Deci-AI
/
super-gradients
connected to https://github.com/Deci-AI/super-gradients.git


  
1

	
2

	
3

	
4

	
5

	
6

	
7

	
8

	
9

	
10

	
11

	
12

	
13

	
14

	
15

	
16

	
17

	
18

	
19

	
20

	
21

	
22

	
23

	
24

	
25

	
26

	
27

	
28

	
29

	
30

	
31

	
32

	
33

	
34

	
35

	
36

	
37

	
38

	
39

	
40

	
41

	
42

	
43

	
44

	
45

	
46

	
47

	
48

	
49

	
50

	
51

	
52

	
53

	
54

	
55

	
56

	
57

	
58

	
59

	
60

	
61

	
62

	
63

	
64

	
65

	
66

	
67

	
68

	
69

	
70

	
71

	
72

	
73

	
74

	
75

	
76

	
77

	
78

	
79

	
80

	
81

	
82

	
83

	
84

	
85

	
86

	
87

	
88

	
89

	
90

	
91

	
92

	
93

	
94

	
95

	
96

	
97

	
98

	
99

	
100

	
101

	
102

	
103

	
104

	
105

	
106

	
107

	
108

	
109

	
110

	
111

	
112

	
113

	
114

	
115

	
116

	
117

	
118

	
119

	
120

	
121

	
122

	
123

	
124

	
125

	
126

	
127

	
128

	
129

	
130

	
131

	
132

	
133

	
134

	
135

	
136

	
137

	
138

	
139

	
140

	
141

	
142

	
143

	
144

	
145

	
146

	
147

	
148

	
149

	
150

	
151

	
152

	
153

	
154

	
155

	
156

	
157

	
158

	
159

	
160

	
161

	
162

	
163

	
164

	
165

	
166

	
167

	
168

	
169

	
170

	
171

	
172

	
173

	
174

	
175

	
176

	
177

	
178

	
179

	
180

	
181

	
182

	
183

	
184

	
185

	
186

	
187

	
188

	
189

	
190

	
191

	
192

	
193

	
194

	
195

	
196

	
197

	
198

	
199

	
200

	
201

	
202

	
203

	
204

	
205

	
206

	
207

	
208

	
209

	
210

	
211

	
212

	
213

	
214

	
215

	
216

	
217

	
218

	
219

	
220

	
221

	
222

	
223

	
224

	
225

	
226

	
227

	
228

	
            <!DOCTYPE html>
<html class="writer-html5" lang="en" >
<head>
  <meta charset="utf-8" />
  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
  <title>super_gradients.training.utils.optimizers.rmsprop_tf &mdash; SuperGradients 1.0 documentation</title>
      <link rel="stylesheet" href="../../../../../_static/pygments.css" type="text/css" />
      <link rel="stylesheet" href="../../../../../_static/css/theme.css" type="text/css" />
      <link rel="stylesheet" href="../../../../../_static/graphviz.css" type="text/css" />
  <!--[if lt IE 9]>
    <script src="../../../../../_static/js/html5shiv.min.js"></script>
  <![endif]-->
  
        <script data-url_root="../../../../../" id="documentation_options" src="../../../../../_static/documentation_options.js"></script>
        <script src="../../../../../_static/jquery.js"></script>
        <script src="../../../../../_static/underscore.js"></script>
        <script src="../../../../../_static/doctools.js"></script>
    <script src="../../../../../_static/js/theme.js"></script>
    <link rel="index" title="Index" href="../../../../../genindex.html" />
    <link rel="search" title="Search" href="../../../../../search.html" /> 
</head>

<body class="wy-body-for-nav"> 
  <div class="wy-grid-for-nav">
    <nav data-toggle="wy-nav-shift" class="wy-nav-side">
      <div class="wy-side-scroll">
        <div class="wy-side-nav-search" >
            <a href="../../../../../index.html" class="icon icon-home"> SuperGradients
          </a>
<div role="search">
  <form id="rtd-search-form" class="wy-form" action="../../../../../search.html" method="get">
    <input type="text" name="q" placeholder="Search docs" />
    <input type="hidden" name="check_keywords" value="yes" />
    <input type="hidden" name="area" value="default" />
  </form>
</div>
        </div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
              <p class="caption"><span class="caption-text">SuperGradients</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html">SuperGradients</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../super_gradients.common.html">Common</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../super_gradients.training.html">Training</a></li>
</ul>

        </div>
      </div>
    </nav>

    <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
          <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
          <a href="../../../../../index.html">SuperGradients</a>
      </nav>

