Files
Varuna Jayasiri 6a41c82b30 FTA (#115)
2022-05-23 22:26:39 +05:30

402 lines
64 KiB
HTML
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!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="PyTorch implementation and tutorial of Fuzzy Tiling Activations from the paper Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online."/>
<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="Fuzzy Tiling Activations"/>
<meta name="twitter:description" content="PyTorch implementation and tutorial of Fuzzy Tiling Activations from the paper Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online."/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/activations/fta/index.html"/>
<meta property="og:title" content="Fuzzy Tiling Activations"/>
<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="Fuzzy Tiling Activations"/>
<meta property="og:description" content="PyTorch implementation and tutorial of Fuzzy Tiling Activations from the paper Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online."/>
<title>Fuzzy Tiling Activations</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/activations/fta/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>
<a class="parent" href="../index.html">activations</a>
<a class="parent" href="index.html">fta</a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/activations/fta/__init__.py">
<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">
<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>Fuzzy Tiling Activations (FTA)</h1>
<p>This is a <a href="https://pytorch.org">PyTorch</a> implementation/tutorial of <a href="https://papers.labml.ai/paper/aca66d8edc8911eba3db37f65e372566">Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online</a>.</p>
<p>Fuzzy tiling activations are a form of sparse activations based on binning.</p>
<p>Binning is classification of a scalar value into a bin based on intervals. One problem with binning is that it gives zero gradients for most values (except at the boundary of bins). The other is that binning loses precision if the bin intervals are large.</p>
<p>FTA overcomes these disadvantages. Instead of hard boundaries like in Tiling Activations, FTA uses soft boundaries between bins. This gives non-zero gradients for all or a wide range of values. And also doesn&#x27;t lose precision since it&#x27;s captured in partial values.</p>
<h4>Tiling Activations</h4>
<p><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.44444em;vertical-align:0em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span></span></span></span> is the tiling vector,</p>
<p><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.44444em;vertical-align:0em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord mathnormal" style="margin-right:0.03785em;">δ</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord">2</span><span class="mord mathnormal" style="margin-right:0.03785em;">δ</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="minner"></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqr" style=""><span class="mord mathnormal" style="">u</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord">2</span><span class="mord mathnormal" style="margin-right:0.03785em;">δ</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqr" style=""><span class="mord mathnormal" style="">u</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span><span class="mclose">)</span></span></span></span></span></p>
<p>where <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">[</span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqr" style=""><span class="mord mathnormal" style="">u</span></span><span class="mclose">]</span></span></span></span> is the input range, <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span></span></span></span> is the bin size, and <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.77777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqm" style=""><span class="mord coloredeq eqr" style=""><span class="mord mathnormal" style="">u</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style=""></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span></span></span></span></span> is divisible by <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span></span></span></span>.</p>
<p>Tiling activation is,</p>
<p><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal">ϕ</span><span class="mopen">(</span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqp" style=""><span class="mord" style="">1</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1.20001em;vertical-align:-0.35001em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mbin mtight">+</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mord"><span class="delimsizing size1">(</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style="">0</span></span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.77777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1.20001em;vertical-align:-0.35001em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span><span class="mclose">)</span><span class="mord"><span class="delimsizing size1">)</span></span></span></span></span></span></p>
<p>where <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mbin mtight">+</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"></span><span class="mclose">)</span></span></span></span> is the indicator function which gives <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqp" style=""><span class="mord" style="">1</span></span></span></span></span> if the input is positive and <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style="">0</span></span></span></span></span> otherwise.</p>
<p>Note that tiling activation gives zero gradients because it has hard boundaries.</p>
<h4>Fuzzy Tiling Activations</h4>
<p>The fuzzy indicator function,</p>
<p><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.036108em;vertical-align:-0.286108em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight" style="margin-right:0.03588em;">η</span><span class="mpunct mtight">,</span><span class="mord mtight">+</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mbin mtight">+</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mbin mtight">+</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span><span class="mclose">)</span></span></span></span></span></p>
