#561 Feature/sg 193 extend output formator

Merged
Ghost merged 1 commits into Deci-AI:master from deci-ai:feature/SG-193-extend_detection_target_transform
  
    
        
          
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

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

          
            <!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.datasets.detection_datasets.pascal_voc_detection &mdash; SuperGradients 3.0.3 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" />
      <link rel="stylesheet" href="../../../../../_static/custom.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/_sphinx_javascript_frameworks_compat.js"></script>
        <script src="../../../../../_static/doctools.js"></script>
        <script src="../../../../../_static/sphinx_highlight.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" role="heading"><span class="caption-text">Welcome To SuperGradients</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html">Version 3 is out! Notebooks have been updated!</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#build-with-supergradients">Build with SuperGradients</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#quick-installation">Quick Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#what-s-new">What’s New</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#coming-soon">Coming soon</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#table-of-content">Table of Content</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#getting-started">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#advanced-features">Advanced Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#installation-methods">Installation Methods</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#implemented-model-architectures">Implemented Model Architectures</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#documentation">Documentation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#contributing">Contributing</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#citation">Citation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#community">Community</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#license">License</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../welcome.html#deci-platform">Deci Platform</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Technical Documentation</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../../super_gradients.common.html">Common package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../super_gradients.training.html">Training package</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.datasets.detection_datasets.pascal_voc_detection</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.datasets.detection_datasets.pascal_voc_detection</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">glob</span>
<span class="kn">from</span> <span class="nn">pathlib</span> <span class="kn">import</span> <span class="n">Path</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span>
<span class="kn">from</span> <span class="nn">xml.etree</span> <span class="kn">import</span> <span class="n">ElementTree</span>
<span class="kn">from</span> <span class="nn">torch.utils.data</span> <span class="kn">import</span> <span class="n">ConcatDataset</span>
<span class="kn">from</span> <span class="nn">tqdm</span> <span class="kn">import</span> <span class="n">tqdm</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">super_gradients.training.transforms.transforms</span> <span class="kn">import</span> <span class="n">DetectionTransform</span>
<span class="kn">from</span> <span class="nn">super_gradients.training.utils.utils</span> <span class="kn">import</span> <span class="n">download_and_untar_from_url</span><span class="p">,</span> <span class="n">get_image_size_from_path</span>
<span class="kn">from</span> <span class="nn">super_gradients.training.datasets.detection_datasets.detection_dataset</span> <span class="kn">import</span> <span class="n">DetectionDataset</span>
<span class="kn">from</span> <span class="nn">super_gradients.training.utils.detection_utils</span> <span class="kn">import</span> <span class="n">DetectionTargetsFormat</span>
<span class="kn">from</span> <span class="nn">super_gradients.common.abstractions.abstract_logger</span> <span class="kn">import</span> <span class="n">get_logger</span>
<span class="kn">from</span> <span class="nn">super_gradients.training.datasets.datasets_conf</span> <span class="kn">import</span> <span class="n">PASCAL_VOC_2012_CLASSES_LIST</span>
<span class="n">logger</span> <span class="o">=</span> <span class="n">get_logger</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span>
<div class="viewcode-block" id="PascalVOCDetectionDataset"><a class="viewcode-back" href="../../../../../super_gradients.training.html#super_gradients.training.datasets.PascalVOCDetectionDataset">[docs]</a><span class="k">class</span> <span class="nc">PascalVOCDetectionDataset</span><span class="p">(</span><span class="n">DetectionDataset</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;Dataset for Pascal VOC object detection&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">images_sub_directory</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">download</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Dataset for Pascal VOC object detection</span>
