build based on 07873dc

Author: Documenter.jl

dev/.documenter-siteinfo.json

@@ -1 +1 @@
-{"documenter":{"julia_version":"1.12.1","generation_timestamp":"2025-10-25T19:17:39","documenter_version":"1.15.0"}}
+{"documenter":{"julia_version":"1.12.1","generation_timestamp":"2025-10-25T19:22:50","documenter_version":"1.15.0"}}

dev/index.html

@@ -5,7 +5,7 @@
 (4, 3)
 
 julia> rff(rand(2, 3, 5)) |> size # extra batch dim
-(4, 3, 5)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/1c1a0035343c127eed86c5c15d823e3728d46423/src/RandomFeatureMaps.jl#L78-L96">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="RandomFeatureMaps.RandomOrientationFeatures" href="#RandomFeatureMaps.RandomOrientationFeatures"><code>RandomFeatureMaps.RandomOrientationFeatures</code></a> — <span class="docstring-category">Type</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">RandomOrientationFeatures</code></pre><p>Holds two random matrices which are used to embed rigid transformations.</p><p>This type has no trainable parameters.</p><p><strong>Methods</strong></p><ul><li><code>(::RandomOrientationFeatures)(rigid1, rigid2)</code>: returns the distances between the corresponding</li></ul><p>rigid transformations, embedded using the two random matrices of the random orientation features.</p><ul><li><code>(::RandomOrientationFeatures)(rigid1, rigid2; dims::Int)</code>: unsqueezes batch dimension <code>dim+1</code></li></ul><p>of <code>rigid1</code> and <code>dim</code> of <code>rigid2</code> to broadcast the <code>rof</code> call and produce a pairwise map.</p><ul><li><code>(::RandomOrientationFeatures)(rigid1, rigid2, graph::GraphNeuralNetworks.GNNGraph)</code>: similar to</li></ul><p>the first method, but takes two sets rigid transformations of equal size and unrolls a graph to get the pairs of rigid transformations. Equivalent to the second method (with broadcasted dimensions flattened) when the graph is complete.</p><p>Each of these have single rigid argument methods for when <code>rigid1 == rigid2</code>, i.e. <code>rof(rigid)</code></p><p><strong>Examples</strong></p><pre><code class="language-julia-repl hljs">julia&gt; rof = RandomOrientationFeatures(10, 0.1f0);
+(4, 3, 5)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/07873dc9d18ac72f09d77d554879e7b9f7a7c981/src/RandomFeatureMaps.jl#L78-L96">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="RandomFeatureMaps.RandomOrientationFeatures" href="#RandomFeatureMaps.RandomOrientationFeatures"><code>RandomFeatureMaps.RandomOrientationFeatures</code></a> — <span class="docstring-category">Type</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">RandomOrientationFeatures</code></pre><p>Holds two random matrices which are used to embed rigid transformations.</p><p>This type has no trainable parameters.</p><p><strong>Methods</strong></p><ul><li><code>(::RandomOrientationFeatures)(rigid1, rigid2)</code>: returns the distances between the corresponding</li></ul><p>rigid transformations, embedded using the two random matrices of the random orientation features.</p><ul><li><code>(::RandomOrientationFeatures)(rigid1, rigid2; dims::Int)</code>: unsqueezes batch dimension <code>dim+1</code></li></ul><p>of <code>rigid1</code> and <code>dim</code> of <code>rigid2</code> to broadcast the <code>rof</code> call and produce a pairwise map.</p><ul><li><code>(::RandomOrientationFeatures)(rigid1, rigid2, graph::GraphNeuralNetworks.GNNGraph)</code>: similar to</li></ul><p>the first method, but takes two sets rigid transformations of equal size and unrolls a graph to get the pairs of rigid transformations. Equivalent to the second method (with broadcasted dimensions flattened) when the graph is complete.</p><p>Each of these have single rigid argument methods for when <code>rigid1 == rigid2</code>, i.e. <code>rof(rigid)</code></p><p><strong>Examples</strong></p><pre><code class="language-julia-repl hljs">julia&gt; rof = RandomOrientationFeatures(10, 0.1f0);
 
 julia&gt; rigid = rand_rigid(Float32, (4, 3));
 
