build based on 1fd44b7

JuliaGNI · Sep 20, 2023 · cc5fa0a · cc5fa0a
1 parent cfdc1fa
commit cc5fa0a
Show file tree

Hide file tree

Showing 34 changed files with 131 additions and 25 deletions.
diff --git a/latest/Optimizer/index.html b/latest/Optimizer/index.html
diff --git a/latest/architectures/sympnet/index.html b/latest/architectures/sympnet/index.html
diff --git a/latest/arrays/stiefel_lie_alg_horizontal/index.html b/latest/arrays/stiefel_lie_alg_horizontal/index.html
diff --git a/latest/data_loader/data_loader/index.html b/latest/data_loader/data_loader/index.html
@@ -0,0 +1,2 @@
+<!DOCTYPE html>
+<html lang="en"><head><meta charset="UTF-8"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><title>Routines · GeometricMachineLearning.jl</title><script data-outdated-warner src="../../assets/warner.js"></script><link rel="canonical" href="https://juliagni.github.io/GeometricMachineLearning.jl/data_loader/data_loader/"/><link href="https://cdnjs.cloudflare.com/ajax/libs/lato-font/3.0.0/css/lato-font.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/juliamono/0.045/juliamono.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/fontawesome.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/solid.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/brands.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.13.24/katex.min.css" rel="stylesheet" type="text/css"/><script>documenterBaseURL="../.."</script><script src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.6/require.min.js" data-main="../../assets/documenter.js"></script><script src="../../siteinfo.js"></script><script src="../../../versions.js"></script><link class="docs-theme-link" rel="stylesheet" type="text/css" href="../../assets/themes/documenter-dark.css" data-theme-name="documenter-dark" data-theme-primary-dark/><link class="docs-theme-link" rel="stylesheet" type="text/css" href="../../assets/themes/documenter-light.css" data-theme-name="documenter-light" data-theme-primary/><script src="../../assets/themeswap.js"></script></head><body><div id="documenter"><nav class="docs-sidebar"><div class="docs-package-name"><span class="docs-autofit"><a href="../../">GeometricMachineLearning.jl</a></span></div><form class="docs-search" action="../../search/"><input class="docs-search-query" id="documenter-search-query" name="q" type="text" placeholder="Search docs"/></form><ul class="docs-menu"><li><a class="tocitem" href="../../">Home</a></li><li><span class="tocitem">Architectures</span><ul><li><a class="tocitem" href="../../architectures/sympnet/">SympNet</a></li></ul></li><li><span class="tocitem">Manifolds</span><ul><li><a class="tocitem" href="../../manifolds/homogeneous_spaces/">Homogeneous Spaces</a></li><li><a class="tocitem" href="../../manifolds/stiefel_manifold/">Stiefel</a></li><li><a class="tocitem" href="../../manifolds/grassmann_manifold/">Grassmann</a></li></ul></li><li><span class="tocitem">Arrays</span><ul><li><a class="tocitem" href="../../arrays/stiefel_lie_alg_horizontal/">Global Tangent Space</a></li></ul></li><li><a class="tocitem" href="../../Optimizer/">Optimizer Framework</a></li><li><span class="tocitem">Optimizer Functions</span><ul><li><a class="tocitem" href="../../optimizers/manifold_related/horizontal_lift/">Horizontal Lift</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/global_sections/">Global Sections</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/retractions/">Retractions</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/geodesic/">Geodesic Retraction</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/cayley/">Cayley Retraction</a></li><li><a class="tocitem" href="../../optimizers/adam_optimizer/">Adam Optimizer</a></li></ul></li><li><span class="tocitem">Special Neural Network Layers</span><ul><li><a class="tocitem" href="../../layers/attention_layer/">Attention</a></li><li><a