build based on 7bf3127

dev/.documenter-siteinfo.json

@@ -1 +1 @@
-{"documenter":{"julia_version":"1.10.2","generation_timestamp":"2024-04-27T04:44:25","documenter_version":"1.4.0"}}
+{"documenter":{"julia_version":"1.10.3","generation_timestamp":"2024-05-01T06:30:35","documenter_version":"1.4.0"}}

dev/api/index.html

@@ -21,7 +21,7 @@
 julia> ps, st = Lux.setup(rng, model);
 
 julia> model(ones(Float32, 2, 1), ps, st);
-</code></pre><p>See also: <a href="#DeepEquilibriumNetworks.SkipDeepEquilibriumNetwork"><code>SkipDeepEquilibriumNetwork</code></a>, <a href="#DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork"><code>MultiScaleDeepEquilibriumNetwork</code></a>, <a href="#DeepEquilibriumNetworks.MultiScaleSkipDeepEquilibriumNetwork"><code>MultiScaleSkipDeepEquilibriumNetwork</code></a>.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/47bcaa9f181141c8d423812c57e742d3fd4810e2/src/layers.jl#L129-L182">source</a></section></article><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.SkipDeepEquilibriumNetwork" href="#DeepEquilibriumNetworks.SkipDeepEquilibriumNetwork"><code>DeepEquilibriumNetworks.SkipDeepEquilibriumNetwork</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">SkipDeepEquilibriumNetwork(model, [init=nothing,] solver; kwargs...)</code></pre><p>Skip Deep Equilibrium Network as proposed in (<a href="../references/#pal2022mixing">Pal <em>et al.</em>, 2022</a>). Alias which creates a <a href="#DeepEquilibriumNetworks.DeepEquilibriumNetwork"><code>DeepEquilibriumNetwork</code></a> with <code>init</code> kwarg set to passed value.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/47bcaa9f181141c8d423812c57e742d3fd4810e2/src/layers.jl#L199-L204">source</a></section></article><h2 id="MultiScale-Models"><a class="docs-heading-anchor" href="#MultiScale-Models">MultiScale Models</a><a id="MultiScale-Models-1"></a><a class="docs-heading-anchor-permalink" href="#MultiScale-Models" title="Permalink"></a></h2><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork" href="#DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork"><code>DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">MultiScaleDeepEquilibriumNetwork(main_layers::Tuple, mapping_layers::Matrix,
+</code></pre><p>See also: <a href="#DeepEquilibriumNetworks.SkipDeepEquilibriumNetwork"><code>SkipDeepEquilibriumNetwork</code></a>, <a href="#DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork"><code>MultiScaleDeepEquilibriumNetwork</code></a>, <a href="#DeepEquilibriumNetworks.MultiScaleSkipDeepEquilibriumNetwork"><code>MultiScaleSkipDeepEquilibriumNetwork</code></a>.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/7bf31270c84f2118261d17ae5ff1446c79d55bcd/src/layers.jl#L129-L182">source</a></section></article><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.SkipDeepEquilibriumNetwork" href="#DeepEquilibriumNetworks.SkipDeepEquilibriumNetwork"><code>DeepEquilibriumNetworks.SkipDeepEquilibriumNetwork</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">SkipDeepEquilibriumNetwork(model, [init=nothing,] solver; kwargs...)</code></pre><p>Skip Deep Equilibrium Network as proposed in (<a href="../references/#pal2022mixing">Pal <em>et al.</em>, 2022</a>). Alias which creates a <a href="#DeepEquilibriumNetworks.DeepEquilibriumNetwork"><code>DeepEquilibriumNetwork</code></a> with <code>init</code> kwarg set to passed value.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/7bf31270c84f2118261d17ae5ff1446c79d55bcd/src/layers.jl#L199-L204">source</a></section></article><h2 id="MultiScale-Models"><a class="docs-heading-anchor" href="#MultiScale-Models">MultiScale Models</a><a id="MultiScale-Models-1"></a><a class="docs-heading-anchor-permalink" href="#MultiScale-Models" title="Permalink"></a></h2><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork" href="#DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork"><code>DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">MultiScaleDeepEquilibriumNetwork(main_layers::Tuple, mapping_layers::Matrix,
     post_fuse_layer::Union{Nothing, Tuple}, solver,
     scales::NTuple{N, NTuple{L, Int64}}; kwargs...)</code></pre><p>Multi Scale Deep Equilibrium Network as proposed in (<a href="../references/#baimultiscale2020">Bai <em>et al.</em>, 2020</a>).</p><p><strong>Arguments</strong></p><ul><li><code>main_layers</code>: Tuple of Neural Networks. Each Neural Network is applied to the corresponding scale.</li><li><code>mapping_layers</code>: Matrix of Neural Networks. Each Neural Network is applied to the corresponding scale and the corresponding layer.</li><li><code>post_fuse_layer</code>: Neural Network applied to the fused output of the main layers.</li><li><code>solver</code>: Solver for the rootfinding problem. ODE Solvers and Nonlinear Solvers are both supported.</li><li><code>scales</code>: Scales of the Multi Scale DEQ. Each scale is a tuple of integers. The length of the tuple is the number of layers in the corresponding main layer.</li></ul><p>For keyword arguments, see <a href="#DeepEquilibriumNetworks.DeepEquilibriumNetwork"><code>DeepEquilibriumNetwork</code></a>.</p><p><strong>Example</strong></p><pre><code class="language-julia hljs">julia&gt; using DeepEquilibriumNetworks, Lux, Random, NonlinearSolve
 