@@ -27,16 +27,16 @@
 julia&gt; rigid = rand_rigid(Float32, (2,));
 
 julia&gt; rof(rigid, graph) |&gt; size
-(10, 3)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/1c1a0035343c127eed86c5c15d823e3728d46423/src/RandomFeatureMaps.jl#L125-L174">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="RandomFeatureMaps.RandomOrientationFeatures-Tuple{Integer, AbstractFloat}" href="#RandomFeatureMaps.RandomOrientationFeatures-Tuple{Integer, AbstractFloat}"><code>RandomFeatureMaps.RandomOrientationFeatures</code></a> — <span class="docstring-category">Method</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">RandomOrientationFeatures(m, σ)</code></pre><p>Creates a <code>RandomOrientationFeatures</code> instance, mapping to <code>m</code> features.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/1c1a0035343c127eed86c5c15d823e3728d46423/src/RandomFeatureMaps.jl#L182-L186">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="RandomFeatureMaps.RandomTriangleFeatures" href="#RandomFeatureMaps.RandomTriangleFeatures"><code>RandomFeatureMaps.RandomTriangleFeatures</code></a> — <span class="docstring-category">Type</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">RandomFourierFeatures(n =&gt; m, σ)</code></pre><p>Maps <code>n</code>-dimensional data and projects it to <code>m</code>-dimensional random fourier features.</p><p>This type has no trainable parameters.</p><p><strong>Examples</strong></p><pre><code class="language-julia-repl hljs">julia&gt; rff = RandomFourierFeatures(2 =&gt; 4, 1.0); # maps 2D data to 4D
+(10, 3)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/07873dc9d18ac72f09d77d554879e7b9f7a7c981/src/RandomFeatureMaps.jl#L125-L174">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="RandomFeatureMaps.RandomOrientationFeatures-Tuple{Integer, AbstractFloat}" href="#RandomFeatureMaps.RandomOrientationFeatures-Tuple{Integer, AbstractFloat}"><code>RandomFeatureMaps.RandomOrientationFeatures</code></a> — <span class="docstring-category">Method</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">RandomOrientationFeatures(m, σ)</code></pre><p>Creates a <code>RandomOrientationFeatures</code> instance, mapping to <code>m</code> features.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/07873dc9d18ac72f09d77d554879e7b9f7a7c981/src/RandomFeatureMaps.jl#L182-L186">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="RandomFeatureMaps.RandomTriangleFeatures" href="#RandomFeatureMaps.RandomTriangleFeatures"><code>RandomFeatureMaps.RandomTriangleFeatures</code></a> — <span class="docstring-category">Type</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">RandomFourierFeatures(n =&gt; m, σ)</code></pre><p>Maps <code>n</code>-dimensional data and projects it to <code>m</code>-dimensional random fourier features.</p><p>This type has no trainable parameters.</p><p><strong>Examples</strong></p><pre><code class="language-julia-repl hljs">julia&gt; rff = RandomFourierFeatures(2 =&gt; 4, 1.0); # maps 2D data to 4D
 
 julia&gt; rff(rand(2, 3)) |&gt; size # 3 samples
 (4, 3)
 
