loss(ŷ, y, agg=identity) # no aggregation. </code></pre><h3id="Losses-Reference-1"><aclass="docs-heading-anchor"href="#Losses-Reference-1">Losses Reference</a><aclass="docs-heading-anchor-permalink"href="#Losses-Reference-1"title="Permalink"></a></h3><articleclass="docstring"><header><aclass="docstring-binding"id="Flux.mae"href="#Flux.mae"><code>Flux.mae</code></a> — <spanclass="docstring-category">Function</span></header><section><div><pre><codeclass="language-julia">mae(ŷ, y; agg=mean)</code></pre><p>Return the loss corresponding to mean absolute error: </p><pre><codeclass="language-none">agg(abs.(ŷ .- y))</code></pre></div><aclass="docs-sourcelink"target="_blank"href="https://github.com/FluxML/Flux.jl/blob/8e9cce94e9496c0de96ef85d7da676a1a5387565/src/layers/stateless.jl#L1-L7">source</a></section></article><articleclass="docstring"><header><aclass="docstring-binding"id="Flux.mse"href="#Flux.mse"><code>Flux.mse</code></a> — <spanclass="docstring-category">Function</span></header><section><div><pre><codeclass="language-julia">mse(ŷ, y; agg=mean)</code></pre><p>Return the loss corresponding to mean square error: </p><pre><codeclass="language-none">agg((ŷ .- y).^2)</code></pre></div><aclass="docs-sourcelink"target="_blank"href="https://github.com/FluxML/Flux.jl/blob/8e9cce94e9496c0de96ef85d7da676a1a5387565/src/layers/stateless.jl#L10-L16">source</a></section></article><articleclass="docstring"><header><aclass="docstring-binding"id="Flux.msle"href="#Flux.msle"><code>Flux.msle</code></a> — <spanclass="docstring-category">Function</span></header><section><div><pre><codeclass="language-julia">msle(ŷ, y; agg=mean, ϵ=eps(eltype(ŷ)))</code></pre><p>The loss corresponding to mean squared logarithmic errors, calculated as</p><pre><codeclass="language-none">agg((log.(ŷ .+ ϵ) .- log.(y .+ ϵ)).^2)</code></pre><p>The <code>ϵ</code> term provides numerical stability. Penalizes an under-predicted estimate more than an over-predicted estimate.</p></div><aclass="docs-sourcelink"target="_blank"href="https://github.com/FluxML/Flux.jl/blob/8e9cce94e9496c0de96ef85d7da676a1a5387565/src/layers/stateless.jl#L19-L28">source</a></section></article><articleclass="docstring"><header><aclass="docstring-binding"id="Flux.huber_loss"href="#Flux.huber_loss"><code>Flux.huber_loss</code></a> — <spanclass="docstring-category">Function</span></header><section><div><pre><codeclass="language-julia">huber_loss(ŷ, y; δ=1, agg=mean)</code></pre><p>Return the mean of the <ahref="https://en.wikipedia.org/wiki/Huber_loss">Huber loss</a> given the prediction <code>ŷ</code> and true values <code>y</code>.</p><pre><codeclass="language-none"> | 0.5 * |ŷ - y|, for |ŷ - y| <= δ
logits=false, agg=mean)</code></pre><p>Return the cross entropy between the given probability distributions; calculated as</p><pre><codeclass="language-none">agg(.-sum(weight .* y .* log.(ŷ .+ ϵ); dims=dims))agg=mean,</code></pre><p><code>weight</code> can be <code>nothing</code>, a number or an array. <code>weight=nothing</code> acts like <code>weight=1</code> but is faster.</p><p>If <code>logits=true</code>, the input <code>̂y</code> is first fed to a <ahref="../nnlib/#NNlib.softmax"><code>softmax</code></a> layer.</p><p>See also: <ahref="#Flux.logitcrossentropy"><code>Flux.logitcrossentropy</code></a>, <ahref="#Flux.binarycrossentropy"><code>Flux.binarycrossentropy</code></a>, <ahref="#Flux.logitbinarycrossentropy"><code>Flux.logitbinarycrossentropy</code></a></p></div><aclass="docs-sourcelink"target="_blank"href="https://github.com/FluxML/Flux.jl/blob/8e9cce94e9496c0de96ef85d7da676a1a5387565/src/layers/stateless.jl#L52-L67">source</a></section></article><articleclass="docstring"><header><aclass="docstring-binding"id="Flux.logitcrossentropy"href="#Flux.logitcrossentropy"><code>Flux.logitcrossentropy</code></a> — <spanclass="docstring-category">Function</span></header><section><div><pre><codeclass="language-julia">logitcrossentropy(ŷ, y; weight=nothing, agg=mean, dims=1)</code></pre><p>Return the crossentropy computed after a <ahref="../nnlib/#NNlib.logsoftmax"><code>Flux.logsoftmax</code></a> operation; calculated as</p><pre><codeclass="language-none">agg(.