chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,501 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="Adam 优化器的一个简单的 PyTorch 实现/教程"/>
|
||||
|
||||
<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="半精度训练的 Adam Optimizer"/>
|
||||
<meta name="twitter:description" content="Adam 优化器的一个简单的 PyTorch 实现/教程"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/adam_fp16.html"/>
|
||||
<meta property="og:title" content="半精度训练的 Adam Optimizer"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="半精度训练的 Adam Optimizer"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="半精度训练的 Adam Optimizer"/>
|
||||
<meta property="og:description" content="Adam 优化器的一个简单的 PyTorch 实现/教程"/>
|
||||
|
||||
<title>半精度训练的 Adam Optimizer</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/adam_fp16.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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/adam_fp16.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>半精度训练的 Adam Optimizer</h1>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">10</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Any</span>
|
||||
<span class="lineno">11</span>
|
||||
<span class="lineno">12</span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">13</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">torch.optim</span> <span class="kn">import</span> <span class="n">Optimizer</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">torch.cuda.amp</span> <span class="kn">import</span> <span class="n">grad_scaler</span>
|
||||
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">defaultdict</span><span class="p">,</span> <span class="n">abc</span>
|
||||
<span class="lineno">17</span>
|
||||
<span class="lineno">18</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</span>
|
||||
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam</span> <span class="kn">import</span> <span class="n">Adam</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>半精度训练的 Adam Optimizer</h2>
|
||||
<p>我们扩展了 <a href="adam.html">Adam Optimizer</a>，但使用 FP32 来存储渐变和时刻。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">22</span><span class="k">class</span> <span class="nc">AdamFP16</span><span class="p">(</span><span class="n">Adam</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">29</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">params</span><span class="p">,</span> <span class="n">lr</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-3</span><span class="p">,</span> <span class="n">betas</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</span><span class="p">),</span> <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-16</span><span class="p">,</span>
|
||||
<span class="lineno">30</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="n">WeightDecay</span> <span class="o">=</span> <span class="n">WeightDecay</span><span class="p">(),</span> <span class="n">optimized_update</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
|
||||
<span class="lineno">31</span> <span class="n">defaults</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</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>
|
||||
<p>用于存储 32 位渐变的参数。这由下面<code class="highlight"><span></span><span class="n">GradScaler</span></code>
|
||||
定义的填充。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">33</span> <span class="bp">self</span><span class="o">.</span><span class="n">grad_fp32</span> <span class="o">=</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>调用 <a href="adam.html">Adam 优化器</a>初始化器</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">35</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">params</span><span class="p">,</span> <span class="n">lr</span><span class="p">,</span> <span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span> <span class="n">weight_decay</span><span class="p">,</span> <span class="n">optimized_update</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-5'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-5'>#</a>
|
||||
</div>
|
||||
<h3>初始化参数状态</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">state</span></code>
|
||||
是参数（张量）的优化器状态</li>
|
||||
<li><code class="highlight"><span></span><span class="n">group</span></code>
|
||||
存储参数组的优化程序属性</li>
|
||||
<li><code class="highlight"><span></span><span class="n">param</span></code>
|
||||
是参数张量<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.902771em;vertical-align:-0.208331em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.02778em">θ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-left:-0.02778em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span><span class="mbin mtight" style="">−</span><span class="mord mtight" style="">1</span></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></span></span></span></span></li></ul>
|
||||
<p>所有状态张量都使用 FP32。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">37</span> <span class="k">def</span> <span class="nf">init_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">state</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">param</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Parameter</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>这是优化器对参数采取的步骤数，<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.61508em;vertical-align:0em;"></span><span class="mord coloredeq eqe" style=""><span class="mord mathnormal" style="">t</span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">49</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</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>梯度的指数移动平均线，<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style=""><span class="mord mathnormal" style="">m</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><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" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">51</span> <span class="n">state</span><span class="p">[</span><span class="s1">'exp_avg'</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">zeros_like</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="n">memory_format</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">preserve_format</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
<p>梯度平方值的指数移动平均线，<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.03588em">v</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-left:-0.03588em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">53</span> <span class="n">state</span><span class="p">[</span><span class="s1">'exp_avg_sq'</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">zeros_like</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="n">memory_format</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">preserve_format</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float</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>
|
||||
<p>维护参数的 FP32 副本</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">55</span> <span class="n">state</span><span class="p">[</span><span class="s1">'fp32_copy'</span><span class="p">]</span> <span class="o">=</span> <span class="n">param</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">float</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-10'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-10'>#</a>
|
||||
</div>
|
||||
<h3>对给定参数张量执行更新步骤</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">state</span></code>
|
||||
是参数（张量）的优化器状态</li>
|
||||
<li><code class="highlight"><span></span><span class="n">group</span></code>
|
||||
存储参数组的优化程序属性</li>
|
||||
<li><code class="highlight"><span></span><span class="n">grad</span></code>
|
||||
是参数的当前梯<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"><span class="mord mathnormal" style="margin-right:0.03588em;">g</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-left:-0.03588em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight coloredeq eqe" style=""><span class="mord mathnormal mtight" style="">t</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>度张量<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.902771em;vertical-align:-0.208331em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.02778em">θ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-left:-0.02778em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span><span class="mbin mtight" style="">−</span><span class="mord mtight" style="">1</span></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></span></span></span></span></li>
|
||||
<li><code class="highlight"><span></span><span class="n">param</span></code>
|
||||
是参数张量<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.902771em;vertical-align:-0.208331em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.02778em">θ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-left:-0.02778em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span><span class="mbin mtight" style="">−</span><span class="mord mtight" style="">1</span></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></span></span></span></span></li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">57</span> <span class="k">def</span> <span class="nf">step_param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">state</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">grad</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">param</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">Parameter</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>获取 FP32 参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">68</span> <span class="n">param_fp32</span> <span class="o">=</span> <span class="n">state</span><span class="p">[</span><span class="s1">'fp32_copy'</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>获取 FP32 渐变（如果有）</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">70</span> <span class="n">grad_fp32</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">grad_fp32</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
||||
<span class="lineno">71</span> <span class="k">if</span> <span class="n">grad_fp32</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="lineno">72</span> <span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">grad_fp32</span><span class="p">[</span><span class="n">param</span><span class="p">]</span>
|
||||
<span class="lineno">73</span> <span class="n">grad</span> <span class="o">=</span> <span class="n">grad_fp32</span>
|
||||
<span class="lineno">74</span> <span class="k">else</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>否则，将渐变转换为 FP32</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">76</span> <span class="n">grad</span> <span class="o">=</span> <span class="n">grad</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">float</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-14'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-14'>#</a>
|
||||
</div>
|
||||
<p>计算体重衰减</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">79</span> <span class="n">grad</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">(</span><span class="n">param_fp32</span><span class="p">,</span> <span class="n">grad</span><span class="p">,</span> <span class="n">group</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>
|
||||
<p>获取<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style=""><span class="mord mathnormal" style="">m</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><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" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span></span>和<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.03588em">v</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-left:-0.03588em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">82</span> <span class="n">m</span><span class="p">,</span> <span class="n">v</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_mv</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="n">group</span><span class="p">,</span> <span class="n">grad</span><span class="p">)</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.61508em;vertical-align:0em;"></span><span class="mord coloredeq eqe" style=""><span class="mord mathnormal" style="">t</span></span></span></span></span></span>增加优化器步数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">85</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">+=</span> <span class="mi">1</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>执行 <em>Adam</em> 更新</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">88</span> <span class="bp">self</span><span class="o">.</span><span class="n">adam_update</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="n">group</span><span class="p">,</span> <span class="n">param_fp32</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">v</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>设置参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">91</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="n">param_fp32</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-19'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-19'>#</a>
|
||||
</div>
|
||||
<h2>具有半精度渐变的渐变缩放器</h2>
|
||||
<p>我们将 PyTorch 梯度缩放器扩展为使用 FP32 渐变。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">94</span><span class="k">class</span> <span class="nc">GradScalerFP16</span><span class="p">(</span><span class="n">grad_scaler</span><span class="o">.</span><span class="n">GradScaler</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">101</span> <span class="k">def</span> <span class="nf">_unscale_grads_</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">Optimizer</span><span class="p">,</span> <span class="n">inv_scale</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">found_inf</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span>
|
||||
<span class="lineno">102</span> <span class="n">allow_fp16</span><span class="p">:</span> <span class="nb">bool</span><span class="p">)</span> <span class="o">-></span> <span class="n">Dict</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">]:</span>
|
||||
<span class="lineno">103</span> <span class="n">per_device_inv_scale</span> <span class="o">=</span> <span class="n">grad_scaler</span><span class="o">.</span><span class="n">_MultiDeviceReplicator</span><span class="p">(</span><span class="n">inv_scale</span><span class="p">)</span>
|
||||
<span class="lineno">104</span> <span class="n">per_device_found_inf</span> <span class="o">=</span> <span class="n">grad_scaler</span><span class="o">.</span><span class="n">_MultiDeviceReplicator</span><span class="p">(</span><span class="n">found_inf</span><span class="p">)</span>
|
||||
<span class="lineno">105</span>
|
||||
<span class="lineno">106</span> <span class="n">per_device_and_dtype_grads</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">defaultdict</span><span class="p">(</span><span class="nb">list</span><span class="p">))</span> <span class="c1"># type: ignore[var-annotated]</span>
|
||||
<span class="lineno">107</span>
|
||||