<p>which increases linearly from <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style="">0</span></span></span></span></span> to <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqp" style=""><span class="mord" style="">1</span></span></span></span></span> when <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.78041em;vertical-align:-0.13597em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style="">0</span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel"></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.5782em;vertical-align:-0.0391em;"></span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">&lt;</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span></span></span></span> and is equal to <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqp" style=""><span class="mord" style="">1</span></span></span></span></span> for <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8304100000000001em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel"></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord mathnormal">x</span></span></span></span>. <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span></span></span></span> is a hyper-parameter.</p>
<p>FTA uses this to create soft boundaries between bins.</p>
<p><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.036108em;vertical-align:-0.286108em;"></span><span class="mord coloredeq eqg" style=""><span class="mord" style=""><span class="mord mathnormal" style="">ϕ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.15139200000000003em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight coloredeq eqn" style=""><span class="mord mathnormal mtight" style="margin-right:0.03588em">η</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><span></span></span></span></span></span></span><span class="mopen" style="">(</span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mclose" style="">)</span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqp" style=""><span class="mord" style="">1</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1.20001em;vertical-align:-0.35001em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight" style="margin-right:0.03588em;">η</span><span class="mpunct mtight">,</span><span class="mord mtight">+</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><span></span></span></span></span></span></span><span class="mord"><span class="delimsizing size1">(</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style="">0</span></span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.77777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1.20001em;vertical-align:-0.35001em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style="">0</span></span><span class="mclose">)</span><span class="mord"><span class="delimsizing size1">)</span></span></span></span></span></span></p>
<p><a href="experiment.html">Here&#x27;s a simple experiment</a> that uses FTA in a transformer.</p>
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/activations/fta/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://www.comet.ml/labml/fta/69be11f83693407f82a86dcbb232bcfe?experiment-tab=chart&showOutliers=true&smoothing=0&transformY=smoothing&viewId=rlJOpXDGtL8zbkcX66R77P5me&xAxis=step"><img alt="Open In Comet" src="https://images.labml.ai/images/comet.svg?experiment=capsule_networks&file=model"></a></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">62</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
<span class="lineno">63</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</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>
<h3>Fuzzy Tiling Activations (FTA)</h3>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">66</span><span class="k">class</span> <span class="nc">FTA</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-2'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-2'>#</a>
</div>
<ul><li><code>lower_limit</code> is the lower limit <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span></span></span></span> </li>
<li><code>upper_limit</code> is the upper limit <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqr" style=""><span class="mord mathnormal" style="">u</span></span></span></span></span> </li>
<li><code>delta</code> is the bin size <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span></span></span></span> </li>
<li><code>eta</code> is the parameter <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span></span></span></span> that detemines the softness of the boundaries.</li></ul>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">71</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">lower_limit</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">upper_limit</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">delta</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">eta</span><span class="p">:</span> <span class="nb">float</span><span class="p">):</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">78</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-4'>
<div class='docs'>
<div class='section-link'>
<a href='#section-4'>#</a>
</div>
<p>Initialize tiling vector <span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.44444em;vertical-align:0em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord mathnormal" style="margin-right:0.03785em;">δ</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqq" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord">2</span><span class="mord mathnormal" style="margin-right:0.03785em;">δ</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="minner"></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqr" style=""><span class="mord mathnormal" style="">u</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord">2</span><span class="mord mathnormal" style="margin-right:0.03785em;">δ</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqr" style=""><span class="mord mathnormal" style="">u</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span><span class="mclose">)</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">81</span> <span class="bp">self</span><span class="o">.</span><span class="n">c</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Parameter</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="n">lower_limit</span><span class="p">,</span> <span class="n">upper_limit</span><span class="p">,</span> <span class="n">delta</span><span class="p">),</span> <span class="n">requires_grad</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-5'>
<div class='docs'>
<div class='section-link'>
<a href='#section-5'>#</a>
</div>
