mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-14 01:13:00 +08:00
236 lines
16 KiB
HTML
236 lines
16 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.ai Annotated PyTorch Paper Implementations"/>
|
||
<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?v=1">
|
||
<link rel="canonical" href="https://nn.labml.ai/index.html"/>
|
||
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.18/dist/katex.min.css" integrity="sha384-zTROYFVGOfTw7JV7KUu8udsvW2fx4lWOsCEDqhBreBwlHI4ioVRtmIvEThzJHGET" crossorigin="anonymous">
|
||
|
||
<!-- 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/sponsors/labmlai" target="_blank">
|
||
<img alt="Sponsor"
|
||
src="https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86"
|
||
style="max-width:100%;"/></a>
|
||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
|
||
<img alt="Github"
|
||
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
|
||
style="max-width:100%;"/></a>
|
||
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
|
||
<img alt="Twitter"
|
||
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
||
style="max-width:100%;"/></a>
|
||
</p>
|
||
<p>
|
||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/__init__.py" target="_blank">
|
||
View code on Github</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/labmlai/annotated_deep_learning_paper_implementations">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><img alt="Screenshot" src="dqn-light.png"></p>
|
||
<p>We are actively maintaining this repo and adding new implementations. <a href="https://twitter.com/labmlai"><img alt="Twitter" src="https://img.shields.io/twitter/follow/labmlai?style=social"></a> for updates.</p>
|
||
<h2>Paper Implementations</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> </li>
|
||
<li><a href="transformers/xl/relative_mha.html">Relative multi-headed attention</a> </li>
|
||
<li><a href="transformers/rope/index.html">Rotary Positional Embeddings (RoPE)</a> </li>
|
||
<li><a href="transformers/alibi/index.html">Attention with Linear Biases (ALiBi)</a> </li>
|
||
<li><a href="transformers/retro/index.html">RETRO</a> </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>
|
||
<li><a href="transformers/vit/index.html">Vision Transformer (ViT)</a> </li>
|
||
<li><a href="transformers/primer_ez/index.html">Primer EZ</a> </li>
|
||
<li><a href="transformers/hour_glass/index.html">Hourglass</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="resnet/index.html">ResNet</a></h4>
|
||
<h4>✨ <a href="conv_mixer/index.html">ConvMixer</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="diffusion/index.html">Diffusion models</a></h4>
|
||
<ul><li><a href="diffusion/ddpm/index.html">Denoising Diffusion Probabilistic Models (DDPM)</a></li></ul>
|
||
<h4>✨ <a href="sketch_rnn/index.html">Sketch RNN</a></h4>
|
||
<h4>✨ Graph Neural Networks</h4>
|
||
<ul><li><a href="graphs/gat/index.html">Graph Attention Networks (GAT)</a> </li>
|
||
<li><a href="graphs/gatv2/index.html">Graph Attention Networks v2 (GATv2)</a></li></ul>
|
||
<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="normalization/index.html">Normalization Layers</a></h4>
|
||
<ul><li><a href="normalization/batch_norm/index.html">Batch Normalization</a> </li>
|
||
<li><a href="normalization/layer_norm/index.html">Layer Normalization</a> </li>
|
||
<li><a href="normalization/instance_norm/index.html">Instance Normalization</a> </li>
|
||
<li><a href="normalization/group_norm/index.html">Group Normalization</a> </li>
|
||
<li><a href="normalization/weight_standardization/index.html">Weight Standardization</a> </li>
|
||
<li><a href="normalization/batch_channel_norm/index.html">Batch-Channel Normalization</a> </li>
|
||
<li><a href="normalization/deep_norm/index.html">DeepNorm</a></li></ul>
|
||
<h4>✨ <a href="distillation/index.html">Distillation</a></h4>
|
||
<h4>✨ <a href="adaptive_computation/index.html">Adaptive Computation</a></h4>
|
||
<ul><li><a href="adaptive_computation/ponder_net/index.html">PonderNet</a></li></ul>
|
||
<h4>✨ <a href="uncertainty/index.html">Uncertainty</a></h4>
|
||
<ul><li><a href="uncertainty/evidence/index.html">Evidential Deep Learning to Quantify Classification Uncertainty</a></li></ul>
|
||
<h4>✨ <a href="activations/index.html">Activations</a></h4>
|
||
<ul><li><a href="activations/fta/index.html">Fuzzy Tiling Activations</a></li></ul>
|
||
