mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-06 15:22:21 +08:00
223 lines
9.4 KiB
HTML
223 lines
9.4 KiB
HTML
<!DOCTYPE html>
|
|
<html>
|
|
<head>
|
|
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
|
<meta name="description" content=""/>
|
|
|
|
<meta name="twitter:card" content="summary"/>
|
|
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta name="twitter:title" content="labml.ai Annotated PyTorch Paper Implementations"/>
|
|
<meta name="twitter:description" content=""/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/index.html"/>
|
|
<meta property="og:title" content="labml.ai Annotated PyTorch Paper Implementations"/>
|
|
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta property="og:site_name" content="LabML Neural Networks"/>
|
|
<meta property="og:type" content="object"/>
|
|
<meta property="og:title" content="labml.ai Annotated PyTorch Paper Implementations"/>
|
|
<meta property="og:description" content=""/>
|
|
|
|
<title>labml.ai Annotated PyTorch Paper Implementations</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="./pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/index.html"/>
|
|
<!-- Global site tag (gtag.js) - Google Analytics -->
|
|
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
|
|
<script>
|
|
window.dataLayer = window.dataLayer || [];
|
|
|
|
function gtag() {
|
|
dataLayer.push(arguments);
|
|
}
|
|
|
|
gtag('js', new Date());
|
|
|
|
gtag('config', 'G-4V3HC8HBLH');
|
|
</script>
|
|
</head>
|
|
<body>
|
|
<div id='container'>
|
|
<div id="background"></div>
|
|
<div class='section'>
|
|
<div class='docs'>
|
|
<p>
|
|
<a class="parent" href="/">home</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/__init__.py">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
|
|
style="max-width:100%;"/></a>
|
|
<a href="https://twitter.com/labmlai"
|
|
rel="nofollow">
|
|
<img alt="Twitter"
|
|
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
|
style="max-width:100%;"/></a>
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-0'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-0'>#</a>
|
|
</div>
|
|
<h1><a href="index.html">labml.ai Annotated PyTorch Paper Implementations</a></h1>
|
|
<p>This is a collection of simple PyTorch implementations of
|
|
neural networks and related algorithms.
|
|
<a href="https://github.com/lab-ml/nn">These implementations</a> are documented with explanations,
|
|
and the <a href="index.html">website</a>
|
|
renders these as side-by-side formatted notes.
|
|
We believe these would help you understand these algorithms better.</p>
|
|
<p>We are actively maintaining this repo and adding new
|
|
implementations.</p>
|
|
<h2>Modules</h2>
|
|
<h4>✨ <a href="transformers/index.html">Transformers</a></h4>
|
|
<ul>
|
|
<li><a href="transformers/mha.html">Multi-headed attention</a></li>
|
|
<li><a href="transformers/models.html">Transformer building blocks</a></li>
|
|
<li><a href="transformers/xl/index.html">Transformer XL</a><ul>
|
|
<li><a href="transformers/xl/relative_mha.html">Relative multi-headed attention</a></li>
|
|
</ul>
|
|
</li>
|
|
<li><a href="transformers/compressive/index.html">Compressive Transformer</a></li>
|
|
<li><a href="transformers/gpt/index.html">GPT Architecture</a></li>
|
|
<li><a href="transformers/glu_variants/simple.html">GLU Variants</a></li>
|
|
<li><a href="transformers/knn/index.html">kNN-LM: Generalization through Memorization</a></li>
|
|
<li><a href="transformers/feedback/index.html">Feedback Transformer</a></li>
|
|
<li><a href="transformers/switch/index.html">Switch Transformer</a></li>
|
|
<li><a href="transformers/fast_weights/index.html">Fast Weights Transformer</a></li>
|
|
<li><a href="transformers/fnet/index.html">FNet</a></li>
|
|
<li><a href="transformers/aft/index.html">Attention Free Transformer</a></li>
|
|
<li><a href="transformers/mlm/index.html">Masked Language Model</a></li>
|
|
<li><a href="transformers/mlp_mixer/index.html">MLP-Mixer: An all-MLP Architecture for Vision</a></li>
|
|
<li><a href="transformers/gmlp/index.html">Pay Attention to MLPs (gMLP)</a></li>
|
|
</ul>
|
|
<h4>✨ <a href="recurrent_highway_networks/index.html">Recurrent Highway Networks</a></h4>
|
|
<h4>✨ <a href="lstm/index.html">LSTM</a></h4>
|
|
<h4>✨ <a href="hypernetworks/hyper_lstm.html">HyperNetworks - HyperLSTM</a></h4>
|
|
<h4>✨ <a href="capsule_networks/index.html">Capsule Networks</a></h4>
|
|
<h4>✨ <a href="gan/index.html">Generative Adversarial Networks</a></h4>
|
|
<ul>
|
|
