Update docs for v2.3.0 (#1355)

Co-authored-by: reuvenp <[email protected]>
sony · Feb 12, 2025 · 9578f3c · 9578f3c
1 parent d9530b1
commit 9578f3c
Show file tree

Hide file tree

Showing 66 changed files with 973 additions and 751 deletions.
diff --git a/docs/.buildinfo b/docs/.buildinfo
@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 463b5d411b812fb296a8f7bff970d1cf
+config: e8534f6a2f0b425ce862dbeb0800af00
 tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/docs/_sources/api/api_docs/classes/GradientPTQConfig.rst.txt b/docs/_sources/api/api_docs/classes/GradientPTQConfig.rst.txt
@@ -8,7 +8,7 @@ GradientPTQConfig Class
 =================================
 
 
-**The following API can be used to create a GradientPTQConfig instance which can be used for post training quantization using knowledge distillation from a teacher (float Keras model) to a student (the quantized Keras model)**
+**The following API can be used to create a GradientPTQConfig instance which can be used for post training quantization using knowledge distillation from a teacher (float model) to a student (the quantized model)**
 
 .. autoclass:: model_compression_toolkit.gptq.GradientPTQConfig
     :members:
@@ -30,3 +30,22 @@ RoundingType
 
 .. autoclass:: model_compression_toolkit.gptq.RoundingType
     :members:
+
+
+=====================================
+GradualActivationQuantizationConfig
+=====================================
+
+**The following API can be used to configure the gradual activation quantization when using GPTQ.**
+
+.. autoclass:: model_compression_toolkit.gptq.GradualActivationQuantizationConfig
+    :members:
+
+
+=====================================
+QFractionLinearAnnealingConfig
+=====================================
+
+.. autoclass:: model_compression_toolkit.gptq.QFractionLinearAnnealingConfig
+    :members:
+
diff --git a/docs/_sources/api/api_docs/index.rst.txt b/docs/_sources/api/api_docs/index.rst.txt
@@ -106,9 +106,9 @@ keras_load_quantized_model
 - :ref:`keras_load_quantized_model<ug-keras_load_quantized_model>`: A function to load a quantized keras model.
 
 
-target_platform
-================
-- :ref:`target_platform<ug-target_platform>`: Module to create and model hardware-related settings to optimize the model according to, by the hardware the optimized model will use during inference.
+target_platform_capabilities
+==============================
+- :ref:`target_platform_capabilities<ug-target_platform_capabilities>`: Module to create and model hardware-related settings to optimize the model according to, by the hardware the optimized model will use during inference.
 - :ref:`get_target_platform_capabilities<ug-get_target_platform_capabilities>`: A function to get a target platform model for Tensorflow and Pytorch.
 - :ref:`DefaultDict<ug-DefaultDict>`: Util class for creating a TargetPlatformCapabilities.
 

diff --git a/docs/_sources/api/api_docs/methods/get_target_platform_capabilities.rst.txt b/docs/_sources/api/api_docs/methods/get_target_platform_capabilities.rst.txt
@@ -4,7 +4,7 @@
 
 
 =======================================
-Get TargetPlatformCapabilities
+Get FrameworkQuantizationCapabilities
 =======================================
 
 .. autofunction:: model_compression_toolkit.get_target_platform_capabilities

diff --git a/docs/_sources/api/api_docs/modules/layer_filters.rst.txt b/docs/_sources/api/api_docs/modules/layer_filters.rst.txt
@@ -15,30 +15,30 @@ one may use the next filters to check if a layer configuration holds the created
 Attribute Filters
 ==================
 
-.. autoclass:: model_compression_toolkit.target_platform.AttributeFilter
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.AttributeFilter
 
 |
 
-.. autoclass:: model_compression_toolkit.target_platform.Eq
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.Eq
 
 |
 
-.. autoclass:: model_compression_toolkit.target_platform.NotEq
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.NotEq
 
 |
 
-.. autoclass:: model_compression_toolkit.target_platform.Greater
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.Greater
 
 |
 
 
-.. autoclass:: model_compression_toolkit.target_platform.GreaterEq
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.GreaterEq
 
 |
 
 
-.. autoclass:: model_compression_toolkit.target_platform.Smaller
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.Smaller
 
 |
 
-.. autoclass:: model_compression_toolkit.target_platform.SmallerEq
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.SmallerEq
diff --git a/docs/_sources/api/api_docs/modules/qat_config.rst.txt b/docs/_sources/api/api_docs/modules/qat_config.rst.txt
@@ -10,10 +10,7 @@ qat_config Module
 