class="tocitem" href="../../layers/multihead_attention_layer/">Multihead Attention</a></li></ul></li><li><span class="tocitem">Data Loader</span><ul><li class="is-active"><a class="tocitem" href>Routines</a></li><li><a class="tocitem" href="../snapshot_matrix/">Snapshot matrix</a></li></ul></li><li><span class="tocitem">Reduced Order Modelling</span><ul><li><a class="tocitem" href="../../reduced_order_modeling/autoencoder/">POD and Autoencoders</a></li><li><a class="tocitem" href="../../reduced_order_modeling/symplectic_autoencoder/">PSD and Symplectic Autoencoders</a></li><li><a class="tocitem" href="../../reduced_order_modeling/kolmogorov_n_width/">Kolmogorov n-width</a></li></ul></li><li><span class="tocitem">Tutorials</span><ul><li><a class="tocitem" href="../../tutorials/mnist_tutorial/">MNIST</a></li></ul></li><li><a class="tocitem" href="../../library/">Library</a></li></ul><div class="docs-version-selector field has-addons"><div class="control"><span class="docs-label button is-static is-size-7">Version</span></div><div class="docs-selector control is-expanded"><div class="select is-fullwidth is-size-7"><select id="documenter-version-selector"></select></div></div></div></nav><div class="docs-main"><header class="docs-navbar"><nav class="breadcrumb"><ul class="is-hidden-mobile"><li><a class="is-disabled">Data Loader</a></li><li class="is-active"><a href>Routines</a></li></ul><ul class="is-hidden-tablet"><li class="is-active"><a href>Routines</a></li></ul></nav><div class="docs-right"><a class="docs-edit-link" href="https://github.com/JuliaGNI/GeometricMachineLearning.jl/blob/main/docs/src/data_loader/data_loader.md#L" title="Edit on GitHub"><span class="docs-icon fab"></span><span class="docs-label is-hidden-touch">Edit on GitHub</span></a><a class="docs-settings-button fas fa-cog" id="documenter-settings-button" href="#" title="Settings"></a><a class="docs-sidebar-button fa fa-bars is-hidden-desktop" id="documenter-sidebar-button" href="#"></a></div></header><article class="content" id="documenter-page"><h1 id="Data-Loader"><a class="docs-heading-anchor" href="#Data-Loader">Data Loader</a><a id="Data-Loader-1"></a><a class="docs-heading-anchor-permalink" href="#Data-Loader" title="Permalink"></a></h1><p><code>GeometricMachineLearning</code> provides flexible routines to load and manage data for training neural networks.  <code>DataLoader</code> has several constructors: </p><ol><li><p>If provided with a tensor, then it assumes the first axis is the system dimension, the second axis is the dimension of the parameter space, and the third axis gives the time evolution of the system. </p></li><li><p>If provided with a tensor and a vector, it assumes the data are related to a classification task. </p></li></ol></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../../layers/multihead_attention_layer/">« Multihead Attention</a><a class="docs-footer-nextpage" href="../snapshot_matrix/">Snapshot matrix »</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="Wednesday 20 September 2023 07:24">Wednesday 20 September 2023</span>. Using Julia version 1.9.3.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
diff --git a/latest/data_loader/snapshot_matrix/index.html b/latest/data_loader/snapshot_matrix/index.html
@@ -0,0 +1,8 @@
+<!DOCTYPE html>