<p>The input vector expands by a factor equal to the number of bins <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.2251079999999999em;vertical-align:-0.345em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8801079999999999em;"><span style="top:-2.6550000000000002em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight coloredeq eql" style=""><span class="mord mathnormal mtight" style="margin-right:0.03785em">δ</span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.394em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight coloredeq eqm" style=""><span class="mord mtight coloredeq eqr" style=""><span class="mord mathnormal mtight" style="">u</span></span><span class="mbin mtight" style=""></span><span class="mord mtight coloredeq eqq" style=""><span class="mord mathnormal mtight" style="margin-right:0.01968em">l</span></span></span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.345em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">83</span> <span class="bp">self</span><span class="o">.</span><span class="n">expansion_factor</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">c</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-6'>
<div class='docs'>
<div class='section-link'>
<a href='#section-6'>#</a>
</div>
<p><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">85</span> <span class="bp">self</span><span class="o">.</span><span class="n">delta</span> <span class="o">=</span> <span class="n">delta</span></pre></div>
</div>
</div>
<div class='section' id='section-7'>
<div class='docs'>
<div class='section-link'>
<a href='#section-7'>#</a>
</div>
<p><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">87</span> <span class="bp">self</span><span class="o">.</span><span class="n">eta</span> <span class="o">=</span> <span class="n">eta</span></pre></div>
</div>
</div>
<div class='section' id='section-8'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-8'>#</a>
</div>
<h4>Fuzzy indicator function</h4>
<p><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.036108em;vertical-align:-0.286108em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight" style="margin-right:0.03588em;">η</span><span class="mpunct mtight">,</span><span class="mord mtight">+</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mbin mtight">+</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mbin mtight">+</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.03588em">η</span></span><span class="mclose">)</span></span></span></span></span></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">89</span> <span class="k">def</span> <span class="nf">fuzzy_i_plus</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-9'>
<div class='docs'>
<div class='section-link'>
<a href='#section-9'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">95</span> <span class="k">return</span> <span class="p">(</span><span class="n">x</span> <span class="o">&lt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">eta</span><span class="p">)</span> <span class="o">*</span> <span class="n">x</span> <span class="o">+</span> <span class="p">(</span><span class="n">x</span> <span class="o">&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">eta</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-10'>
<div class='docs'>
<div class='section-link'>
<a href='#section-10'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">97</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">z</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-11'>
<div class='docs'>
<div class='section-link'>
<a href='#section-11'>#</a>
</div>
<p>Add another dimension of size <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqp" style=""><span class="mord" style="">1</span></span></span></span></span>. We will expand this into bins. </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">100</span> <span class="n">z</span> <span class="o">=</span> <span class="n">z</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">*</span><span class="n">z</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-12'>
<div class='docs'>
<div class='section-link'>
<a href='#section-12'>#</a>
</div>
<p><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.036108em;vertical-align:-0.286108em;"></span><span class="mord coloredeq eqg" style=""><span class="mord" style=""><span class="mord mathnormal" style="">ϕ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.15139200000000003em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight coloredeq eqn" style=""><span class="mord mathnormal mtight" style="margin-right:0.03588em">η</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><span></span></span></span></span></span></span><span class="mopen" style="">(</span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mclose" style="">)</span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqp" style=""><span class="mord" style="">1</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1.20001em;vertical-align:-0.35001em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07847em;">I</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.25833100000000003em;"><span style="top:-2.5500000000000003em;margin-left:-0.07847em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight" style="margin-right:0.03588em;">η</span><span class="mpunct mtight">,</span><span class="mord mtight">+</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><span></span></span></span></span></span></span><span class="mord"><span class="delimsizing size1">(</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style="">0</span></span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.77777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.03785em">δ</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin"></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1.20001em;vertical-align:-0.35001em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style="">0</span></span><span class="mclose">)</span><span class="mord"><span class="delimsizing size1">)</span></span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">103</span> <span class="n">z</span> <span class="o">=</span> <span class="mf">1.</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">fuzzy_i_plus</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">c</span> <span class="o">-</span> <span class="n">z</span><span class="p">,</span> <span class="nb">min</span><span class="o">=</span><span class="mf">0.</span><span class="p">)</span> <span class="o">+</span> <span class="n">torch</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">z</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">delta</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">c</span><span class="p">,</span> <span class="nb">min</span><span class="o">=</span><span class="mf">0.</span><span class="p">))</span></pre></div>
</div>
</div>
<div class='section' id='section-13'>
<div class='docs'>
<div class='section-link'>
<a href='#section-13'>#</a>
</div>
