Refactor MCTWrapper documentation and comments for clarity

Author: KazunoriSumiya

docs/api/api_docs/classes/Wrapper.html

@@ -52,13 +52,10 @@ <h3>Navigation</h3>
 <p>The wrapper manages the complete quantization pipeline from model input to
 quantized model export, handling framework-specific configurations and
 Target Platform Capabilities (TPC) setup.</p>
-<p>Initialize MCTWrapper with default parameters.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="model_compression_toolkit.wrapper.mct_wrapper.MCTWrapper.quantize_and_export">
 <span class="sig-name descname"><span class="pre">quantize_and_export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">float_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">representative_dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">framework</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'pytorch'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'PTQ'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_mixed_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param_items</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#model_compression_toolkit.wrapper.mct_wrapper.MCTWrapper.quantize_and_export" title="Link to this definition">¶</a></dt>
-<dd><p>Main function to perform model quantization and export.
-The wrapper manages the complete quantization pipeline from model input to quantized model export,
-handling framework-specific configurations and Target Platform Capabilities (TPC) setup.</p>
+<dd><p>Main function to perform model quantization and export.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type<span class="colon">:</span></dt>
 <dd class="field-odd"><p><span class="sphinx_autodoc_typehints-type"><code class="xref py py-data docutils literal notranslate"><span class="pre">Tuple</span></code>[<code class="xref py py-class docutils literal notranslate"><span class="pre">bool</span></code>, <code class="xref py py-data docutils literal notranslate"><span class="pre">Any</span></code>]</span></p>
@@ -82,7 +79,7 @@ <h3>Navigation</h3>
 </dd>
 </dl>
 <p class="rubric">Examples</p>
-<p>Import MCT:</p>
+<p>Import MCT</p>
 <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">import</span><span class="w"> </span><span class="nn">model_compression_toolkit</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">mct</span>
 </pre></div>
 </div>
@@ -95,13 +92,13 @@ <h3>Navigation</h3>
 <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">wrapper</span> <span class="o">=</span> <span class="n">mct</span><span class="o">.</span><span class="n">MCTWrapper</span><span class="p">()</span>
 </pre></div>
 </div>
-<p>set framework, method, and other parameters</p>
+<p>Set framework, method, and other parameters</p>
 <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">framework</span> <span class="o">=</span> <span class="s1">&#39;tensorflow&#39;</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">method</span> <span class="o">=</span> <span class="s1">&#39;PTQ&#39;</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">use_mixed_precision</span> <span class="o">=</span> <span class="kc">False</span>
 </pre></div>
 </div>
-<p>set parameters if needed</p>
+<p>Set parameters if needed</p>
 <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">param_items</span> <span class="o">=</span> <span class="p">[[</span><span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">]</span><span class="o">...</span><span class="p">]</span>
 </pre></div>
 </div>
@@ -116,7 +113,7 @@ <h3>Navigation</h3>
 <span class="gp">... </span><span class="p">)</span>
 </pre></div>
 </div>
-<p><strong>Parameters</strong></p>
+<p><strong>Initialize MCTWrapper with default parameters</strong></p>
 <p>Users can update the following parameters in param_items.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -139,7 +136,7 @@ <h3>Navigation</h3>
 <tbody>
 <tr class="row-even"><td><p>sdsp_version</p></td>
 <td><p>‘3.14’</p></td>
-<td><p>By specifying the SDSP converter version, you can select the optimal quantization settings for IMX500.Here, we use the settings for SDSP Converter 3.14. For other settings, please see <a class="reference external" href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities">here</a></p></td>
+<td><p>By specifying the SDSP converter version, you can select the <a class="reference external" href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities">optimal quantization settings</a> for IMX500.</p></td>
 </tr>
 <tr class="row-odd"><td><p>save_model_path</p></td>
 <td><p>‘./qmodel.keras’ / ‘./qmodel.onnx’</p></td>
@@ -183,7 +180,7 @@ <h3>Navigation</h3>
 <tbody>
 <tr class="row-even"><td><p>sdsp_version</p></td>
 <td><p>‘3.14’</p></td>
-<td><p>By specifying the SDSP converter version, you can select the optimal quantization settings for IMX500.Here, we use the settings for SDSP Converter 3.14. For other settings, please see <a class="reference external" href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities">here</a></p></td>
+<td><p>By specifying the SDSP converter version, you can select the <a class="reference external" href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities">optimal quantization settings</a> for IMX500.</p></td>
 </tr>
 <tr class="row-odd"><td><p>save_model_path</p></td>
 <td><p>‘./qmodel.keras’ / ‘./qmodel.onnx’</p></td>
@@ -243,7 +240,7 @@ <h3>Navigation</h3>
 <tbody>
 <tr class="row-even"><td><p>sdsp_version</p></td>
 <td><p>‘3.14’</p></td>
-<td><p>By specifying the SDSP converter version, you can select the optimal quantization settings for IMX500.Here, we use the settings for SDSP Converter 3.14. For other settings, please see <a class="reference external" href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities">here</a></p></td>
+<td><p>By specifying the SDSP converter version, you can select the <a class="reference external" href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities">optimal quantization settings</a> for IMX500.</p></td>
 </tr>
 <tr class="row-odd"><td><p>save_model_path</p></td>
 <td><p>‘./qmodel.keras’ / ‘./qmodel.onnx’</p></td>
@@ -295,7 +292,7 @@ <h3>Navigation</h3>
 <tbody>
 <tr class="row-even"><td><p>sdsp_version</p></td>
 <td><p>‘3.14’</p></td>
-<td><p>By specifying the SDSP converter version, you can select the optimal quantization settings for IMX500.Here, we use the settings for SDSP Converter 3.14. For other settings, please see <a class="reference external" href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities">here</a></p></td>
+<td><p>By specifying the SDSP converter version, you can select the <a class="reference external" href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities">optimal quantization settings</a> for IMX500.</p></td>
 </tr>
 <tr class="row-odd"><td><p>save_model_path</p></td>
 <td><p>‘./qmodel.keras’ / ‘./qmodel.onnx’</p></td>

