Update Sphinx documentation

Author: actions-user

docs/py_docs/build/html/.doctrees/api/perceptionmetrics.models.utils.doctree

@@ -553,10 +553,14 @@ <h1>Source code for perceptionmetrics.models.torch_detection</h1><div class="hig
         <span class="c1"># Load confidence and NMS thresholds from config</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">confidence_threshold</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_cfg</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;confidence_threshold&quot;</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">nms_threshold</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_cfg</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;nms_threshold&quot;</span><span class="p">,</span> <span class="mf">0.3</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">max_detections_per_image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_cfg</span><span class="o">.</span><span class="n">get</span><span class="p">(</span>
+            <span class="s2">&quot;max_detections_per_image&quot;</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span>
+        <span class="p">)</span>
 
         <span class="bp">self</span><span class="o">.</span><span class="n">postprocess_args</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">confidence_threshold</span><span class="p">]</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_format</span> <span class="o">==</span> <span class="s2">&quot;yolo&quot;</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">postprocess_args</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">nms_threshold</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">postprocess_args</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">max_detections_per_image</span><span class="p">)</span>
 
         <span class="c1"># Add reverse mapping for idx to class_name</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">idx_to_class_name</span> <span class="o">=</span> <span class="p">{</span><span class="n">v</span><span class="p">[</span><span class="s2">&quot;idx&quot;</span><span class="p">]:</span> <span class="n">k</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">ontology</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span>

docs/py_docs/build/html/.doctrees/environment.pickle

@@ -241,13 +241,17 @@
           <h1>Source code for perceptionmetrics.models.utils.torchvision</h1><div class="highlight"><pre>
 <div class="viewcode-block" id="postprocess_detection">
 <a class="viewcode-back" href="../../../../api/perceptionmetrics.models.utils.html#perceptionmetrics.models.utils.torchvision.postprocess_detection">[docs]</a>
-<span></span><span class="k">def</span><span class="w"> </span><span class="nf">postprocess_detection</span><span class="p">(</span><span class="n">output</span><span class="p">:</span> <span class="nb">dict</span><span class="p">,</span> <span class="n">confidence_threshold</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.5</span><span class="p">):</span>
+<span></span><span class="k">def</span><span class="w"> </span><span class="nf">postprocess_detection</span><span class="p">(</span>
+    <span class="n">output</span><span class="p">:</span> <span class="nb">dict</span><span class="p">,</span> <span class="n">confidence_threshold</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.5</span><span class="p">,</span> <span class="n">max_detections</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span>
+<span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Post-process torchvision model output.</span>
 
 <span class="sd">    :param output: Dictionary with keys &#39;boxes&#39;, &#39;labels&#39;, and &#39;scores&#39;.</span>
 <span class="sd">    :type output: dict</span>
 <span class="sd">    :param confidence_threshold: Confidence threshold to filter boxes.</span>
 <span class="sd">    :type confidence_threshold: float</span>
+<span class="sd">    :param max_detections: Maximum number of best detections to keep per image after filtering.</span>
+<span class="sd">    :type max_detections: int</span>
 <span class="sd">    :return: Dictionary with keys &#39;boxes&#39;, &#39;labels&#39;, and &#39;scores&#39;.</span>
 <span class="sd">    :rtype: dict</span>
 <span class="sd">    &quot;&quot;&quot;</span>
@@ -258,6 +262,15 @@ <h1>Source code for perceptionmetrics.models.utils.torchvision</h1><div class="h
             <span class="s2">&quot;labels&quot;</span><span class="p">:</span> <span class="n">output</span><span class="p">[</span><span class="s2">&quot;labels&quot;</span><span class="p">][</span><span class="n">keep_mask</span><span class="p">],</span>
             <span class="s2">&quot;scores&quot;</span><span class="p">:</span> <span class="n">output</span><span class="p">[</span><span class="s2">&quot;scores&quot;</span><span class="p">][</span><span class="n">keep_mask</span><span class="p">],</span>
         <span class="p">}</span>
+
+    <span class="k">if</span> <span class="n">max_detections</span> <span class="o">&lt;</span> <span class="n">output</span><span class="p">[</span><span class="s2">&quot;scores&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">and</span> <span class="n">max_detections</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
+        <span class="n">limited_idx</span> <span class="o">=</span> <span class="n">output</span><span class="p">[</span><span class="s2">&quot;scores&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">argsort</span><span class="p">(</span><span class="n">descending</span><span class="o">=</span><span class="kc">True</span><span class="p">)[:</span><span class="n">max_detections</span><span class="p">]</span>
+        <span class="n">output</span> <span class="o">=</span> <span class="p">{</span>
+            <span class="s2">&quot;boxes&quot;</span><span class="p">:</span> <span class="n">output</span><span class="p">[</span><span class="s2">&quot;boxes&quot;</span><span class="p">][</span><span class="n">limited_idx</span><span class="p">],</span>
+            <span class="s2">&quot;labels&quot;</span><span class="p">:</span> <span class="n">output</span><span class="p">[</span><span class="s2">&quot;labels&quot;</span><span class="p">][</span><span class="n">limited_idx</span><span class="p">],</span>
+            <span class="s2">&quot;scores&quot;</span><span class="p">:</span> <span class="n">output</span><span class="p">[</span><span class="s2">&quot;scores&quot;</span><span class="p">][</span><span class="n">limited_idx</span><span class="p">],</span>
+        <span class="p">}</span>
+
     <span class="k">return</span> <span class="n">output</span></div>
 
