tell gradient to collect the gradients of all of them at once.W = param(2) # 2.0 (tracked)\nb = param(3) # 3.0 (tracked)\n\nf(x) = W * x + b\n\nparams = Params([W, b])\ngrads = Tracker.gradient(() -> f(4), params)\n\ngrads[W] # 4.0\ngrads[b] # 1.0There are a few things to notice here. Firstly, W and b now show up as tracked. Tracked things behave like normal numbers or arrays, but keep records of everything you do with them, allowing Flux to calculate their gradients. gradient takes a zero-argument function; no arguments are necessary because the Params tell it what to differentiate.This will come in really handy when dealing with big, complicated models. For now, though, let\'s start with something simple."
|
||||
},
|
||||
|
||||
{
|
||||
"location": "models/basics.html#Simple-Models-1",
|
||||
"page": "Basics",
|
||||
"title": "Simple Models",
|
||||
"category": "section",
|
||||
"text": "Consider a simple linear regression, which tries to predict an output array y from an input x.W = rand(2, 5)\nb = rand(2)\n\npredict(x) = W*x .+ b\n\nfunction loss(x, y)\n ŷ = predict(x)\n sum((y .- ŷ).^2)\nend\n\nx, y = rand(5), rand(2) # Dummy data\nloss(x, y) # ~ 3To improve the prediction we can take the gradients of W and b with respect to the loss and perform gradient descent. Let\'s tell Flux that W and b are parameters, just like we did above.using Flux.Tracker\n\nW = param(W)\nb = param(b)\n\ngs = Tracker.gradient(() -> loss(x, y), Params([W, b]))Now that we have gradients, we can pull them out and update W to train the model. The update!(W, Δ) function applies W = W + Δ, which we can use for gradient descent.using Flux.Tracker: update!\n\nΔ = gs[W]\n\n# Update the parameter and reset the gradient\nupdate!(W, -0.1Δ)\n\nloss(x, y) # ~ 2.5The loss has decreased a little, meaning that our prediction x is closer to the target y. If we have some data we can already try training the model.All deep learning in Flux, however complex, is a simple generalisation of this example. Of course, models can look very different – they might have millions of parameters or complex control flow. Let\'s see how Flux handles more complex models."
|
||||
},
|
||||
|
||||
{
|
||||
@ -117,7 +125,7 @@ var documenterSearchIndex = {"docs": [
|
||||
"page": "Recurrence",
|
||||
"title": "Truncating Gradients",
|
||||
"category": "section",
|
||||
"text": "By default, calculating the gradients in a recurrent layer involves the entire history. For example, if we call the model on 100 inputs, calling back! will calculate the gradient for those 100 calls. If we then calculate another 10 inputs we have to calculate 110 gradients – this accumulates and quickly becomes expensive.To avoid this we can truncate the gradient calculation, forgetting the history.truncate!(m)Calling truncate! wipes the slate clean, so we can call the model with more inputs without building up an expensive gradient computation.truncate! makes sense when you are working with multiple chunks of a large sequence, but we may also want to work with a set of independent sequences. In this case the hidden state should be completely reset to its original value, throwing away any accumulated information. reset! does this for you."
|
||||
"text": "By default, calculating the gradients in a recurrent layer involves its entire history. For example, if we call the model on 100 inputs, we\'ll have to calculate the gradient for those 100 calls. If we then calculate another 10 inputs we have to calculate 110 gradients – this accumulates and quickly becomes expensive.To avoid this we can truncate the gradient calculation, forgetting the history.truncate!(m)Calling truncate! wipes the slate clean, so we can call the model with more inputs without building up an expensive gradient computation.truncate! makes sense when you are working with multiple chunks of a large sequence, but we may also want to work with a set of independent sequences. In this case the hidden state should be completely reset to its original value, throwing away any accumulated information. reset! does this for you."
