Merge branch 'master' into tj/plugin/template/test/preprocess-opencv

docs/articles_en/about-openvino/performance-benchmarks/performance-benchmarks-faq.rst

@@ -133,8 +133,7 @@ Performance Information F.A.Q.
 
 .. dropdown:: Why are INT8 optimized models used for benchmarking on CPUs with no VNNI support?
 
-   The benefit of low-precision optimization using the OpenVINO™
-   toolkit model optimizer extends beyond processors supporting VNNI
+   The benefit of low-precision optimization extends beyond processors supporting VNNI
    through Intel® DL Boost. The reduced bit width of INT8 compared to FP32
    allows Intel® CPU to process the data faster. Therefore, it offers
    better throughput on any converted model, regardless of the

docs/articles_en/documentation/openvino-extensibility/frontend-extensions.rst

@@ -68,16 +68,14 @@ to OpenVINO template extension ``Identity`` class.
 The mapping doesn’t involve any attributes, as operation Identity doesn’t have them.
 
 Extension objects, like just constructed ``extension`` can be used to add to the
-OpenVINO runtime just before the loading a model that contains custom operations:
+OpenVINO runtime just before loading a model that contains custom operations:
 
 .. doxygensnippet:: docs/articles_en/assets/snippets/ov_extensions.cpp
    :language: cpp
    :fragment: [frontend_extension_read_model]
 
-Or extensions can be constructed in a separately compiled shared library.
-Separately compiled library can be used in Model Optimizer or ``benchmark_app``.
-Read about how to build and load such a library in the chapter of “Create library with extensions” in
-:doc:`Introduction to OpenVINO Extension <../openvino-extensibility>`.
+However, extensions can also be constructed in a separately compiled shared library, that is suitable for loading models with custom operations in a Python application or tools like ``benchmark_app``.
+For details on how to build and load such library, check the following :ref:`guide <create_a_library_with_extensions>`.
 
 If operation have multiple inputs and/or outputs they will be mapped in order.
 The type of elements in input/output tensors should match expected types in the surrounding operations.

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset1.rst

@@ -12,8 +12,7 @@ opset1
 This specification document describes ``opset1`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset1``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset1``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset10.rst

@@ -12,8 +12,7 @@ opset10
 This specification document describes the ``opset10`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset10``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset10``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset11.rst

@@ -12,8 +12,7 @@ opset11
 This specification document describes the ``opset11`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset11``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset11``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset12.rst

@@ -12,8 +12,7 @@ opset12
 This specification document describes the ``opset12`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset12``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset12``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset13.rst

@@ -12,8 +12,7 @@ opset13
 This specification document describes the ``opset13`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset13``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset13``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset14.rst

@@ -12,8 +12,7 @@ opset14
 This specification document describes the ``opset14`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset14``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset14``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset2.rst

@@ -12,8 +12,7 @@ opset2
 This specification document describes ``opset2`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset2``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset2``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset3.rst

@@ -12,8 +12,7 @@ opset3
 This specification document describes ``opset3`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset3``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset3``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset4.rst

@@ -12,8 +12,7 @@ opset4
 This specification document describes ``opset4`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset4``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset4``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset5.rst

@@ -12,8 +12,7 @@ opset5
 This specification document describes ``opset5`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset5``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset5``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset6.rst

@@ -12,8 +12,7 @@ opset6
 This specification document describes ``opset6`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset6``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset6``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset7.rst

@@ -12,8 +12,7 @@ opset7
 This specification document describes the ``opset7`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset7``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset7``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset8.rst

@@ -12,8 +12,7 @@ opset8
 This specification document describes the ``opset8`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset8``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset8``.
 
 
 Table of Contents

docs/articles_en/documentation/openvino-ir-format/operation-sets/available-opsets/opset9.rst

@@ -12,8 +12,7 @@ opset9
 This specification document describes the ``opset9`` operation set supported in OpenVINO™.
 Support for each particular operation from the list below depends on the capabilities of an inference plugin
 and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR xml
-snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes
-declared in ``namespace opset9``.
+snippets. The semantics match corresponding OpenVINO operation classes declared in ``namespace opset9``.
 
 
 Table of Contents

docs/articles_en/get-started/install-openvino/install-openvino-archive-windows.rst

@@ -85,8 +85,7 @@ Step 1: Download and Install OpenVINO Core Components
    .. code-block:: sh
 
       cd <user_home>/Downloads
-      curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2024.2/windows/w_openvino_toolkit_windows_2024.2.0.15519.5c0f38f83f6_x86_64.zip --output openvino_2024.2.0.zip --output openvino_2024.2.0.zip
-
+      curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2024.2/windows/w_openvino_toolkit_windows_2024.2.0.15519.5c0f38f83f6_x86_64.zip --output openvino_2024.2.0.zip
 
    .. note::
 

docs/articles_en/openvino-workflow/running-inference/optimize-inference/optimize-preprocessing/layout-api-overview.rst

@@ -21,7 +21,12 @@ Below is a list of cases where input/output layout is important:
   * Applying the :doc:`preprocessing <../optimize-preprocessing>` steps, such as subtracting means, dividing by scales, resizing an image, and converting ``RGB`` <-> ``BGR``.
   * Setting/getting a batch for a model.
 