 </pre></div>

docs/py_docs/build/html/_modules/perceptionmetrics/models/torch_detection.html

@@ -242,7 +242,6 @@ <h1>Source code for perceptionmetrics.models.utils.yolo</h1><div class="highligh
 <span></span><span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
 <span class="kn">from</span><span class="w"> </span><span class="nn">torchvision.ops</span><span class="w"> </span><span class="kn">import</span> <span class="n">nms</span>
 
-
 <span class="n">CLASS_NMS_OFFSET</span> <span class="o">=</span> <span class="mi">7680</span>  <span class="c1"># offset to apply to boxes for class-wise NMS</span>
 
 
@@ -252,6 +251,7 @@ <h1>Source code for perceptionmetrics.models.utils.yolo</h1><div class="highligh
     <span class="n">output</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span>
     <span class="n">confidence_threshold</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.25</span><span class="p">,</span>
     <span class="n">nms_threshold</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.45</span><span class="p">,</span>
+    <span class="n">max_detections</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span>
 <span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Post-process YOLO model output.</span>
 
@@ -261,6 +261,8 @@ <h1>Source code for perceptionmetrics.models.utils.yolo</h1><div class="highligh
 <span class="sd">    :type confidence_threshold: float</span>
 <span class="sd">    :param nms_threshold: IoU threshold for Non-Maximum Suppression (NMS). Some models may not perform NMS (e.g. YOLOv26).</span>
 <span class="sd">    :type nms_threshold: float</span>
+<span class="sd">    :param max_detections: Maximum number of best detections to keep per image after filtering.</span>
+<span class="sd">    :type max_detections: int</span>
 <span class="sd">    :return: Dictionary with keys &#39;boxes&#39;, &#39;labels&#39;, and &#39;scores&#39;.</span>
 <span class="sd">    :rtype: dict</span>
 <span class="sd">    &quot;&quot;&quot;</span>
@@ -300,6 +302,12 @@ <h1>Source code for perceptionmetrics.models.utils.yolo</h1><div class="highligh
         <span class="n">scores</span> <span class="o">=</span> <span class="n">scores</span><span class="p">[</span><span class="n">keep_idx</span><span class="p">]</span>
         <span class="n">labels</span> <span class="o">=</span> <span class="n">labels</span><span class="p">[</span><span class="n">keep_idx</span><span class="p">]</span>
 
+        <span class="k">if</span> <span class="n">max_detections</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">max_detections</span> <span class="o">&lt;</span> <span class="n">scores</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span>
+            <span class="n">limited_idx</span> <span class="o">=</span> <span class="n">scores</span><span class="o">.</span><span class="n">argsort</span><span class="p">(</span><span class="n">descending</span><span class="o">=</span><span class="kc">True</span><span class="p">)[:</span><span class="n">max_detections</span><span class="p">]</span>
+            <span class="n">boxes_xyxy</span> <span class="o">=</span> <span class="n">boxes_xyxy</span><span class="p">[</span><span class="n">limited_idx</span><span class="p">]</span>
+            <span class="n">scores</span> <span class="o">=</span> <span class="n">scores</span><span class="p">[</span><span class="n">limited_idx</span><span class="p">]</span>
+            <span class="n">labels</span> <span class="o">=</span> <span class="n">labels</span><span class="p">[</span><span class="n">limited_idx</span><span class="p">]</span>
+
     <span class="k">return</span> <span class="p">{</span><span class="s2">&quot;boxes&quot;</span><span class="p">:</span> <span class="n">boxes_xyxy</span><span class="p">,</span> <span class="s2">&quot;labels&quot;</span><span class="p">:</span> <span class="n">labels</span><span class="p">,</span> <span class="s2">&quot;scores&quot;</span><span class="p">:</span> <span class="n">scores</span><span class="p">}</span></div>
 
