Deploying to gh-pages from @ 70eab6f 🚀

dataflowr · Jul 11, 2024 · 8727ea9 · 8727ea9
1 parent 966f6ab
commit 8727ea9
Show file tree

Hide file tree

Showing 52 changed files with 126 additions and 126 deletions.
diff --git a/404.html b/404.html
diff --git a/homework/1-mlp-from-scratch/index.html b/homework/1-mlp-from-scratch/index.html
diff --git a/homework/2-CAM-adversarial/index.html b/homework/2-CAM-adversarial/index.html
diff --git a/homework/3-VAE/index.html b/homework/3-VAE/index.html
diff --git a/index.html b/index.html
diff --git a/modules/0-julia-setup/index.html b/modules/0-julia-setup/index.html
@@ -35,7 +35,7 @@ <h2 id=start_documenting ><a href="#start_documenting" class=header-anchor >Star
 <div class=page-foot >
   <div class=copyright >
     <a href="https://github.com/dataflowr/website/tree/master"><b>Edit this page on <img class=github-logo  src="https://unpkg.com/[email protected]/dist/svg/logo-github.svg"></b></a>
-    Last modified: February 23, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>.
+    Last modified: July 11, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>.
   </div>
 </div>
 </div>

diff --git a/modules/0-sotfware-installation/index.html b/modules/0-sotfware-installation/index.html
@@ -37,7 +37,7 @@ <h3 id=tldr ><a href="#tldr" class=header-anchor >tl;dr</a></h3>
 <div class=page-foot >
   <div class=copyright >
     <a href="https://github.com/dataflowr/website/tree/master"><b>Edit this page on <img class=github-logo  src="https://unpkg.com/[email protected]/dist/svg/logo-github.svg"></b></a>
-    Last modified: February 23, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>.
+    Last modified: July 11, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>.
   </div>
 </div>
 </div>

diff --git a/modules/1-intro-general-overview/index.html b/modules/1-intro-general-overview/index.html
diff --git a/modules/10-generative-adversarial-networks/index.html b/modules/10-generative-adversarial-networks/index.html
diff --git a/modules/11a-recurrent-neural-networks-theory/index.html b/modules/11a-recurrent-neural-networks-theory/index.html
diff --git a/modules/11b-recurrent-neural-networks-practice/index.html b/modules/11b-recurrent-neural-networks-practice/index.html
diff --git a/modules/11c-batches-with-sequences/index.html b/modules/11c-batches-with-sequences/index.html
diff --git a/modules/12-attention/index.html b/modules/12-attention/index.html
diff --git a/modules/12-intro-julia/index.html b/modules/12-intro-julia/index.html
diff --git a/modules/13-siamese/index.html b/modules/13-siamese/index.html
diff --git a/modules/14a-depth/index.html b/modules/14a-depth/index.html
diff --git a/modules/14b-depth/index.html b/modules/14b-depth/index.html
diff --git a/modules/15-dropout/index.html b/modules/15-dropout/index.html
diff --git a/modules/16-batchnorm/index.html b/modules/16-batchnorm/index.html
diff --git a/modules/17-resnets/index.html b/modules/17-resnets/index.html
diff --git a/modules/18a-diffusion/index.html b/modules/18a-diffusion/index.html
diff --git a/modules/19-clip/index.html b/modules/19-clip/index.html
diff --git a/modules/2a-pytorch-tensors/index.html b/modules/2a-pytorch-tensors/index.html
diff --git a/modules/2b-automatic-differentiation/index.html b/modules/2b-automatic-differentiation/index.html
diff --git a/modules/2c-jax/index.html b/modules/2c-jax/index.html
diff --git a/modules/3-loss-functions-for-classification/index.html b/modules/3-loss-functions-for-classification/index.html
@@ -10,4 +10,4 @@
 C = <span class=hljs-number >8</span>
 <span class=hljs-built_in >input</span> = torch.randn(<span class=hljs-number >3</span>,C,<span class=hljs-number >4</span>,<span class=hljs-number >5</span>)
 target = torch.empty(<span class=hljs-number >3</span>,<span class=hljs-number >4</span>,<span class=hljs-number >5</span>, dtype=torch.long).random_(<span class=hljs-number >0</span>,C) 
-<span class=hljs-keyword >assert</span> loss1(m(<span class=hljs-built_in >input</span>),target) == loss2(<span class=hljs-built_in >input</span>,target)</code></pre> <h2 id=quiz ><a href="#quiz" class=header-anchor >Quiz</a></h2> <p>To check you know your loss, you can do the <a href="https://dataflowr.github.io/quiz/module3.html">quizzes</a></p> <div class=page-foot > <div class=copyright > <a href="https://github.com/dataflowr/website/tree/master"><b>Edit this page on <img class=github-logo  src="https://unpkg.com/[email protected]/dist/svg/logo-github.svg"></b></a> Last modified: February 23, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>. </div> </div> </div> </div>