<p>Reshape back to original number of dimensions. The last dimension size gets expanded by the number of bins, <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.2251079999999999em;vertical-align:-0.345em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8801079999999999em;"><span style="top:-2.6550000000000002em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight coloredeq eql" style=""><span class="mord mathnormal mtight" style="margin-right:0.03785em">δ</span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.394em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight coloredeq eqm" style=""><span class="mord mtight coloredeq eqr" style=""><span class="mord mathnormal mtight" style="">u</span></span><span class="mbin mtight" style=""></span><span class="mord mtight coloredeq eqq" style=""><span class="mord mathnormal mtight" style="margin-right:0.01968em">l</span></span></span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.345em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span></span></span></span>. </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">107</span> <span class="k">return</span> <span class="n">z</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">*</span><span class="n">z</span><span class="o">.</span><span class="n">shape</span><span class="p">[:</span><span class="o">-</span><span class="mi">2</span><span class="p">],</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-14'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-14'>#</a>
</div>
<h4>Code to test the FTA module</h4>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">110</span><span class="k">def</span> <span class="nf">_test</span><span class="p">():</span></pre></div>
</div>
</div>
<div class='section' id='section-15'>
<div class='docs'>
<div class='section-link'>
<a href='#section-15'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">114</span> <span class="kn">from</span> <span class="nn">labml.logger</span> <span class="kn">import</span> <span class="n">inspect</span></pre></div>
</div>
</div>
<div class='section' id='section-16'>
<div class='docs'>
<div class='section-link'>
<a href='#section-16'>#</a>
</div>
<p>Initialize </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">117</span> <span class="n">a</span> <span class="o">=</span> <span class="n">FTA</span><span class="p">(</span><span class="o">-</span><span class="mi">10</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="mf">2.</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-17'>
<div class='docs'>
<div class='section-link'>
<a href='#section-17'>#</a>
</div>
<p>Print <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.44444em;vertical-align:0em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathbf" style="">c</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">119</span> <span class="n">inspect</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">c</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-18'>
<div class='docs'>
<div class='section-link'>
<a href='#section-18'>#</a>
</div>
<p>Print number of bins <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.2251079999999999em;vertical-align:-0.345em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8801079999999999em;"><span style="top:-2.6550000000000002em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight coloredeq eql" style=""><span class="mord mathnormal mtight" style="margin-right:0.03785em">δ</span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.394em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight coloredeq eqm" style=""><span class="mord mtight coloredeq eqr" style=""><span class="mord mathnormal mtight" style="">u</span></span><span class="mbin mtight" style=""></span><span class="mord mtight coloredeq eqq" style=""><span class="mord mathnormal mtight" style="margin-right:0.01968em">l</span></span></span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.345em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">121</span> <span class="n">inspect</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">expansion_factor</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-19'>
<div class='docs'>
<div class='section-link'>
<a href='#section-19'>#</a>
</div>
<p>Input <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">124</span> <span class="n">z</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">([</span><span class="mf">1.1</span><span class="p">,</span> <span class="mf">2.2</span><span class="p">,</span> <span class="mf">3.3</span><span class="p">,</span> <span class="mf">4.4</span><span class="p">,</span> <span class="mf">5.5</span><span class="p">,</span> <span class="mf">6.6</span><span class="p">,</span> <span class="mf">7.7</span><span class="p">,</span> <span class="mf">8.8</span><span class="p">,</span> <span class="mf">9.</span><span class="p">,</span> <span class="mf">10.</span><span class="p">,</span> <span class="mf">11.</span><span class="p">])</span></pre></div>
</div>
</div>
<div class='section' id='section-20'>
<div class='docs'>
<div class='section-link'>
<a href='#section-20'>#</a>
</div>
<p>Print <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">126</span> <span class="n">inspect</span><span class="p">(</span><span class="n">z</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-21'>
<div class='docs'>
<div class='section-link'>
<a href='#section-21'>#</a>
</div>
<p>Print <span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.036108em;vertical-align:-0.286108em;"></span><span class="mord coloredeq eqg" style=""><span class="mord" style=""><span class="mord mathnormal" style="">ϕ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.15139200000000003em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight coloredeq eqn" style=""><span class="mord mathnormal mtight" style="margin-right:0.03588em">η</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><span></span></span></span></span></span></span><span class="mopen" style="">(</span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="margin-right:0.04398em">z</span></span><span class="mclose" style="">)</span></span></span></span></span> </p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">128</span> <span class="n">inspect</span><span class="p">(</span><span class="n">a</span><span class="p">(</span><span class="n">z</span><span class="p">))</span>
<span class="lineno">129</span>
<span class="lineno">130</span>
<span class="lineno">131</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">132</span> <span class="n">_test</span><span class="p">()</span></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>