<h2>Highlighted Research Paper PDFs</h2>
|
||
<ul><li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2204.10628.pdf">Autoregressive Search Engines: Generating Substrings as Document Identifiers</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2203.15556.pdf">Training Compute-Optimal Large Language Models</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/1910.02054.pdf">ZeRO: Memory Optimizations Toward Training Trillion Parameter Models</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2204.02311.pdf">PaLM: Scaling Language Modeling with Pathways</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/dall-e-2.pdf">Hierarchical Text-Conditional Image Generation with CLIP Latents</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2203.14465.pdf">STaR: Self-Taught Reasoner Bootstrapping Reasoning With Reasoning</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2112.04426.pdf">Improving language models by retrieving from trillions of tokens</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2003.08934.pdf">NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/1706.03762.pdf">Attention Is All You Need</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2006.11239.pdf">Denoising Diffusion Probabilistic Models</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2109.08668.pdf">Primer: Searching for Efficient Transformers for Language Modeling</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/1803.02999.pdf">On First-Order Meta-Learning Algorithms</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2103.00020.pdf">Learning Transferable Visual Models From Natural Language Supervision</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/2109.02869.pdf">The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/1805.09801.pdf">Meta-Gradient Reinforcement Learning</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/google_maps_eta.pdf">ETA Prediction with Graph Neural Networks in Google Maps</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/ponder_net.pdf">PonderNet: Learning to Ponder</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/muzero.pdf">Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/gans_n_roses.pdf">GANs N’ Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/vit.pdf">An Image is Worth 16X16 Word: Transformers for Image Recognition at Scale</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/resnet.pdf">Deep Residual Learning for Image Recognition</a> </li>
|
||
<li><a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/papers/distillation.pdf">Distilling the Knowledge in a Neural Network</a></li></ul>
|
||
<h3>Installation</h3>
|
||
<pre class="highlight lang-bash"><code><span></span>pip install labml-nn</code></pre>
|
||
<h3>Citing LabML</h3>
|
||
<p>If you use this for academic research, please cite it using the following BibTeX entry.</p>
|
||
<pre class="highlight lang-bibtex"><code><span></span><span class="nc">@misc</span><span class="p">{</span><span class="nl">labml</span><span class="p">,</span><span class="w"></span>
|
||
<span class="w"> </span><span class="na">author</span><span class="w"> </span><span class="p">=</span><span class="w"> </span><span class="s">{Varuna Jayasiri, Nipun Wijerathne}</span><span class="p">,</span><span class="w"></span>
|
||
<span class="w"> </span><span class="na">title</span><span class="w"> </span><span class="p">=</span><span class="w"> </span><span class="s">{labml.ai Annotated Paper Implementations}</span><span class="p">,</span><span class="w"></span>
|
||
<span class="w"> </span><span class="na">year</span><span class="w"> </span><span class="p">=</span><span class="w"> </span><span class="s">{2020}</span><span class="p">,</span><span class="w"></span>
|
||
<span class="w"> </span><span class="na">url</span><span class="w"> </span><span class="p">=</span><span class="w"> </span><span class="s">{}</span><span class="p">,</span><span class="w"></span>
|
||
<span class="p">}</span><span class="w"></span></code></pre>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='footer'>
|
||
<a href="https://papers.labml.ai">Trending Research Papers</a>
|
||
<a href="https://labml.ai">labml.ai</a>
|
||
</div>
|
||
</div>
|
||
<script src=./interactive.js?v=1"></script>
|
||
<script>
|
||
function handleImages() {
|
||
var images = document.querySelectorAll('p>img')
|
||
|
||
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> |