+<html lang="en"><head><meta charset="UTF-8"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><title>Snapshot matrix · GeometricMachineLearning.jl</title><script data-outdated-warner src="../../assets/warner.js"></script><link rel="canonical" href="https://juliagni.github.io/GeometricMachineLearning.jl/data_loader/snapshot_matrix/"/><link href="https://cdnjs.cloudflare.com/ajax/libs/lato-font/3.0.0/css/lato-font.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/juliamono/0.045/juliamono.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/fontawesome.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/solid.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/brands.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.13.24/katex.min.css" rel="stylesheet" type="text/css"/><script>documenterBaseURL="../.."</script><script src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.6/require.min.js" data-main="../../assets/documenter.js"></script><script src="../../siteinfo.js"></script><script src="../../../versions.js"></script><link class="docs-theme-link" rel="stylesheet" type="text/css" href="../../assets/themes/documenter-dark.css" data-theme-name="documenter-dark" data-theme-primary-dark/><link class="docs-theme-link" rel="stylesheet" type="text/css" href="../../assets/themes/documenter-light.css" data-theme-name="documenter-light" data-theme-primary/><script src="../../assets/themeswap.js"></script></head><body><div id="documenter"><nav class="docs-sidebar"><div class="docs-package-name"><span class="docs-autofit"><a href="../../">GeometricMachineLearning.jl</a></span></div><form class="docs-search" action="../../search/"><input class="docs-search-query" id="documenter-search-query" name="q" type="text" placeholder="Search docs"/></form><ul class="docs-menu"><li><a class="tocitem" href="../../">Home</a></li><li><span class="tocitem">Architectures</span><ul><li><a class="tocitem" href="../../architectures/sympnet/">SympNet</a></li></ul></li><li><span class="tocitem">Manifolds</span><ul><li><a class="tocitem" href="../../manifolds/homogeneous_spaces/">Homogeneous Spaces</a></li><li><a class="tocitem" href="../../manifolds/stiefel_manifold/">Stiefel</a></li><li><a class="tocitem" href="../../manifolds/grassmann_manifold/">Grassmann</a></li></ul></li><li><span class="tocitem">Arrays</span><ul><li><a class="tocitem" href="../../arrays/stiefel_lie_alg_horizontal/">Global Tangent Space</a></li></ul></li><li><a class="tocitem" href="../../Optimizer/">Optimizer Framework</a></li><li><span class="tocitem">Optimizer Functions</span><ul><li><a class="tocitem" href="../../optimizers/manifold_related/horizontal_lift/">Horizontal Lift</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/global_sections/">Global Sections</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/retractions/">Retractions</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/geodesic/">Geodesic Retraction</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/cayley/">Cayley Retraction</a></li><li><a class="tocitem" href="../../optimizers/adam_optimizer/">Adam Optimizer</a></li></ul></li><li><span class="tocitem">Special Neural Network Layers</span><ul><li><a class="tocitem" href="../../layers/attention_layer/">Attention</a></li><li><a class="tocitem" href="../../layers/multihead_attention_layer/">Multihead Attention</a></li></ul></li><li><span class="tocitem">Data Loader</span><ul><li><a class="tocitem" href="../data_loader/">Routines</a></li><li class="is-active"><a class="tocitem" href>Snapshot matrix</a></li></ul></li><li><span class="tocitem">Reduced Order Modelling</span><ul><li><a class="tocitem" href="../../reduced_order_modeling/autoencoder/">POD and Autoencoders</a></li><li><a class="tocitem" href="../../reduced_order_modeling/symplectic_autoencoder/">PSD and Symplectic Autoencoders</a></li><li><a class="tocitem" href="../../reduced_order_modeling/kolmogorov_n_width/">Kolmogorov n-width</a></li></ul></li><li><span class="tocitem">Tutorials</span><ul><li><a class="tocitem" href="../../tutorials/mnist_tutorial/">MNIST</a></li></ul></li><li><a class="tocitem" href="../../library/">Library</a></li></ul><div class="docs-version-selector field has-addons"><div class="control"><span class="docs-label button is-static is-size-7">Version</span></div><div class="docs-selector control is-expanded"><div class="select is-fullwidth is-size-7"><select