<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>pathflowai.schedulers — PathFlowAI 0.1 documentation</title>
<script type="text/javascript" src="../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../_static/jquery.js"></script>
<script type="text/javascript" src="../../_static/underscore.js"></script>
<script type="text/javascript" src="../../_static/doctools.js"></script>
<script type="text/javascript" src="../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../genindex.html" />
<link rel="search" title="Search" href="../../search.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../index.html" class="icon icon-home"> PathFlowAI
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<!-- Local TOC -->
<div class="local-toc"></div>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../index.html">PathFlowAI</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../index.html">Docs</a> »</li>
<li><a href="../index.html">Module code</a> »</li>
<li>pathflowai.schedulers</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for pathflowai.schedulers</h1><div class="highlight"><pre>
<span></span><span class="sd">"""</span>
<span class="sd">schedulers.py</span>
<span class="sd">=======================</span>
<span class="sd">Modulates the learning rate during the training process.</span>
<span class="sd">"""</span>
<span class="kn">import</span> <span class="nn">torch</span>
<span class="kn">import</span> <span class="nn">math</span>
<span class="kn">from</span> <span class="nn">torch.optim.lr_scheduler</span> <span class="k">import</span> <span class="n">ExponentialLR</span>
<div class="viewcode-block" id="CosineAnnealingWithRestartsLR"><a class="viewcode-back" href="../../index.html#pathflowai.schedulers.CosineAnnealingWithRestartsLR">[docs]</a><span class="k">class</span> <span class="nc">CosineAnnealingWithRestartsLR</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">lr_scheduler</span><span class="o">.</span><span class="n">_LRScheduler</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Set the learning rate of each parameter group using a cosine annealing</span>
<span class="sd"> schedule, where :math:`\eta_{max}` is set to the initial lr and</span>
<span class="sd"> :math:`T_{cur}` is the number of epochs since the last restart in SGDR:</span>
<span class="sd"> .. math::</span>
<span class="sd"> \eta_t = \eta_{min} + \frac{1}{2}(\eta_{max} - \eta_{min})(1 +</span>
<span class="sd"> \cos(\frac{T_{cur}}{T_{max}}\pi))</span>
<span class="sd"> When last_epoch=-1, sets initial lr as lr.</span>
<span class="sd"> It has been proposed in</span>
<span class="sd"> `SGDR: Stochastic Gradient Descent with Warm Restarts`_. This implements</span>
<span class="sd"> the cosine annealing part of SGDR, the restarts and number of iterations multiplier.</span>
<span class="sd"> Args:</span>
<span class="sd"> optimizer (Optimizer): Wrapped optimizer.</span>
<span class="sd"> T_max (int): Maximum number of iterations.</span>
<span class="sd"> T_mult (float): Multiply T_max by this number after each restart. Default: 1.</span>
<span class="sd"> eta_min (float): Minimum learning rate. Default: 0.</span>
<span class="sd"> last_epoch (int): The index of last epoch. Default: -1.</span>
<span class="sd"> .. _SGDR\: Stochastic Gradient Descent with Warm Restarts:</span>
<span class="sd"> https://arxiv.org/abs/1608.03983</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">optimizer</span><span class="p">,</span> <span class="n">T_max</span><span class="p">,</span> <span class="n">eta_min</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">last_epoch</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">T_mult</span><span class="o">=</span><span class="mf">1.</span><span class="p">,</span> <span class="n">alpha_decay</span><span class="o">=</span><span class="mf">1.0</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">T_max</span> <span class="o">=</span> <span class="n">T_max</span>
<span class="bp">self</span><span class="o">.</span><span class="n">T_mult</span> <span class="o">=</span> <span class="n">T_mult</span>
<span class="bp">self</span><span class="o">.</span><span class="n">restart_every</span> <span class="o">=</span> <span class="n">T_max</span>
<span class="bp">self</span><span class="o">.</span><span class="n">eta_min</span> <span class="o">=</span> <span class="n">eta_min</span>
<span class="bp">self</span><span class="o">.</span><span class="n">restarts</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">restarted_at</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">alpha</span> <span class="o">=</span> <span class="n">alpha_decay</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">last_epoch</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">restart</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">restarts</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="bp">self</span><span class="o">.</span><span class="n">restart_every</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">restart_every</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">T_mult</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">restarted_at</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_epoch</span>
<span class="k">def</span> <span class="nf">cosine</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">base_lr</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">eta_min</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">alpha</span><span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">restarts</span> <span class="o">*</span> <span class="p">(</span><span class="n">base_lr</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">eta_min</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">math</span><span class="o">.</span><span class="n">cos</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">pi</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">step_n</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">restart_every</span><span class="p">))</span> <span class="o">/</span> <span class="mi">2</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">step_n</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_epoch</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">restarted_at</span>
<span class="k">def</span> <span class="nf">get_lr</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">step_n</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">restart_every</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">restart</span><span class="p">()</span>
<span class="k">return</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">cosine</span><span class="p">(</span><span class="n">base_lr</span><span class="p">)</span> <span class="k">for</span> <span class="n">base_lr</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">base_lrs</span><span class="p">]</span></div>