 TrainingMethod
 ================================
-**Select a QAT training method:**
-
-.. autoclass:: model_compression_toolkit.qat.TrainingMethod
-
+In order to select a training method, please visit the :ref:`trainable_infrastructure API.<ug-trainable_infrastructure>`
 
 |
 

diff --git a/.../api_docs/modules/target_platform.rst.txt → ...ules/target_platform_capabilities.rst.txt b/.../api_docs/modules/target_platform.rst.txt → ...ules/target_platform_capabilities.rst.txt
@@ -1,11 +1,11 @@
 :orphan:
 
-.. _ug-target_platform:
+.. _ug-target_platform_capabilities:
 
 
-=================================
-target_platform Module
-=================================
+=====================================
+target_platform_capabilities Module
+=====================================
 
 MCT can be configured to quantize and optimize models for different hardware settings.
 For example, when using qnnpack backend for Pytorch model inference, Pytorch `quantization
@@ -14,7 +14,7 @@ uses `per-tensor weights quantization <https://github.com/pytorch/pytorch/blob/m
 for Conv2d, while when using tflite modeling, Tensorflow uses `per-channel weights quantization for
 Conv2D <https://www.tensorflow.org/lite/performance/quantization_spec#per-axis_vs_per-tensor>`_.
 
-This can be addressed in MCT by using the target_platform module, that can configure different
+This can be addressed in MCT by using the target_platform_capabilities module, that can configure different
 parameters that are hardware-related, and the optimization process will use this to optimize the model accordingly.
 Models for IMX500, TFLite and qnnpack can be observed `here <https://github.com/sony/model_optimization/tree/main/model_compression_toolkit/target_platform_capabilities>`_, and can be used using :ref:`get_target_platform_capabilities function<ug-get_target_platform_capabilities>`.
 
@@ -27,7 +27,7 @@ Models for IMX500, TFLite and qnnpack can be observed `here <https://github.com/
 The object MCT should get called TargetPlatformCapabilities (or shortly TPC).
 This diagram demonstrates the main components:
 
-.. image:: ../../../../images/tpc.jpg
+.. image:: ../../../../images/tpc_diagram.png
   :scale: 80%
 
 Now, we will detail about the different components.
@@ -36,68 +36,43 @@ Now, we will detail about the different components.
 
 QuantizationMethod
 ==========================
-.. autoclass:: model_compression_toolkit.target_platform.QuantizationMethod
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.QuantizationMethod
 
 
 
 OpQuantizationConfig
 ======================
-.. autoclass:: model_compression_toolkit.target_platform.OpQuantizationConfig
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.schema.mct_current_schema.OpQuantizationConfig
 
 
 
 AttributeQuantizationConfig
 ============================
-.. autoclass:: model_compression_toolkit.target_platform.AttributeQuantizationConfig
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.schema.mct_current_schema.AttributeQuantizationConfig
 
 
 QuantizationConfigOptions
 ============================
-.. autoclass:: model_compression_toolkit.target_platform.QuantizationConfigOptions
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.schema.mct_current_schema.QuantizationConfigOptions
 
 
-TargetPlatformModel
-=======================
-.. autoclass:: model_compression_toolkit.target_platform.TargetPlatformModel
+TargetPlatformCapabilities
+============================
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.schema.mct_current_schema.TargetPlatformCapabilities
 
 
 OperatorsSet
 ================
-.. autoclass:: model_compression_toolkit.target_platform.OperatorsSet
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.schema.mct_current_schema.OperatorsSet
 
 
 
 Fusing
 ==============
-.. autoclass:: model_compression_toolkit.target_platform.Fusing
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.schema.mct_current_schema.Fusing
 
 
 