|
||||
},
|
||||
|
||||
{
|
||||
@ -317,7 +325,7 @@ var documenterSearchIndex = {"docs": [
|
||||
"page": "Optimisers",
|
||||
"title": "Optimisers",
|
||||
"category": "section",
|
||||
"text": "Consider a simple linear regression. We create some dummy data, calculate a loss, and backpropagate to calculate gradients for the parameters W and b.W = param(rand(2, 5))\nb = param(rand(2))\n\npredict(x) = W*x .+ b\nloss(x, y) = sum((predict(x) .- y).^2)\n\nx, y = rand(5), rand(2) # Dummy data\nl = loss(x, y) # ~ 3\nback!(l)We want to update each parameter, using the gradient, in order to improve (reduce) the loss. Here\'s one way to do that:using Flux.Tracker: grad, update!\n\nfunction sgd()\n η = 0.1 # Learning Rate\n for p in (W, b)\n update!(p, -η * grad(p))\n end\nendIf we call sgd, the parameters W and b will change and our loss should go down.There are two pieces here: one is that we need a list of trainable parameters for the model ([W, b] in this case), and the other is the update step. In this case the update is simply gradient descent (x .-= η .* Δ), but we might choose to do something more advanced, like adding momentum.In this case, getting the variables is trivial, but you can imagine it\'d be more of a pain with some complex stack of layers.m = Chain(\n Dense(10, 5, σ),\n Dense(5, 2), softmax)Instead of having to write [m[1].W, m[1].b, ...], Flux provides a params function params(m) that returns a list of all parameters in the model for you.For the update step, there\'s nothing whatsoever wrong with writing the loop above – it\'ll work just fine – but Flux provides various optimisers that make it more convenient.opt = SGD([W, b], 0.1) # Gradient descent with learning rate 0.1\n\nopt() # Carry out the update, modifying `W` and `b`.An optimiser takes a parameter list and returns a function that does the same thing as update above. We can pass either opt or update to our training loop, which will then run the optimiser after every mini-batch of data."
|
||||
"text": "Consider a simple linear regression. We create some dummy data, calculate a loss, and backpropagate to calculate gradients for the parameters W and b.using Flux.Tracker\n\nW = param(rand(2, 5))\nb = param(rand(2))\n\npredict(x) = W*x .+ b\nloss(x, y) = sum((predict(x) .- y).^2)\n\nx, y = rand(5), rand(2) # Dummy data\nl = loss(x, y) # ~ 3\n\nparams = Params([W, b])\ngrads = Tracker.gradient(() -> loss(x, y), params)We want to update each parameter, using the gradient, in order to improve (reduce) the loss. Here\'s one way to do that:using Flux.Tracker: grad, update!\n\nfunction sgd()\n η = 0.1 # Learning Rate\n for p in (W, b)\n update!(p, -η * grads[p])\n end\nendIf we call sgd, the parameters W and b will change and our loss should go down.There are two pieces here: one is that we need a list of trainable parameters for the model ([W, b] in this case), and the other is the update step. In this case the update is simply gradient descent (x .-= η .* Δ), but we might choose to do something more advanced, like adding momentum.In this case, getting the variables is trivial, but you can imagine it\'d be more of a pain with some complex stack of layers.m = Chain(\n Dense(10, 5, σ),\n Dense(5, 2), softmax)Instead of having to write [m[1].W, m[1].b, ...], Flux provides a params function params(m) that returns a list of all parameters in the model for you.For the update step, there\'s nothing whatsoever wrong with writing the loop above – it\'ll work just fine – but Flux provides various optimisers that make it more convenient.opt = SGD([W, b], 0.1) # Gradient descent with learning rate 0.1\n\nopt() # Carry out the update, modifying `W` and `b`.An optimiser takes a parameter list and returns a function that does the same thing as update above. We can pass either opt or update to our training loop, which will then run the optimiser after every mini-batch of data."
