#286 Sg/yolox readme

Merged
GitHub User merged 1 commits into Deci-AI:master from deci-ai:SG/yolox_readme
  
    
        
          
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

          
            <!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.losses.yolo_v3_loss &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.losses.yolo_v3_loss</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.losses.yolo_v3_loss</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</span> <span class="kn">import</span> <span class="n">nn</span>
<span class="kn">from</span> <span class="nn">torch.nn.modules.loss</span> <span class="kn">import</span> <span class="n">_Loss</span>
<span class="kn">from</span> <span class="nn">super_gradients.training.utils.detection_utils</span> <span class="kn">import</span> <span class="n">build_detection_targets</span><span class="p">,</span> <span class="n">calculate_bbox_iou_elementwise</span>
<div class="viewcode-block" id="YoLoV3DetectionLoss"><a class="viewcode-back" href="../../../../super_gradients.training.losses.html#super_gradients.training.losses.yolo_v3_loss.YoLoV3DetectionLoss">[docs]</a><span class="k">class</span> <span class="nc">YoLoV3DetectionLoss</span><span class="p">(</span><span class="n">_Loss</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    YoLoV3DetectionLoss - Loss Class for Object Detection</span>
<span class="sd">    &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">model</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">,</span> <span class="n">cls_pw</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.</span><span class="p">,</span> <span class="n">obj_pw</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.</span><span class="p">,</span> <span class="n">giou</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">3.54</span><span class="p">,</span> <span class="n">obj</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">64.3</span><span class="p">,</span>
                 <span class="bp">cls</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">37.4</span><span class="p">):</span>
        <span class="nb">super</span><span class="p">(</span><span class="n">YoLoV3DetectionLoss</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="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">cls_pw</span> <span class="o">=</span> <span class="n">cls_pw</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">obj_pw</span> <span class="o">=</span> <span class="n">obj_pw</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">giou</span> <span class="o">=</span> <span class="n">giou</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">obj</span> <span class="o">=</span> <span class="n">obj</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">cls</span> <span class="o">=</span> <span class="bp">cls</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">classes_num</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">net</span><span class="o">.</span><span class="n">module</span><span class="o">.</span><span class="n">num_classes</span>
<div class="viewcode-block" id="YoLoV3DetectionLoss.forward"><a class="viewcode-back" href="../../../../super_gradients.training.losses.html#super_gradients.training.losses.yolo_v3_loss.YoLoV3DetectionLoss.forward">[docs]</a>    <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">model_output</span><span class="p">,</span> <span class="n">targets</span><span class="p">):</span>
        <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">model_output</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">model_output</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
            <span class="c1"># in test/eval mode the Yolo v3 model output a tuple where the second item is the raw predictions</span>
            <span class="n">_</span><span class="p">,</span> <span class="n">predictions</span> <span class="o">=</span> <span class="n">model_output</span>
        <span class="k">else</span><span class="p">:</span>
            <span class="n">predictions</span> <span class="o">=</span> <span class="n">model_output</span>
        <span class="n">detection_targets</span> <span class="o">=</span> <span class="n">build_detection_targets</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">net</span><span class="o">.</span><span class="n">module</span><span class="p">,</span> <span class="n">targets</span><span class="p">)</span>
        <span class="n">float_tensor</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">FloatTensor</span> <span class="k">if</span> <span class="n">predictions</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">is_cuda</span> <span class="k">else</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span>
        <span class="n">class_loss</span><span class="p">,</span> <span class="n">giou_loss</span><span class="p">,</span> <span class="n">objectness_loss</span> <span class="o">=</span> <span class="n">float_tensor</span><span class="p">([</span><span class="mi">0</span><span class="p">]),</span> <span class="n">float_tensor</span><span class="p">([</span><span class="mi">0</span><span class="p">]),</span> <span class="n">float_tensor</span><span class="p">([</span><span class="mi">0</span><span class="p">])</span>
        <span class="n">target_class</span><span class="p">,</span> <span class="n">target_box</span><span class="p">,</span> <span class="n">indices</span><span class="p">,</span> <span class="n">anchor_vec</span> <span class="o">=</span> <span class="n">detection_targets</span>
        <span class="n">reduction</span> <span class="o">=</span> <span class="s1">&#39;mean&#39;</span>  <span class="c1"># Loss reduction (sum or mean)</span>
        <span class="c1"># DEFINE CRITERIA</span>
        <span class="n">BCEcls</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BCEWithLogitsLoss</span><span class="p">(</span><span class="n">pos_weight</span><span class="o">=</span><span class="n">float_tensor</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">cls_pw</span><span class="p">]),</span> <span class="n">reduction</span><span class="o">=</span><span class="n">reduction</span><span class="p">)</span>
        <span class="n">BCEobj</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BCEWithLogitsLoss</span><span class="p">(</span><span class="n">pos_weight</span><span class="o">=</span><span class="n">float_tensor</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">obj_pw</span><span class="p">]),</span> <span class="n">reduction</span><span class="o">=</span><span class="n">reduction</span><span class="p">)</span>
        <span class="c1"># COMPUTE THE LOSSES BASED ON EACH ONE OF THE YOLO LAYERS PREDICTIONS</span>
        <span class="n">grid_points_num</span><span class="p">,</span> <span class="n">targets_num</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span>
        <span class="k">for</span> <span class="n">yolo_layer_index</span><span class="p">,</span> <span class="n">yolo_layer_prediction</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">predictions</span><span class="p">):</span>