@@ -99,6 +99,6 @@
 julia&gt; x = rand(rng, Float32, 4, 12);
 
 julia&gt; model(x, ps, st);
-</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/47bcaa9f181141c8d423812c57e742d3fd4810e2/src/layers.jl#L214-L316">source</a></section></article><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.MultiScaleSkipDeepEquilibriumNetwork" href="#DeepEquilibriumNetworks.MultiScaleSkipDeepEquilibriumNetwork"><code>DeepEquilibriumNetworks.MultiScaleSkipDeepEquilibriumNetwork</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">MultiScaleSkipDeepEquilibriumNetwork(main_layers::Tuple, mapping_layers::Matrix,
+</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/7bf31270c84f2118261d17ae5ff1446c79d55bcd/src/layers.jl#L214-L316">source</a></section></article><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.MultiScaleSkipDeepEquilibriumNetwork" href="#DeepEquilibriumNetworks.MultiScaleSkipDeepEquilibriumNetwork"><code>DeepEquilibriumNetworks.MultiScaleSkipDeepEquilibriumNetwork</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">MultiScaleSkipDeepEquilibriumNetwork(main_layers::Tuple, mapping_layers::Matrix,
     post_fuse_layer::Union{Nothing, Tuple}, [init = nothing,] solver,
-    scales::NTuple{N, NTuple{L, Int64}}; kwargs...)</code></pre><p>Skip Multi Scale Deep Equilibrium Network as proposed in (<a href="../references/#pal2022mixing">Pal <em>et al.</em>, 2022</a>). Alias which creates a <a href="#DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork"><code>MultiScaleDeepEquilibriumNetwork</code></a> with <code>init</code> kwarg set to passed value.</p><p>If <code>init</code> is not passed, it creates a MultiScale Regularized Deep Equilibrium Network.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/47bcaa9f181141c8d423812c57e742d3fd4810e2/src/layers.jl#L335-L344">source</a></section></article><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.MultiScaleNeuralODE" href="#DeepEquilibriumNetworks.MultiScaleNeuralODE"><code>DeepEquilibriumNetworks.MultiScaleNeuralODE</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">MultiScaleNeuralODE(args...; kwargs...)</code></pre><p>Same arguments as <a href="#DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork"><code>MultiScaleDeepEquilibriumNetwork</code></a> but sets <code>problem_type</code> to <code>ODEProblem{false}</code>.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/47bcaa9f181141c8d423812c57e742d3fd4810e2/src/layers.jl#L358-L363">source</a></section></article><h2 id="Solution"><a class="docs-heading-anchor" href="#Solution">Solution</a><a id="Solution-1"></a><a class="docs-heading-anchor-permalink" href="#Solution" title="Permalink"></a></h2><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.DeepEquilibriumSolution" href="#DeepEquilibriumNetworks.DeepEquilibriumSolution"><code>DeepEquilibriumNetworks.DeepEquilibriumSolution</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">DeepEquilibriumSolution(z_star, u₀, residual, jacobian_loss, nfe, solution)</code></pre><p>Stores the solution of a DeepEquilibriumNetwork and its variants.</p><p><strong>Fields</strong></p><ul><li><code>z_star</code>: Steady-State or the value reached due to maxiters</li><li><code>u0</code>: Initial Condition</li><li><code>residual</code>: Difference of the <span>$z^*$</span> and <span>$f(z^*, x)$</span></li><li><code>jacobian_loss</code>: Jacobian Stabilization Loss (see individual networks to see how it can be computed)</li><li><code>nfe</code>: Number of Function Evaluations</li><li><code>original</code>: Original Internal Solution</li></ul></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/47bcaa9f181141c8d423812c57e742d3fd4810e2/src/layers.jl#L1-L15">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../tutorials/reduced_dim_deq/">« Modelling Equilibrium Models with Reduced State Size</a><a class="docs-footer-nextpage" href="../references/">References »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="auto">Automatic (OS)</option><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.4.0 on <span class="colophon-date" title="Saturday 27 April 2024 04:44">Saturday 27 April 2024</span>. Using Julia version 1.10.2.