<span class="sd">        :param images_sub_directory:    Sub directory of data_dir that includes images.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">images_sub_directory</span> <span class="o">=</span> <span class="n">images_sub_directory</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">img_and_target_path_list</span> <span class="o">=</span> <span class="kc">None</span>
        <span class="n">data_dir</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;data_dir&quot;</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">data_dir</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Must pass data_dir != None through **kwargs&quot;</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">download</span><span class="p">:</span>
            <span class="n">PascalVOCDetectionDataset</span><span class="o">.</span><span class="n">download</span><span class="p">(</span><span class="n">data_dir</span><span class="p">)</span>
        <span class="n">kwargs</span><span class="p">[</span><span class="s2">&quot;original_target_format&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">DetectionTargetsFormat</span><span class="o">.</span><span class="n">XYXY_LABEL</span>
        <span class="n">kwargs</span><span class="p">[</span><span class="s2">&quot;all_classes_list&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">PASCAL_VOC_2012_CLASSES_LIST</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="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
    <span class="k">def</span> <span class="nf">_setup_data_source</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Initialize img_and_target_path_list and warn if label file is missing</span>
<span class="sd">        :return: List of tuples made of (img_path,target_path)</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">img_files_folder</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_dir</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">images_sub_directory</span>
        <span class="k">if</span> <span class="ow">not</span> <span class="n">Path</span><span class="p">(</span><span class="n">img_files_folder</span><span class="p">)</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
            <span class="k">raise</span> <span class="ne">FileNotFoundError</span><span class="p">(</span>
                <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">data_dir</span><span class="si">}</span><span class="s2"> does not include </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">images_sub_directory</span><span class="si">}</span><span class="s2">. &quot;</span>
                <span class="sa">f</span><span class="s2">&quot;Please make sure that f</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">data_dir</span><span class="si">}</span><span class="s2"> refers to PascalVOC dataset and that &quot;</span>
                <span class="s2">&quot;it was downloaded using PascalVOCDetectionDataSetV2.download()&quot;</span>
            <span class="p">)</span>
        <span class="n">img_files</span> <span class="o">=</span> <span class="n">glob</span><span class="o">.</span><span class="n">glob</span><span class="p">(</span><span class="n">img_files_folder</span> <span class="o">+</span> <span class="s2">&quot;*.jpg&quot;</span><span class="p">)</span>
        <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">img_files</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
            <span class="k">raise</span> <span class="ne">FileNotFoundError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;No image file found at </span><span class="si">{</span><span class="n">img_files_folder</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
        <span class="n">target_files</span> <span class="o">=</span> <span class="p">[</span><span class="n">img_file</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">&quot;images&quot;</span><span class="p">,</span> <span class="s2">&quot;labels&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">&quot;.jpg&quot;</span><span class="p">,</span> <span class="s2">&quot;.txt&quot;</span><span class="p">)</span> <span class="k">for</span> <span class="n">img_file</span> <span class="ow">in</span> <span class="n">img_files</span><span class="p">]</span>
        <span class="n">img_and_target_path_list</span> <span class="o">=</span> <span class="p">[(</span><span class="n">img_file</span><span class="p">,</span> <span class="n">target_file</span><span class="p">)</span> <span class="k">for</span> <span class="n">img_file</span><span class="p">,</span> <span class="n">target_file</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">img_files</span><span class="p">,</span> <span class="n">target_files</span><span class="p">)</span> <span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">target_file</span><span class="p">)]</span>