|
||||
},
|
||||
|
||||
{
|
||||
@ -485,15 +493,23 @@ var documenterSearchIndex = {"docs": [
|
||||
"page": "Backpropagation",
|
||||
"title": "Flux.Tracker",
|
||||
"category": "section",
|
||||
"text": "Backpropagation, or reverse-mode automatic differentiation, is handled by the Flux.Tracker module.julia> using Flux.TrackerThe param function converts a normal Julia array into a new object that, while behaving like an array, tracks extra information that allows us to calculate derivatives. For example, say we multiply two parameters:julia> W = param([1 2; 3 4])\nTracked 2×2 Array{Float64,2}:\n 1.0 2.0\n 3.0 4.0\n\njulia> x = param([5, 6])\nTracked 2-element Array{Float64,1}:\n 5.0\n 6.0\n\njulia> y = W*x\nTracked 2-element Array{Float64,1}:\n 17.0\n 39.0The output y is also a TrackedArray object. We can now backpropagate sensitivities to W and x via the back! function, and see the gradients accumulated in the W and x tracked arrays:julia> Tracker.back!(y, [1, -1])\n\njulia> W.grad\n2×2 Array{Float64,2}:\n 5.0 6.0\n-5.0 -6.0\n\njulia> x.grad\n2-element Array{Float64,1}:\n -2.0\n -2.0"
|
||||
"text": "Backpropagation, or reverse-mode automatic differentiation, is handled by the Flux.Tracker module.julia> using Flux.TrackerHere we discuss some more advanced uses of this module, as well as covering its internals."
|
||||
},
|
||||
|
||||
{
|
||||
"location": "internals/tracker.html#Internals-1",
|
||||
"location": "internals/tracker.html#Taking-Gradients-1",
|
||||
"page": "Backpropagation",
|
||||
"title": "Internals",
|
||||
"title": "Taking Gradients",
|
||||
"category": "section",
|
||||
"text": "All Tracked* objects (TrackedArray, TrackedReal) are light wrappers around the Tracked type, which you can access via the .tracker field.julia> x.tracker\nFlux.Tracker.Tracked{Array{Float64,1}}(0x00000000, Flux.Tracker.Call{Void,Tuple{}}(nothing, ()), true, [5.0, 6.0], [-2.0, -2.0])The Tracker stores the value and gradient of a given object, which we\'ve seen before.julia> x.tracker.data\n2-element Array{Float64,1}:\n 5.0\n 6.0\n\njulia> x.tracker.grad\n2-element Array{Float64,1}:\n -2.0\n -2.0The tracker also contains a Call object, which simply represents a function call that was made at some point during the forward pass. For example, the + call would look like this:julia> Tracker.Call(+, 1, 2)\nFlux.Tracker.Call{Base.#+,Tuple{Int64,Int64}}(+, (1, 2))In the case of the y we produced above, we can see that it stores the call that produced it – that is, W*x.julia> y.tracker.f\nFlux.Tracker.Call{...}(*, (param([1.0 2.0; 3.0 4.0]), param([5.0, 6.0])))Notice that because the arguments to the call may also be tracked arrays, storing their own calls, this means that Tracker ends up forming a data structure that records everything that happened during the forward pass (often known as a tape).When we call back!(y, [1, -1]), the sensitivities [1, -1] simply get forwarded to y\'s call (*), effectively callingTracker.back(*, [1, -1], W, x)which in turn calculates the sensitivities of the arguments (W and x) and backpropagates through their calls. This is recursive, so it will walk the entire program graph and propagate gradients to the original model parameters."