<div class="viewcode-block" id="Scheduler"><a class="viewcode-back" href="../../index.html#pathflowai.schedulers.Scheduler">[docs]</a><span class="k">class</span> <span class="nc">Scheduler</span><span class="p">:</span>
<span class="sd">"""Scheduler class that modulates learning rate of torch optimizers over epochs.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> optimizer : type</span>
<span class="sd"> torch.Optimizer object</span>
<span class="sd"> opts : type</span>
<span class="sd"> Options of setting the learning rate scheduler, see default.</span>
<span class="sd"> Attributes</span>
<span class="sd"> ----------</span>
<span class="sd"> schedulers : type</span>
<span class="sd"> Different types of schedulers to choose from.</span>
<span class="sd"> scheduler_step_fn : type</span>
<span class="sd"> How scheduler updates learning rate.</span>
<span class="sd"> initial_lr : type</span>
<span class="sd"> Initial set learning rate.</span>
<span class="sd"> scheduler_choice : type</span>
<span class="sd"> What scheduler type was chosen.</span>
<span class="sd"> scheduler : type</span>
<span class="sd"> Scheduler object chosen that will more directly update optimizer LR.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">optimizer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">opts</span><span class="o">=</span><span class="nb">dict</span><span class="p">(</span><span class="n">scheduler</span><span class="o">=</span><span class="s1">'null'</span><span class="p">,</span><span class="n">lr_scheduler_decay</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span><span class="n">T_max</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span><span class="n">eta_min</span><span class="o">=</span><span class="mf">5e-8</span><span class="p">,</span><span class="n">T_mult</span><span class="o">=</span><span class="mi">2</span><span class="p">)):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">schedulers</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'exp'</span><span class="p">:(</span><span class="k">lambda</span> <span class="n">optimizer</span><span class="p">:</span> <span class="n">ExponentialLR</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">opts</span><span class="p">[</span><span class="s2">"lr_scheduler_decay"</span><span class="p">])),</span>
<span class="s1">'null'</span><span class="p">:(</span><span class="k">lambda</span> <span class="n">optimizer</span><span class="p">:</span> <span class="kc">None</span><span class="p">),</span>
<span class="s1">'warm_restarts'</span><span class="p">:(</span><span class="k">lambda</span> <span class="n">optimizer</span><span class="p">:</span> <span class="n">CosineAnnealingWithRestartsLR</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">T_max</span><span class="o">=</span><span class="n">opts</span><span class="p">[</span><span class="s1">'T_max'</span><span class="p">],</span> <span class="n">eta_min</span><span class="o">=</span><span class="n">opts</span><span class="p">[</span><span class="s1">'eta_min'</span><span class="p">],</span> <span class="n">last_epoch</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">T_mult</span><span class="o">=</span><span class="n">opts</span><span class="p">[</span><span class="s1">'T_mult'</span><span class="p">]))}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">scheduler_step_fn</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'exp'</span><span class="p">:(</span><span class="k">lambda</span> <span class="n">scheduler</span><span class="p">:</span> <span class="n">scheduler</span><span class="o">.</span><span class="n">step</span><span class="p">()),</span>
<span class="s1">'warm_restarts'</span><span class="p">:(</span><span class="k">lambda</span> <span class="n">scheduler</span><span class="p">:</span> <span class="n">scheduler</span><span class="o">.</span><span class="n">step</span><span class="p">()),</span>
<span class="s1">'null'</span><span class="p">:(</span><span class="k">lambda</span> <span class="n">scheduler</span><span class="p">:</span> <span class="kc">None</span><span class="p">)}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">initial_lr</span> <span class="o">=</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">param_groups</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="s1">'lr'</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">scheduler_choice</span> <span class="o">=</span> <span class="n">opts</span><span class="p">[</span><span class="s1">'scheduler'</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">scheduler</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">schedulers</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">scheduler_choice</span><span class="p">](</span><span class="n">optimizer</span><span class="p">)</span> <span class="k">if</span> <span class="n">optimizer</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="k">else</span> <span class="kc">None</span>
<div class="viewcode-block" id="Scheduler.step"><a class="viewcode-back" href="../../index.html#pathflowai.schedulers.Scheduler.step">[docs]</a> <span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Update optimizer learning rate"""</span>
<span class="bp">self</span><span class="o">.</span><span class="n">scheduler_step_fn</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">scheduler_choice</span><span class="p">](</span><span class="bp">self</span><span class="o">.</span><span class="n">scheduler</span><span class="p">)</span></div>
<div class="viewcode-block" id="Scheduler.get_lr"><a class="viewcode-back" href="../../index.html#pathflowai.schedulers.Scheduler.get_lr">[docs]</a> <span class="k">def</span> <span class="nf">get_lr</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Return current learning rate.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> float</span>
<span class="sd"> Current learning rate.</span>
<span class="sd"> """</span>
<span class="n">lr</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">initial_lr</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">scheduler_choice</span> <span class="o">==</span> <span class="s1">'null'</span> <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">scheduler</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">param_groups</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="s1">'lr'</span><span class="p">])</span>
<span class="k">return</span> <span class="n">lr</span></div></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
© Copyright 2019, Joshua Levy
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>
Datasets
Models