+<span class=hljs-keyword >assert</span> loss1(m(<span class=hljs-built_in >input</span>),target) == loss2(<span class=hljs-built_in >input</span>,target)</code></pre> <h2 id=quiz ><a href="#quiz" class=header-anchor >Quiz</a></h2> <p>To check you know your loss, you can do the <a href="https://dataflowr.github.io/quiz/module3.html">quizzes</a></p> <div class=page-foot > <div class=copyright > <a href="https://github.com/dataflowr/website/tree/master"><b>Edit this page on <img class=github-logo  src="https://unpkg.com/[email protected]/dist/svg/logo-github.svg"></b></a> Last modified: July 11, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>. </div> </div> </div> </div>
diff --git a/modules/4-optimization-for-deep-learning/index.html b/modules/4-optimization-for-deep-learning/index.html
diff --git a/modules/5-stacking-layers/index.html b/modules/5-stacking-layers/index.html
diff --git a/modules/6-convolutional-neural-network/index.html b/modules/6-convolutional-neural-network/index.html
diff --git a/modules/7-dataloading/index.html b/modules/7-dataloading/index.html
diff --git a/modules/8a-embedding-layers/index.html b/modules/8a-embedding-layers/index.html
diff --git a/modules/8b-collaborative-filtering/index.html b/modules/8b-collaborative-filtering/index.html
diff --git a/modules/8c-word2vec/index.html b/modules/8c-word2vec/index.html
diff --git a/modules/9a-autoencoders/index.html b/modules/9a-autoencoders/index.html
diff --git a/modules/9b-unet/index.html b/modules/9b-unet/index.html
@@ -1 +1 @@
-<!doctype html> <html lang=en > <meta charset=UTF-8 > <meta name=viewport  content="width=device-width, initial-scale=1"> <link rel=stylesheet  href="/website/css/franklin.css"> <link rel=stylesheet  href="/website/css/poole_hyde.css"> <link rel=stylesheet  href="/website/css/custom.css"> <style> html {font-size: 17px;} .franklin-content {position: relative; padding-left: 8%; padding-right: 5%; line-height: 1.35em;} @media (min-width: 940px) { .franklin-content {width: 100%; margin-left: auto; margin-right: auto;} } @media (max-width: 768px) { .franklin-content {padding-left: 6%; padding-right: 6%;} } </style> <link rel=icon  href="/website/assets/favicon.png"> <title>Dataflowr - Deep Learning DIY</title> <div class=sidebar > <div class="container sidebar-sticky"> <div class=sidebar-about > <img src="/website/assets/dataflowr_violet_plain_square.png" style="width: 120px; height: auto; display: inline"> <img src="/website/assets/favicon.png" style="margin-left:1em; position:relative;left:0px; top:-30px; width: 60px; height: auto; display: inline"> <h1 style="font-size:1em; opacity: 0.95;"><a href="/website/">Deep Learning DIY</a></h1> </div> <nav class=sidebar-nav > <a class="sidebar-nav-item " href="/website/modules/0-sotfware-installation"> <b>Module 0</b> - <em> Software installation</em> </a> <a class="sidebar-nav-item " href="/website/modules/1-intro-general-overview"> <b>Module 1</b> - <em>Introduction & General Overview</em> </a> <a class="sidebar-nav-item " href="/website/modules/2a-pytorch-tensors"> <b>Module 2a</b> - <em>PyTorch tensors</em> </a> <a class="sidebar-nav-item " href="/website/modules/2b-automatic-differentiation"> <b>Module 2b</b> - <em>Automatic differentiation</em> </a> <a class="sidebar-nav-item " href="/website/modules/2c-jax"> <b>Module 2c</b> - <em>Automatic differentiation: VJP and intro to JAX</em> </a> <a class="sidebar-nav-item " href="/website/modules/3-loss-functions-for-classification"> <b>Module 3</b> - <em>Loss functions for classification</em> </a> <a class="sidebar-nav-item " href="/website/modules/4-optimization-for-deep-learning"> <b>Module 4</b> - <em>Optimization for DL</em> </a> <a class="sidebar-nav-item " href="/website/modules/5-stacking-layers"> <b>Module 5</b> - <em>Stacking layers</em> </a> <a class="sidebar-nav-item " href="/website/modules/6-convolutional-neural-network"> <b>Module 6</b> - <em>Convolutional neural network</em> </a> <a class="sidebar-nav-item " href="/website/modules/7-dataloading"> <b>Module 7</b> - <em>Dataloading</em> </a> <a class="sidebar-nav-item " href="/website/modules/8a-embedding-layers"> <b>Module 8a</b> - <em>Embedding layers</em> </a> <a class="sidebar-nav-item " href="/website/modules/8b-collaborative-filtering"> <b>Module 8b</b> - <em>Collaborative filtering</em> </a> <a class="sidebar-nav-item " href="/website/modules/8c-word2vec"> <b>Module 8c</b> - <em>Word2vec</em> </a> <a class="sidebar-nav-item " href="/website/modules/9a-autoencoders"> <b>Module 9a</b> - <em>Autoencoders</em> </a> <a class="sidebar-nav-item active" href="/website/modules/9b-unet"> <b>Module 9b</b> - <em>UNets</em> </a> <a class="sidebar-nav-item " href="/website/modules/9c-flows"> <b>Module 9c</b> - <em>Flows</em> </a> <a class="sidebar-nav-item " href="/website/modules/10-generative-adversarial-networks"> <b>Module 10</b> - <em>Generative adversarial networks</em> </a> <a class="sidebar-nav-item " href="/website/modules/11a-recurrent-neural-networks-theory"> <b>Module 11a</b> - <em>Recurrent Neural Networks (theory)</em> </a> <a class="sidebar-nav-item " href="/website/modules/11b-recurrent-neural-networks-practice"> <b>Module 11b</b> - <em>RNN in practice</em> </a> <a class="sidebar-nav-item " href="/website/modules/11c-batches-with-sequences"> <b>Module 11c</b> - <em>Batches with sequences in Pytorch</em> </a> <a class="sidebar-nav-item " href="/website/modules/12-attention"> <b>Module 12</b> - <em>Attention and Transformers</em> </a> <a class="sidebar-nav-item " href="/website/modules/13-siamese"> <b>Module 13</b> - <em>Siamese Networks and Representation Learning</em> </a> <a class="sidebar-nav-item " href="/website/modules/14a-depth"> <b>Module 14a</b> - <em>The Benefits of Depth</em> </a> <a class="sidebar-nav-item " href="/website/modules/14b-depth"> <b>Module 14b</b> - <em>The Problems with Depth</em> </a> <a class="sidebar-nav-item " href="/website/modules/15-dropout"> <b>Module 15</b> - <em>Dropout</em> </a> <a class="sidebar-nav-item " href="/website/modules/16-batchnorm"> <b>Module 16</b> - <em>Batchnorm</em> </a> <a class="sidebar-nav-item " href="/website/modules/17-resnets"> <b>Module 17</b> - <em>Resnets</em> </a> <a class="sidebar-nav-item " href="/website/modules/18a-diffusion"> <b>Module 18a</b> - <em>Denoising Diffusion Probabilistic Models</em> </a> <a class="sidebar-nav-item " href="/website/modules/19-clip"> <b>Module 19</b> - <em>Zero-shot classification with CLIP</em> </a> <!-- <div class=week >Unit 7</div>--> <div class=week >Homeworks</div> <a class="sidebar-nav-item " href="/website/homework/1-mlp-from-scratch"> <b>Homework 1</b> - <em>MLP from scratch</em> </a> <a class="sidebar-nav-item " href="/website/homework/2-CAM-adversarial"> <b>Homework 2</b> - <em>Class Activation Map and adversarial examples</em> </a> <a class="sidebar-nav-item " href="/website/homework/3-VAE"> <b>Homework 3</b> - <em>VAE for MNIST clustering and generation</em> </a> <div class=week >Bonus</div> <a class="sidebar-nav-item " href="/website/modules/12-intro-julia"> <b>Module</b> - <em>Intro to Julia: Autodiff with dual numbers</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph0"> <b>Module</b> - <em>Deep learning on graphs</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph1"> <b>Graph</b> - <em>Node embeddings</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph2"> <b>Graph</b> - <em>Signal processing on graphs</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph3"> <b>Graph</b> - <em> Graph embeddings and GNNs</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/GCN_inductivebias_spectral"> <b>Post</b> - <em>Spectral GCN</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/Convolutions_first"> <b>Post</b> - <em>Convolutions from first principles</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/invariant_equivariant"> <b>Post</b> - <em>Invariant and equivariant networks</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/graph_invariant"> <b>Graph</b> - <em>Exploiting Graph Invariants in Deep Learning</em> </a> <div class=week >Guest Lectures</div> <a class="sidebar-nav-item " href="/website/modules/privacy-preserving-ML"> <b>Privacy Preserving ML</b> - <em>Daniel Huynh</em> </a> </nav> </div> </div> <div class="content container"> <div class=franklin-content ><h1 id=module_9b_-_unets ><a href="#module_9b_-_unets" class=header-anchor >Module 9b - UNets</a></h1> <p><img src="../extras/unet/unet.png" alt="" /></p> <ul> <li><p><a href="https://github.com/dataflowr/notebooks/blob/master/Module9/UNet_image_seg.ipynb">UNet for image segmentation</a></p> </ul> <div class=page-foot > <div class=copyright > <a href="https://github.com/dataflowr/website/tree/master"><b>Edit this page on <img class=github-logo  src="https://unpkg.com/[email protected]/dist/svg/logo-github.svg"></b></a> Last modified: February 23, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>. </div> </div> </div> </div>