|
||||
"text": "In the basics section we covered basic usage of the gradient function.using Flux.Tracker\n\nTracker.gradient((a, b) -> a*b, 2, 3) # (3.0 (tracked), 2.0 (tracked))gradient is actually just a thin wrapper around the backpropagator-based interface, forward.using Flux.Tracker: forward\n\ny, back = forward((a, b) -> a*b, 2, 3) # (6.0 (tracked), Flux.Tracker.#9)\n\nback(1) # (3.0 (tracked), 2.0 (tracked))The forward function returns two results. The first, y, is the original value of the function (perhaps with tracking applied). The second, back, is a new function which, given a sensitivity, returns the sensitivity of the inputs to forward (we call this a \"backpropagator\"). One use of this interface is to provide custom sensitivities when outputs are not scalar.julia> y, back = forward((a, b) -> a.*b, [1,2,3],[4,5,6])\n(param([4.0, 10.0, 18.0]), Flux.Tracker.#9)\n\njulia> back([1,1,1])\n(param([4.0, 5.0, 6.0]), param([1.0, 2.0, 3.0]))We can also take gradients in-place. This can be useful if you only care about first-order gradients.a, b = param(2), param(3)\n\nc = a*b # 6.0 (tracked)\n\nTracker.back!(c)\n\nTracker.grad(a), Tracker.grad(b) # (3.0, 2.0)"
|
||||
},
|
||||
|
||||
{
|
||||
"location": "internals/tracker.html#Tracked-Arrays-1",
|
||||
"page": "Backpropagation",
|
||||
"title": "Tracked Arrays",
|
||||
"category": "section",
|
||||
"text": "The param function converts a normal Julia array into a new object that, while behaving like an array, tracks extra information that allows us to calculate derivatives. For example, say we multiply two parameters:julia> W = param([1 2; 3 4])\nTracked 2×2 Array{Float64,2}:\n 1.0 2.0\n 3.0 4.0\n\njulia> x = param([5, 6])\nTracked 2-element Array{Float64,1}:\n 5.0\n 6.0\n\njulia> y = W*x\nTracked 2-element Array{Float64,1}:\n 17.0\n 39.0The output y is also a TrackedArray object. We can now backpropagate sensitivities to W and x via the back! function, and see the gradients accumulated in the W and x tracked arrays:julia> Tracker.back!(y, [1, -1])\n\njulia> W.grad\n2×2 Array{Float64,2}:\n 5.0 6.0\n-5.0 -6.0\n\njulia> x.grad\n2-element Array{Float64,1}:\n -2.0\n -2.0You may sometimes want to drop derivative information and just get the plain value back. You can do this by calling Tracker.data(W)."
|
||||
},
|
||||
|
||||
{
|
||||
@ -501,15 +517,15 @@ var documenterSearchIndex = {"docs": [
|
||||
"page": "Backpropagation",
|
||||
"title": "Custom Gradients",
|
||||
"category": "section",
|
||||
"text": "We can hook in to the processes above to implement custom gradients for a function or kernel. For a toy example, imagine a custom implementation of minus:julia> minus(a, b) = a - bFirstly, we must tell the tracker system to stop when it sees a call to minus, and record it. We can do this using dispatch:julia> minus(a::TrackedArray, b::TrackedArray) = Tracker.track(minus, a, b)\nminus (generic function with 2 methods)Tracker.track does two things: (1) it makes sure minus is called with normal array, not tracked ones (you can use @show inside minus to verify this), and (2) it uses the result to add a minus node to the tape. Look inside the result of calling minus to see what happened:julia> a, b = param([6,5,4]), param([1,2,3])\n(param([6.0, 5.0, 4.0]), param([1.0, 2.0, 3.0]))\n\njulia> c = minus(a, b)\nTracked 3-element Array{Float64,1}:\n 5.0\n 3.0\n 1.0\n\njulia> c.tracker.f\nFlux.Tracker.Call{...}(minus, (param([6.0, 5.0, 4.0]), param([1.0, 2.0, 3.0])))Finally, we have to specify the gradient of minus.julia> Tracker.back(::typeof(minus), Δ, a, b) =\n (Tracker.@back(a, Δ); Tracker.@back(b, -Δ))@back(x, Δ) tells the tracker to continue propagating the sensitivity Δ through x. Now, AD will work with any program that calls minus.julia> Flux.back!(c, 1)\n\njulia> a.grad\n3-element Array{Float64,1}:\n 1.0\n 1.0\n 1.0\n\njulia> b.grad\n3-element Array{Float64,1}:\n -1.0\n -1.0\n -1.0"