<li><a href="gan/original/index.html">Original GAN</a></li>
|
|
<li><a href="gan/dcgan/index.html">GAN with deep convolutional network</a></li>
|
|
<li><a href="gan/cycle_gan/index.html">Cycle GAN</a></li>
|
|
<li><a href="gan/wasserstein/index.html">Wasserstein GAN</a></li>
|
|
<li><a href="gan/wasserstein/gradient_penalty/index.html">Wasserstein GAN with Gradient Penalty</a></li>
|
|
<li><a href="gan/stylegan/index.html">StyleGAN 2</a></li>
|
|
</ul>
|
|
<h4>✨ <a href="sketch_rnn/index.html">Sketch RNN</a></h4>
|
|
<h4>✨ <a href="cfr/index.html">Counterfactual Regret Minimization (CFR)</a></h4>
|
|
<p>Solving games with incomplete information such as poker with CFR.</p>
|
|
<ul>
|
|
<li><a href="cfr/kuhn/index.html">Kuhn Poker</a></li>
|
|
</ul>
|
|
<h4>✨ <a href="rl/index.html">Reinforcement Learning</a></h4>
|
|
<ul>
|
|
<li><a href="rl/ppo/index.html">Proximal Policy Optimization</a> with
|
|
<a href="rl/ppo/gae.html">Generalized Advantage Estimation</a></li>
|
|
<li><a href="rl/dqn/index.html">Deep Q Networks</a> with
|
|
with <a href="rl/dqn/model.html">Dueling Network</a>,
|
|
<a href="rl/dqn/replay_buffer.html">Prioritized Replay</a>
|
|
and Double Q Network.</li>
|
|
</ul>
|
|
<h4>✨ <a href="optimizers/index.html">Optimizers</a></h4>
|
|
<ul>
|
|
<li><a href="optimizers/adam.html">Adam</a></li>
|
|
<li><a href="optimizers/amsgrad.html">AMSGrad</a></li>
|
|
<li><a href="optimizers/adam_warmup.html">Adam Optimizer with warmup</a></li>
|
|
<li><a href="optimizers/noam.html">Noam Optimizer</a></li>
|
|
<li><a href="optimizers/radam.html">Rectified Adam Optimizer</a></li>
|
|
<li><a href="optimizers/ada_belief.html">AdaBelief Optimizer</a></li>
|
|
</ul>
|
|
<h4>✨ <a href="https://nn.labml.ai/normalization/index.html">Normalization Layers</a></h4>
|
|
<ul>
|
|
<li><a href="https://nn.labml.ai/normalization/batch_norm/index.html">Batch Normalization</a></li>
|
|
<li><a href="https://nn.labml.ai/normalization/layer_norm/index.html">Layer Normalization</a></li>
|
|
<li><a href="https://nn.labml.ai/normalization/instance_norm/index.html">Instance Normalization</a></li>
|
|
<li><a href="https://nn.labml.ai/normalization/group_norm/index.html">Group Normalization</a></li>
|
|
<li><a href="https://nn.labml.ai/normalization/weight_standardization/index.html">Weight Standardization</a></li>
|
|
<li><a href="https://nn.labml.ai/normalization/batch_channel_norm/index.html">Batch-Channel Normalization</a></li>
|
|
</ul>
|
|
<h3>Installation</h3>
|
|
<pre><code class="bash">pip install labml-nn
|
|
</code></pre>
|
|
|
|
<h3>Citing LabML</h3>
|
|
<p>If you use LabML for academic research, please cite the library using the following BibTeX entry.</p>
|
|
<pre><code class="bibtex">@misc{labml,
|
|
author = {Varuna Jayasiri, Nipun Wijerathne},
|
|
title = {LabML: A library to organize machine learning experiments},
|
|
year = {2020},
|
|
url = {https://nn.labml.ai/},
|
|
}
|
|
</code></pre>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></pre></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/MathJax.js?config=TeX-AMS_HTML">
|
|
</script>
|
|
<!-- MathJax configuration -->
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
tex2jax: {
|
|
inlineMath: [ ['$','$'] ],
|
|
displayMath: [ ['$$','$$'] ],
|
|
processEscapes: true,
|
|
processEnvironments: true
|
|
},
|
|
// Center justify equations in code and markdown cells. Elsewhere
|
|
// we use CSS to left justify single line equations in code cells.
|
|
displayAlign: 'center',
|
|
"HTML-CSS": { fonts: ["TeX"] }
|
|
});
|
|
</script>
|
|
<script>
|
|
function handleImages() {
|
|
var images = document.querySelectorAll('p>img')
|
|
|
|
console.log(images);
|
|
for (var i = 0; i < images.length; ++i) {
|
|
handleImage(images[i])
|
|
}
|
|
}
|
|
|
|
function handleImage(img) {
|
|
img.parentElement.style.textAlign = 'center'
|
|
|
|
var modal = document.createElement('div')
|
|
modal.id = 'modal'
|
|
|
|
var modalContent = document.createElement('div')
|
|
modal.appendChild(modalContent)
|
|
|
|
var modalImage = document.createElement('img')
|
|
modalContent.appendChild(modalImage)
|
|
|
|
var span = document.createElement('span')
|
|
span.classList.add('close')
|
|
span.textContent = 'x'
|
|
modal.appendChild(span)
|
|
|
|
img.onclick = function () {
|
|
console.log('clicked')
|
|
document.body.appendChild(modal)
|
|
modalImage.src = img.src
|
|
}
|
|
|
|
span.onclick = function () {
|
|
document.body.removeChild(modal)
|
|
}
|
|
}
|
|
|
|
handleImages()
|
|
</script>
|
|
</body>
|
|
</html> |