        <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">img_and_target_path_list</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
            <span class="k">raise</span> <span class="ne">FileNotFoundError</span><span class="p">(</span><span class="s2">&quot;No target file associated to the images was found&quot;</span><span class="p">)</span>
        <span class="n">num_missing_files</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">img_files</span><span class="p">)</span> <span class="o">-</span> <span class="nb">len</span><span class="p">(</span><span class="n">img_and_target_path_list</span><span class="p">)</span>
        <span class="k">if</span> <span class="n">num_missing_files</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
            <span class="n">logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">num_missing_files</span><span class="si">}</span><span class="s2"> labels files were not loaded our of </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">img_files</span><span class="p">)</span><span class="si">}</span><span class="s2"> image files&quot;</span><span class="p">)</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">img_and_target_path_list</span> <span class="o">=</span> <span class="n">img_and_target_path_list</span>
        <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">img_and_target_path_list</span><span class="p">)</span>
    <span class="k">def</span> <span class="nf">_load_annotation</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sample_id</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">dict</span><span class="p">:</span>
        <span class="sd">&quot;&quot;&quot;Load annotations associated to a specific sample.</span>
<span class="sd">        :return: Annotation including:</span>
<span class="sd">                    - target in XYXY_LABEL format</span>
<span class="sd">                    - img_path</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">img_path</span><span class="p">,</span> <span class="n">target_path</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">img_and_target_path_list</span><span class="p">[</span><span class="n">sample_id</span><span class="p">]</span>
        <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">target_path</span><span class="p">,</span> <span class="s2">&quot;r&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">targets_file</span><span class="p">:</span>
            <span class="n">target</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">x</span><span class="o">.</span><span class="n">split</span><span class="p">()</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">targets_file</span><span class="o">.</span><span class="n">read</span><span class="p">()</span><span class="o">.</span><span class="n">splitlines</span><span class="p">()],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
        <span class="n">height</span><span class="p">,</span> <span class="n">width</span> <span class="o">=</span> <span class="n">get_image_size_from_path</span><span class="p">(</span><span class="n">img_path</span><span class="p">)</span>
        <span class="c1"># We have to rescale the targets because the images will be resized.</span>
        <span class="n">r</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">input_dim</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">/</span> <span class="n">height</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">input_dim</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">/</span> <span class="n">width</span><span class="p">)</span>
        <span class="n">target</span><span class="p">[:,</span> <span class="p">:</span><span class="mi">4</span><span class="p">]</span> <span class="o">*=</span> <span class="n">r</span>
        <span class="n">resized_img_shape</span> <span class="o">=</span> <span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">height</span> <span class="o">*</span> <span class="n">r</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">width</span> <span class="o">*</span> <span class="n">r</span><span class="p">))</span>
        <span class="k">return</span> <span class="p">{</span><span class="s2">&quot;img_path&quot;</span><span class="p">:</span> <span class="n">img_path</span><span class="p">,</span> <span class="s2">&quot;target&quot;</span><span class="p">:</span> <span class="n">target</span><span class="p">,</span> <span class="s2">&quot;resized_img_shape&quot;</span><span class="p">:</span> <span class="n">resized_img_shape</span><span class="p">}</span>
<div class="viewcode-block" id="PascalVOCDetectionDataset.download"><a class="viewcode-back" href="../../../../../super_gradients.training.html#super_gradients.training.datasets.PascalVOCDetectionDataset.download">[docs]</a>    <span class="nd">@staticmethod</span>
    <span class="k">def</span> <span class="nf">download</span><span class="p">(</span><span class="n">data_dir</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Download Pascal dataset in XYXY_LABEL format.</span>