      <div class="wy-nav-content">
        <div class="rst-content">
          <div role="navigation" aria-label="Page navigation">
  <ul class="wy-breadcrumbs">
      <li><a href="../../../../../index.html" class="icon icon-home"></a> &raquo;</li>
          <li><a href="../../../../index.html">Module code</a> &raquo;</li>
      <li>super_gradients.training.utils.optimizers.rmsprop_tf</li>
      <li class="wy-breadcrumbs-aside">
      </li>
  </ul>
  <hr/>
</div>
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
             
  <h1>Source code for super_gradients.training.utils.optimizers.rmsprop_tf</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span> <span class="nn">torch</span>
<span class="kn">from</span> <span class="nn">torch.optim</span> <span class="kn">import</span> <span class="n">Optimizer</span>

<span class="sd">&quot;&quot;&quot;</span>
<span class="sd">This implementation is taken from timm&#39;s github:</span>
<span class="sd">https://github.com/rwightman/pytorch-image-models/blob/master/timm/optim/rmsprop_tf.py</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd">&quot;&quot;&quot; RMSProp modified to behave like Tensorflow impl</span>
<span class="sd">Originally cut &amp; paste from PyTorch RMSProp</span>
<span class="sd">https://github.com/pytorch/pytorch/blob/063946d2b3f3f1e953a2a3b54e0b34f1393de295/torch/optim/rmsprop.py</span>
<span class="sd">Licensed under BSD-Clause 3 (ish), https://github.com/pytorch/pytorch/blob/master/LICENSE</span>
<span class="sd">Modifications Copyright 2020 Ross Wightman</span>
<span class="sd">&quot;&quot;&quot;</span>


<div class="viewcode-block" id="RMSpropTF"><a class="viewcode-back" href="../../../../../super_gradients.training.utils.optimizers.html#super_gradients.training.utils.optimizers.rmsprop_tf.RMSpropTF">[docs]</a><span class="k">class</span> <span class="nc">RMSpropTF</span><span class="p">(</span><span class="n">Optimizer</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;Implements RMSprop algorithm (TensorFlow style epsilon)</span>
<span class="sd">    NOTE: This is a direct cut-and-paste of PyTorch RMSprop with eps applied before sqrt</span>
<span class="sd">    and a few other modifications to closer match Tensorflow for matching hyper-params.</span>
<span class="sd">    Noteworthy changes include:</span>
<span class="sd">    1. Epsilon applied inside square-root</span>
<span class="sd">    2. square_avg initialized to ones</span>
<span class="sd">    3. LR scaling of update accumulated in momentum buffer</span>
<span class="sd">    Proposed by G. Hinton in his</span>
<span class="sd">    `course &lt;http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf&gt;`_.</span>
<span class="sd">    The centered version first appears in `Generating Sequences</span>
<span class="sd">    With Recurrent Neural Networks &lt;https://arxiv.org/pdf/1308.0850v5.pdf&gt;`_.&quot;&quot;&quot;</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-2</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">0.9</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-10</span><span class="p">,</span> <span class="n">weight_decay</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">momentum</span><span class="o">=</span><span class="mf">0.</span><span class="p">,</span> <span class="n">centered</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
                 <span class="n">decoupled_decay</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">lr_in_momentum</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;RMSprop optimizer that follows the tf&#39;s RMSprop characteristics</span>
<span class="sd">        :param params (iterable): iterable of parameters to optimize or dicts defining parameter groups</span>
<span class="sd">        :param lr (float, optional): learning rate</span>
<span class="sd">        :param momentum (float, optional): momentum factor</span>
<span class="sd">        :param alpha (float, optional): smoothing (decay) constant</span>
<span class="sd">        :param eps (float, optional): term added to the denominator to improve numerical stability</span>
<span class="sd">        :param centered (bool, optional) : if ``True``, compute the centered RMSProp, the gradient is normalized by an</span>
<span class="sd">         estimation of its variance</span>
<span class="sd">        :param weight_decay (float, optional): weight decay (L2 penalty)</span>
<span class="sd">        :param decoupled_decay (bool, optional): decoupled weight decay as per https://arxiv.org/abs/1711.05101</span>
<span class="sd">        :param lr_in_momentum (bool, optional): learning rate scaling is included in the momentum buffer update as per</span>
<span class="sd">         defaults in Tensorflow</span>
<span class="sd">    &quot;&quot;&quot;</span>
        <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o">&lt;=</span> <span class="n">lr</span><span class="p">:</span>
            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Invalid learning rate: </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">lr</span><span class="p">))</span>
        <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o">&lt;=</span> <span class="n">eps</span><span class="p">:</span>
            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Invalid epsilon value: </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">eps</span><span class="p">))</span>
        <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o">&lt;=</span> <span class="n">momentum</span><span class="p">:</span>
            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Invalid momentum value: </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">momentum</span><span class="p">))</span>
        <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o">&lt;=</span> <span class="n">weight_decay</span><span class="p">:</span>
            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Invalid weight_decay value: </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">weight_decay</span><span class="p">))</span>
        <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o">&lt;=</span> <span class="n">alpha</span><span class="p">:</span>
            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Invalid alpha value: </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">alpha</span><span class="p">))</span>