<span class="lineno">108</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</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>循环浏览参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">110</span> <span class="k">for</span> <span class="n">group</span> <span class="ow">in</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">param_groups</span><span class="p">:</span>
|
||||
<span class="lineno">111</span> <span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="n">group</span><span class="p">[</span><span class="s2">"params"</span><span class="p">]:</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-22'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-22'>#</a>
|
||||
</div>
|
||||
<p>跳过不可训练的参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">113</span> <span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="lineno">114</span> <span class="k">continue</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-23'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-23'>#</a>
|
||||
</div>
|
||||
<p>未针对稀疏张量实现</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">116</span> <span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span><span class="o">.</span><span class="n">is_sparse</span><span class="p">:</span>
|
||||
<span class="lineno">117</span> <span class="k">raise</span> <span class="ne">NotImplementedError</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-24'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-24'>#</a>
|
||||
</div>
|
||||
<p>如果我们使用设置为<code class="highlight"><span></span><span class="n">optimizer</span><span class="o">.</span><span class="n">grad_fp32</span><span class="p">[</span><span class="n">param</span><span class="p">]</span></code>
|
||||
FP32 渐变的<code class="highlight"><span></span><span class="n">AdamFP16</span></code>
|
||||
优化器</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">120</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">AdamFP16</span><span class="p">):</span>
|
||||
<span class="lineno">121</span> <span class="n">grad</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</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">float</span><span class="p">)</span>
|
||||
<span class="lineno">122</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">grad_fp32</span><span class="p">[</span><span class="n">param</span><span class="p">]</span> <span class="o">=</span> <span class="n">grad</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-25'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-25'>#</a>
|
||||
</div>
|
||||
<p>否则，不要将渐变转换为 FP32</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">124</span> <span class="k">else</span><span class="p">:</span>
|
||||
<span class="lineno">125</span> <span class="n">grad</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span>
|
||||
<span class="lineno">126</span>
|
||||
<span class="lineno">127</span> <span class="n">per_device_and_dtype_grads</span><span class="p">[</span><span class="n">grad</span><span class="o">.</span><span class="n">device</span><span class="p">][</span><span class="n">grad</span><span class="o">.</span><span class="n">dtype</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">grad</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-26'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-26'>#</a>
|
||||
</div>
|
||||
<p>取消缩放所有渐变</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">130</span> <span class="k">for</span> <span class="n">device</span><span class="p">,</span> <span class="n">per_dtype_grads</span> <span class="ow">in</span> <span class="n">per_device_and_dtype_grads</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||||
<span class="lineno">131</span> <span class="k">for</span> <span class="n">grads</span> <span class="ow">in</span> <span class="n">per_dtype_grads</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
|
||||
<span class="lineno">132</span> <span class="n">torch</span><span class="o">.</span><span class="n">_amp_foreach_non_finite_check_and_unscale_</span><span class="p">(</span><span class="n">grads</span><span class="p">,</span>
|
||||
<span class="lineno">133</span> <span class="n">per_device_found_inf</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">device</span><span class="p">),</span>
|
||||
<span class="lineno">134</span> <span class="n">per_device_inv_scale</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">device</span><span class="p">))</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-27'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-27'>#</a>
|
||||
</div>
|
||||
<p></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">136</span> <span class="k">return</span> <span class="n">per_device_found_inf</span><span class="o">.</span><span class="n">_per_device_tensors</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
@@ -0,0 +1,242 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="一个简单的 PyTorch 实现/教程的 Adam 优化器，带有预热功能。"/>
|
||||
|
||||
<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="带热身功能的 Adam 优化器"/>
|
||||
<meta name="twitter:description" content="一个简单的 PyTorch 实现/教程的 Adam 优化器，带有预热功能。"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/adam_warmup.html"/>
|
||||
<meta property="og:title" content="带热身功能的 Adam 优化器"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="带热身功能的 Adam 优化器"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="带热身功能的 Adam 优化器"/>
|
||||
<meta property="og:description" content="一个简单的 PyTorch 实现/教程的 Adam 优化器，带有预热功能。"/>
|
||||
|
||||
<title>带热身功能的 Adam 优化器</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/adam_warmup.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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/adam_warmup.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>Adam Optimizer 带热身</h1>
|
||||
<p>这扩展了 <a href="amsgrad.html">AmsGrad 优化器</a>并增加了预热阶段。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">12</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span>
|
||||
<span class="lineno">13</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.amsgrad</span> <span class="kn">import</span> <span class="n">AMSGrad</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>Adam Optimizer 带热身</h2>
|
||||
<p>这个类是从中定义的 AmsGrad 优化器扩展而来的<a href="amsgrad.html"><code class="highlight"><span></span><span class="n">amsgrad</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a>。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">18</span><span class="k">class</span> <span class="nc">AdamWarmup</span><span class="p">(</span><span class="n">AMSGrad</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>
|
||||
<h3>初始化优化器</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">params</span></code>
|
||||
是参数列表</li>
|
||||
<li><code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
是学习率<span ><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 eqf" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span></li>
|
||||
<li><code class="highlight"><span></span><span class="n">betas</span></code>
|
||||
是 (<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>,<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>) 的元组</li>
|
||||
<li><code class="highlight"><span></span><span class="n">eps</span></code>
|
||||
是<span ><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 accent"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.69444em;"><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord coloredeq eqc" style=""><span class="mord mathnormal" style="">ϵ</span></span></span><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="accent-body" style="left:-0.19444em;"><span class="mord">^</span></span></span></span></span></span></span></span></span></span></span>或<span ><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 eqc" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span>基于<code class="highlight"><span></span><span class="n">optimized_update</span></code>
|
||||
</li>
|
||||
<li><code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||||
是在中<code class="highlight"><span></span><span class="n">WeightDecay</span></code>
|
||||
定义的类的实例 <a href="index.html"><code class="highlight"><span></span><span class="fm">__init__</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a></li>
|
||||
<li>“optimized_update” 是一个标志，在添加后是否要优化第二个时刻的偏差校正<span ><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 eqc" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span></li>
|
||||
<li><code class="highlight"><span></span><span class="n">amsgrad</span></code>
|
||||
是一个标志，指示是使用 AmsGrad 还是回退到普通的 Adam</li>
|
||||
<li><code class="highlight"><span></span><span class="n">warmup</span></code>
|
||||
预热步数</li>
|
||||
<li><code class="highlight"><span></span><span class="n">defaults</span></code>
|
||||
是组值的默认字典。当你想扩展类时，这很有用<code class="highlight"><span></span><span class="n">AdamWarmup</span></code>
|
||||
。</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">24</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">params</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</span><span class="p">),</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-16</span><span class="p">,</span>
|
||||
<span class="lineno">25</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="n">WeightDecay</span> <span class="o">=</span> <span class="n">WeightDecay</span><span class="p">(),</span>
|
||||
<span class="lineno">26</span> <span class="n">optimized_update</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
|
||||
<span class="lineno">27</span> <span class="n">amsgrad</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">defaults</span><span class="o">=</span><span class="kc">None</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">44</span> <span class="n">defaults</span> <span class="o">=</span> <span class="p">{}</span> <span class="k">if</span> <span class="n">defaults</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">defaults</span>
|
||||
<span class="lineno">45</span> <span class="n">defaults</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">warmup</span><span class="o">=</span><span class="n">warmup</span><span class="p">))</span>
|
||||
<span class="lineno">46</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">params</span><span class="p">,</span> <span class="n">lr</span><span class="p">,</span> <span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span> <span class="n">weight_decay</span><span class="p">,</span> <span class="n">optimized_update</span><span class="p">,</span> <span class="n">amsgrad</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<h3>获取学习率</h3>
|
||||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqf" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mop">min</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="delimsizing size3">(</span></span><span class="mord">1</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></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:1.29208em;"><span style="top:-2.314em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq eqh" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord mathnormal">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.686em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord"><span class="delimsizing size3">)</span></span></span></span></span></span></span>其中<span ><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 eqh" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</span></span></span></span></span></span>是预热步骤的数量。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">48</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="n">state</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</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>如果我们处于热身阶段</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">56</span> <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">]</span> <span class="o">></span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</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>学习率从线性增加<span ><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">0</span></span></span></span></span>到<span ><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 eqf" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">58</span> <span class="k">return</span> <span class="mf">1e-8</span> <span class="o">+</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">*</span> <span class="n">group</span><span class="p">[</span><span class="s1">'lr'</span><span class="p">]</span> <span class="o">/</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">]</span>
|
||||
<span class="lineno">59</span> <span class="k">else</span><span class="p">:</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>持续的学习速率<span ><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 eqf" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">61</span> <span class="k">return</span> <span class="n">group</span><span class="p">[</span><span class="s1">'lr'</span><span class="p">]</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
@@ -0,0 +1,293 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="Adam 优化器的 PyTorch 实现/教程，具有 GPT 的预热和余弦衰减。"/>
|
||||
|
||||
<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="具有预热和余弦衰减的 Adam 优化器"/>
|
||||
<meta name="twitter:description" content="Adam 优化器的 PyTorch 实现/教程，具有 GPT 的预热和余弦衰减。"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/adam_warmup_cosine_decay.html"/>
|
||||
<meta property="og:title" content="具有预热和余弦衰减的 Adam 优化器"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="具有预热和余弦衰减的 Adam 优化器"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="具有预热和余弦衰减的 Adam 优化器"/>
|
||||
<meta property="og:description" content="Adam 优化器的 PyTorch 实现/教程，具有 GPT 的预热和余弦衰减。"/>
|
||||
|
||||
<title>具有预热和余弦衰减的 Adam 优化器</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/adam_warmup_cosine_decay.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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/adam_warmup_cosine_decay.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>带有预热和余弦衰减的 Adam Optimizer</h1>
|
||||
<p>这扩展了 <a href="adam.html">AmsGrad 优化器</a>并增加了预热阶段。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">11</span><span></span><span class="kn">import</span> <span class="nn">math</span>
|
||||
<span class="lineno">12</span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span>
|
||||
<span class="lineno">13</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.amsgrad</span> <span class="kn">import</span> <span class="n">AMSGrad</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>
|
||||
<p><a id="EmbeddingsWithPositionalEncoding"></a></p>
|
||||
<h2>带有预热和余弦衰减的 Adam Optimizer</h2>
|
||||
<p>这个类是从中定义的 AmsGrad 优化器扩展而来的<a href="amsgrad.html"><code class="highlight"><span></span><span class="n">amsgrad</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a>。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">18</span><span class="k">class</span> <span class="nc">AdamWarmupCosineDecay</span><span class="p">(</span><span class="n">AMSGrad</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>
|
||||
<h3>初始化优化器</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">params</span></code>
|
||||
是参数列表</li>
|
||||
<li><code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