<span class="sd">        Data extracted form http://host.robots.ox.ac.uk/pascal/VOC/</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">def</span> <span class="nf">_parse_and_save_labels</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">new_label_path</span><span class="p">,</span> <span class="n">year</span><span class="p">,</span> <span class="n">image_id</span><span class="p">):</span>
            <span class="sd">&quot;&quot;&quot;Parse and save the labels of an image in XYXY_LABEL format.&quot;&quot;&quot;</span>
            <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">path</span><span class="si">}</span><span class="s2">/VOC</span><span class="si">{</span><span class="n">year</span><span class="si">}</span><span class="s2">/Annotations/</span><span class="si">{</span><span class="n">image_id</span><span class="si">}</span><span class="s2">.xml&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
                <span class="n">xml_parser</span> <span class="o">=</span> <span class="n">ElementTree</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">f</span><span class="p">)</span><span class="o">.</span><span class="n">getroot</span><span class="p">()</span>
            <span class="n">labels</span> <span class="o">=</span> <span class="p">[]</span>
            <span class="k">for</span> <span class="n">obj</span> <span class="ow">in</span> <span class="n">xml_parser</span><span class="o">.</span><span class="n">iter</span><span class="p">(</span><span class="s2">&quot;object&quot;</span><span class="p">):</span>
                <span class="bp">cls</span> <span class="o">=</span> <span class="n">obj</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">&quot;name&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">text</span>
                <span class="k">if</span> <span class="bp">cls</span> <span class="ow">in</span> <span class="n">PASCAL_VOC_2012_CLASSES_LIST</span> <span class="ow">and</span> <span class="ow">not</span> <span class="nb">int</span><span class="p">(</span><span class="n">obj</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">&quot;difficult&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">text</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
                    <span class="n">xml_box</span> <span class="o">=</span> <span class="n">obj</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">&quot;bndbox&quot;</span><span class="p">)</span>
                    <span class="k">def</span> <span class="nf">get_coord</span><span class="p">(</span><span class="n">box_coord</span><span class="p">):</span>
                        <span class="k">return</span> <span class="n">xml_box</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="n">box_coord</span><span class="p">)</span><span class="o">.</span><span class="n">text</span>
                    <span class="n">xmin</span><span class="p">,</span> <span class="n">ymin</span><span class="p">,</span> <span class="n">xmax</span><span class="p">,</span> <span class="n">ymax</span> <span class="o">=</span> <span class="n">get_coord</span><span class="p">(</span><span class="s2">&quot;xmin&quot;</span><span class="p">),</span> <span class="n">get_coord</span><span class="p">(</span><span class="s2">&quot;ymin&quot;</span><span class="p">),</span> <span class="n">get_coord</span><span class="p">(</span><span class="s2">&quot;xmax&quot;</span><span class="p">),</span> <span class="n">get_coord</span><span class="p">(</span><span class="s2">&quot;ymax&quot;</span><span class="p">)</span>
                    <span class="n">labels</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">&quot; &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">xmin</span><span class="p">,</span> <span class="n">ymin</span><span class="p">,</span> <span class="n">xmax</span><span class="p">,</span> <span class="n">ymax</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">PASCAL_VOC_2012_CLASSES_LIST</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="bp">cls</span><span class="p">))]))</span>
            <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">new_label_path</span><span class="p">,</span> <span class="s2">&quot;w&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
                <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s2">&quot;</span><span class="se">\n</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">labels</span><span class="p">))</span>
        <span class="n">urls</span> <span class="o">=</span> <span class="p">[</span>
            <span class="s2">&quot;http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar&quot;</span><span class="p">,</span>  <span class="c1"># 439M 5011 images</span>
            <span class="s2">&quot;http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar&quot;</span><span class="p">,</span>  <span class="c1"># 430M, 4952 images</span>
            <span class="s2">&quot;http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar&quot;</span><span class="p">,</span>
        <span class="p">]</span>  <span class="c1"># 1.86G, 17125 images</span>
        <span class="n">data_dir</span> <span class="o">=</span> <span class="n">Path</span><span class="p">(</span><span class="n">data_dir</span><span class="p">)</span>