id="documenter-version-selector"></select></div></div></div></nav><div class="docs-main"><header class="docs-navbar"><nav class="breadcrumb"><ul class="is-hidden-mobile"><li><a class="is-disabled">Data Loader</a></li><li class="is-active"><a href>Snapshot matrix</a></li></ul><ul class="is-hidden-tablet"><li class="is-active"><a href>Snapshot matrix</a></li></ul></nav><div class="docs-right"><a class="docs-edit-link" href="https://github.com/JuliaGNI/GeometricMachineLearning.jl/blob/main/docs/src/data_loader/snapshot_matrix.md#L" title="Edit on GitHub"><span class="docs-icon fab"></span><span class="docs-label is-hidden-touch">Edit on GitHub</span></a><a class="docs-settings-button fas fa-cog" id="documenter-settings-button" href="#" title="Settings"></a><a class="docs-sidebar-button fa fa-bars is-hidden-desktop" id="documenter-sidebar-button" href="#"></a></div></header><article class="content" id="documenter-page"><h1 id="Snapshot-matrix"><a class="docs-heading-anchor" href="#Snapshot-matrix">Snapshot matrix</a><a id="Snapshot-matrix-1"></a><a class="docs-heading-anchor-permalink" href="#Snapshot-matrix" title="Permalink"></a></h1><p>The snapshot matrix stores solutions of the high-dimensional ODE (obtained from discretizing a PDE). This is then used to construct <a href="../../reduced_order_modeling/autoencoder/">reduced bases</a> in a data-driven way. So (for a single parameter<sup class="footnote-reference"><a id="citeref-1" href="#footnote-1">[1]</a></sup>) the snapshot matrix takes the following form: </p><p class="math-container">\[M = \left[\begin{array}{c:c:c:c}
+\hat{u}_1(t_0) &amp;  \hat{u}_1(t_1) &amp; \quad\ldots\quad &amp; \hat{u}_1(t_f) \\
+\hat{u}_2(t_0) &amp;  \hat{u}_2(t_1) &amp; \ldots &amp; \hat{u}_2(t_f) \\
+\hat{u}_3(t_0) &amp;  \hat{u}_3(t_1) &amp; \ldots &amp; \hat{u}_3(t_f) \\
+\ldots &amp;  \ldots &amp; \ldots &amp; \ldots \\
+\hat{u}_{2N}(t_0) &amp;  \hat{u}_{2N}(t_1) &amp; \ldots &amp; \hat{u}_{2N}(t_f) \\
+\end{array}\right].\]</p><section class="footnotes is-size-7"><ul><li class="footnote" id="footnote-1"><a class="tag is-link" href="#citeref-1">1</a>If we deal with a parametrized PDE then there are <strong>two stages</strong> at which the snapshot matrix has to be processed: the offline stage and the online stage. </li></ul></section></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../data_loader/">« Routines</a><a class="docs-footer-nextpage" href="../../reduced_order_modeling/autoencoder/">POD and Autoencoders »</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="Wednesday 20 September 2023 07:24">Wednesday 20 September 2023</span>. Using Julia version 1.9.3.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
diff --git a/latest/images/adam_optimizer.png b/latest/images/adam_optimizer.png
diff --git a/latest/images/adam_optimizer.tex b/latest/images/adam_optimizer.tex
@@ -24,7 +24,7 @@
     \coordinate[right of=R3, xshift=.5cm] (addition);
     \node[fit=(R2)(cache)(R3)(R4)(addition),draw, ultra thick, rounded corners, label=below:$\mathtt{optimization\_step(o, ::}\mathbb{R}^N\mathtt{,::}\mathbb{R}^N\mathtt{)}$] (optimization_step) {};
 
-    \draw[->] (R2) -- (R3) node[pos=.5, sloped, below] {Adam};
+    \draw[->] (R2) -- (cache) node[pos=.5, sloped, below] {Adam};
     \draw[->] (cache) -- (R3) node[pos=.5, sloped, above] {Adam};
     \draw[->] (R3) -- (R4) node[pos=.5, right] {Addition};
     \draw[->, mgreen] (R1) -- (R2) node[pos=.5, left] {\color{mgreen}AD};

diff --git a/latest/images/general_optimization.pdf b/latest/images/general_optimization.pdf
diff --git a/latest/images/general_optimization.png b/latest/images/general_optimization.png
diff --git a/latest/images/general_optimization.tex b/latest/images/general_optimization.tex
@@ -18,7 +18,7 @@
 
     \draw[->] (TYM) -- (ghorY) node[pos=.5, left] {$\Omega$};
     \draw[->, mred] (ghorY) -- (ghor);