|
||||
"text": "We can hook in to the processes above to implement custom gradients for a function or kernel. For a toy example, imagine a custom implementation of minus:minus(a, b) = a - bFirstly, we must tell the tracker system to stop when it sees a call to minus, and record it. We can do this using dispatch:using Flux.Tracker: TrackedReal, track, @grad\n\nminus(a::TrackedArray, b::TrackedArray) = Tracker.track(minus, a, b)track takes care of building a new Tracked object and recording the operation on the tape. We just need to provide a gradient definition.@grad function minus(a, b)\n return minus(data(a),data(b)), Δ -> (Δ, -Δ)\nendThis is essentially just a way of overloading the forward function we saw above. We strip tracking from a and b so that we are calling the original definition of minus (otherwise, we\'d just try to track the call again and hit an infinite regress).Note that in the backpropagator we don\'t call data(a); we do in fact want to track this, since nest AD will take a derivative through the backpropagator itself. For example, the gradient of * might look like this.@grad a * b = data(a)*data(b), Δ -> (Δ*b, a*Δ)For multi-argument functions with custom gradients, you likely want to catch not just minus(::TrackedArray, ::TrackedArray) but also minus(::Array, TrackedArray) and so on. To do so, just define those extra signatures as needed:minus(a::AbstractArray, b::TrackedArray) = Tracker.track(minus, a, b)\nminus(a::TrackedArray, b::AbstractArray) = Tracker.track(minus, a, b)"
|
||||
},
|
||||
|
||||
{
|
||||
"location": "internals/tracker.html#Notes-1",
|
||||
"location": "internals/tracker.html#Tracked-Internals-1",
|
||||
"page": "Backpropagation",
|
||||
"title": "Notes",
|
||||
"title": "Tracked Internals",
|
||||
"category": "section",
|
||||
"text": "For multi-argument functions with custom gradients, you likely want to catch not just minus(::TrackedArray, ::TrackedArray) but also minus(::Array, TrackedArray) and so on. To do so, just define those extra signatures as needed:minus(a::AbstractArray, b::TrackedArray) = Tracker.track(minus, a, b)\nminus(a::TrackedArray, b::AbstractArray) = Tracker.track(minus, a, b)@back must be called exactly once on each tracked input argument. You do not need to do any special handling if one of the arguments is not tracked, as @back will just become a no-op."
|
||||
"text": "All Tracked* objects (TrackedArray, TrackedReal) are light wrappers around the Tracked type, which you can access via the .tracker field.julia> x.tracker\nFlux.Tracker.Tracked{Array{Float64,1}}(0x00000000, Flux.Tracker.Call{Void,Tuple{}}(nothing, ()), true, [5.0, 6.0], [-2.0, -2.0])The Tracker stores the gradient of a given object, which we\'ve seen before.julia> x.tracker.grad\n2-element Array{Float64,1}:\n -2.0\n -2.0The tracker also contains a Call object, which simply represents a function call that was made at some point during the forward pass. For example, the + call would look like this:julia> Tracker.Call(+, 1, 2)\nFlux.Tracker.Call{Base.#+,Tuple{Int64,Int64}}(+, (1, 2))In the case of the y we produced above, we can see that it stores the call that produced it – that is, W*x.julia> y.tracker.f\nFlux.Tracker.Call{...}(*, (param([1.0 2.0; 3.0 4.0]), param([5.0, 6.0])))Notice that because the arguments to the call may also be tracked arrays, storing their own calls, this means that Tracker ends up forming a data structure that records everything that happened during the forward pass (often known as a tape).When we call back!(y, [1, -1]), the sensitivities [1, -1] simply get forwarded to y\'s call (*), effectively callingTracker.back(*, [1, -1], W, x)which in turn calculates the sensitivities of the arguments (W and x) and back-propagates through their calls. This is recursive, so it will walk the entire program graph and propagate gradients to the original model parameters."