        <span class="n">defaults</span> <span class="o">=</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">momentum</span><span class="o">=</span><span class="n">momentum</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="n">alpha</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">eps</span><span class="p">,</span> <span class="n">centered</span><span class="o">=</span><span class="n">centered</span><span class="p">,</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">weight_decay</span><span class="p">,</span>
                        <span class="n">decoupled_decay</span><span class="o">=</span><span class="n">decoupled_decay</span><span class="p">,</span> <span class="n">lr_in_momentum</span><span class="o">=</span><span class="n">lr_in_momentum</span><span class="p">)</span>
        <span class="nb">super</span><span class="p">(</span><span class="n">RMSpropTF</span><span class="p">,</span> <span class="bp">self</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>

    <span class="k">def</span> <span class="nf">__setstate__</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="nb">super</span><span class="p">(</span><span class="n">RMSpropTF</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__setstate__</span><span class="p">(</span><span class="n">state</span><span class="p">)</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>
            <span class="n">group</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="s1">&#39;momentum&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
            <span class="n">group</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="s1">&#39;centered&#39;</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>

<div class="viewcode-block" id="RMSpropTF.step"><a class="viewcode-back" href="../../../../../super_gradients.training.utils.optimizers.html#super_gradients.training.utils.optimizers.rmsprop_tf.RMSpropTF.step">[docs]</a>    <span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">closure</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>  <span class="c1"># noqa: C901</span>
        <span class="sd">&quot;&quot;&quot;Performs a single optimization step.</span>
<span class="sd">        Arguments:</span>
<span class="sd">            closure (callable, optional): A closure that reevaluates the model</span>
<span class="sd">                and returns the loss.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">loss</span> <span class="o">=</span> <span class="kc">None</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="n">loss</span> <span class="o">=</span> <span class="n">closure</span><span class="p">()</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>
            <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">]:</span>
                <span class="k">if</span> <span class="n">p</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="k">continue</span>
                <span class="n">grad</span> <span class="o">=</span> <span class="n">p</span><span class="o">.</span><span class="n">grad</span><span class="o">.</span><span class="n">data</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="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">&#39;RMSprop does not support sparse gradients&#39;</span><span class="p">)</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">p</span><span class="p">]</span>

                <span class="c1"># State initialization</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="n">state</span><span class="p">[</span><span class="s1">&#39;step&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</span>
                    <span class="n">state</span><span class="p">[</span><span class="s1">&#39;square_avg&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">ones_like</span><span class="p">(</span><span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>  <span class="c1"># PyTorch inits to zero</span>
                    <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;momentum&#39;</span><span class="p">]</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
                        <span class="n">state</span><span class="p">[</span><span class="s1">&#39;momentum_buffer&#39;</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">p</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
                    <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;centered&#39;</span><span class="p">]:</span>
                        <span class="n">state</span><span class="p">[</span><span class="s1">&#39;grad_avg&#39;</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">p</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>

                <span class="n">square_avg</span> <span class="o">=</span> <span class="n">state</span><span class="p">[</span><span class="s1">&#39;square_avg&#39;</span><span class="p">]</span>
                <span class="n">one_minus_alpha</span> <span class="o">=</span> <span class="mf">1.</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;alpha&#39;</span><span class="p">]</span>

                <span class="n">state</span><span class="p">[</span><span class="s1">&#39;step&#39;</span><span class="p">]</span> <span class="o">+=</span> <span class="mi">1</span>

                <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;weight_decay&#39;</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
                    <span class="k">if</span> <span class="s1">&#39;decoupled_decay&#39;</span> <span class="ow">in</span> <span class="n">group</span> <span class="ow">and</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;decoupled_decay&#39;</span><span class="p">]:</span>
                        <span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">add_</span><span class="p">(</span><span class="o">-</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;weight_decay&#39;</span><span class="p">],</span> <span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
                    <span class="k">else</span><span class="p">:</span>
                        <span class="n">grad</span> <span class="o">=</span> <span class="n">grad</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;weight_decay&#39;</span><span class="p">],</span> <span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>