是学习率<span ><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 eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span></li>
|
||||
<li><code class="highlight"><span></span><span class="n">betas</span></code>
|
||||
是 (<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>,<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>) 的元组</li>
|
||||
<li><code class="highlight"><span></span><span class="n">eps</span></code>
|
||||
是<span ><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 accent"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.69444em;"><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord coloredeq eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="accent-body" style="left:-0.19444em;"><span class="mord">^</span></span></span></span></span></span></span></span></span></span></span>或<span ><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 eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span>基于<code class="highlight"><span></span><span class="n">optimized_update</span></code>
|
||||
</li>
|
||||
<li><code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||||
是在中<code class="highlight"><span></span><span class="n">WeightDecay</span></code>
|
||||
定义的类的实例 <a href="index.html"><code class="highlight"><span></span><span class="fm">__init__</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a></li>
|
||||
<li>“optimized_update” 是一个标志，在添加后是否要优化第二个时刻的偏差校正<span ><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 eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span></li>
|
||||
<li><code class="highlight"><span></span><span class="n">amsgrad</span></code>
|
||||
是一个标志，指示是使用 AmsGrad 还是回退到普通的 Adam</li>
|
||||
<li><code class="highlight"><span></span><span class="n">warmup</span></code>
|
||||
预热步数</li>
|
||||
<li><code class="highlight"><span></span><span class="n">total_steps</span></code>
|
||||
总步数。此时余弦衰减达到 0，但保持在 10%，<code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
因为我们得</li>到<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.46528em;vertical-align:0em;"></span><span class="mord coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</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="mop">max</span><span class="mopen">(</span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span><span class="mord">.1</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord mathnormal">d</span><span class="mord mathnormal">ec</span><span class="mord mathnormal">a</span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mclose">)</span></span></span></span></span>
|
||||
<li><code class="highlight"><span></span><span class="n">defaults</span></code>
|
||||
是组值的默认字典。当你想扩展类时，这很有用<code class="highlight"><span></span><span class="n">AdamWarmup</span></code>
|
||||
。</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">27</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">params</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</span><span class="p">),</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-16</span><span class="p">,</span>
|
||||
<span class="lineno">28</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="n">WeightDecay</span> <span class="o">=</span> <span class="n">WeightDecay</span><span class="p">(),</span>
|
||||
<span class="lineno">29</span> <span class="n">optimized_update</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
|
||||
<span class="lineno">30</span> <span class="n">amsgrad</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">total_steps</span><span class="o">=</span><span class="mf">1e10</span><span class="p">,</span> <span class="n">defaults</span><span class="o">=</span><span class="kc">None</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">49</span> <span class="n">defaults</span> <span class="o">=</span> <span class="p">{}</span> <span class="k">if</span> <span class="n">defaults</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">defaults</span>
|
||||
<span class="lineno">50</span> <span class="n">defaults</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">warmup</span><span class="o">=</span><span class="n">warmup</span><span class="p">,</span> <span class="n">total_steps</span><span class="o">=</span><span class="n">total_steps</span><span class="p">))</span>
|
||||
<span class="lineno">51</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">params</span><span class="p">,</span> <span class="n">lr</span><span class="p">,</span> <span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span> <span class="n">weight_decay</span><span class="p">,</span> <span class="n">optimized_update</span><span class="p">,</span> <span class="n">amsgrad</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<h3>获取学习率</h3>
|
||||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mop">min</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="delimsizing size3">(</span></span><span class="mord">1</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></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:1.29208em;"><span style="top:-2.314em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq eqi" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord mathnormal">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.686em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord"><span class="delimsizing size3">)</span></span></span></span></span></span></span>其中<span ><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 eqi" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</span></span></span></span></span></span>是预热步骤的数量。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">53</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="n">state</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</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>如果我们处于热身阶段</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">61</span> <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">]</span> <span class="o">></span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</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>学习率从线性增加<span ><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 eqh" style=""><span class="mord" style="">0</span></span></span></span></span></span>到<span ><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 eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">63</span> <span class="k">return</span> <span class="mf">1e-8</span> <span class="o">+</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">*</span> <span class="n">group</span><span class="p">[</span><span class="s1">'lr'</span><span class="p">]</span> <span class="o">/</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">]</span>
|
||||
<span class="lineno">64</span> <span class="k">else</span><span class="p">:</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>持续的学习速率<span ><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 eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">66</span> <span class="n">progress</span> <span class="o">=</span> <span class="p">(</span><span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">])</span> <span class="o">/</span> <span class="nb">max</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">group</span><span class="p">[</span><span class="s1">'total_steps'</span><span class="p">]</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">])</span>
|
||||
<span class="lineno">67</span> <span class="k">return</span> <span class="n">group</span><span class="p">[</span><span class="s1">'lr'</span><span class="p">]</span> <span class="o">*</span> <span class="nb">max</span><span class="p">(</span><span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.5</span> <span class="o">*</span> <span class="p">(</span><span class="mf">1.0</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="n">progress</span><span class="p">)))</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>
|
||||
<h3>绘制不同预热和模型大小的学习速率</h3>
|
||||
<p><img alt="Plot of learning rate" src="noam_lr.png"></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">70</span><span class="k">def</span> <span class="nf">_test_lr</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">76</span> <span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
|
||||
<span class="lineno">77</span> <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
<span class="lineno">78</span> <span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">79</span>
|
||||
<span class="lineno">80</span> <span class="n">model</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
|
||||
<span class="lineno">81</span> <span class="n">opt</span> <span class="o">=</span> <span class="n">AdamWarmupCosineDecay</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">5000</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mf">1e-4</span><span class="p">,</span> <span class="n">total_steps</span><span class="o">=</span><span class="mf">4e6</span><span class="p">)</span>
|
||||
<span class="lineno">82</span> <span class="n">steps</span> <span class="o">=</span> <span class="mi">20_000</span>
|
||||
<span class="lineno">83</span> <span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">steps</span><span class="p">),</span> <span class="p">[</span><span class="n">opt</span><span class="o">.</span><span class="n">get_lr</span><span class="p">({</span><span class="s1">'step'</span><span class="p">:</span> <span class="n">i</span><span class="p">},</span> <span class="n">opt</span><span class="o">.</span><span class="n">defaults</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">steps</span><span class="p">)])</span>
|
||||
<span class="lineno">84</span> <span class="n">plt</span><span class="o">.</span><span class="n">legend</span><span class="p">([</span><span class="s2">"5000:4e6"</span><span class="p">,</span> <span class="s2">"5000:2e6"</span><span class="p">,</span> <span class="s2">"5000:1e6"</span><span class="p">])</span>
|
||||
<span class="lineno">85</span> <span class="n">plt</span><span class="o">.</span><span class="n">title</span><span class="p">(</span><span class="s2">"Learning Rate"</span><span class="p">)</span>
|
||||
<span class="lineno">86</span> <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
|
||||
<span class="lineno">87</span>
|
||||
<span class="lineno">88</span> <span class="n">steps</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="mf">6e6</span><span class="p">)</span>
|
||||
<span class="lineno">89</span> <span class="n">step_size</span> <span class="o">=</span> <span class="mi">1000</span>
|
||||
<span class="lineno">90</span> <span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">steps</span><span class="p">,</span> <span class="n">step_size</span><span class="p">),</span> <span class="p">[</span><span class="n">opt</span><span class="o">.</span><span class="n">get_lr</span><span class="p">({</span><span class="s1">'step'</span><span class="p">:</span> <span class="n">i</span><span class="p">},</span> <span class="n">opt</span><span class="o">.</span><span class="n">defaults</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">steps</span><span class="p">,</span> <span class="n">step_size</span><span class="p">)])</span>
|
||||
<span class="lineno">91</span> <span class="n">plt</span><span class="o">.</span><span class="n">legend</span><span class="p">([</span><span class="s2">"5000:4e6"</span><span class="p">,</span> <span class="s2">"5000:2e6"</span><span class="p">,</span> <span class="s2">"5000:1e6"</span><span class="p">])</span>
|
||||
<span class="lineno">92</span> <span class="n">plt</span><span class="o">.</span><span class="n">title</span><span class="p">(</span><span class="s2">"Learning Rate"</span><span class="p">)</span>
|
||||
<span class="lineno">93</span> <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
|
||||
<span class="lineno">94</span>
|
||||
<span class="lineno">95</span>
|
||||
<span class="lineno">96</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
||||
<span class="lineno">97</span> <span class="n">_test_lr</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,452 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="这为优化器实现了一个可配置的模块。"/>
|
||||
|
||||
<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="可配置的优化器模块"/>
|
||||
<meta name="twitter:description" content="这为优化器实现了一个可配置的模块。"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/configs.html"/>
|
||||
<meta property="og:title" content="可配置的优化器模块"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="可配置的优化器模块"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="可配置的优化器模块"/>
|
||||
<meta property="og:description" content="这为优化器实现了一个可配置的模块。"/>
|
||||
|
||||
<title>可配置的优化器模块</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/configs.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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/configs.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>可配置的优化器</h1>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">10</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span>
|
||||
<span class="lineno">11</span>
|
||||
<span class="lineno">12</span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">13</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">BaseConfigs</span><span class="p">,</span> <span class="n">option</span><span class="p">,</span> <span class="n">meta_config</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</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>
|
||||
<p><a id="OptimizerConfigs"></a></p>
|
||||
<h2>优化器配置</h2>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">18</span><span class="k">class</span> <span class="nc">OptimizerConfigs</span><span class="p">(</span><span class="n">BaseConfigs</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>
|
||||
<p>优化器</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">26</span> <span class="n">optimizer</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">Adam</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-3'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-3'>#</a>
|
||||
</div>
|
||||
<p>体重衰减</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">29</span> <span class="n">weight_decay_obj</span><span class="p">:</span> <span class="n">WeightDecay</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>权重衰减是否解耦；即权重衰减不添加到梯度中</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">32</span> <span class="n">weight_decouple</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</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>体重衰减</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">34</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</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>体重衰减是绝对的还是应该乘以学习速率</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">36</span> <span class="n">weight_decay_absolute</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</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>adam 更新是否经过优化（不同的 epsilon）</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">39</span> <span class="n">optimized_adam_update</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