-* Doing the same operations as used during the model conversion phase. For more information, refer to the :doc:`Model Optimizer Embedding Preprocessing Computation <../../../../documentation/legacy-features/transition-legacy-conversion-api/legacy-conversion-api/[legacy]-embedding-preprocessing-computation>` guide.
+* Doing the same operations as used during the model conversion phase. For more information, refer to the:
+
+  * :doc:`Convert to OpenVINO <../../../model-preparation/convert-model-to-ir>`
+  * `OpenVINO Model Conversion Tutorial <https://docs.openvino.ai/2024/notebooks/convert-to-openvino-with-output.html>`__
+  * :doc:`[LEGACY] Model Optimizer Embedding Preprocessing Computation <../../../../documentation/legacy-features/transition-legacy-conversion-api/legacy-conversion-api/[legacy]-embedding-preprocessing-computation>` guide.
+
 * Improving the readability of a model input and output.
 
 Syntax of Layout

docs/articles_en/openvino-workflow/running-inference/stateful-models/obtaining-stateful-openvino-model.rst

@@ -1,7 +1,7 @@
 .. {#openvino_docs_OV_UG_ways_to_get_stateful_model}
 
 Obtaining a Stateful OpenVINO Model
-====================================
+======================================
 
 If the original framework does not offer a dedicated API for working with states, the
 resulting OpenVINO IR model will not be stateful by default. This means it will not contain
@@ -23,7 +23,7 @@ and you have three ways to do it:
 .. _ov_ug_make_stateful:
 
 MakeStateful Transformation
-###########################
+###############################
 
 The MakeStateful transformation changes the structure of the model by replacing the
 user-defined pairs of Parameter and Results with the Assign and ReadValue operations:
@@ -83,7 +83,7 @@ Parameter/Result tensor names. If there are no tensor names,
 .. _ov_ug_low_latency:
 
 LowLatency2 Transformation
-##########################
+###############################
 
 The LowLatency2 transformation changes the structure of a model containing
 :doc:`TensorIterator <../../../documentation/openvino-ir-format/operation-sets/operation-specs/infrastructure/tensor-iterator-1>`
@@ -102,8 +102,7 @@ the current State API implementation. Input values are ignored, and the initial
 for the ReadValue operations are set to zeros unless the user specifies otherwise via
 :doc:`State API <../stateful-models>`.
 
-Applying LowLatency2 Transformation
-++++++++++++++++++++++++++++++++++++
+To apply LowLatency2 Transformation, follow the instruction below:
 
 1. Get :doc:`ov::Model <../integrate-openvino-with-your-application/model-representation>`,
    for example:
@@ -195,11 +194,11 @@ Applying LowLatency2 Transformation
    somewhere in the model.
 
    In such a case, trim non-reshapable layers via
-   :doc:`Model Optimizer command-line <../../../documentation/legacy-features/transition-legacy-conversion-api/legacy-conversion-api/[legacy]-setting-input-shapes>`
-   arguments: ``--input`` and ``--output``.
+   :doc:`Conversion Parameters <../../model-preparation/conversion-parameters>`:
+   ``--input`` and ``--output``. For example, check the `OpenVINO Model Conversion Tutorial <https://docs.openvino.ai/2024/notebooks/convert-to-openvino-with-output.html>`__.
 
-   For example, the parameter and the problematic constant in the picture above can be
-   trimmed using the ``--input Reshape_layer_name`` command-line option. The problematic
+   As for the parameter and the problematic constant in the picture above, it can be
+   trimmed by using the ``--input Reshape_layer_name`` command-line option. The problematic
    constant can be also replaced using OpenVINO, as shown in the following example:
 
    .. tab-set::
@@ -210,27 +209,7 @@ Applying LowLatency2 Transformation
             :language: cpp
             :fragment: [ov:replace_const]
 
-
-
-Obtaining TensorIterator/Loop Operations using Model Optimizer
-###############################################################
-
-**ONNX and frameworks supported via ONNX format:** *LSTM, RNN, GRU* original layers are
-converted to the GRU/RNN/LSTM Sequence operations. *ONNX Loop* layer is converted to the
-OpenVINO Loop operation.
-
-**TensorFlow:** *BlockLSTM* is converted to a TensorIterator operation. TensorIterator
-body contains LSTM Cell operation. Modifications such as Peepholes and InputForget are
-not supported. The *While* layer is converted to a TensorIterator. TensorIterator body
-can contain any supported operations. However, dynamic cases where the count of iterations
-cannot be calculated during shape inference (Model Optimizer conversion) are not supported.
-
-**TensorFlow2:** *While* layer is converted to a Loop operation. The Loop body can contain
-any supported operations.
-
-
-
-Creating a Model via OpenVINO API
+Stateful Model from Scratch
 ##################################
 
 The main approach to obtaining stateful OpenVINO IR models is converting from other
@@ -251,3 +230,17 @@ a sink from `ov::Model` after deleting the node from the graph with the `delete_
          :language: cpp
          :fragment: [ov:state_network]
 
+.. note::
+
+   **ONNX and frameworks supported via ONNX format:** *LSTM, RNN, GRU* original layers are
+   converted to the GRU/RNN/LSTM Sequence operations. *ONNX Loop* layer is converted to the
+   OpenVINO Loop operation.
+
+   **TensorFlow:** *BlockLSTM* is converted to a TensorIterator operation. The TensorIterator
+   body contains LSTM Cell operation. Modifications such as Peepholes and InputForget are
+   not supported. The *While* layer is converted to a TensorIterator. The TensorIterator body
+   can contain any supported operations. However, dynamic cases where the count of iterations
+   cannot be calculated during shape inference are not supported.
+
+   **TensorFlow2:** *While* layer is converted to a Loop operation. The Loop body can contain
+   any supported operations.