        <span class="n">download_and_untar_from_url</span><span class="p">(</span><span class="n">urls</span><span class="p">,</span> <span class="nb">dir</span><span class="o">=</span><span class="n">data_dir</span> <span class="o">/</span> <span class="s2">&quot;images&quot;</span><span class="p">)</span>
        <span class="c1"># Convert</span>
        <span class="n">data_path</span> <span class="o">=</span> <span class="n">data_dir</span> <span class="o">/</span> <span class="s2">&quot;images&quot;</span> <span class="o">/</span> <span class="s2">&quot;VOCdevkit&quot;</span>
        <span class="k">for</span> <span class="n">year</span><span class="p">,</span> <span class="n">image_set</span> <span class="ow">in</span> <span class="p">(</span><span class="s2">&quot;2012&quot;</span><span class="p">,</span> <span class="s2">&quot;train&quot;</span><span class="p">),</span> <span class="p">(</span><span class="s2">&quot;2012&quot;</span><span class="p">,</span> <span class="s2">&quot;val&quot;</span><span class="p">),</span> <span class="p">(</span><span class="s2">&quot;2007&quot;</span><span class="p">,</span> <span class="s2">&quot;train&quot;</span><span class="p">),</span> <span class="p">(</span><span class="s2">&quot;2007&quot;</span><span class="p">,</span> <span class="s2">&quot;val&quot;</span><span class="p">),</span> <span class="p">(</span><span class="s2">&quot;2007&quot;</span><span class="p">,</span> <span class="s2">&quot;test&quot;</span><span class="p">):</span>
            <span class="n">dest_imgs_path</span> <span class="o">=</span> <span class="n">data_dir</span> <span class="o">/</span> <span class="s2">&quot;images&quot;</span> <span class="o">/</span> <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">image_set</span><span class="si">}{</span><span class="n">year</span><span class="si">}</span><span class="s2">&quot;</span>
            <span class="n">dest_imgs_path</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">exist_ok</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">parents</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
            <span class="n">dest_labels_path</span> <span class="o">=</span> <span class="n">data_dir</span> <span class="o">/</span> <span class="s2">&quot;labels&quot;</span> <span class="o">/</span> <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">image_set</span><span class="si">}{</span><span class="n">year</span><span class="si">}</span><span class="s2">&quot;</span>
            <span class="n">dest_labels_path</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">exist_ok</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">parents</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
            <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">data_path</span> <span class="o">/</span> <span class="sa">f</span><span class="s2">&quot;VOC</span><span class="si">{</span><span class="n">year</span><span class="si">}</span><span class="s2">/ImageSets/Main/</span><span class="si">{</span><span class="n">image_set</span><span class="si">}</span><span class="s2">.txt&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
                <span class="n">image_ids</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">()</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
            <span class="k">for</span> <span class="nb">id</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span><span class="n">image_ids</span><span class="p">,</span> <span class="n">desc</span><span class="o">=</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">image_set</span><span class="si">}{</span><span class="n">year</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">):</span>
                <span class="n">img_path</span> <span class="o">=</span> <span class="n">data_path</span> <span class="o">/</span> <span class="sa">f</span><span class="s2">&quot;VOC</span><span class="si">{</span><span class="n">year</span><span class="si">}</span><span class="s2">/JPEGImages/</span><span class="si">{</span><span class="nb">id</span><span class="si">}</span><span class="s2">.jpg&quot;</span>
                <span class="n">new_img_path</span> <span class="o">=</span> <span class="n">dest_imgs_path</span> <span class="o">/</span> <span class="n">img_path</span><span class="o">.</span><span class="n">name</span>
                <span class="n">new_label_path</span> <span class="o">=</span> <span class="p">(</span><span class="n">dest_labels_path</span> <span class="o">/</span> <span class="n">img_path</span><span class="o">.</span><span class="n">name</span><span class="p">)</span><span class="o">.</span><span class="n">with_suffix</span><span class="p">(</span><span class="s2">&quot;.txt&quot;</span><span class="p">)</span>
                <span class="n">img_path</span><span class="o">.</span><span class="n">rename</span><span class="p">(</span><span class="n">new_img_path</span><span class="p">)</span>  <span class="c1"># Move image to dest folder</span>