-OperatorSetConcat
+OperatorSetGroup
 ====================
-.. autoclass:: model_compression_toolkit.target_platform.OperatorSetConcat
-
-
-OperationsToLayers
-=====================
-.. autoclass:: model_compression_toolkit.target_platform.OperationsToLayers
-
-
-OperationsSetToLayers
-=========================
-.. autoclass:: model_compression_toolkit.target_platform.OperationsSetToLayers
-
-
-LayerFilterParams
-=========================
-.. autoclass:: model_compression_toolkit.target_platform.LayerFilterParams
-
-More filters and usage examples are detailed :ref:`here<ug-layer_filters>`.
-
-
-TargetPlatformCapabilities
-=============================
-.. autoclass:: model_compression_toolkit.target_platform.TargetPlatformCapabilities
-
-
-
+.. autoclass:: model_compression_toolkit.target_platform_capabilities.schema.mct_current_schema.OperatorSetGroup
diff --git a/docs/_sources/api/api_docs/modules/trainable_infrastructure.rst.txt b/docs/_sources/api/api_docs/modules/trainable_infrastructure.rst.txt
@@ -36,6 +36,15 @@ It adds to the base quantizer a get_config and from_config functions to enable l
 
 .. autoclass:: model_compression_toolkit.trainable_infrastructure.BasePytorchTrainableQuantizer
 
+
+
+TrainingMethod
+================================
+**Select a training method:**
+
+.. autoclass:: model_compression_toolkit.trainable_infrastructure.TrainingMethod
+
+
 TrainableQuantizerWeightsConfig
 =================================
 This configuration object contains the necessary attributes for configuring a weights trainable quantizer.
@@ -46,7 +55,7 @@ For example, we can set a trainable weights quantizer with the following configu
 
 .. code-block:: python
 
-    from model_compression_toolkit.target_platform_capabilities.target_platform import QuantizationMethod
+    from model_compression_toolkit.target_platform_capabilities.target_platform_capabilities import QuantizationMethod
     from model_compression_toolkit.constants import THRESHOLD, MIN_THRESHOLD
 
     TrainableQuantizerWeightsConfig(weights_quantization_method=QuantizationMethod.SYMMETRIC,
@@ -70,7 +79,7 @@ For example, we can set a trainable activation quantizer with the following conf
 
 .. code-block:: python
 
-    from model_compression_toolkit.target_platform_capabilities.target_platform import QuantizationMethod
+    from model_compression_toolkit.target_platform_capabilities.target_platform_capabilities import QuantizationMethod
     from model_compression_toolkit.constants import THRESHOLD, MIN_THRESHOLD
 
     TrainableQuantizerActivationConfig(activation_quantization_method=QuantizationMethod.UNIFORM,

diff --git a/docs/_sources/api/api_docs/notes/tpc_note.rst.txt b/docs/_sources/api/api_docs/notes/tpc_note.rst.txt
@@ -1,7 +1,7 @@
 
 .. note::
-   For now, some fields of :class:`~model_compression_toolkit.target_platform.OpQuantizationConfig` are ignored during
+   For now, some fields of :class:`~model_compression_toolkit.target_platform_capabilities.OpQuantizationConfig` are ignored during
    the optimization process such as quantization_preserving, fixed_scale, and fixed_zero_point.
 
-   - MCT will use more information from :class:`~model_compression_toolkit.target_platform.OpQuantizationConfig`, in the future.
+   - MCT will use more information from :class:`~model_compression_toolkit.target_platform_capabilities.OpQuantizationConfig`, in the future.
 
diff --git a/docs/api/api_docs/classes/BitWidthConfig.html b/docs/api/api_docs/classes/BitWidthConfig.html
@@ -7,7 +7,7 @@
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
 
