build based on b1e5669

dev/api/basic/index.html

@@ -9,7 +9,7 @@
 
 julia> dotdec(g, rand(2, 5))
 1×6 Matrix{Float64}:
- 0.345098  0.458305  0.106353  0.345098  0.458305  0.106353</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/3f3ce2ffecb529d3d0fe0fab5fd8362c01bd0cd9/src/layers/basic.jl#L193-L215">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="GraphNeuralNetworks.GNNChain" href="#GraphNeuralNetworks.GNNChain"><code>GraphNeuralNetworks.GNNChain</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">GNNChain(layers...)
+ 0.345098  0.458305  0.106353  0.345098  0.458305  0.106353</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/b1e56691455b4851b854509786851b3742bb10af/src/layers/basic.jl#L193-L215">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="GraphNeuralNetworks.GNNChain" href="#GraphNeuralNetworks.GNNChain"><code>GraphNeuralNetworks.GNNChain</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">GNNChain(layers...)
 GNNChain(name = layer, ...)</code></pre><p>Collects multiple layers / functions to be called in sequence on given input graph and input node features. </p><p>It allows to compose layers in a sequential fashion as <code>Flux.Chain</code> does, propagating the output of each layer to the next one. In addition, <code>GNNChain</code> handles the input graph as well, providing it  as a first argument only to layers subtyping the <a href="#GraphNeuralNetworks.GNNLayer"><code>GNNLayer</code></a> abstract type. </p><p><code>GNNChain</code> supports indexing and slicing, <code>m[2]</code> or <code>m[1:end-1]</code>, and if names are given, <code>m[:name] == m[1]</code> etc.</p><p><strong>Examples</strong></p><pre><code class="language-julia-repl hljs">julia&gt; using Flux, GraphNeuralNetworks
 
 julia&gt; m = GNNChain(GCNConv(2=&gt;5), 
@@ -41,7 +41,7 @@
  2.90053  2.90053  2.90053  2.90053  2.90053  2.90053
 
 julia&gt; m2[:enc](g, x) == m(g, x)
-true</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/3f3ce2ffecb529d3d0fe0fab5fd8362c01bd0cd9/src/layers/basic.jl#L60-L111">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="GraphNeuralNetworks.GNNLayer" href="#GraphNeuralNetworks.GNNLayer"><code>GraphNeuralNetworks.GNNLayer</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">abstract type GNNLayer end</code></pre><p>An abstract type from which graph neural network layers are derived.</p><p>See also <a href="#GraphNeuralNetworks.GNNChain"><code>GNNChain</code></a>.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/3f3ce2ffecb529d3d0fe0fab5fd8362c01bd0cd9/src/layers/basic.jl#L1-L7">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="GraphNeuralNetworks.WithGraph" href="#GraphNeuralNetworks.WithGraph"><code>GraphNeuralNetworks.WithGraph</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">WithGraph(model, g::GNNGraph; traingraph=false)</code></pre><p>A type wrapping the <code>model</code> and tying it to the graph <code>g</code>. In the forward pass, can only take feature arrays as inputs, returning <code>model(g, x...; kws...)</code>.</p><p>If <code>traingraph=false</code>, the graph&#39;s parameters won&#39;t be part of  the <code>trainable</code> parameters in the gradient updates.</p><p><strong>Examples</strong></p><pre><code class="language-julia hljs">g = GNNGraph([1,2,3], [2,3,1])
+true</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/b1e56691455b4851b854509786851b3742bb10af/src/layers/basic.jl#L60-L111">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="GraphNeuralNetworks.GNNLayer" href="#GraphNeuralNetworks.GNNLayer"><code>GraphNeuralNetworks.GNNLayer</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">abstract type GNNLayer end</code></pre><p>An abstract type from which graph neural network layers are derived.</p><p>See also <a href="#GraphNeuralNetworks.GNNChain"><code>GNNChain</code></a>.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/b1e56691455b4851b854509786851b3742bb10af/src/layers/basic.jl#L1-L7">source</a></section></article><article class="docstring"><header><a class="docstring-binding" id="GraphNeuralNetworks.WithGraph" href="#GraphNeuralNetworks.WithGraph"><code>GraphNeuralNetworks.WithGraph</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">WithGraph(model, g::GNNGraph; traingraph=false)</code></pre><p>A type wrapping the <code>model</code> and tying it to the graph <code>g</code>. In the forward pass, can only take feature arrays as inputs, returning <code>model(g, x...; kws...)</code>.</p><p>If <code>traingraph=false</code>, the graph&#39;s parameters won&#39;t be part of  the <code>trainable</code> parameters in the gradient updates.</p><p><strong>Examples</strong></p><pre><code class="language-julia hljs">g = GNNGraph([1,2,3], [2,3,1])
 x = rand(Float32, 2, 3)
 model = SAGEConv(2 =&gt; 3)
 wg = WithGraph(model, g)
@@ -51,4 +51,4 @@
 g2 = GNNGraph([1,1,2,3], [2,4,1,1])
 x2 = rand(Float32, 2, 4)
 # WithGraph will ignore the internal graph if fed with a new one. 
-@assert wg(g2, x2) == model(g2, x2)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/3f3ce2ffecb529d3d0fe0fab5fd8362c01bd0cd9/src/layers/basic.jl#L20-L45">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../gnngraph/">« GNNGraph</a><a class="docs-footer-nextpage" href="../conv/">Convolutional Layers »</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="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 0.27.25 on <span class="colophon-date" title="Sunday 21 July 2024 10:31">Sunday 21 July 2024</span>. Using Julia version 1.9.1.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
+@assert wg(g2, x2) == model(g2, x2)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/b1e56691455b4851b854509786851b3742bb10af/src/layers/basic.jl#L20-L45">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../gnngraph/">« GNNGraph</a><a class="docs-footer-nextpage" href="../conv/">Convolutional Layers »</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="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 0.27.25 on <span class="colophon-date" title="Sunday 21 July 2024 10:39">Sunday 21 July 2024</span>. Using Julia version 1.9.1.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>