+<!doctype html> <html lang=en > <meta charset=UTF-8 > <meta name=viewport  content="width=device-width, initial-scale=1"> <link rel=stylesheet  href="/website/css/franklin.css"> <link rel=stylesheet  href="/website/css/poole_hyde.css"> <link rel=stylesheet  href="/website/css/custom.css"> <style> html {font-size: 17px;} .franklin-content {position: relative; padding-left: 8%; padding-right: 5%; line-height: 1.35em;} @media (min-width: 940px) { .franklin-content {width: 100%; margin-left: auto; margin-right: auto;} } @media (max-width: 768px) { .franklin-content {padding-left: 6%; padding-right: 6%;} } </style> <link rel=icon  href="/website/assets/favicon.png"> <title>Dataflowr - Deep Learning DIY</title> <div class=sidebar > <div class="container sidebar-sticky"> <div class=sidebar-about > <img src="/website/assets/dataflowr_violet_plain_square.png" style="width: 120px; height: auto; display: inline"> <img src="/website/assets/favicon.png" style="margin-left:1em; position:relative;left:0px; top:-30px; width: 60px; height: auto; display: inline"> <h1 style="font-size:1em; opacity: 0.95;"><a href="/website/">Deep Learning DIY</a></h1> </div> <nav class=sidebar-nav > <a class="sidebar-nav-item " href="/website/modules/0-sotfware-installation"> <b>Module 0</b> - <em> Software installation</em> </a> <a class="sidebar-nav-item " href="/website/modules/1-intro-general-overview"> <b>Module 1</b> - <em>Introduction & General Overview</em> </a> <a class="sidebar-nav-item " href="/website/modules/2a-pytorch-tensors"> <b>Module 2a</b> - <em>PyTorch tensors</em> </a> <a class="sidebar-nav-item " href="/website/modules/2b-automatic-differentiation"> <b>Module 2b</b> - <em>Automatic differentiation</em> </a> <a class="sidebar-nav-item " href="/website/modules/2c-jax"> <b>Module 2c</b> - <em>Automatic differentiation: VJP and intro to JAX</em> </a> <a class="sidebar-nav-item " href="/website/modules/3-loss-functions-for-classification"> <b>Module 3</b> - <em>Loss functions for classification</em> </a> <a class="sidebar-nav-item " href="/website/modules/4-optimization-for-deep-learning"> <b>Module 4</b> - <em>Optimization for DL</em> </a> <a class="sidebar-nav-item " href="/website/modules/5-stacking-layers"> <b>Module 5</b> - <em>Stacking layers</em> </a> <a class="sidebar-nav-item " href="/website/modules/6-convolutional-neural-network"> <b>Module 6</b> - <em>Convolutional neural network</em> </a> <a class="sidebar-nav-item " href="/website/modules/7-dataloading"> <b>Module 7</b> - <em>Dataloading</em> </a> <a class="sidebar-nav-item " href="/website/modules/8a-embedding-layers"> <b>Module 8a</b> - <em>Embedding layers</em> </a> <a class="sidebar-nav-item " href="/website/modules/8b-collaborative-filtering"> <b>Module 8b</b> - <em>Collaborative filtering</em> </a> <a class="sidebar-nav-item " href="/website/modules/8c-word2vec"> <b>Module 8c</b> - <em>Word2vec</em> </a> <a class="sidebar-nav-item " href="/website/modules/9a-autoencoders"> <b>Module 9a</b> - <em>Autoencoders</em> </a> <a class="sidebar-nav-item active" href="/website/modules/9b-unet"> <b>Module 9b</b> - <em>UNets</em> </a> <a class="sidebar-nav-item " href="/website/modules/9c-flows"> <b>Module 9c</b> - <em>Flows</em> </a> <a class="sidebar-nav-item " href="/website/modules/10-generative-adversarial-networks"> <b>Module 10</b> - <em>Generative adversarial networks</em> </a> <a class="sidebar-nav-item " href="/website/modules/11a-recurrent-neural-networks-theory"> <b>Module 11a</b> - <em>Recurrent Neural Networks (theory)</em> </a> <a class="sidebar-nav-item " href="/website/modules/11b-recurrent-neural-networks-practice"> <b>Module 11b</b> - <em>RNN in practice</em> </a> <a class="sidebar-nav-item " href="/website/modules/11c-batches-with-sequences"> <b>Module 11c</b> - <em>Batches with sequences in Pytorch</em> </a> <a class="sidebar-nav-item " href="/website/modules/12-attention"> <b>Module 12</b> - <em>Attention and Transformers</em> </a> <a class="sidebar-nav-item " href="/website/modules/13-siamese"> <b>Module 13</b> - <em>Siamese Networks and Representation Learning</em> </a> <a class="sidebar-nav-item " href="/website/modules/14a-depth"> <b>Module 14a</b> - <em>The Benefits of Depth</em> </a> <a class="sidebar-nav-item " href="/website/modules/14b-depth"> <b>Module 14b</b> - <em>The Problems with Depth</em> </a> <a class="sidebar-nav-item " href="/website/modules/15-dropout"> <b>Module 15</b> - <em>Dropout</em> </a> <a class="sidebar-nav-item " href="/website/modules/16-batchnorm"> <b>Module 16</b> - <em>Batchnorm</em> </a> <a class="sidebar-nav-item " href="/website/modules/17-resnets"> <b>Module 17</b> - <em>Resnets</em> </a> <a class="sidebar-nav-item " href="/website/modules/18a-diffusion"> <b>Module 18a</b> - <em>Denoising Diffusion Probabilistic Models</em> </a> <a class="sidebar-nav-item " href="/website/modules/19-clip"> <b>Module 19</b> - <em>Zero-shot classification with CLIP</em> </a> <!