-    \draw[->] (ghor) -- (ghor2) node[pos=.5, sloped, below] {Adam};
+    \draw[->] (ghor) -- (cache) node[pos=.5, sloped, below] {Adam};
     \draw[->] (cache) -- (ghor2) node[pos=.5, sloped, above] {Adam};
     \draw[->] (ghor2) -- (M) node[pos=.5, right] {Retraction};
 \end{tikzpicture}

diff --git a/latest/images/general_optimization_with_boundary.png b/latest/images/general_optimization_with_boundary.png
diff --git a/latest/images/general_optimization_with_boundary.tex b/latest/images/general_optimization_with_boundary.tex
@@ -31,7 +31,7 @@
 
     \draw[->] (TYM) -- (ghorY) node[pos=.5, left] {$\Omega$};
     \draw[->, mred] (ghorY) -- (ghor);
-    \draw[->] (ghor) -- (ghor2) node[pos=.5, sloped, below] {Adam};
+    \draw[->] (ghor) -- (cache) node[pos=.5, sloped, below] {Adam};
     \draw[->] (cache) -- (ghor2) node[pos=.5, sloped, above] {Adam};
     \draw[->] (ghor2) -- (M) node[pos=.5, right] {Retraction};
     \draw[->, mgreen] (M2) -- (Euc) node[pos=.5, left] {\color{mgreen}AD};

diff --git a/latest/images/mha.png b/latest/images/mha.png
diff --git a/latest/images/solution_manifold_2.png b/latest/images/solution_manifold_2.png
diff --git a/latest/images/symplectic_autoencoder.png b/latest/images/symplectic_autoencoder.png
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		<!DOCTYPE html>
		<html lang="en"><head><meta charset="UTF-8"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><title>Routines · GeometricMachineLearning.jl</title><script data-outdated-warner src="../../assets/warner.js"></script><link rel="canonical" href="https://juliagni.github.io/GeometricMachineLearning.jl/data_loader/data_loader/"/><link href="https://cdnjs.cloudflare.com/ajax/libs/lato-font/3.0.0/css/lato-font.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/juliamono/0.045/juliamono.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/fontawesome.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/solid.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/brands.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.13.24/katex.min.css" rel="stylesheet" type="text/css"/><script>documenterBaseURL="../.."</script><script src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.6/require.min.js" data-main="../../assets/documenter.js"></script><script src="../../siteinfo.js"></script><script src="../../../versions.js"></script><link class="docs-theme-link" rel="stylesheet" type="text/css" href="../../assets/themes/documenter-dark.css" data-theme-name="documenter-dark" data-theme-primary-dark/><link class="docs-theme-link" rel="stylesheet" type="text/css" href="../../assets/themes/documenter-light.css" data-theme-name="documenter-light" data-theme-primary/><script src="../../assets/themeswap.js"></script></head><body><div id="documenter"><nav class="docs-sidebar"><div class="docs-package-name"><span class="docs-autofit"><a href="../../">GeometricMachineLearning.jl</a></span></div><form class="docs-search" action="../../search/"><input class="docs-search-query" id="documenter-search-query" name="q" type="text" placeholder="Search docs"/></form><ul class="docs-menu"><li><a class="tocitem" href="../../">Home</a></li><li><span class="tocitem">Architectures</span><ul><li><a class="tocitem" href="../../architectures/sympnet/">SympNet</a></li></ul></li><li><span class="tocitem">Manifolds</span><ul><li><a class="tocitem" href="../../manifolds/homogeneous_spaces/">Homogeneous Spaces</a></li><li><a class="tocitem" href="../../manifolds/stiefel_manifold/">Stiefel</a></li><li><a class="tocitem" href="../../manifolds/grassmann_manifold/">Grassmann</a></li></ul></li><li><span class="tocitem">Arrays</span><ul><li><a class="tocitem" href="../../arrays/stiefel_lie_alg_horizontal/">Global Tangent Space</a></li></ul></li><li><a class="tocitem" href="../../Optimizer/">Optimizer Framework</a></li><li><span class="tocitem">Optimizer Functions</span><ul><li><a