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
+    scales::NTuple{N, NTuple{L, Int64}}; kwargs...)</code></pre><p>Skip Multi Scale Deep Equilibrium Network as proposed in (<a href="../references/#pal2022mixing">Pal <em>et al.</em>, 2022</a>). Alias which creates a <a href="#DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork"><code>MultiScaleDeepEquilibriumNetwork</code></a> with <code>init</code> kwarg set to passed value.</p><p>If <code>init</code> is not passed, it creates a MultiScale Regularized Deep Equilibrium Network.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/7bf31270c84f2118261d17ae5ff1446c79d55bcd/src/layers.jl#L335-L344">source</a></section></article><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.MultiScaleNeuralODE" href="#DeepEquilibriumNetworks.MultiScaleNeuralODE"><code>DeepEquilibriumNetworks.MultiScaleNeuralODE</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">MultiScaleNeuralODE(args...; kwargs...)</code></pre><p>Same arguments as <a href="#DeepEquilibriumNetworks.MultiScaleDeepEquilibriumNetwork"><code>MultiScaleDeepEquilibriumNetwork</code></a> but sets <code>problem_type</code> to <code>ODEProblem{false}</code>.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/7bf31270c84f2118261d17ae5ff1446c79d55bcd/src/layers.jl#L358-L363">source</a></section></article><h2 id="Solution"><a class="docs-heading-anchor" href="#Solution">Solution</a><a id="Solution-1"></a><a class="docs-heading-anchor-permalink" href="#Solution" title="Permalink"></a></h2><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="DeepEquilibriumNetworks.DeepEquilibriumSolution" href="#DeepEquilibriumNetworks.DeepEquilibriumSolution"><code>DeepEquilibriumNetworks.DeepEquilibriumSolution</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">DeepEquilibriumSolution(z_star, u₀, residual, jacobian_loss, nfe, solution)</code></pre><p>Stores the solution of a DeepEquilibriumNetwork and its variants.</p><p><strong>Fields</strong></p><ul><li><code>z_star</code>: Steady-State or the value reached due to maxiters</li><li><code>u0</code>: Initial Condition</li><li><code>residual</code>: Difference of the <span>$z^*$</span> and <span>$f(z^*, x)$</span></li><li><code>jacobian_loss</code>: Jacobian Stabilization Loss (see individual networks to see how it can be computed)</li><li><code>nfe</code>: Number of Function Evaluations</li><li><code>original</code>: Original Internal Solution</li></ul></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/DeepEquilibriumNetworks.jl/blob/7bf31270c84f2118261d17ae5ff1446c79d55bcd/src/layers.jl#L1-L15">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../tutorials/reduced_dim_deq/">« Modelling Equilibrium Models with Reduced State Size</a><a class="docs-footer-nextpage" href="../references/">References »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="auto">Automatic (OS)</option><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.4.0 on <span class="colophon-date" title="Wednesday 1 May 2024 06:30">Wednesday 1 May 2024</span>. Using Julia version 1.10.3.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>