-- <div class=week >Unit 7</div>--> <div class=week >Homeworks</div> <a class="sidebar-nav-item " href="/website/homework/1-mlp-from-scratch"> <b>Homework 1</b> - <em>MLP from scratch</em> </a> <a class="sidebar-nav-item " href="/website/homework/2-CAM-adversarial"> <b>Homework 2</b> - <em>Class Activation Map and adversarial examples</em> </a> <a class="sidebar-nav-item " href="/website/homework/3-VAE"> <b>Homework 3</b> - <em>VAE for MNIST clustering and generation</em> </a> <div class=week >Bonus</div> <a class="sidebar-nav-item " href="/website/modules/12-intro-julia"> <b>Module</b> - <em>Intro to Julia: Autodiff with dual numbers</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph0"> <b>Module</b> - <em>Deep learning on graphs</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph1"> <b>Graph</b> - <em>Node embeddings</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph2"> <b>Graph</b> - <em>Signal processing on graphs</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph3"> <b>Graph</b> - <em> Graph embeddings and GNNs</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/GCN_inductivebias_spectral"> <b>Post</b> - <em>Spectral GCN</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/Convolutions_first"> <b>Post</b> - <em>Convolutions from first principles</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/invariant_equivariant"> <b>Post</b> - <em>Invariant and equivariant networks</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/graph_invariant"> <b>Graph</b> - <em>Exploiting Graph Invariants in Deep Learning</em> </a> <div class=week >Guest Lectures</div> <a class="sidebar-nav-item " href="/website/modules/privacy-preserving-ML"> <b>Privacy Preserving ML</b> - <em>Daniel Huynh</em> </a> </nav> </div> </div> <div class="content container"> <div class=franklin-content ><h1 id=module_9b_-_unets ><a href="#module_9b_-_unets" class=header-anchor >Module 9b - UNets</a></h1> <p><img src="../extras/unet/unet.png" alt="" /></p> <ul> <li><p><a href="https://github.com/dataflowr/notebooks/blob/master/Module9/UNet_image_seg.ipynb">UNet for image segmentation</a></p> </ul> <div class=page-foot > <div class=copyright > <a href="https://github.com/dataflowr/website/tree/master"><b>Edit this page on <img class=github-logo  src="https://unpkg.com/[email protected]/dist/svg/logo-github.svg"></b></a> Last modified: July 11, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>. </div> </div> </div> </div>
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		<!doctype html> <html lang=en > <meta charset=UTF-8 > <meta name=viewport content="width=device-width, initial-scale=1"> <link rel=stylesheet href="/website/css/franklin.css"> <link rel=stylesheet href="/website/css/poole_hyde.css"> <link rel=stylesheet href="/website/css/custom.css"> <style> html {font-size: 17px;} .franklin-content {position: relative; padding-left: 8%; padding-right: 5%; line-height: 1.35em;} @media (min-width: 940px) { .franklin-content {width: 100%; margin-left: auto; margin-right: auto;} } @media (max-width: 768px) { .franklin-content {padding-left: 6%; padding-right: 6%;} } </style> <link rel=icon href="/website/assets/favicon.png"> <title>Dataflowr - Deep Learning DIY</title> <div class=sidebar > <div class="container sidebar-sticky"> <div class=sidebar-about > <img src="/website/assets/dataflowr_violet_plain_square.png" style="width: 120px; height: auto; display: inline"> <img src="/website/assets/favicon.png" style="margin-left:1em; position:relative;left:0px; top:-30px; width: 60px; height: auto; display: inline"> <h1 style="font-size:1em; opacity: 0.95;"><a href="/website/">Deep Learning DIY</a></h1> </div> <nav class=sidebar-nav > <a class="sidebar-nav-item " href="/website/modules/0-sotfware-installation"> <b>Module 0</b> - <em> Software installation</em> </a> <a class="sidebar-nav-item " href="/website/modules/1-intro-general-overview"> <b>Module 1</b> - <em>Introduction & General Overview</em> </a> <a