                <span class="n">_parse_and_save_labels</span><span class="p">(</span><span class="n">data_path</span><span class="p">,</span> <span class="n">new_label_path</span><span class="p">,</span> <span class="n">year</span><span class="p">,</span> <span class="nb">id</span><span class="p">)</span></div></div>
<span class="k">class</span> <span class="nc">PascalVOCUnifiedDetectionTrainDataset</span><span class="p">(</span><span class="n">ConcatDataset</span><span class="p">):</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">data_dir</span><span class="p">,</span>
        <span class="n">input_dim</span><span class="p">:</span> <span class="nb">tuple</span><span class="p">,</span>
        <span class="n">cache</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
        <span class="n">cache_dir</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
        <span class="n">transforms</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">DetectionTransform</span><span class="p">]</span> <span class="o">=</span> <span class="p">[],</span>
        <span class="n">class_inclusion_list</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
        <span class="n">max_num_samples</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
        <span class="n">download</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
    <span class="p">):</span>
        <span class="k">if</span> <span class="n">download</span><span class="p">:</span>
            <span class="n">PascalVOCDetectionDataset</span><span class="o">.</span><span class="n">download</span><span class="p">(</span><span class="n">data_dir</span><span class="o">=</span><span class="n">data_dir</span><span class="p">)</span>
        <span class="n">train_dataset_names</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;train2007&quot;</span><span class="p">,</span> <span class="s2">&quot;val2007&quot;</span><span class="p">,</span> <span class="s2">&quot;train2012&quot;</span><span class="p">,</span> <span class="s2">&quot;val2012&quot;</span><span class="p">]</span>
        <span class="c1"># We divide train_max_num_samples between the datasets</span>
        <span class="k">if</span> <span class="n">max_num_samples</span><span class="p">:</span>
            <span class="n">max_num_samples_per_train_dataset</span> <span class="o">=</span> <span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">segment</span><span class="p">)</span> <span class="k">for</span> <span class="n">segment</span> <span class="ow">in</span> <span class="n">np</span><span class="o">.</span><span class="n">array_split</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">max_num_samples</span><span class="p">),</span> <span class="nb">len</span><span class="p">(</span><span class="n">train_dataset_names</span><span class="p">))]</span>
        <span class="k">else</span><span class="p">:</span>
            <span class="n">max_num_samples_per_train_dataset</span> <span class="o">=</span> <span class="p">[</span><span class="kc">None</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">train_dataset_names</span><span class="p">)</span>
        <span class="n">train_sets</span> <span class="o">=</span> <span class="p">[</span>
            <span class="n">PascalVOCDetectionDataset</span><span class="p">(</span>
                <span class="n">data_dir</span><span class="o">=</span><span class="n">data_dir</span><span class="p">,</span>
                <span class="n">input_dim</span><span class="o">=</span><span class="n">input_dim</span><span class="p">,</span>
                <span class="n">cache</span><span class="o">=</span><span class="n">cache</span><span class="p">,</span>
                <span class="n">cache_dir</span><span class="o">=</span><span class="n">cache_dir</span><span class="p">,</span>
                <span class="n">transforms</span><span class="o">=</span><span class="n">transforms</span><span class="p">,</span>
                <span class="n">images_sub_directory</span><span class="o">=</span><span class="s2">&quot;images/&quot;</span> <span class="o">+</span> <span class="n">trainset_name</span> <span class="o">+</span> <span class="s2">&quot;/&quot;</span><span class="p">,</span>
                <span class="n">class_inclusion_list</span><span class="o">=</span><span class="n">class_inclusion_list</span><span class="p">,</span>
                <span class="n">max_num_samples</span><span class="o">=</span><span class="n">max_num_samples_per_train_dataset</span><span class="p">[</span><span class="n">i</span><span class="p">],</span>
            <span class="p">)</span>
            <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">trainset_name</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">train_dataset_names</span><span class="p">)</span>
        <span class="p">]</span>
        <span class="nb">super</span><span class="p">(</span><span class="n">PascalVOCUnifiedDetectionTrainDataset</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">train_sets</span><span class="p">)</span>
</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

#561 Feature/sg 193 extend output formator

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