                <span class="c1"># Tensorflow order of ops for updating squared avg</span>
                <span class="n">square_avg</span><span class="o">.</span><span class="n">add_</span><span class="p">(</span><span class="n">one_minus_alpha</span><span class="p">,</span> <span class="n">grad</span><span class="o">.</span><span class="n">pow</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">-</span> <span class="n">square_avg</span><span class="p">)</span>
                <span class="c1"># square_avg.mul_(alpha).addcmul_(1 - alpha, grad, grad)  # PyTorch original</span>

                <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;centered&#39;</span><span class="p">]:</span>
                    <span class="n">grad_avg</span> <span class="o">=</span> <span class="n">state</span><span class="p">[</span><span class="s1">&#39;grad_avg&#39;</span><span class="p">]</span>
                    <span class="n">grad_avg</span><span class="o">.</span><span class="n">add_</span><span class="p">(</span><span class="n">one_minus_alpha</span><span class="p">,</span> <span class="n">grad</span> <span class="o">-</span> <span class="n">grad_avg</span><span class="p">)</span>
                    <span class="c1"># grad_avg.mul_(alpha).add_(1 - alpha, grad)  # PyTorch original</span>
                    <span class="n">avg</span> <span class="o">=</span> <span class="n">square_avg</span><span class="o">.</span><span class="n">addcmul</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">grad_avg</span><span class="p">,</span> <span class="n">grad_avg</span><span class="p">)</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;eps&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">sqrt_</span><span class="p">()</span>  <span class="c1"># eps moved in sqrt</span>
                <span class="k">else</span><span class="p">:</span>
                    <span class="n">avg</span> <span class="o">=</span> <span class="n">square_avg</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;eps&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">sqrt_</span><span class="p">()</span>  <span class="c1"># eps moved in sqrt</span>

                <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;momentum&#39;</span><span class="p">]</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
                    <span class="n">buf</span> <span class="o">=</span> <span class="n">state</span><span class="p">[</span><span class="s1">&#39;momentum_buffer&#39;</span><span class="p">]</span>
                    <span class="c1"># Tensorflow accumulates the LR scaling in the momentum buffer</span>
                    <span class="k">if</span> <span class="s1">&#39;lr_in_momentum&#39;</span> <span class="ow">in</span> <span class="n">group</span> <span class="ow">and</span> <span class="n">group</span><span class="p">[</span><span class="s1">&#39;lr_in_momentum&#39;</span><span class="p">]:</span>
                        <span class="n">buf</span><span class="o">.</span><span class="n">mul_</span><span class="p">(</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;momentum&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">addcdiv_</span><span class="p">(</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;lr&#39;</span><span class="p">],</span> <span class="n">grad</span><span class="p">,</span> <span class="n">avg</span><span class="p">)</span>
                        <span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">add_</span><span class="p">(</span><span class="o">-</span><span class="n">buf</span><span class="p">)</span>
                    <span class="k">else</span><span class="p">:</span>
                        <span class="c1"># PyTorch scales the param update by LR</span>
                        <span class="n">buf</span><span class="o">.</span><span class="n">mul_</span><span class="p">(</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;momentum&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">addcdiv_</span><span class="p">(</span><span class="n">grad</span><span class="p">,</span> <span class="n">avg</span><span class="p">)</span>
                        <span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">add_</span><span class="p">(</span><span class="o">-</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;lr&#39;</span><span class="p">],</span> <span class="n">buf</span><span class="p">)</span>
                <span class="k">else</span><span class="p">:</span>
                    <span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">addcdiv_</span><span class="p">(</span><span class="o">-</span><span class="n">group</span><span class="p">[</span><span class="s1">&#39;lr&#39;</span><span class="p">],</span> <span class="n">grad</span><span class="p">,</span> <span class="n">avg</span><span class="p">)</span>

        <span class="k">return</span> <span class="n">loss</span></div></div>
</pre></div>

           </div>
          </div>
          <footer>

  <hr/>

  <div role="contentinfo">
    <p>&#169; Copyright 2021, SuperGradients team.</p>
  </div>

  Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
    <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
    provided by <a href="https://readthedocs.org">Read the Docs</a>.
   

</footer>
        </div>
      </div>
    </section>
  </div>
  <script>
      jQuery(function () {
          SphinxRtdTheme.Navigation.enable(true);
      });
  </script> 

</body>
</html>