class="sidebar-nav-item " href="/website/modules/2a-pytorch-tensors"> <b>Module 2a</b> - <em>PyTorch tensors</em> </a> <a class="sidebar-nav-item " href="/website/modules/2b-automatic-differentiation"> <b>Module 2b</b> - <em>Automatic differentiation</em> </a> <a class="sidebar-nav-item " href="/website/modules/2c-jax"> <b>Module 2c</b> - <em>Automatic differentiation: VJP and intro to JAX</em> </a> <a class="sidebar-nav-item " href="/website/modules/3-loss-functions-for-classification"> <b>Module 3</b> - <em>Loss functions for classification</em> </a> <a class="sidebar-nav-item " href="/website/modules/4-optimization-for-deep-learning"> <b>Module 4</b> - <em>Optimization for DL</em> </a> <a class="sidebar-nav-item " href="/website/modules/5-stacking-layers"> <b>Module 5</b> - <em>Stacking layers</em> </a> <a class="sidebar-nav-item " href="/website/modules/6-convolutional-neural-network"> <b>Module 6</b> - <em>Convolutional neural network</em> </a> <a class="sidebar-nav-item " href="/website/modules/7-dataloading"> <b>Module 7</b> - <em>Dataloading</em> </a> <a class="sidebar-nav-item " href="/website/modules/8a-embedding-layers"> <b>Module 8a</b> - <em>Embedding layers</em> </a> <a class="sidebar-nav-item " href="/website/modules/8b-collaborative-filtering"> <b>Module 8b</b> - <em>Collaborative filtering</em> </a> <a class="sidebar-nav-item " href="/website/modules/8c-word2vec"> <b>Module 8c</b> - <em>Word2vec</em> </a> <a class="sidebar-nav-item " href="/website/modules/9a-autoencoders"> <b>Module 9a</b> - <em>Autoencoders</em> </a> <a class="sidebar-nav-item active" href="/website/modules/9b-unet"> <b>Module 9b</b> - <em>UNets</em> </a> <a class="sidebar-nav-item " href="/website/modules/9c-flows"> <b>Module 9c</b> - <em>Flows</em> </a> <a class="sidebar-nav-item " href="/website/modules/10-generative-adversarial-networks"> <b>Module 10</b> - <em>Generative adversarial networks</em> </a> <a class="sidebar-nav-item " href="/website/modules/11a-recurrent-neural-networks-theory"> <b>Module 11a</b> - <em>Recurrent Neural Networks (theory)</em> </a> <a class="sidebar-nav-item " href="/website/modules/11b-recurrent-neural-networks-practice"> <b>Module 11b</b> - <em>RNN in practice</em> </a> <a class="sidebar-nav-item " href="/website/modules/11c-batches-with-sequences"> <b>Module 11c</b> - <em>Batches with sequences in Pytorch</em> </a> <a class="sidebar-nav-item " href="/website/modules/12-attention"> <b>Module 12</b> - <em>Attention and Transformers</em> </a> <a class="sidebar-nav-item " href="/website/modules/13-siamese"> <b>Module 13</b> - <em>Siamese Networks and Representation Learning</em> </a> <a class="sidebar-nav-item " href="/website/modules/14a-depth"> <b>Module 14a</b> - <em>The Benefits of Depth</em> </a> <a class="sidebar-nav-item " href="/website/modules/14b-depth"> <b>Module 14b</b> - <em>The Problems with Depth</em> </a> <a class="sidebar-nav-item " href="/website/modules/15-dropout"> <b>Module 15</b> - <em>Dropout</em> </a> <a class="sidebar-nav-item " href="/website/modules/16-batchnorm"> <b>Module 16</b> - <em>Batchnorm</em> </a> <a class="sidebar-nav-item " href="/website/modules/17-resnets"> <b>Module 17</b> - <em>Resnets</em> </a> <a class="sidebar-nav-item " href="/website/modules/18a-diffusion"> <b>Module 18a</b> - <em>Denoising Diffusion Probabilistic Models</em> </a> <a class="sidebar-nav-item " href="/website/modules/19-clip"> <b>Module 19</b> - <em>Zero-shot classification with CLIP</em> </a> <!-- <div class=week >Unit 7</div>--> <div class=week >Homeworks</div> <a class="sidebar-nav-item " href="/website/homework/1-mlp-from-scratch"> <b>Homework 1</b> - <em>MLP from scratch</em> </a> <a class="sidebar-nav-item " href="/website/homework/2-CAM-adversarial"> <b>Homework 2</b> - <em>Class Activation Map and adversarial examples</em> </a> <a class="sidebar-nav-item " href="/website/homework/3-VAE"> <b>Homework 3</b> - <em>VAE for MNIST clustering and generation</em> </a> <div class=week >Bonus</div> <a class="sidebar-nav-item " href="/website/modules/12-intro-julia"> <b>Module</b> - <em>Intro to Julia: Autodiff with dual numbers</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph0"> <b>Module</b> - <em>Deep learning on graphs</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph1"> <b>Graph</b> - <em>Node embeddings</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph2"> <b>Graph</b> - <em>Signal processing on graphs</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph3"> <b>Graph</b> - <em> Graph