<p>要优化的参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">42</span> <span class="n">parameters</span><span class="p">:</span> <span class="nb">any</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-9'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-9'>#</a>
|
||||
</div>
|
||||
<p>学习率<span ><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 mathnormal" style="margin-right:0.0037em;">α</span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">45</span> <span class="n">learning_rate</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-10'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-10'>#</a>
|
||||
</div>
|
||||
<p>Adam<span ><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"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> 的 Beta 值</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">47</span> <span class="n">betas</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</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>Epsilon<span ><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 mathnormal">ϵ</span></span></span></span></span> 代表亚当</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">49</span> <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-08</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>新加坡元的势头</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">52</span> <span class="n">momentum</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.5</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>是否使用 AmsGrad</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">54</span> <span class="n">amsgrad</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-14'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-14'>#</a>
|
||||
</div>
|
||||
<p>预热优化器步骤数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">57</span> <span class="n">warmup</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2_000</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-15'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-15'>#</a>
|
||||
</div>
|
||||
<p>优化器步长总数（余弦衰减）</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">59</span> <span class="n">total_steps</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="mf">1e10</span><span class="p">)</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>是否在 AdaBeLief 中退化为新加坡元</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">62</span> <span class="n">degenerate_to_sgd</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</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>是否在 AdaBelief 中使用整改过的亚当</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">65</span> <span class="n">rectify</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</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>Noam 优化器的模型嵌入大小</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">68</span> <span class="n">d_model</span><span class="p">:</span> <span class="nb">int</span>
|
||||
<span class="lineno">69</span>
|
||||
<span class="lineno">70</span> <span class="n">rho</span><span class="p">:</span> <span class="nb">float</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-19'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-19'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">72</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="lineno">73</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">_primary</span><span class="o">=</span><span class="s1">'optimizer'</span><span class="p">)</span>
|
||||
<span class="lineno">74</span>
|
||||
<span class="lineno">75</span>
|
||||
<span class="lineno">76</span><span class="n">meta_config</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">parameters</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">79</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="s1">'L2'</span><span class="p">)</span>
|
||||
<span class="lineno">80</span><span class="k">def</span> <span class="nf">_weight_decay</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">81</span> <span class="k">return</span> <span class="n">WeightDecay</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">weight_decouple</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">weight_decay_absolute</span><span class="p">)</span>
|
||||
<span class="lineno">82</span>
|
||||
<span class="lineno">83</span>
|
||||
<span class="lineno">84</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'SGD'</span><span class="p">)</span>
|
||||
<span class="lineno">85</span><span class="k">def</span> <span class="nf">_sgd_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">86</span> <span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">SGD</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">momentum</span><span class="p">,</span>
|
||||
<span class="lineno">87</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">)</span>
|
||||
<span class="lineno">88</span>
|
||||
<span class="lineno">89</span>
|
||||
<span class="lineno">90</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'Adam'</span><span class="p">)</span>
|
||||
<span class="lineno">91</span><span class="k">def</span> <span class="nf">_adam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">92</span> <span class="k">if</span> <span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">:</span>
|
||||
<span class="lineno">93</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.amsgrad</span> <span class="kn">import</span> <span class="n">AMSGrad</span>
|
||||
<span class="lineno">94</span> <span class="k">return</span> <span class="n">AMSGrad</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">95</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">96</span> <span class="n">optimized_update</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">optimized_adam_update</span><span class="p">,</span>
|
||||
<span class="lineno">97</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">)</span>
|
||||
<span class="lineno">98</span> <span class="k">else</span><span class="p">:</span>
|
||||
<span class="lineno">99</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam</span> <span class="kn">import</span> <span class="n">Adam</span>
|
||||
<span class="lineno">100</span> <span class="k">return</span> <span class="n">Adam</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">101</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">102</span> <span class="n">optimized_update</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">optimized_adam_update</span><span class="p">,</span>
|
||||
<span class="lineno">103</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">)</span>
|
||||
<span class="lineno">104</span>
|
||||
<span class="lineno">105</span>
|
||||
<span class="lineno">106</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'AdamW'</span><span class="p">)</span>
|
||||
<span class="lineno">107</span><span class="k">def</span> <span class="nf">_adam_warmup_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">108</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam_warmup</span> <span class="kn">import</span> <span class="n">AdamWarmup</span>
|
||||
<span class="lineno">109</span> <span class="k">return</span> <span class="n">AdamWarmup</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">110</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">111</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">warmup</span><span class="p">)</span>
|
||||
<span class="lineno">112</span>
|
||||
<span class="lineno">113</span>
|
||||
<span class="lineno">114</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'RAdam'</span><span class="p">)</span>
|
||||
<span class="lineno">115</span><span class="k">def</span> <span class="nf">_radam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">116</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.radam</span> <span class="kn">import</span> <span class="n">RAdam</span>
|
||||
<span class="lineno">117</span> <span class="k">return</span> <span class="n">RAdam</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">118</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">119</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span>
|
||||
<span class="lineno">120</span> <span class="n">degenerated_to_sgd</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">degenerate_to_sgd</span><span class="p">)</span>
|
||||
<span class="lineno">121</span>
|
||||
<span class="lineno">122</span>
|
||||
<span class="lineno">123</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'AdaBelief'</span><span class="p">)</span>
|
||||
<span class="lineno">124</span><span class="k">def</span> <span class="nf">_ada_belief_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">125</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.ada_belief</span> <span class="kn">import</span> <span class="n">AdaBelief</span>
|
||||
<span class="lineno">126</span> <span class="k">return</span> <span class="n">AdaBelief</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">127</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">128</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span>
|
||||
<span class="lineno">129</span> <span class="n">degenerate_to_sgd</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">degenerate_to_sgd</span><span class="p">,</span>
|
||||
<span class="lineno">130</span> <span class="n">rectify</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">rectify</span><span class="p">)</span>
|
||||
<span class="lineno">131</span>
|
||||
<span class="lineno">132</span>
|
||||
<span class="lineno">133</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'Noam'</span><span class="p">)</span>
|
||||
<span class="lineno">134</span><span class="k">def</span> <span class="nf">_noam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">135</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.noam</span> <span class="kn">import</span> <span class="n">Noam</span>
|
||||
<span class="lineno">136</span> <span class="k">return</span> <span class="n">Noam</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">137</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">138</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">warmup</span><span class="p">,</span>
|
||||
<span class="lineno">139</span> <span class="n">d_model</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">d_model</span><span class="p">)</span>
|
||||
<span class="lineno">140</span>
|
||||
<span class="lineno">141</span>
|
||||
<span class="lineno">142</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'Sophia'</span><span class="p">)</span>
|
||||
<span class="lineno">143</span><span class="k">def</span> <span class="nf">_sophia_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">144</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.sophia</span> <span class="kn">import</span> <span class="n">Sophia</span>
|
||||
<span class="lineno">145</span> <span class="k">return</span> <span class="n">Sophia</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">146</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">147</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">rho</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">rho</span><span class="p">)</span>
|
||||
<span class="lineno">148</span>
|
||||
<span class="lineno">149</span>
|
||||
<span class="lineno">150</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'AdamWarmupCosineDecay'</span><span class="p">)</span>
|
||||
<span class="lineno">151</span><span class="k">def</span> <span class="nf">_noam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">152</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam_warmup_cosine_decay</span> <span class="kn">import</span> <span class="n">AdamWarmupCosineDecay</span>
|
||||
<span class="lineno">153</span> <span class="k">return</span> <span class="n">AdamWarmupCosineDecay</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">154</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">155</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span>
|
||||
<span class="lineno">156</span> <span class="n">warmup</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">warmup</span><span class="p">,</span> <span class="n">total_steps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">total_steps</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
@@ -0,0 +1,583 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="一组流行的基于梯度下降的优化器的 PyTorch 实现/教程。目前包括 Adam、AmsGrad 和 RadAM 优化器。"/>
|
||||
|
||||
<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="优化器"/>
|
||||
<meta name="twitter:description" content="一组流行的基于梯度下降的优化器的 PyTorch 实现/教程。目前包括 Adam、AmsGrad 和 RadAM 优化器。"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/index.html"/>
|
||||
<meta property="og:title" content="优化器"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="优化器"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="优化器"/>
|
||||
<meta property="og:description" content="一组流行的基于梯度下降的优化器的 PyTorch 实现/教程。目前包括 Adam、AmsGrad 和 RadAM 优化器。"/>
|
||||
|
||||
<title>优化器</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/__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>Optimizers</h1>
|
||||
<h2>Optimizer Implementations</h2>
|
||||
<ul><li><a href="adam.html">Adam Optimizer</a> </li>
|
||||
<li><a href="amsgrad.html">AMSGrad Optimizer</a> </li>
|
||||
<li><a href="adam_warmup.html">Adam Optimizer with warmup</a> </li>
|
||||
<li><a href="noam.html">Noam Optimizer</a> </li>
|
||||
<li><a href="radam.html">Rectified Adam Optimizer</a> </li>
|
||||
<li><a href="ada_belief.html">AdaBelief Optimizer</a> </li>
|
||||
<li><a href="sophia.html">Sophia-G Optimizer</a></li></ul>
|
||||
<p>This <a href="mnist_experiment.html">MNIST example</a> uses these optimizers.</p>
|
||||
<h2>Generic Adaptive Optimizer Base class and Weight Decay</h2>
|
||||
<p>This file defines a common base class for <em>Adam</em> and extensions of it. The base class helps use implement other optimizers with minimal code because of re-usability.</p>
|
||||
<p>We also define a special class for L2 weight decay, so that we don't have to implement it inside each of the optimizers, and can easily extend to other weight decays like L1 without changing the optimizers.</p>
|
||||
<p>Here are some concepts on PyTorch optimizers:</p>
|
||||
<h3>Parameter groups</h3>
|
||||
<p>PyTorch optimizers group parameters into sets called groups. Each group can have its own hyper-parameters like learning rates.</p>
|
||||
<p>In most common cases there will be only one group. This is when you initialize your optimizer with,</p>
|
||||
<pre class="highlight lang-python"><code><span></span><span class="n">Optimizer</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">())</span></code></pre>
|
||||
<p>You can define multiple parameter groups when initializing the optimizer:</p>
|
||||