class="tocitem" href="../../optimizers/manifold_related/horizontal_lift/">Horizontal Lift</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/global_sections/">Global Sections</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/retractions/">Retractions</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/geodesic/">Geodesic Retraction</a></li><li><a class="tocitem" href="../../optimizers/manifold_related/cayley/">Cayley Retraction</a></li><li><a class="tocitem" href="../../optimizers/adam_optimizer/">Adam Optimizer</a></li></ul></li><li><span class="tocitem">Special Neural Network Layers</span><ul><li><a class="tocitem" href="../../layers/attention_layer/">Attention</a></li><li><a class="tocitem" href="../../layers/multihead_attention_layer/">Multihead Attention</a></li></ul></li><li><span class="tocitem">Data Loader</span><ul><li class="is-active"><a class="tocitem" href>Routines</a></li><li><a class="tocitem" href="../snapshot_matrix/">Snapshot matrix</a></li></ul></li><li><span class="tocitem">Reduced Order Modelling</span><ul><li><a class="tocitem" href="../../reduced_order_modeling/autoencoder/">POD and Autoencoders</a></li><li><a class="tocitem" href="../../reduced_order_modeling/symplectic_autoencoder/">PSD and Symplectic Autoencoders</a></li><li><a class="tocitem" href="../../reduced_order_modeling/kolmogorov_n_width/">Kolmogorov n-width</a></li></ul></li><li><span class="tocitem">Tutorials</span><ul><li><a class="tocitem" href="../../tutorials/mnist_tutorial/">MNIST</a></li></ul></li><li><a class="tocitem" href="../../library/">Library</a></li></ul><div class="docs-version-selector field has-addons"><div class="control"><span class="docs-label button is-static is-size-7">Version</span></div><div class="docs-selector control is-expanded"><div class="select is-fullwidth is-size-7"><select id="documenter-version-selector"></select></div></div></div></nav><div class="docs-main"><header class="docs-navbar"><nav class="breadcrumb"><ul class="is-hidden-mobile"><li><a class="is-disabled">Data Loader</a></li><li class="is-active"><a href>Routines</a></li></ul><ul class="is-hidden-tablet"><li class="is-active"><a href>Routines</a></li></ul></nav><div class="docs-right"><a class="docs-edit-link" href="https://github.com/JuliaGNI/GeometricMachineLearning.jl/blob/main/docs/src/data_loader/data_loader.md#L" title="Edit on GitHub"><span class="docs-icon fab"></span><span class="docs-label is-hidden-touch">Edit on GitHub</span></a><a class="docs-settings-button fas fa-cog" id="documenter-settings-button" href="#" title="Settings"></a><a class="docs-sidebar-button fa fa-bars is-hidden-desktop" id="documenter-sidebar-button" href="#"></a></div></header><article class="content" id="documenter-page"><h1 id="Data-Loader"><a class="docs-heading-anchor" href="#Data-Loader">Data Loader</a><a id="Data-Loader-1"></a><a class="docs-heading-anchor-permalink" href="#Data-Loader" title="Permalink"></a></h1><p><code>GeometricMachineLearning</code> provides flexible routines to load and manage data for training neural networks. <code>DataLoader</code> has several constructors: </p><ol><li><p>If provided with a tensor, then it assumes the first axis is the system dimension, the second axis is the dimension of the parameter space, and the third axis gives the time evolution of the system. </p></li><li><p>If provided with a tensor and a vector, it assumes the data are related to a classification task. </p></li></ol></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../../layers/multihead_attention_layer/">« Multihead Attention</a><a class="docs-footer-nextpage" href="../snapshot_matrix/">Snapshot matrix »</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="Wednesday 20 September 2023 07:24">Wednesday 20 September 2023</span>. Using Julia version 1.9.3.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>