embeddings and GNNs</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/GCN_inductivebias_spectral"> <b>Post</b> - <em>Spectral GCN</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/Convolutions_first"> <b>Post</b> - <em>Convolutions from first principles</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/invariant_equivariant"> <b>Post</b> - <em>Invariant and equivariant networks</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/graph_invariant"> <b>Graph</b> - <em>Exploiting Graph Invariants in Deep Learning</em> </a> <div class=week >Guest Lectures</div> <a class="sidebar-nav-item " href="/website/modules/privacy-preserving-ML"> <b>Privacy Preserving ML</b> - <em>Daniel Huynh</em> </a> </nav> </div> </div> <div class="content container"> <div class=franklin-content ><h1 id=module_9b_-_unets ><a href="#module_9b_-_unets" class=header-anchor >Module 9b - UNets</a></h1> <p><img src="../extras/unet/unet.png" alt="" /></p> <ul> <li><p><a href="https://github.com/dataflowr/notebooks/blob/master/Module9/UNet_image_seg.ipynb">UNet for image segmentation</a></p> </ul> <div class=page-foot > <div class=copyright > <a href="https://github.com/dataflowr/website/tree/master"><b>Edit this page on <img class=github-logo src="https://unpkg.com/[email protected]/dist/svg/logo-github.svg"></b></a> Last modified: February 23, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>. </div> </div> </div> </div>
		<!doctype html> <html lang=en > <meta charset=UTF-8 > <meta name=viewport content="width=device-width, initial-scale=1"> <link rel=stylesheet href="/website/css/franklin.css"> <link rel=stylesheet href="/website/css/poole_hyde.css"> <link rel=stylesheet href="/website/css/custom.css"> <style> html {font-size: 17px;} .franklin-content {position: relative; padding-left: 8%; padding-right: 5%; line-height: 1.35em;} @media (min-width: 940px) { .franklin-content {width: 100%; margin-left: auto; margin-right: auto;} } @media (max-width: 768px) { .franklin-content {padding-left: 6%; padding-right: 6%;} } </style> <link rel=icon href="/website/assets/favicon.png"> <title>Dataflowr - Deep Learning DIY</title> <div class=sidebar > <div class="container sidebar-sticky"> <div class=sidebar-about > <img src="/website/assets/dataflowr_violet_plain_square.png" style="width: 120px; height: auto; display: inline"> <img src="/website/assets/favicon.png" style="margin-left:1em; position:relative;left:0px; top:-30px; width: 60px; height: auto; display: inline"> <h1 style="font-size:1em; opacity: 0.95;"><a href="/website/">Deep Learning DIY</a></h1> </div> <nav class=sidebar-nav > <a class="sidebar-nav-item " href="/website/modules/0-sotfware-installation"> <b>Module 0</b> - <em> Software installation</em> </a> <a class="sidebar-nav-item " href="/website/modules/1-intro-general-overview"> <b>Module 1</b> - <em>Introduction & General Overview</em> </a> <a class="sidebar-nav-item " href="/website/modules/2a-pytorch-tensors"> <b>Module 2a</b> - <em>PyTorch tensors</em> </a> <a class="sidebar-nav-item " href="/website/modules/2b-automatic-differentiation"> <b>Module 2b</b> - <em>Automatic differentiation</em> </a> <a class="sidebar-nav-item " href="/website/modules/2c-jax"> <b>Module 2c</b> - <em>Automatic differentiation: VJP and intro to JAX</em> </a> <a class="sidebar-nav-item " href="/website/modules/3-loss-functions-for-classification"> <b>Module 3</b> - <em>Loss functions for classification</em> </a> <a class="sidebar-nav-item " href="/website/modules/4-optimization-for-deep-learning"> <b>Module 4</b> - <em>Optimization for DL</em> </a> <a class="sidebar-nav-item " href="/website/modules/5-stacking-layers"> <b>Module 5</b> - <em>Stacking layers</em> </a> <a class="sidebar-nav-item " href="/website/modules/6-convolutional-neural-network"> <b>Module 6</b> - <em>Convolutional neural network</em> </a> <a class="sidebar-nav-item " href="/website/modules/7-dataloading"> <b>Module 7</b> - <em>Dataloading</em> </a> <a class="sidebar-nav-item " href="/website/modules/8a-embedding-layers"> <b>Module 8a</b> - <em>Embedding layers</em> </a> <a class="sidebar-nav-item " href="/website/modules/8b-collaborative-filtering"> <b>Module 8b</b> - <em>Collaborative filtering</em> </a> <a class="sidebar-nav-item " href="/website/modules/8c-word2vec"> <b>Module 8c</b> - <em>Word2vec</em> </a> <a class="sidebar-nav-item " href="/website/modules/9a-autoencoders"> <b>Module 9a</b> - <em>Autoencoders</em> </a> <a