<pre class="highlight lang-python"><code><span></span><span class="n">Optimizer</span><span class="p">([{</span><span class="s1">'params'</span><span class="p">:</span> <span class="n">model1</span><span class="o">.</span><span class="n">parameters</span><span class="p">()},</span> <span class="p">{</span><span class="s1">'params'</span><span class="p">:</span> <span class="n">model2</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="s1">'lr'</span><span class="p">:</span> <span class="mi">2</span><span class="p">}])</span></code></pre>
|
||||
<p>Here we pass a list of groups. Each group is a dictionary with its parameters under the key 'params'. You specify any hyper-parameters as well. If the hyper parameters are not defined they will default to the optimizer level defaults.</p>
|
||||
<p>You can access (and even change) these groups, and their hyper-parameters with <code class="highlight"><span></span><span class="n">optimizer</span><span class="o">.</span><span class="n">param_groups</span></code>
|
||||
. Most learning rate schedule implementations I've come across do access this and change 'lr'.</p>
|
||||
<h3>States</h3>
|
||||
<p>Optimizer maintains states (a dictionary) for each parameter (a tensor), in a dictionary <code class="highlight"><span></span><span class="n">optimizer</span><span class="o">.</span><span class="n">state</span></code>
|
||||
. This is where the optimizer maintains things like exponential averages.</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">63</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">Any</span>
|
||||
<span class="lineno">64</span>
|
||||
<span class="lineno">65</span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">66</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">67</span><span class="kn">from</span> <span class="nn">torch.optim.optimizer</span> <span class="kn">import</span> <span class="n">Optimizer</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><em>Adam</em> 和扩展的基类</h2>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">70</span><span class="k">class</span> <span class="nc">GenericAdaptiveOptimizer</span><span class="p">(</span><span class="n">Optimizer</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>
|
||||
<h3>初始化</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">params</span></code>
|
||||
是参数的集合或一组参数组。</li>
|
||||
<li><code class="highlight"><span></span><span class="n">defaults</span></code>
|
||||
默认超参数的字典</li>
|
||||
<li><code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
是学习率，<span ><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 mathnormal" style="margin-right:0.0037em;">α</span></span></span></span></span></li>
|
||||
<li><code class="highlight"><span></span><span class="n">betas</span></code>
|
||||
是元组<span ><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"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span></li>
|
||||
</ul><li><code class="highlight"><span></span><span class="n">eps</span></code>
|
||||
是<span ><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 mathnormal">ϵ</span></span></span></span></span></li>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">75</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">params</span><span class="p">,</span> <span class="n">defaults</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">],</span> <span class="n">lr</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">betas</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">],</span> <span class="n">eps</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>
|
||||
<p>检查超参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">87</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">lr</span><span class="p">:</span>
|
||||
<span class="lineno">88</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid learning rate: </span><span class="si">{</span><span class="n">lr</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||||
<span class="lineno">89</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">eps</span><span class="p">:</span>
|
||||
<span class="lineno">90</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid epsilon value: </span><span class="si">{</span><span class="n">eps</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||||
<span class="lineno">91</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">betas</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><</span> <span class="mf">1.0</span><span class="p">:</span>
|
||||
<span class="lineno">92</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid beta parameter at index 0: </span><span class="si">{</span><span class="n">betas</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||||
<span class="lineno">93</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">betas</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o"><</span> <span class="mf">1.0</span><span class="p">:</span>
|
||||
<span class="lineno">94</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid beta parameter at index 1: </span><span class="si">{</span><span class="n">betas</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="si">}</span><span class="s2">"</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>将超参数添加到默认值</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">97</span> <span class="n">defaults</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">lr</span><span class="o">=</span><span class="n">lr</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">eps</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>初始化 PyTorch 优化器。这将使用默认的超参数创建参数组</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">100</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">params</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-6'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-6'>#</a>
|
||||
</div>
|
||||
<h3>初始化给定参数张量的状态</h3>
|
||||
<p>这应该被代码覆盖，以便初始<code class="highlight"><span></span><span class="n">state</span></code>
|
||||
化参数<code class="highlight"><span></span><span class="n">param</span></code>
|
||||
。<code class="highlight"><span></span><span class="n">group</span></code>
|
||||
是所<code class="highlight"><span></span><span class="n">param</span></code>
|
||||
属的参数组字典。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">102</span> <span class="k">def</span> <span class="nf">init_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">state</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">param</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Parameter</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-7'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-7'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">109</span> <span class="k">pass</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>
|
||||
<h3>在参数张量上采取优化器步骤</h3>
|
||||
<p>这应该被重写并对<code class="highlight"><span></span><span class="n">param</span></code>
|
||||
张量采取优化步骤<span ><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 mathnormal" style="margin-right:0.02778em;">θ</span></span></span></span></span>，其中<code class="highlight"><span></span><span class="n">grad</span></code>
|
||||
是该参数的梯度<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"><span class="mord mathnormal" style="margin-right:0.03588em;">g</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-left:-0.03588em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>，<code class="highlight"><span></span><span class="n">state</span></code>
|
||||
是该参数的优化器状态字典，<code class="highlight"><span></span><span class="n">group</span></code>
|
||||
也是参数组字典<code class="highlight"><span></span><span class="n">param</span></code>
|
||||
所属的。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">111</span> <span class="k">def</span> <span class="nf">step_param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">state</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">grad</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">param</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">120</span> <span class="k">pass</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-10'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-10'>#</a>
|
||||
</div>
|
||||
<h3>优化器步骤</h3>
|
||||
<p>我们创建了一个模板方法，它可以完成每个基于 <em>Adam</em> 的优化器所需要的常用内容。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">122</span> <span class="nd">@torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">()</span>
|
||||
<span class="lineno">123</span> <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="n">closure</span><span class="o">=</span><span class="kc">None</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>计算损失。</p>
|
||||
<p>🤔 我不确定你什么时候需要这个。我想如果你定义一个函数来计算损失，做<code class="highlight"><span></span><span class="n">loss</span><span class="o">.</span><span class="n">backward</span></code>
|
||||
和返回损失，而不是自己调用它，你可以传递给它<code class="highlight"><span></span><span class="n">optimizer</span><span class="o">.</span><span class="n">step</span></code>
|
||||
。🤷♂️</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">134</span> <span class="n">loss</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="lineno">135</span> <span class="k">if</span> <span class="n">closure</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="lineno">136</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">enable_grad</span><span class="p">():</span>
|
||||
<span class="lineno">137</span> <span class="n">loss</span> <span class="o">=</span> <span class="n">closure</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>遍历参数组</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">140</span> <span class="k">for</span> <span class="n">group</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">param_groups</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>遍历参数组中的参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">142</span> <span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="n">group</span><span class="p">[</span><span class="s1">'params'</span><span class="p">]:</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-14'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-14'>#</a>
|
||||
</div>
|
||||
<p>如果参数没有渐变，则跳过</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">144</span> <span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="lineno">145</span> <span class="k">continue</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-15'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-15'>#</a>
|
||||
</div>
|
||||
<p>获取梯度张量</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">147</span> <span class="n">grad</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span><span class="o">.</span><span class="n">data</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>我们不处理稀疏渐变</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">149</span> <span class="k">if</span> <span class="n">grad</span><span class="o">.</span><span class="n">is_sparse</span><span class="p">:</span>
|
||||
<span class="lineno">150</span> <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">'GenericAdaptiveOptimizer does not support sparse gradients,'</span>
|
||||
<span class="lineno">151</span> <span class="s1">' please consider SparseAdam instead'</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>获取参数的状态</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">154</span> <span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="n">param</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>如果状态未初始化，则初始化状态</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">157</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">state</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="lineno">158</span> <span class="bp">self</span><span class="o">.</span><span class="n">init_state</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="n">group</span><span class="p">,</span> <span class="n">param</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>对参数采取优化步骤</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">161</span> <span class="bp">self</span><span class="o">.</span><span class="n">step_param</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="n">group</span><span class="p">,</span> <span class="n">grad</span><span class="p">,</span> <span class="n">param</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>返回从闭包计算得出的损失</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">164</span> <span class="k">return</span> <span class="n">loss</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-21'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-21'>#</a>
|
||||
</div>
|
||||
<h2>L2 重量衰减</h2>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">167</span><span class="k">class</span> <span class="nc">WeightDecay</span><span class="p">:</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-22'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-22'>#</a>
|
||||
</div>
|
||||
<h3>初始化权重衰减</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||||
是衰减系数</li>
|
||||
<li><code class="highlight"><span></span><span class="n">weight_decouple</span></code>
|
||||
是一个标志，指示是将权重衰减添加到梯度还是直接从参数中衰减。如果添加到渐变中，它将通过普通的优化器更新。</li>
|
||||
<li><code class="highlight"><span></span><span class="n">absolute</span></code>
|
||||
此标志指示权重衰减系数是否为绝对值。当直接对参数执行衰减时，这适用。如果此值为假，则实际衰减为<code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||||
</li>
|
||||
<li><code class="highlight"><span></span><span class="n">learning_rate</span></code>
|
||||
。</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">172</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">weight_decay</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.</span><span class="p">,</span> <span class="n">weight_decouple</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> <span class="n">absolute</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-23'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-23'>#</a>
|
||||
</div>
|
||||
<p>检查超参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">185</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">weight_decay</span><span class="p">:</span>
|
||||
<span class="lineno">186</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid weight_decay value: </span><span class="si">{</span><span class="n">weight_decay</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||||
<span class="lineno">187</span>
|
||||
<span class="lineno">188</span> <span class="bp">self</span><span class="o">.</span><span class="n">absolute</span> <span class="o">=</span> <span class="n">absolute</span>
|
||||
<span class="lineno">189</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_decouple</span> <span class="o">=</span> <span class="n">weight_decouple</span>
|
||||
<span class="lineno">190</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_decay</span> <span class="o">=</span> <span class="n">weight_decay</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-24'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-24'>#</a>
|
||||
</div>
|
||||
<p>返回参数组的默认值</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">192</span> <span class="k">def</span> <span class="nf">defaults</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-25'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-25'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">196</span> <span class="k">return</span> <span class="nb">dict</span><span class="p">(</span><span class="n">weight_decay</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-26'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-26'>#</a>