 julia&gt; rff(rand(2, 3, 5)) |&gt; size # extra batch dim
-(4, 3, 5)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/1c1a0035343c127eed86c5c15d823e3728d46423/src/RandomFeatureMaps.jl#L32-L50">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="RandomFeatureMaps.TrainableRBF" href="#RandomFeatureMaps.TrainableRBF"><code>RandomFeatureMaps.TrainableRBF</code></a> — <span class="docstring-category">Type</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">TrainableRBF(n =&gt; m, [σ])</code></pre><p>Maps <code>n</code>-dimensional data to <code>m</code> Gaussian radial basis responses with trainable centers and isotropic radii per basis.</p><p>The optional <code>σ</code> controls the initialization scale and element type.</p><p>Examples</p><pre><code class="language-julia-repl hljs">julia&gt; rbf = TrainableRBF(2 =&gt; 4, 1.0); # 4 bases in 2D
+(4, 3, 5)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/07873dc9d18ac72f09d77d554879e7b9f7a7c981/src/RandomFeatureMaps.jl#L32-L50">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="RandomFeatureMaps.TrainableRBF" href="#RandomFeatureMaps.TrainableRBF"><code>RandomFeatureMaps.TrainableRBF</code></a> — <span class="docstring-category">Type</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">TrainableRBF(n =&gt; m, [σ])</code></pre><p>Maps <code>n</code>-dimensional data to <code>m</code> Gaussian radial basis responses with trainable centers and isotropic radii per basis.</p><p>The optional <code>σ</code> controls the initialization scale and element type.</p><p>Examples</p><pre><code class="language-julia-repl hljs">julia&gt; rbf = TrainableRBF(2 =&gt; 4, 1.0); # 4 bases in 2D
 
 julia&gt; rbf(rand(2, 3)) |&gt; size # 3 samples
 (4, 3)
 
 julia&gt; rbf(rand(2, 3, 5)) |&gt; size # extra batch dim
-(4, 3, 5)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/1c1a0035343c127eed86c5c15d823e3728d46423/src/RandomFeatureMaps.jl#L225-L244">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="RandomFeatureMaps.get_rigid-Tuple{AbstractArray, AbstractArray}" href="#RandomFeatureMaps.get_rigid-Tuple{AbstractArray, AbstractArray}"><code>RandomFeatureMaps.get_rigid</code></a> — <span class="docstring-category">Method</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">get_rigid(R::AbstractArray, t::AbstractArray)</code></pre><p>Converts a rotation <code>R</code> and translation <code>t</code> to a <code>BatchedTransformations.Rigid</code>, designed to handle batch dimensions.</p><p>The transformation gets applied according to <code>NNlib.batched_mul(R,  x) .+ t</code></p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/1c1a0035343c127eed86c5c15d823e3728d46423/src/RandomFeatureMaps.jl#L206-L213">source</a></section></article></article><nav class="docs-footer"><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><option value="catppuccin-latte">catppuccin-latte</option><option value="catppuccin-frappe">catppuccin-frappe</option><option value="catppuccin-macchiato">catppuccin-macchiato</option><option value="catppuccin-mocha">catppuccin-mocha</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.15.0 on <span class="colophon-date" title="Saturday 25 October 2025 19:17">Saturday 25 October 2025</span>. Using Julia version 1.12.1.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
+(4, 3, 5)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/07873dc9d18ac72f09d77d554879e7b9f7a7c981/src/RandomFeatureMaps.jl#L225-L244">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="RandomFeatureMaps.get_rigid-Tuple{AbstractArray, AbstractArray}" href="#RandomFeatureMaps.get_rigid-Tuple{AbstractArray, AbstractArray}"><code>RandomFeatureMaps.get_rigid</code></a> — <span class="docstring-category">Method</span><span class="is-flex-grow-1 docstring-article-toggle-button" title="Collapse docstring"></span></header><section><div><pre><code class="language-julia hljs">get_rigid(R::AbstractArray, t::AbstractArray)</code></pre><p>Converts a rotation <code>R</code> and translation <code>t</code> to a <code>BatchedTransformations.Rigid</code>, designed to handle batch dimensions.</p><p>The transformation gets applied according to <code>NNlib.batched_mul(R,  x) .+ t</code></p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/MurrellGroup/RandomFeatureMaps.jl/blob/07873dc9d18ac72f09d77d554879e7b9f7a7c981/src/RandomFeatureMaps.jl#L206-L213">source</a></section></article></article><nav class="docs-footer"><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><option value="catppuccin-latte">catppuccin-latte</option><option value="catppuccin-frappe">catppuccin-frappe</option><option value="catppuccin-macchiato">catppuccin-macchiato</option><option value="catppuccin-mocha">catppuccin-mocha</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.15.0 on <span class="colophon-date" title="Saturday 25 October 2025 19:22">Saturday 25 October 2025</span>. Using Julia version 1.12.1.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>