Files
Varuna Jayasiri 8168b04440 🚧 transformer xl docs
2021-02-05 19:16:46 +05:30

153 lines
7.1 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="A bunch of utility functions and classes for transformers."/>
<meta name="twitter:card" content="summary"/>
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta name="twitter:title" content="Utilities for Transformer"/>
<meta name="twitter:description" content="A bunch of utility functions and classes for transformers."/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/transformers/utils.html"/>
<meta property="og:title" content="Utilities for Transformer"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="LabML Neural Networks"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="Utilities for Transformer"/>
<meta property="og:description" content="A bunch of utility functions and classes for transformers."/>
<title>Utilities for Transformer</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css">
<link rel="canonical" href="https://nn.labml.ai/transformers/utils.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>
<a class="parent" href="index.html">transformers</a>
</p>
<p>
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/transformers/utils.py">
<img alt="Github"
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
style="max-width:100%;"/></a>
<a href="https://join.slack.com/t/labforml/shared_invite/zt-egj9zvq9-Dl3hhZqobexgT7aVKnD14g/"
rel="nofollow">
<img alt="Join Slact"
src="https://img.shields.io/badge/slack-chat-green.svg?logo=slack"
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>Utilities for Transformer</h1>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">10</span><span></span><span class="kn">import</span> <span class="nn">torch</span></pre></div>
</div>
</div>
<div class='section' id='section-1'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-1'>#</a>
</div>
<h2>Subsequent mask to mask out data from future (subsequent) time steps</h2>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">13</span><span class="k">def</span> <span class="nf">subsequent_mask</span><span class="p">(</span><span class="n">seq_len</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-2'>
<div class='docs'>
<div class='section-link'>
<a href='#section-2'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">17</span> <span class="n">mask</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tril</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">ones</span><span class="p">(</span><span class="n">seq_len</span><span class="p">,</span> <span class="n">seq_len</span><span class="p">))</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">bool</span><span class="p">)</span><span class="o">.</span><span class="n">unsqueeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="lineno">18</span> <span class="k">return</span> <span class="n">mask</span></pre></div>
</div>
</div>
<div class='section' id='section-3'>
<div class='docs'>
<div class='section-link'>
<a href='#section-3'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">21</span><span class="k">def</span> <span class="nf">_subsequent_mask</span><span class="p">():</span>
<span class="lineno">22</span> <span class="kn">from</span> <span class="nn">labml.logger</span> <span class="kn">import</span> <span class="n">inspect</span>
<span class="lineno">23</span> <span class="n">inspect</span><span class="p">(</span><span class="n">subsequent_mask</span><span class="p">(</span><span class="mi">10</span><span class="p">)[:,</span> <span class="p">:,</span> <span class="mi">0</span><span class="p">])</span>
<span class="lineno">24</span>
<span class="lineno">25</span>
<span class="lineno">26</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="lineno">27</span> <span class="n">_subsequent_mask</span><span class="p">()</span></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>
</body>
</html>