|
||||
</div>
|
||||
<h3>执行权重衰减并返回梯度</h3>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">198</span> <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">param</span><span class="p">:</span> <span class="n">torch</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">grad</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">]):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-27'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-27'>#</a>
|
||||
</div>
|
||||
<p>如果我们直接对参数进行衰减</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">204</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_decouple</span><span class="p">:</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-28'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-28'>#</a>
|
||||
</div>
|
||||
<p>如果权重衰减系数为绝对值</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">206</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">absolute</span><span class="p">:</span>
|
||||
<span class="lineno">207</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">mul_</span><span class="p">(</span><span class="mf">1.0</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">'weight_decay'</span><span class="p">])</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-29'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-29'>#</a>
|
||||
</div>
|
||||
<p>否则，</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">209</span> <span class="k">else</span><span class="p">:</span>
|
||||
<span class="lineno">210</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">mul_</span><span class="p">(</span><span class="mf">1.0</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">'lr'</span><span class="p">]</span> <span class="o">*</span> <span class="n">group</span><span class="p">[</span><span class="s1">'weight_decay'</span><span class="p">])</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-30'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-30'>#</a>
|
||||
</div>
|
||||
<p>返回未修改的渐变</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">212</span> <span class="k">return</span> <span class="n">grad</span>
|
||||
<span class="lineno">213</span> <span class="k">else</span><span class="p">:</span>
|
||||
<span class="lineno">214</span> <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">'weight_decay'</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-31'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-31'>#</a>
|
||||
</div>
|
||||
<p>将权重衰减添加到渐变并返回修改后的渐变</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">216</span> <span class="k">return</span> <span class="n">grad</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="n">group</span><span class="p">[</span><span class="s1">'weight_decay'</span><span class="p">])</span>
|
||||
<span class="lineno">217</span> <span class="k">else</span><span class="p">:</span>
|
||||
<span class="lineno">218</span> <span class="k">return</span> <span class="n">grad</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
@@ -0,0 +1,459 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="这是一个简单的 MNIST 示例，其中包含 CNN 模型来测试优化器。"/>
|
||||
|
||||
<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="测试优化器的 MNIST 示例"/>
|
||||
<meta name="twitter:description" content="这是一个简单的 MNIST 示例，其中包含 CNN 模型来测试优化器。"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/mnist_experiment.html"/>
|
||||
<meta property="og:title" content="测试优化器的 MNIST 示例"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="测试优化器的 MNIST 示例"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="测试优化器的 MNIST 示例"/>
|
||||
<meta property="og:description" content="这是一个简单的 MNIST 示例，其中包含 CNN 模型来测试优化器。"/>
|
||||
|
||||
<title>测试优化器的 MNIST 示例</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/mnist_experiment.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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/mnist_experiment.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>测试优化器的 MNIST 示例</h1>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">9</span><span></span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span>
|
||||
<span class="lineno">10</span><span class="kn">import</span> <span class="nn">torch.utils.data</span>
|
||||
<span class="lineno">11</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span>
|
||||
<span class="lineno">12</span>
|
||||
<span class="lineno">13</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">experiment</span><span class="p">,</span> <span class="n">tracker</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">option</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">labml_helpers.datasets.mnist</span> <span class="kn">import</span> <span class="n">MNISTConfigs</span>
|
||||
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">labml_helpers.device</span> <span class="kn">import</span> <span class="n">DeviceConfigs</span>
|
||||
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">labml_helpers.metrics.accuracy</span> <span class="kn">import</span> <span class="n">Accuracy</span>
|
||||
<span class="lineno">18</span><span class="kn">from</span> <span class="nn">labml_helpers.seed</span> <span class="kn">import</span> <span class="n">SeedConfigs</span>
|
||||
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml_helpers.train_valid</span> <span class="kn">import</span> <span class="n">TrainValidConfigs</span><span class="p">,</span> <span class="n">BatchIndex</span><span class="p">,</span> <span class="n">hook_model_outputs</span>
|
||||
<span class="lineno">20</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.configs</span> <span class="kn">import</span> <span class="n">OptimizerConfigs</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>该模型</h2>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">23</span><span class="k">class</span> <span class="nc">Model</span><span class="p">(</span><span class="n">Module</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">27</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="lineno">28</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="lineno">29</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="lineno">30</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2d</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
|
||||
<span class="lineno">31</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">20</span><span class="p">,</span> <span class="mi">50</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="lineno">32</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2d</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
|
||||
<span class="lineno">33</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="mi">16</span> <span class="o">*</span> <span class="mi">50</span><span class="p">,</span> <span class="mi">500</span><span class="p">)</span>
|
||||
<span class="lineno">34</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="mi">500</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
|
||||
<span class="lineno">35</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</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">37</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">x</span><span class="p">):</span>
|
||||
<span class="lineno">38</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv1</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
|
||||
<span class="lineno">39</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
||||
<span class="lineno">40</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv2</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
|
||||
<span class="lineno">41</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
||||
<span class="lineno">42</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fc1</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">16</span> <span class="o">*</span> <span class="mi">50</span><span class="p">)))</span>
|
||||
<span class="lineno">43</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<h2>可配置的实验定义</h2>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">46</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">MNISTConfigs</span><span class="p">,</span> <span class="n">TrainValidConfigs</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">50</span> <span class="n">optimizer</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">Adam</span>
|
||||
<span class="lineno">51</span> <span class="n">model</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span>
|
||||
<span class="lineno">52</span> <span class="n">set_seed</span> <span class="o">=</span> <span class="n">SeedConfigs</span><span class="p">()</span>
|
||||
<span class="lineno">53</span> <span class="n">device</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span> <span class="o">=</span> <span class="n">DeviceConfigs</span><span class="p">()</span>
|
||||
<span class="lineno">54</span> <span class="n">epochs</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span>
|
||||
<span class="lineno">55</span>
|
||||
<span class="lineno">56</span> <span class="n">is_save_models</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
<span class="lineno">57</span> <span class="n">model</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span>
|
||||
<span class="lineno">58</span> <span class="n">inner_iterations</span> <span class="o">=</span> <span class="mi">10</span>
|
||||
<span class="lineno">59</span>
|
||||
<span class="lineno">60</span> <span class="n">accuracy_func</span> <span class="o">=</span> <span class="n">Accuracy</span><span class="p">()</span>
|
||||
<span class="lineno">61</span> <span class="n">loss_func</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">CrossEntropyLoss</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">63</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="lineno">64</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_queue</span><span class="p">(</span><span class="s2">"loss.*"</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
|
||||
<span class="lineno">65</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_scalar</span><span class="p">(</span><span class="s2">"accuracy.*"</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
|
||||
<span class="lineno">66</span> <span class="n">hook_model_outputs</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">,</span> <span class="s1">'model'</span><span class="p">)</span>
|
||||
<span class="lineno">67</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_modules</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">accuracy_func</span><span class="p">]</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-7'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-7'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">69</span> <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="n">batch</span><span class="p">:</span> <span class="nb">any</span><span class="p">,</span> <span class="n">batch_idx</span><span class="p">:</span> <span class="n">BatchIndex</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
<p>获取批次</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">71</span> <span class="n">data</span><span class="p">,</span> <span class="n">target</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">),</span> <span class="n">batch</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</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>
|
||||
<p>如果我们处于训练模式，则添加全局步长</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">74</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</span><span class="p">:</span>
|
||||
<span class="lineno">75</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add_global_step</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">data</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>
|
||||
<p>运行模型并指定是否记录激活</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">78</span> <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">is_log_activations</span><span class="o">=</span><span class="n">batch_idx</span><span class="o">.</span><span class="n">is_last</span><span class="p">):</span>
|
||||
<span class="lineno">79</span> <span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">data</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>计算损失</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">82</span> <span class="n">loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_func</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">target</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>计算精度</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">84</span> <span class="bp">self</span><span class="o">.</span><span class="n">accuracy_func</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">target</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>记录损失</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">86</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">"loss."</span><span class="p">,</span> <span class="n">loss</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-14'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-14'>#</a>
|
||||
</div>
|
||||
<p>如果我们处于训练模式，请进行优化</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">89</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</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>
|
||||
<p>计算梯度</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">91</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</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>采取优化器步骤</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">94</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">step</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>每个纪元记录一次参数和梯度 L2 规范</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">96</span> <span class="k">if</span> <span class="n">batch_idx</span><span class="o">.</span><span class="n">is_last</span><span class="p">:</span>
|
||||
<span class="lineno">97</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'model'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">)</span>
|
||||
<span class="lineno">98</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'optimizer'</span><span class="p">,</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="p">{</span><span class="s1">'model'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</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>清除渐变</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">100</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">zero_grad</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>保存日志</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">103</span> <span class="n">tracker</span><span class="o">.</span><span class="n">save</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-20'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-20'>#</a>
|
||||
</div>
|
||||
<p>创建可配置的优化器。我们可以使用配置更改优化器类型和超参数。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">106</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">model</span><span class="p">)</span>