|
||||
},
|
||||
|
||||
{
|
||||
|
@ -6,7 +6,9 @@ m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
|
||||
|
||||
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://fonts.googleapis.com/css?family=Lato|Roboto+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="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/default.min.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="../siteinfo.js"></script><script src="../../versions.js"></script><link href="../assets/documenter.css" rel="stylesheet" type="text/css"/><link href="../../flux.css" rel="stylesheet" type="text/css"/></head><body><nav class="toc"><h1>Flux</h1><select id="version-selector" onChange="window.location.href=this.value" style="visibility: hidden"></select><form class="search" id="search-form" action="../search.html"><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="../models/basics.html">Basics</a></li><li><a class="toctext" href="../models/recurrence.html">Recurrence</a></li><li><a class="toctext" href="../models/regularisation.html">Regularisation</a></li><li><a class="toctext" href="../models/layers.html">Model Reference</a></li></ul></li><li><span class="toctext">Training Models</span><ul><li class="current"><a class="toctext" href="optimisers.html">Optimisers</a><ul class="internal"><li><a class="toctext" href="#Optimiser-Reference-1">Optimiser Reference</a></li></ul></li><li><a class="toctext" href="training.html">Training</a></li></ul></li><li><a class="toctext" href="../data/onehot.html">One-Hot Encoding</a></li><li><a class="toctext" href="../gpu.html">GPU Support</a></li><li><a class="toctext" href="../saving.html">Saving & Loading</a></li><li><span class="toctext">Internals</span><ul><li><a class="toctext" href="../internals/tracker.html">Backpropagation</a></li></ul></li><li><a class="toctext" href="../community.html">Community</a></li></ul></nav><article id="docs"><header><nav><ul><li>Training Models</li><li><a href="optimisers.html">Optimisers</a></li></ul><a class="edit-page" href="https://github.com/FluxML/Flux.jl/blob/master/docs/src/training/optimisers.md"><span class="fa"></span> Edit on GitHub</a></nav><hr/><div id="topbar"><span>Optimisers</span><a class="fa fa-bars" href="#"></a></div></header><h1><a class="nav-anchor" id="Optimisers-1" href="#Optimisers-1">Optimisers</a></h1><p>Consider a <a href="../models/basics.html">simple linear regression</a>. We create some dummy data, calculate a loss, and backpropagate to calculate gradients for the parameters <code>W</code> and <code>b</code>.</p><pre><code class="language-julia">W = param(rand(2, 5))
|
||||
</script><link href="https://cdnjs.cloudflare.com/ajax/libs/normalize/4.2.0/normalize.min.css" rel="stylesheet" type="text/css"/><link href="https://fonts.googleapis.com/css?family=Lato|Roboto+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="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/default.min.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="../siteinfo.js"></script><script src="../../versions.js"></script><link href="../assets/documenter.css" rel="stylesheet" type="text/css"/><link href="../../flux.css" rel="stylesheet" type="text/css"/></head><body><nav class="toc"><h1>Flux</h1><select id="version-selector" onChange="window.location.href=this.value" style="visibility: hidden"></select><form class="search" id="search-form" action="../search.html"><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="../models/basics.html">Basics</a></li><li><a class="toctext" href="../models/recurrence.html">Recurrence</a></li><li><a class="toctext" href="../models/regularisation.html">Regularisation</a></li><li><a class="toctext" href="../models/layers.html">Model Reference</a></li></ul></li><li><span class="toctext">Training Models</span><ul><li class="current"><a class="toctext" href="optimisers.html">Optimisers</a><ul class="internal"><li><a class="toctext" href="#Optimiser-Reference-1">Optimiser Reference</a></li></ul></li><li><a class="toctext" href="training.html">Training</a></li></ul></li><li><a class="toctext" href="../data/onehot.html">One-Hot Encoding</a></li><li><a class="toctext" href="../gpu.html">GPU Support</a></li><li><a class="toctext" href="../saving.html">Saving & Loading</a></li><li><span class="toctext">Internals</span><ul><li><a