-sum(weight .* y .* logsoftmax(ŷ; dims=dims); dims=dims))</code></pre><p><code>logitcrossentropy(ŷ, y)</code> is mathematically equivalent to <ahref="#Flux.crossentropy"><code>Flux.crossentropy(softmax(log.(ŷ)), y)</code></a> but it is more numerically stable.</p><p>See also: <ahref="#Flux.crossentropy"><code>Flux.crossentropy</code></a>, <ahref="#Flux.binarycrossentropy"><code>Flux.binarycrossentropy</code></a>, <ahref="#Flux.logitbinarycrossentropy"><code>Flux.logitbinarycrossentropy</code></a></p></div><aclass="docs-sourcelink"target="_blank"href="https://github.com/FluxML/Flux.jl/blob/8e9cce94e9496c0de96ef85d7da676a1a5387565/src/layers/stateless.jl#L76-L88">source</a></section></article><articleclass="docstring"><header><aclass="docstring-binding"id="Flux.binarycrossentropy"href="#Flux.binarycrossentropy"><code>Flux.binarycrossentropy</code></a> — <spanclass="docstring-category">Function</span></header><section><div><pre><codeclass="language-julia">binarycrossentropy(ŷ, y; agg=mean, ϵ=epseltype(ŷ), logits=false)</code></pre><p>Return <span>$-y*\log(ŷ + ϵ) - (1-y)*\log(1-ŷ + ϵ)$</span>. The <code>ϵ</code> term provides numerical stability.</p><p>Typically, the prediction <code>ŷ</code> is given by the output of a <ahref="../nnlib/#NNlib.sigmoid"><code>sigmoid</code></a> activation. If <code>logits=true</code>, the input <code>̂y</code> is first fed to a <ahref="../nnlib/#NNlib.sigmoid"><code>sigmoid</code></a> activation. See also: <ahref="#Flux.crossentropy"><code>Flux.crossentropy</code></a>, <ahref="#Flux.logitcrossentropy"><code>Flux.logitcrossentropy</code></a>, <ahref="#Flux.logitbinarycrossentropy"><code>Flux.logitbinarycrossentropy</code></a></p></div><aclass="docs-sourcelink"target="_blank"href="https://github.com/FluxML/Flux.jl/blob/8e9cce94e9496c0de96ef85d7da676a1a5387565/src/layers/stateless.jl#L93-L101">source</a></section></article><articleclass="docstring"><header><aclass="docstring-binding"id="Flux.logitbinarycrossentropy"href="#Flux.logitbinarycrossentropy"><code>Flux.logitbinarycrossentropy</code></a> — <spanclass="docstring-category">Function</span></header><section><div><pre><codeclass="language-julia">logitbinarycrossentropy(ŷ, y; agg=mean)</code></pre><p><code>logitbinarycrossentropy(ŷ, y)</code> is mathematically equivalent to <ahref="#Flux.binarycrossentropy"><code>Flux.binarycrossentropy(σ(log(ŷ)), y)</code></a> but it is more numerically stable.</p><p>See also: <ahref="#Flux.crossentropy"><code>Flux.crossentropy</code></a>, <ahref="#Flu
tversky_loss = 1 - num/den</code></pre><p>and then aggregated with <code>agg</code> over the batch.</p><p>When <code>α+β=1</code>, it is equal to <code>1-F_β</code>, where <code>F_β</code> is an F-score.</p></div><aclass="docs-sourcelink"target="_blank"href="https://github.com/FluxML/Flux.jl/blob/8e9cce94e9496c0de96ef85d7da676a1a5387565/src/layers/stateless.jl#L197-L214">source</a></section></article></article><navclass="docs-footer"><aclass="docs-footer-prevpage"href="../layers/">« Model Reference</a><aclass="docs-footer-nextpage"href="../regularisation/">Regularisation »</a></nav></div><divclass="modal"id="documenter-settings"><divclass="modal-background"></div><divclass="modal-card"><headerclass="modal-card-head"><pclass="modal-card-title">Settings</p><buttonclass="delete"></button></header><sectionclass="modal-card-body"><p><labelclass="label">Theme</label><divclass="select"><selectid="documenter-themepicker"><optionvalue="documenter-light">documenter-light</option><optionvalue="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <ahref="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> on <spanclass="colophon-date"title="Tuesday 5 May 2020 14:57">Tuesday 5 May 2020</span>. Using Julia version 1.3.1.</p></section><footerclass="modal-card-foot"></footer></div></div></div></body></html>