|
||||
<span class="lineno">107</span><span class="k">def</span> <span class="nf">model</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">Configs</span><span class="p">):</span>
|
||||
<span class="lineno">108</span> <span class="k">return</span> <span class="n">Model</span><span class="p">()</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
||||
<span class="lineno">109</span>
|
||||
<span class="lineno">110</span>
|
||||
<span class="lineno">111</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">)</span>
|
||||
<span class="lineno">112</span><span class="k">def</span> <span class="nf">_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">Configs</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">117</span> <span class="n">opt_conf</span> <span class="o">=</span> <span class="n">OptimizerConfigs</span><span class="p">()</span>
|
||||
<span class="lineno">118</span> <span class="n">opt_conf</span><span class="o">.</span><span class="n">parameters</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">()</span>
|
||||
<span class="lineno">119</span> <span class="k">return</span> <span class="n">opt_conf</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-22'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-22'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">122</span><span class="k">def</span> <span class="nf">main</span><span class="p">():</span>
|
||||
<span class="lineno">123</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</span><span class="p">()</span>
|
||||
<span class="lineno">124</span> <span class="n">conf</span><span class="o">.</span><span class="n">inner_iterations</span> <span class="o">=</span> <span class="mi">10</span>
|
||||
<span class="lineno">125</span> <span class="n">experiment</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">'mnist_ada_belief'</span><span class="p">)</span>
|
||||
<span class="lineno">126</span> <span class="n">experiment</span><span class="o">.</span><span class="n">configs</span><span class="p">(</span><span class="n">conf</span><span class="p">,</span> <span class="p">{</span><span class="s1">'inner_iterations'</span><span class="p">:</span> <span class="mi">10</span><span class="p">,</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-23'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-23'>#</a>
|
||||
</div>
|
||||
<p>指定优化器</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">128</span> <span class="s1">'optimizer.optimizer'</span><span class="p">:</span> <span class="s1">'Adam'</span><span class="p">,</span>
|
||||
<span class="lineno">129</span> <span class="s1">'optimizer.learning_rate'</span><span class="p">:</span> <span class="mf">1.5e-4</span><span class="p">})</span>
|
||||
<span class="lineno">130</span> <span class="n">conf</span><span class="o">.</span><span class="n">set_seed</span><span class="o">.</span><span class="n">set</span><span class="p">()</span>
|
||||
<span class="lineno">131</span> <span class="n">experiment</span><span class="o">.</span><span class="n">add_pytorch_models</span><span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">model</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">model</span><span class="p">))</span>
|
||||
<span class="lineno">132</span> <span class="k">with</span> <span class="n">experiment</span><span class="o">.</span><span class="n">start</span><span class="p">():</span>
|
||||
<span class="lineno">133</span> <span class="n">conf</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
|
||||
<span class="lineno">134</span>
|
||||
<span class="lineno">135</span>
|
||||
<span class="lineno">136</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
||||
<span class="lineno">137</span> <span class="n">main</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
@@ -0,0 +1,327 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="这是 Noam 优化器的教程/实现。Noam 优化器有一个预热期，然后学习率呈指数级衰减。"/>
|
||||
|
||||
<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="《注意就是你所需要的 Noam Optimizer》论文"/>
|
||||
<meta name="twitter:description" content="这是 Noam 优化器的教程/实现。Noam 优化器有一个预热期，然后学习率呈指数级衰减。"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/noam.html"/>
|
||||
<meta property="og:title" content="《注意就是你所需要的 Noam Optimizer》论文"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="《注意就是你所需要的 Noam Optimizer》论文"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="《注意就是你所需要的 Noam Optimizer》论文"/>
|
||||
<meta property="og:description" content="这是 Noam 优化器的教程/实现。Noam 优化器有一个预热期，然后学习率呈指数级衰减。"/>
|
||||
|
||||
<title>《注意就是你所需要的 Noam Optimizer》论文</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/noam.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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/noam.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>Noam 优化器</h1>
|
||||
<p>这是《<a href="https://arxiv.org/abs/1706.03762">注意就是你所需要的》一文中介绍的优化器的</a> <a href="https://pytorch.org">PyTorch</a> 实现。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">14</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span>
|
||||
<span class="lineno">15</span>
|
||||
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</span>
|
||||
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.amsgrad</span> <span class="kn">import</span> <span class="n">AMSGrad</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>Noam 优化器</h2>
|
||||
<p>这个类是从中定义的 Adam 优化器扩展而来的<a href="adam.html"><code class="highlight"><span></span><span class="n">adam</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a>。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">20</span><span class="k">class</span> <span class="nc">Noam</span><span class="p">(</span><span class="n">AMSGrad</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>
|
||||
<h3>初始化优化器</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">params</span></code>
|
||||
是参数列表</li>
|
||||
<li><code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
是学习率<span ><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 eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span></li>
|
||||
<li><code class="highlight"><span></span><span class="n">betas</span></code>
|
||||
是 (<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>,<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>) 的元组</li>
|
||||
<li><code class="highlight"><span></span><span class="n">eps</span></code>
|
||||
是<span ><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 accent"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.69444em;"><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord coloredeq eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="accent-body" style="left:-0.19444em;"><span class="mord">^</span></span></span></span></span></span></span></span></span></span></span>或<span ><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 eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span>基于<code class="highlight"><span></span><span class="n">optimized_update</span></code>
|
||||
</li>
|
||||
<li><code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||||
是在中<code class="highlight"><span></span><span class="n">WeightDecay</span></code>
|
||||
定义的类的实例 <a href="index.html"><code class="highlight"><span></span><span class="fm">__init__</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a></li>
|
||||
<li>“optimized_update” 是一个标志，在添加后是否要优化第二个时刻的偏差校正<span ><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 eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span></li>
|
||||
<li><code class="highlight"><span></span><span class="n">amsgrad</span></code>
|
||||
是一个标志，指示是使用 AmsGrad 还是回退到普通的 Adam</li>
|
||||
<li><code class="highlight"><span></span><span class="n">warmup</span></code>
|
||||
预热步数</li>
|
||||
<li><code class="highlight"><span></span><span class="n">d_model</span></code>
|
||||
型号尺寸；即变压器中的尺寸数</li>
|
||||
<li><code class="highlight"><span></span><span class="n">defaults</span></code>
|
||||
是组值的默认字典。当你想扩展类时，这很有用<code class="highlight"><span></span><span class="n">AdamWarmup</span></code>
|
||||
。</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">27</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">params</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</span><span class="p">),</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-16</span><span class="p">,</span>
|
||||
<span class="lineno">28</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="n">WeightDecay</span> <span class="o">=</span> <span class="n">WeightDecay</span><span class="p">(),</span>
|
||||
<span class="lineno">29</span> <span class="n">optimized_update</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
|
||||
<span class="lineno">30</span> <span class="n">amsgrad</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||||
<span class="lineno">31</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">d_model</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">defaults</span><span class="o">=</span><span class="kc">None</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">49</span> <span class="n">defaults</span> <span class="o">=</span> <span class="p">{}</span> <span class="k">if</span> <span class="n">defaults</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">defaults</span>
|
||||
<span class="lineno">50</span> <span class="n">defaults</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">warmup</span><span class="o">=</span><span class="n">warmup</span><span class="p">))</span>
|
||||
<span class="lineno">51</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">params</span><span class="p">,</span> <span class="n">lr</span><span class="p">,</span> <span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span> <span class="n">weight_decay</span><span class="p">,</span> <span class="n">optimized_update</span><span class="p">,</span> <span class="n">amsgrad</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</span>
|
||||
<span class="lineno">52</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_model</span> <span class="o">=</span> <span class="n">d_model</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<h3>获取学习率</h3>
|
||||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqg" style="margin-right:0.0037em">α</span></span><span class="mord" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.25278em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.85722em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord" style=""><span class="mord mathnormal" style="">d</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.33610799999999996em;"><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" style=""><span class="mord mathnormal mtight" style="">m</span><span class="mord mathnormal mtight" style="">o</span><span class="mord mathnormal mtight" style="">d</span><span class="mord mathnormal mtight" style="">e</span><span class="mord mathnormal mtight" style="margin-right:0.01968em">l</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span><span style="top:-2.81722em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.18278000000000005em;"><span></span></span></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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord" style=""><span class="mop coloredeq eqb" style=""><span style="">m</span><span style="">i</span><span style="">n</span></span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mord coloredeq eqb" style=""><span class="delimsizing size3" style=""><span style="">(</span></span></span><span class="mord coloredeq eqb" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.21746em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.89254em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord mathnormal" style="">t</span></span></span><span style="top:-2.85254em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.14746000000000004em;"><span></span></span></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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mpunct coloredeq eqb" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mord coloredeq eqb" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.29208em;"><span style="top:-2.2960000000000003em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqh" style="margin-right:0.02691em">w</span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.814em;"><span style="top:-2.989em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style="">3/2</span></span></span></span></span></span></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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord mathnormal" style="">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.704em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord coloredeq eqb" style=""><span class="delimsizing size3" style=""><span style="">)</span></span></span></span></span></span></span></span></span></span>其中<span ><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 eqh" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</span></span></span></span></span></span>是预热步骤的数量。