docs/searchindex.js

@@ -41,9 +41,8 @@ class MCTWrapper:
     quantized model export, handling framework-specific configurations and
     Target Platform Capabilities (TPC) setup.
     """
-    
+
     def __init__(self):
-        """Initialize MCTWrapper with default parameters."""
         self.params: Dict[str, Any] = {
             # TPC
             FW_NAME: 'pytorch',
@@ -474,8 +473,6 @@ def quantize_and_export(self, float_model: Any,
                             ) -> Tuple[bool, Any]:
         """
         Main function to perform model quantization and export.
-        The wrapper manages the complete quantization pipeline from model input to quantized model export, 
-        handling framework-specific configurations and Target Platform Capabilities (TPC) setup.
 
         Args:
             float_model: The float model to be quantized.
@@ -495,7 +492,7 @@ def quantize_and_export(self, float_model: Any,
             
         Examples:
 
-            Import MCT:
+            Import MCT
 
             >>> import model_compression_toolkit as mct
             
@@ -508,13 +505,13 @@ def quantize_and_export(self, float_model: Any,
 
             >>> wrapper = mct.MCTWrapper()
 
-            set framework, method, and other parameters
+            Set framework, method, and other parameters
 
             >>> framework = 'tensorflow'
             >>> method = 'PTQ'
             >>> use_mixed_precision = False
 
-            set parameters if needed
+            Set parameters if needed
 
             >>> param_items = [[key, value]...]
 
@@ -529,10 +526,8 @@ def quantize_and_export(self, float_model: Any,
             ...     param_items=param_items
             ... )
 
+        **Initialize MCTWrapper with default parameters**
 
-
-        **Parameters**
-    
         Users can update the following parameters in param_items.
     
         .. note::
@@ -545,7 +540,7 @@ def quantize_and_export(self, float_model: Any,
            :header: "Parameter Key", "Default Value", "Description"
            :widths: 30, 30, 40
     
-           "sdsp_version", "'3.14'", "By specifying the SDSP converter version, you can select the optimal quantization settings for IMX500.Here, we use the settings for SDSP Converter 3.14. For other settings, please see `here <https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities>`_"
+           "sdsp_version", "'3.14'", "By specifying the SDSP converter version, you can select the `optimal quantization settings <https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities>`_ for IMX500."
            "save_model_path", "'./qmodel.keras' / './qmodel.onnx'", "Path to save quantized model (Keras/Pytorch)"
            "activation_error_method", "mct.core.QuantizationErrorMethod.MSE", "Activation quantization error method **(low priority)**"
            "weights_bias_correction", "True", "Enable weights bias correction **(low priority)**"
@@ -559,7 +554,7 @@ def quantize_and_export(self, float_model: Any,
            :header: "Parameter Key", "Default Value", "Description"
            :widths: 30, 30, 40
     
-           "sdsp_version", "'3.14'", "By specifying the SDSP converter version, you can select the optimal quantization settings for IMX500.Here, we use the settings for SDSP Converter 3.14. For other settings, please see `here <https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities>`_"
+           "sdsp_version", "'3.14'", "By specifying the SDSP converter version, you can select the `optimal quantization settings <https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities>`_ for IMX500."
            "save_model_path", "'./qmodel.keras' / './qmodel.onnx'", "Path to save quantized model (Keras/Pytorch)"
            "num_of_images", "32", "Number of images for mixed precision"
            "weights_compression_ratio", "0.75", "Weights compression ratio for mixed precision for resource util (0.0～1.0)"
@@ -577,7 +572,7 @@ def quantize_and_export(self, float_model: Any,
            :header: "Parameter Key", "Default Value", "Description"
            :widths: 30, 30, 40
     
-           "sdsp_version", "'3.14'", "By specifying the SDSP converter version, you can select the optimal quantization settings for IMX500.Here, we use the settings for SDSP Converter 3.14. For other settings, please see `here <https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities>`_"
+           "sdsp_version", "'3.14'", "By specifying the SDSP converter version, you can select the `optimal quantization settings <https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities>`_ for IMX500."
            "save_model_path", "'./qmodel.keras' / './qmodel.onnx'", "Path to save quantized model (Keras/Pytorch)"
            "n_epochs", "5", "Number of training epochs for GPTQ"
            "activation_error_method", "mct.core.QuantizationErrorMethod.MSE", "Activation quantization error method **(low priority)**"
@@ -593,7 +588,7 @@ def quantize_and_export(self, float_model: Any,
            :header: "Parameter Key", "Default Value", "Description"
            :widths: 30, 30, 40
     
-           "sdsp_version", "'3.14'", "By specifying the SDSP converter version, you can select the optimal quantization settings for IMX500.Here, we use the settings for SDSP Converter 3.14. For other settings, please see `here <https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities>`_"
+           "sdsp_version", "'3.14'", "By specifying the SDSP converter version, you can select the `optimal quantization settings <https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html#ug-target-platform-capabilities>`_ for IMX500."
            "save_model_path", "'./qmodel.keras' / './qmodel.onnx'", "Path to save quantized model (Keras/Pytorch)"
            "num_of_images", "32", "Number of images for mixed precision"
            "weights_compression_ratio", "0.75", "Weights compression ratio for mixed precision for resource util (0.0～1.0)"