 </pre></div>

docs/py_docs/build/html/_modules/perceptionmetrics/models/utils/torchvision.html

@@ -480,13 +480,14 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Link to this headi
 <span id="perceptionmetrics-models-utils-torchvision-module"></span><h2>perceptionmetrics.models.utils.torchvision module<a class="headerlink" href="#module-perceptionmetrics.models.utils.torchvision" title="Link to this heading">¶</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="perceptionmetrics.models.utils.torchvision.postprocess_detection">
-<span class="sig-prename descclassname"><span class="pre">perceptionmetrics.models.utils.torchvision.</span></span><span class="sig-name descname"><span class="pre">postprocess_detection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">confidence_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/perceptionmetrics/models/utils/torchvision.html#postprocess_detection"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#perceptionmetrics.models.utils.torchvision.postprocess_detection" title="Link to this definition">¶</a></dt>
+<span class="sig-prename descclassname"><span class="pre">perceptionmetrics.models.utils.torchvision.</span></span><span class="sig-name descname"><span class="pre">postprocess_detection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">confidence_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_detections</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/perceptionmetrics/models/utils/torchvision.html#postprocess_detection"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#perceptionmetrics.models.utils.torchvision.postprocess_detection" title="Link to this definition">¶</a></dt>
 <dd><p>Post-process torchvision model output.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>output</strong> (<em>dict</em>) – Dictionary with keys ‘boxes’, ‘labels’, and ‘scores’.</p></li>
 <li><p><strong>confidence_threshold</strong> (<em>float</em>) – Confidence threshold to filter boxes.</p></li>
+<li><p><strong>max_detections</strong> (<em>int</em>) – Maximum number of best detections to keep per image after filtering.</p></li>
 </ul>
 </dd>
 <dt class="field-even">Returns<span class="colon">:</span></dt>
@@ -503,14 +504,15 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Link to this headi
 <span id="perceptionmetrics-models-utils-yolo-module"></span><h2>perceptionmetrics.models.utils.yolo module<a class="headerlink" href="#module-perceptionmetrics.models.utils.yolo" title="Link to this heading">¶</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="perceptionmetrics.models.utils.yolo.postprocess_detection">
-<span class="sig-prename descclassname"><span class="pre">perceptionmetrics.models.utils.yolo.</span></span><span class="sig-name descname"><span class="pre">postprocess_detection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">confidence_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nms_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.45</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/perceptionmetrics/models/utils/yolo.html#postprocess_detection"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#perceptionmetrics.models.utils.yolo.postprocess_detection" title="Link to this definition">¶</a></dt>
+<span class="sig-prename descclassname"><span class="pre">perceptionmetrics.models.utils.yolo.</span></span><span class="sig-name descname"><span class="pre">postprocess_detection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">confidence_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nms_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.45</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_detections</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/perceptionmetrics/models/utils/yolo.html#postprocess_detection"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#perceptionmetrics.models.utils.yolo.postprocess_detection" title="Link to this definition">¶</a></dt>
 <dd><p>Post-process YOLO model output.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>output</strong> (<em>torch.Tensor</em>) – Tensor of shape [num_classes + 4, num_anchors] containing bounding box predictions and class logits.</p></li>
 <li><p><strong>confidence_threshold</strong> (<em>float</em>) – Confidence threshold to filter boxes.</p></li>
 <li><p><strong>nms_threshold</strong> (<em>float</em>) – IoU threshold for Non-Maximum Suppression (NMS). Some models may not perform NMS (e.g. YOLOv26).</p></li>
+<li><p><strong>max_detections</strong> (<em>int</em>) – Maximum number of best detections to keep per image after filtering.</p></li>
 </ul>
 </dd>
 <dt class="field-even">Returns<span class="colon">:</span></dt>