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">54</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="n">state</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</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><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqb" style=""><span class="mop" style=""><span style="">m</span><span style="">i</span><span style="">n</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord" style=""><span class="delimsizing size3" style=""><span style="">(</span></span></span><span class="mord" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.21746em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.89254em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord mathnormal" style="">t</span></span></span><span style="top:-2.85254em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.14746000000000004em;"><span></span></span></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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mpunct" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.29208em;"><span style="top:-2.2960000000000003em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqh" style="margin-right:0.02691em">w</span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.814em;"><span style="top:-2.989em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style="">3/2</span></span></span></span></span></span></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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord mathnormal" style="">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.704em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord" style=""><span class="delimsizing size3" style=""><span style="">)</span></span></span></span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">62</span> <span class="n">factor</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">**</span> <span class="p">(</span><span class="o">-</span><span class="mf">0.5</span><span class="p">),</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">*</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">]</span> <span class="o">**</span> <span class="p">(</span><span class="o">-</span><span class="mf">1.5</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 ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqg" style="margin-right:0.0037em">α</span></span><span class="mord" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.25278em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.85722em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord" style=""><span class="mord mathnormal" style="">d</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.33610799999999996em;"><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" style=""><span class="mord mathnormal mtight" style="">m</span><span class="mord mathnormal mtight" style="">o</span><span class="mord mathnormal mtight" style="">d</span><span class="mord mathnormal mtight" style="">e</span><span class="mord mathnormal mtight" style="margin-right:0.01968em">l</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span><span style="top:-2.81722em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.18278000000000005em;"><span></span></span></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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord" style=""><span class="mop coloredeq eqb" style=""><span style="">m</span><span style="">i</span><span style="">n</span></span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mord coloredeq eqb" style=""><span class="delimsizing size3" style=""><span style="">(</span></span></span><span class="mord coloredeq eqb" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.21746em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.89254em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord mathnormal" style="">t</span></span></span><span style="top:-2.85254em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.14746000000000004em;"><span></span></span></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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mpunct coloredeq eqb" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mord coloredeq eqb" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.29208em;"><span style="top:-2.2960000000000003em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqh" style="margin-right:0.02691em">w</span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.814em;"><span style="top:-2.989em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style="">3/2</span></span></span></span></span></span></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:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord mathnormal" style="">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.704em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord coloredeq eqb" style=""><span class="delimsizing size3" style=""><span style="">)</span></span></span></span></span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">64</span> <span class="k">return</span> <span class="n">group</span><span class="p">[</span><span class="s1">'lr'</span><span class="p">]</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_model</span> <span class="o">**</span> <span class="p">(</span><span class="o">-</span><span class="mf">0.5</span><span class="p">)</span> <span class="o">*</span> <span class="n">factor</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-7'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-7'>#</a>
|
||||
</div>
|
||||
<h3>绘制不同预热和模型大小的学习速率</h3>
|
||||
<p><img alt="Plot of learning rate" src="noam_lr.png"></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">67</span><span class="k">def</span> <span class="nf">_test_noam_lr</span><span class="p">():</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">73</span> <span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
|
||||
<span class="lineno">74</span> <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
<span class="lineno">75</span> <span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">76</span>
|
||||
<span class="lineno">77</span> <span class="n">model</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
|
||||
<span class="lineno">78</span> <span class="n">opts</span> <span class="o">=</span> <span class="p">[</span><span class="n">Noam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">d_model</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">4000</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
|
||||
<span class="lineno">79</span> <span class="n">Noam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">d_model</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">8000</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
|
||||
<span class="lineno">80</span> <span class="n">Noam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">d_model</span><span class="o">=</span><span class="mi">2048</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">2000</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mi">1</span><span class="p">)]</span>
|
||||
<span class="lineno">81</span> <span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">20000</span><span class="p">),</span> <span class="p">[[</span><span class="n">opt</span><span class="o">.</span><span class="n">get_lr</span><span class="p">({</span><span class="s1">'step'</span><span class="p">:</span> <span class="n">i</span><span class="p">},</span> <span class="n">opt</span><span class="o">.</span><span class="n">defaults</span><span class="p">)</span> <span class="k">for</span> <span class="n">opt</span> <span class="ow">in</span> <span class="n">opts</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">20000</span><span class="p">)])</span>
|
||||
<span class="lineno">82</span> <span class="n">plt</span><span class="o">.</span><span class="n">legend</span><span class="p">([</span><span class="s2">"512:4000"</span><span class="p">,</span> <span class="s2">"512:8000"</span><span class="p">,</span> <span class="s2">"2048:2000"</span><span class="p">])</span>
|
||||
<span class="lineno">83</span> <span class="n">plt</span><span class="o">.</span><span class="n">title</span><span class="p">(</span><span class="s2">"Learning Rate"</span><span class="p">)</span>
|
||||
<span class="lineno">84</span> <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
|
||||
<span class="lineno">85</span>
|
||||
<span class="lineno">86</span>
|
||||
<span class="lineno">87</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
||||
<span class="lineno">88</span> <span class="n">_test_noam_lr</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 35 KiB |
@@ -0,0 +1,174 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="本实验比较了 Adam 实现的性能。"/>
|
||||
|
||||
<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="测试 Adam 实现的性能"/>
|
||||
<meta name="twitter:description" content="本实验比较了 Adam 实现的性能。"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/performance_test.html"/>
|
||||
<meta property="og:title" content="测试 Adam 实现的性能"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="测试 Adam 实现的性能"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="测试 Adam 实现的性能"/>
|
||||
<meta property="og:description" content="本实验比较了 Adam 实现的性能。"/>
|
||||
|
||||
<title>测试 Adam 实现的性能</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/performance_test.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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/performance_test.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>性能测试 Adam</h1>
|
||||
<pre class="highlight lang-text"><code><span></span>TorchAdam warmup...[DONE] 222.59ms
|
||||
TorchAdam...[DONE] 1,356.01ms
|
||||
MyAdam warmup...[DONE] 119.15ms
|
||||
MyAdam...[DONE] 1,192.89ms</code></pre>
|
||||
<p><a href="https://colab.research.google.com/drive/1ngowaAsADj8VdZfBifu_6L6rtjGoEeoR?usp=sharing"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">19</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">20</span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span>
|
||||
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml_helpers.device</span> <span class="kn">import</span> <span class="n">DeviceInfo</span>
|
||||
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">torch.optim</span> <span class="kn">import</span> <span class="n">Adam</span> <span class="k">as</span> <span class="n">TorchAdam</span>
|
||||
<span class="lineno">23</span>
|
||||
<span class="lineno">24</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">monit</span>
|
||||
<span class="lineno">25</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam</span> <span class="kn">import</span> <span class="n">Adam</span> <span class="k">as</span> <span class="n">MyAdam</span>
|
||||
<span class="lineno">26</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.mnist_experiment</span> <span class="kn">import</span> <span class="n">Model</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-1'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-1'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">29</span><span class="k">def</span> <span class="nf">test</span><span class="p">():</span>
|
||||
<span class="lineno">30</span> <span class="n">device_info</span> <span class="o">=</span> <span class="n">DeviceInfo</span><span class="p">(</span><span class="n">use_cuda</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">cuda_device</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="lineno">31</span> <span class="nb">print</span><span class="p">(</span><span class="n">device_info</span><span class="p">)</span>
|
||||
<span class="lineno">32</span> <span class="n">inp</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">((</span><span class="mi">64</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">28</span><span class="p">,</span> <span class="mi">28</span><span class="p">),</span> <span class="n">device</span><span class="o">=</span><span class="n">device_info</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
||||
<span class="lineno">33</span> <span class="n">target</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">ones</span><span class="p">(</span><span class="mi">64</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">long</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">device_info</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
||||
<span class="lineno">34</span> <span class="n">loss_func</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">CrossEntropyLoss</span><span class="p">()</span>
|
||||
<span class="lineno">35</span> <span class="n">model</span> <span class="o">=</span> <span class="n">Model</span><span class="p">()</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device_info</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
||||
<span class="lineno">36</span> <span class="n">my_adam</span> <span class="o">=</span> <span class="n">MyAdam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">())</span>
|
||||
<span class="lineno">37</span> <span class="n">torch_adam</span> <span class="o">=</span> <span class="n">TorchAdam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">())</span>
|
||||
<span class="lineno">38</span> <span class="n">loss</span> <span class="o">=</span> <span class="n">loss_func</span><span class="p">(</span><span class="n">model</span><span class="p">(</span><span class="n">inp</span><span class="p">),</span> <span class="n">target</span><span class="p">)</span>
|
||||
<span class="lineno">39</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span>
|
||||
<span class="lineno">40</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'MyAdam warmup'</span><span class="p">):</span>
|
||||
<span class="lineno">41</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">100</span><span class="p">):</span>
|
||||
<span class="lineno">42</span> <span class="n">my_adam</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
||||
<span class="lineno">43</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'MyAdam'</span><span class="p">):</span>
|
||||
<span class="lineno">44</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1000</span><span class="p">):</span>
|
||||
<span class="lineno">45</span> <span class="n">my_adam</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
||||
<span class="lineno">46</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'TorchAdam warmup'</span><span class="p">):</span>
|
||||
<span class="lineno">47</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">100</span><span class="p">):</span>
|
||||
<span class="lineno">48</span> <span class="n">torch_adam</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
||||
<span class="lineno">49</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'TorchAdam'</span><span class="p">):</span>
|
||||
<span class="lineno">50</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1000</span><span class="p">):</span>
|
||||
<span class="lineno">51</span> <span class="n">torch_adam</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
||||
<span class="lineno">52</span>
|
||||
<span class="lineno">53</span>
|
||||
<span class="lineno">54</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
||||
<span class="lineno">55</span> <span class="n">test</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
File diff suppressed because one or more lines are too long
Binary file not shown.
|
After Width: | Height: | Size: 30 KiB |
@@ -0,0 +1,133 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="优化器"/>
|
||||
<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/optimizers/readme.html"/>
|
||||
<meta property="og:title" content="优化器"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="优化器"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="优化器"/>
|
||||
<meta property="og:description" content=""/>
|
||||
|
||||
<title>优化器</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/optimizers/readme.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">optimizers</a>
|
||||
</p>
|
||||
<p>
|
||||
<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/optimizers/readme.md" target="_blank">
|
||||
View code on Github</a>
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-0'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-0'>#</a>
|
||||
</div>
|
||||
<h1><a href="https://nn.labml.ai/optimizers/index.html">Optimizers</a></h1>
|
||||
<h2>Optimizer Implementations</h2>
|
||||
<ul><li><a href="https://nn.labml.ai/optimizers/adam.html">Adam Optimizer</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/amsgrad.html">AMSGrad Optimizer</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/adam_warmup.html">Adam Optimizer with warmup</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/noam.html">Noam Optimizer</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/radam.html">Rectified Adam Optimizer</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/ada_belief.html">AdaBelief Optimizer</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/sophia.html">Sophia-G Optimizer</a> </li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user