class="sidebar-nav-item active" href="/website/modules/9b-unet"> <b>Module 9b</b> - <em>UNets</em> </a> <a class="sidebar-nav-item " href="/website/modules/9c-flows"> <b>Module 9c</b> - <em>Flows</em> </a> <a class="sidebar-nav-item " href="/website/modules/10-generative-adversarial-networks"> <b>Module 10</b> - <em>Generative adversarial networks</em> </a> <a class="sidebar-nav-item " href="/website/modules/11a-recurrent-neural-networks-theory"> <b>Module 11a</b> - <em>Recurrent Neural Networks (theory)</em> </a> <a class="sidebar-nav-item " href="/website/modules/11b-recurrent-neural-networks-practice"> <b>Module 11b</b> - <em>RNN in practice</em> </a> <a class="sidebar-nav-item " href="/website/modules/11c-batches-with-sequences"> <b>Module 11c</b> - <em>Batches with sequences in Pytorch</em> </a> <a class="sidebar-nav-item " href="/website/modules/12-attention"> <b>Module 12</b> - <em>Attention and Transformers</em> </a> <a class="sidebar-nav-item " href="/website/modules/13-siamese"> <b>Module 13</b> - <em>Siamese Networks and Representation Learning</em> </a> <a class="sidebar-nav-item " href="/website/modules/14a-depth"> <b>Module 14a</b> - <em>The Benefits of Depth</em> </a> <a class="sidebar-nav-item " href="/website/modules/14b-depth"> <b>Module 14b</b> - <em>The Problems with Depth</em> </a> <a class="sidebar-nav-item " href="/website/modules/15-dropout"> <b>Module 15</b> - <em>Dropout</em> </a> <a class="sidebar-nav-item " href="/website/modules/16-batchnorm"> <b>Module 16</b> - <em>Batchnorm</em> </a> <a class="sidebar-nav-item " href="/website/modules/17-resnets"> <b>Module 17</b> - <em>Resnets</em> </a> <a class="sidebar-nav-item " href="/website/modules/18a-diffusion"> <b>Module 18a</b> - <em>Denoising Diffusion Probabilistic Models</em> </a> <a class="sidebar-nav-item " href="/website/modules/19-clip"> <b>Module 19</b> - <em>Zero-shot classification with CLIP</em> </a> <!-- <div class=week >Unit 7</div>--> <div class=week >Homeworks</div> <a class="sidebar-nav-item " href="/website/homework/1-mlp-from-scratch"> <b>Homework 1</b> - <em>MLP from scratch</em> </a> <a class="sidebar-nav-item " href="/website/homework/2-CAM-adversarial"> <b>Homework 2</b> - <em>Class Activation Map and adversarial examples</em> </a> <a class="sidebar-nav-item " href="/website/homework/3-VAE"> <b>Homework 3</b> - <em>VAE for MNIST clustering and generation</em> </a> <div class=week >Bonus</div> <a class="sidebar-nav-item " href="/website/modules/12-intro-julia"> <b>Module</b> - <em>Intro to Julia: Autodiff with dual numbers</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph0"> <b>Module</b> - <em>Deep learning on graphs</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph1"> <b>Graph</b> - <em>Node embeddings</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph2"> <b>Graph</b> - <em>Signal processing on graphs</em> </a> <a class="sidebar-nav-item " href="/website/modules/graph3"> <b>Graph</b> - <em> Graph embeddings and GNNs</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/GCN_inductivebias_spectral"> <b>Post</b> - <em>Spectral GCN</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/Convolutions_first"> <b>Post</b> - <em>Convolutions from first principles</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/invariant_equivariant"> <b>Post</b> - <em>Invariant and equivariant networks</em> </a> <a class="sidebar-nav-item " href="/website/modules/extras/graph_invariant"> <b>Graph</b> - <em>Exploiting Graph Invariants in Deep Learning</em> </a> <div class=week >Guest Lectures</div> <a class="sidebar-nav-item " href="/website/modules/privacy-preserving-ML"> <b>Privacy Preserving ML</b> - <em>Daniel Huynh</em> </a> </nav> </div> </div> <div class="content container"> <div class=franklin-content ><h1 id=module_9b_-_unets ><a href="#module_9b_-_unets" class=header-anchor >Module 9b - UNets</a></h1> <p><img src="../extras/unet/unet.png" alt="" /></p> <ul> <li><p><a href="https://github.com/dataflowr/notebooks/blob/master/Module9/UNet_image_seg.ipynb">UNet for image segmentation</a></p> </ul> <div class=page-foot > <div class=copyright > <a href="https://github.com/dataflowr/website/tree/master"><b>Edit this page on <img class=github-logo src="https://unpkg.com/[email protected]/dist/svg/logo-github.svg"></b></a> Last modified: July 11, 2024. Website built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> and the <a href="https://julialang.org">Julia programming language</a>. </div> </div> </div> </div>