class="toctext" href="../internals/tracker.html">Backpropagation</a></li></ul></li><li><a class="toctext" href="../community.html">Community</a></li></ul></nav><article id="docs"><header><nav><ul><li>Training Models</li><li><a href="optimisers.html">Optimisers</a></li></ul><a class="edit-page" href="https://github.com/FluxML/Flux.jl/blob/master/docs/src/training/optimisers.md"><span class="fa"></span> Edit on GitHub</a></nav><hr/><div id="topbar"><span>Optimisers</span><a class="fa fa-bars" href="#"></a></div></header><h1><a class="nav-anchor" id="Optimisers-1" href="#Optimisers-1">Optimisers</a></h1><p>Consider a <a href="../models/basics.html">simple linear regression</a>. We create some dummy data, calculate a loss, and backpropagate to calculate gradients for the parameters <code>W</code> and <code>b</code>.</p><pre><code class="language-julia">using Flux.Tracker
|
||||
|
||||
W = param(rand(2, 5))
|
||||
b = param(rand(2))
|
||||
|
||||
predict(x) = W*x .+ b
|
||||
@ -14,15 +16,17 @@ loss(x, y) = sum((predict(x) .- y).^2)
|
||||
|
||||
x, y = rand(5), rand(2) # Dummy data
|
||||
l = loss(x, y) # ~ 3
|
||||
back!(l)</code></pre><p>We want to update each parameter, using the gradient, in order to improve (reduce) the loss. Here's one way to do that:</p><pre><code class="language-julia">using Flux.Tracker: grad, update!
|
||||
|
||||
params = Params([W, b])
|
||||
grads = Tracker.gradient(() -> loss(x, y), params)</code></pre><p>We want to update each parameter, using the gradient, in order to improve (reduce) the loss. Here's one way to do that:</p><pre><code class="language-julia">using Flux.Tracker: grad, update!
|
||||
|
||||
function sgd()
|
||||
η = 0.1 # Learning Rate
|
||||
for p in (W, b)
|
||||
update!(p, -η * grad(p))
|
||||
update!(p, -η * grads[p])
|
||||
end
|
||||
end</code></pre><p>If we call <code>sgd</code>, the parameters <code>W</code> and <code>b</code> will change and our loss should go down.</p><p>There are two pieces here: one is that we need a list of trainable parameters for the model (<code>[W, b]</code> in this case), and the other is the update step. In this case the update is simply gradient descent (<code>x .-= η .* Δ</code>), but we might choose to do something more advanced, like adding momentum.</p><p>In this case, getting the variables is trivial, but you can imagine it'd be more of a pain with some complex stack of layers.</p><pre><code class="language-julia">m = Chain(
|
||||
Dense(10, 5, σ),
|
||||
Dense(5, 2), softmax)</code></pre><p>Instead of having to write <code>[m[1].W, m[1].b, ...]</code>, Flux provides a params function <code>params(m)</code> that returns a list of all parameters in the model for you.</p><p>For the update step, there's nothing whatsoever wrong with writing the loop above – it'll work just fine – but Flux provides various <em>optimisers</em> that make it more convenient.</p><pre><code class="language-julia">opt = SGD([W, b], 0.1) # Gradient descent with learning rate 0.1
|
||||
|
||||
opt() # Carry out the update, modifying `W` and `b`.</code></pre><p>An optimiser takes a parameter list and returns a function that does the same thing as <code>update</code> above. We can pass either <code>opt</code> or <code>update</code> to our <a href="training.html">training loop</a>, which will then run the optimiser after every mini-batch of data.</p><h2><a class="nav-anchor" id="Optimiser-Reference-1" href="#Optimiser-Reference-1">Optimiser Reference</a></h2><p>All optimisers return a function that, when called, will update the parameters passed to it.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.SGD" href="#Flux.Optimise.SGD"><code>Flux.Optimise.SGD</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">SGD(params, η = 0.1; decay = 0)</code></pre><p>Classic gradient descent optimiser with learning rate <code>η</code>. For each parameter <code>p</code> and its gradient <code>δp</code>, this runs <code>p -= η*δp</code>.</p><p>Supports inverse decaying learning rate if the <code>decay</code> argument is provided.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/optimise/interface.jl#L14-L21">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Momentum" href="#Flux.Optimise.Momentum"><code>Flux.Optimise.Momentum</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">Momentum(params, η = 0.01; ρ = 0.9, decay = 0)</code></pre><p>SGD with learning rate <code>η</code>, momentum <code>ρ</code> and optional learning rate inverse decay.