            <span class="n">image</span><span class="p">,</span> <span class="n">anchor</span><span class="p">,</span> <span class="n">grid_y</span><span class="p">,</span> <span class="n">grid_x</span> <span class="o">=</span> <span class="n">indices</span><span class="p">[</span><span class="n">yolo_layer_index</span><span class="p">]</span>
            <span class="n">target_object</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">yolo_layer_prediction</span><span class="p">[</span><span class="o">...</span><span class="p">,</span> <span class="mi">0</span><span class="p">])</span>
            <span class="n">grid_points_num</span> <span class="o">+=</span> <span class="n">target_object</span><span class="o">.</span><span class="n">numel</span><span class="p">()</span>
            <span class="c1"># COMPUTE LOSSES</span>
            <span class="n">nb</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">image</span><span class="p">)</span>
            <span class="k">if</span> <span class="n">nb</span><span class="p">:</span>  <span class="c1"># number of targets</span>
                <span class="n">targets_num</span> <span class="o">+=</span> <span class="n">nb</span>
                <span class="n">predictions_for_targets</span> <span class="o">=</span> <span class="n">yolo_layer_prediction</span><span class="p">[</span><span class="n">image</span><span class="p">,</span> <span class="n">anchor</span><span class="p">,</span> <span class="n">grid_y</span><span class="p">,</span> <span class="n">grid_x</span><span class="p">]</span>
                <span class="n">target_object</span><span class="p">[</span><span class="n">image</span><span class="p">,</span> <span class="n">anchor</span><span class="p">,</span> <span class="n">grid_y</span><span class="p">,</span> <span class="n">grid_x</span><span class="p">]</span> <span class="o">=</span> <span class="mf">1.0</span>
                <span class="c1"># GIoU LOSS CALCULATION</span>
                <span class="n">pxy</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span>
                    <span class="n">predictions_for_targets</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">:</span><span class="mi">2</span><span class="p">])</span>  <span class="c1"># pxy = pxy * s - (s - 1) / 2,  s = 1.5  (scale_xy)</span>
                <span class="n">bbox_prediction</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">(</span>
                    <span class="p">(</span><span class="n">pxy</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="n">predictions_for_targets</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">:</span><span class="mi">4</span><span class="p">])</span><span class="o">.</span><span class="n">clamp</span><span class="p">(</span><span class="nb">max</span><span class="o">=</span><span class="mf">1E3</span><span class="p">)</span> <span class="o">*</span> <span class="n">anchor_vec</span><span class="p">[</span><span class="n">yolo_layer_index</span><span class="p">]),</span> <span class="mi">1</span><span class="p">)</span>
                <span class="n">giou</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">-</span> <span class="n">calculate_bbox_iou_elementwise</span><span class="p">(</span><span class="n">bbox_prediction</span><span class="o">.</span><span class="n">t</span><span class="p">(),</span> <span class="n">target_box</span><span class="p">[</span><span class="n">yolo_layer_index</span><span class="p">],</span>
                                                            <span class="n">x1y1x2y2</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">GIoU</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
                <span class="n">giou_loss</span> <span class="o">+=</span> <span class="n">giou</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="k">if</span> <span class="n">reduction</span> <span class="o">==</span> <span class="s1">&#39;sum&#39;</span> <span class="k">else</span> <span class="n">giou</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
                <span class="c1"># ONLY RELEVANT TO MULTIPLE CLASSES</span>
                <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">classes_num</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
                    <span class="n">class_targets</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">predictions_for_targets</span><span class="p">[:,</span> <span class="mi">5</span><span class="p">:])</span>
                    <span class="n">class_targets</span><span class="p">[</span><span class="nb">range</span><span class="p">(</span><span class="n">nb</span><span class="p">),</span> <span class="n">target_class</span><span class="p">[</span><span class="n">yolo_layer_index</span><span class="p">]]</span> <span class="o">=</span> <span class="mf">1.0</span>
                    <span class="n">class_loss</span> <span class="o">+=</span> <span class="n">BCEcls</span><span class="p">(</span><span class="n">predictions_for_targets</span><span class="p">[:,</span> <span class="mi">5</span><span class="p">:],</span> <span class="n">class_targets</span><span class="p">)</span>
            <span class="n">objectness_loss</span> <span class="o">+=</span> <span class="n">BCEobj</span><span class="p">(</span><span class="n">yolo_layer_prediction</span><span class="p">[</span><span class="o">...</span><span class="p">,</span> <span class="mi">4</span><span class="p">],</span> <span class="n">target_object</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">reduction</span> <span class="o">==</span> <span class="s1">&#39;sum&#39;</span><span class="p">:</span>
            <span class="n">giou_loss</span> <span class="o">*=</span> <span class="mi">3</span> <span class="o">/</span> <span class="n">targets_num</span>
            <span class="n">objectness_loss</span> <span class="o">*=</span> <span class="mi">3</span> <span class="o">/</span> <span class="n">grid_points_num</span>
            <span class="n">class_loss</span> <span class="o">*=</span> <span class="mi">3</span> <span class="o">/</span> <span class="n">targets_num</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">classes_num</span>
        <span class="n">loss</span> <span class="o">=</span> <span class="n">giou_loss</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">giou</span> <span class="o">+</span> <span class="n">objectness_loss</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">obj</span> <span class="o">+</span> <span class="n">class_loss</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">cls</span>
        <span class="k">return</span> <span class="n">loss</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">((</span><span class="n">giou_loss</span><span class="p">,</span> <span class="n">objectness_loss</span><span class="p">,</span> <span class="n">class_loss</span><span class="p">,</span> <span class="n">loss</span><span class="p">))</span><span class="o">.</span><span class="n">detach</span><span class="p">()</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>

          
        
      

  
Tip!
Press p or to see the previous file or, n or to see the next file
Deci-AI / super-gradients connected to https://github.com/Deci-AI/super-gradients.git

#286 Sg/yolox readme

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