-    <title>BitWidthConfig &#8212; MCT Documentation: ver 2.2.0</title>
+    <title>BitWidthConfig &#8212; MCT Documentation: ver 2.3.0</title>
     <link rel="stylesheet" type="text/css" href="../../../static/pygments.css" />
     <link rel="stylesheet" type="text/css" href="../../../static/bizstyle.css" />
     <link rel="stylesheet" type="text/css" href="../../../static/css/custom.css" />
@@ -31,7 +31,7 @@ <h3>Navigation</h3>
         <li class="right" style="margin-right: 10px">
           <a href="../../../genindex.html" title="General Index"
              accesskey="I">index</a></li>
-        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.2.0</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.3.0</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">BitWidthConfig</a></li> 
       </ul>
     </div>  
@@ -45,7 +45,7 @@ <h3>Navigation</h3>
 <span id="ug-bitwidthconfig"></span><h1>BitWidthConfig<a class="headerlink" href="#bitwidthconfig" title="Permalink to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="model_compression_toolkit.core.BitWidthConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">model_compression_toolkit.core.</span></span><span class="sig-name descname"><span class="pre">BitWidthConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">manual_activation_bit_width_selection_list</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.core.BitWidthConfig" title="Permalink to this definition">¶</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">model_compression_toolkit.core.</span></span><span class="sig-name descname"><span class="pre">BitWidthConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">manual_activation_bit_width_selection_list=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#model_compression_toolkit.core.BitWidthConfig" title="Permalink to this definition">¶</a></dt>
 <dd><p>Class to manage manual bit-width configurations.</p>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="model_compression_toolkit.core.BitWidthConfig.manual_activation_bit_width_selection_list">
@@ -128,7 +128,7 @@ <h3>Navigation</h3>
         <li class="right" style="margin-right: 10px">
           <a href="../../../genindex.html" title="General Index"
              >index</a></li>
-        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.2.0</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.3.0</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">BitWidthConfig</a></li> 
       </ul>
     </div>

diff --git a/docs/api/api_docs/classes/DataGenerationConfig.html b/docs/api/api_docs/classes/DataGenerationConfig.html
@@ -7,7 +7,7 @@
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
 
-    <title>Data Generation Configuration &#8212; MCT Documentation: ver 2.2.0</title>
+    <title>Data Generation Configuration &#8212; MCT Documentation: ver 2.3.0</title>
     <link rel="stylesheet" type="text/css" href="../../../static/pygments.css" />
     <link rel="stylesheet" type="text/css" href="../../../static/bizstyle.css" />
     <link rel="stylesheet" type="text/css" href="../../../static/css/custom.css" />
@@ -31,7 +31,7 @@ <h3>Navigation</h3>
         <li class="right" style="margin-right: 10px">
           <a href="../../../genindex.html" title="General Index"
              accesskey="I">index</a></li>
-        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.2.0</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.3.0</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">Data Generation Configuration</a></li> 
       </ul>
     </div>  
@@ -211,7 +211,7 @@ <h3>Navigation</h3>
         <li class="right" style="margin-right: 10px">
           <a href="../../../genindex.html" title="General Index"
              >index</a></li>
-        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.2.0</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.3.0</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">Data Generation Configuration</a></li> 
       </ul>
     </div>

diff --git a/docs/api/api_docs/classes/DefaultDict.html b/docs/api/api_docs/classes/DefaultDict.html
@@ -7,7 +7,7 @@
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
 
-    <title>DefaultDict Class &#8212; MCT Documentation: ver 2.2.0</title>
+    <title>DefaultDict Class &#8212; MCT Documentation: ver 2.3.0</title>
     <link rel="stylesheet" type="text/css" href="../../../static/pygments.css" />
     <link rel="stylesheet" type="text/css" href="../../../static/bizstyle.css" />
     <link rel="stylesheet" type="text/css" href="../../../static/css/custom.css" />
@@ -31,7 +31,7 @@ <h3>Navigation</h3>
         <li class="right" style="margin-right: 10px">
           <a href="../../../genindex.html" title="General Index"
              accesskey="I">index</a></li>
-        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.2.0</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.3.0</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">DefaultDict Class</a></li> 
       </ul>
     </div>  
@@ -114,7 +114,7 @@ <h3>Navigation</h3>
         <li class="right" style="margin-right: 10px">
           <a href="../../../genindex.html" title="General Index"
              >index</a></li>
-        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.2.0</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">MCT Documentation: ver 2.3.0</a> &#187;</li>
         <li class="nav-item nav-item-this"><a href="">DefaultDict Class</a></li> 
       </ul>
     </div>