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/optimise/interface.jl#L25-L29">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Nesterov" href="#Flux.Optimise.Nesterov"><code>Flux.Optimise.Nesterov</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">Nesterov(params, η = 0.01; ρ = 0.9, decay = 0)</code></pre><p>SGD with learning rate <code>η</code>, Nesterov momentum <code>ρ</code> and optional learning rate inverse decay.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/optimise/interface.jl#L33-L37">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.ADAM" href="#Flux.Optimise.ADAM"><code>Flux.Optimise.ADAM</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">ADAM(params, η = 0.001; β1 = 0.9, β2 = 0.999, ϵ = 1e-08, decay = 0)</code></pre><p><a href="https://arxiv.org/abs/1412.6980v8">ADAM</a> optimiser.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ce88273880730990ef2e236b775b2080eca12f4a/src/optimise/interface.jl#L51-L55">source</a></section><footer><hr/><a class="previous" href="../models/layers.html"><span class="direction">Previous</span><span class="title">Model Reference</span></a><a class="next" href="training.html"><span class="direction">Next</span><span class="title">Training</span></a></footer></article></body></html>
|
||||
opt() # Carry out the update, modifying `W` and `b`.</code></pre><p>An optimiser takes a parameter list and returns a function that does the same thing as <code>update</code> above. We can pass either <code>opt</code> or <code>update</code> to our <a href="training.html">training loop</a>, which will then run the optimiser after every mini-batch of data.</p><h2><a class="nav-anchor" id="Optimiser-Reference-1" href="#Optimiser-Reference-1">Optimiser Reference</a></h2><p>All optimisers return a function that, when called, will update the parameters passed to it.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.SGD" href="#Flux.Optimise.SGD"><code>Flux.Optimise.SGD</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">SGD(params, η = 0.1; decay = 0)</code></pre><p>Classic gradient descent optimiser with learning rate <code>η</code>. For each parameter <code>p</code> and its gradient <code>δp</code>, this runs <code>p -= η*δp</code>.</p><p>Supports inverse decaying learning rate if the <code>decay</code> argument is provided.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/optimise/interface.jl#L14-L21">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Momentum" href="#Flux.Optimise.Momentum"><code>Flux.Optimise.Momentum</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">Momentum(params, η = 0.01; ρ = 0.9, decay = 0)</code></pre><p>SGD with learning rate <code>η</code>, momentum <code>ρ</code> and optional learning rate inverse decay.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/optimise/interface.jl#L25-L29">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Nesterov" href="#Flux.Optimise.Nesterov"><code>Flux.Optimise.Nesterov</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">Nesterov(params, η = 0.01; ρ = 0.9, decay = 0)</code></pre><p>SGD with learning rate <code>η</code>, Nesterov momentum <code>ρ</code> and optional learning rate inverse decay.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/optimise/interface.jl#L33-L37">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.ADAM" href="#Flux.Optimise.ADAM"><code>Flux.Optimise.ADAM</code></a> — <span class="docstring-category">Function</span>.</div><div><pre><code class="language-none">ADAM(params, η = 0.001; β1 = 0.9, β2 = 0.999, ϵ = 1e-08, decay = 0)</code></pre><p><a href="https://arxiv.org/abs/1412.6980v8">ADAM</a> optimiser.</p></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/6d8e6c044051bcdedfce2bdd0f7e478066becf7d/src/optimise/interface.jl#L51-L55">source</a></section><footer><hr/><a class="previous" href="../models/layers.html"><span class="direction">Previous</span><span class="title">Model Reference</span></a><a class="next" href="training.html"><span class="direction">Next</span><span class="title">Training</span></a></footer></article></body></html>
|
||||
|
Loading…
Reference in New Issue
Block a user