diff --git a/docs/Documentation/datumaro.md b/docs/Documentation/datumaro.md index c1d42bb2702..6488a80c810 100644 --- a/docs/Documentation/datumaro.md +++ b/docs/Documentation/datumaro.md @@ -1,6 +1,11 @@ # Datumaro {#datumaro_documentation} -@sphinxdirective +@sphinxdirective + +.. meta:: + :description: Start working with Datumaro, which offers functionalities for basic data + import/export, validation, correction, filtration and transformations. + Datumaro provides a suite of basic data import/export (IE) for more than 35 public vision data formats and manipulation functionalities such as validation, correction, filtration, and some diff --git a/docs/Documentation/media_processing_cv_libraries.md b/docs/Documentation/media_processing_cv_libraries.md index 0ca3ad22408..250660402b0 100644 --- a/docs/Documentation/media_processing_cv_libraries.md +++ b/docs/Documentation/media_processing_cv_libraries.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Explore OpenCV Graph API and other media processing frameworks + used for development of computer vision solutions. + .. toctree:: :maxdepth: 1 diff --git a/docs/Documentation/model_introduction.md b/docs/Documentation/model_introduction.md index a83bfac2122..e169ccbab99 100644 --- a/docs/Documentation/model_introduction.md +++ b/docs/Documentation/model_introduction.md @@ -1,6 +1,11 @@ # Model Preparation {#openvino_docs_model_processing_introduction} @sphinxdirective + +.. meta:: + :description: Preparing models for OpenVINO Runtime. Learn how to convert and compile models from different frameworks or read them directly. + + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/Documentation/openvino_ecosystem.md b/docs/Documentation/openvino_ecosystem.md index 6fe8c9bf224..3bb9982eb9b 100644 --- a/docs/Documentation/openvino_ecosystem.md +++ b/docs/Documentation/openvino_ecosystem.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: OpenVINO™ is an ecosystem of utilities that have advanced capabilities, which help develop deep learning solutions. + + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/Documentation/openvino_training_extensions.md b/docs/Documentation/openvino_training_extensions.md index 1f761fad571..a05ccc7b925 100644 --- a/docs/Documentation/openvino_training_extensions.md +++ b/docs/Documentation/openvino_training_extensions.md @@ -1,6 +1,12 @@ # OpenVINO™ Training Extensions {#ote_documentation} -@sphinxdirective +@sphinxdirective + +.. meta:: + :description: OpenVINO™ Training Extensions include advanced algorithms used + to create, train and convert deep learning models with OpenVINO + Toolkit for optimized inference. + OpenVINO™ Training Extensions provide a suite of advanced algorithms to train Deep Learning models and convert them using the `OpenVINO™ diff --git a/docs/Documentation/openvino_workflow.md b/docs/Documentation/openvino_workflow.md index fe354797599..a304400f102 100644 --- a/docs/Documentation/openvino_workflow.md +++ b/docs/Documentation/openvino_workflow.md @@ -3,6 +3,11 @@ @sphinxdirective +.. meta:: + :description: OpenVINO toolkit workflow usually involves preparation, + optimization, and compression of models, running inference and + deploying deep learning applications. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/Extensibility_UG/GPU_Extensibility.md b/docs/Extensibility_UG/GPU_Extensibility.md index bbb16e389b5..ae830870cff 100644 --- a/docs/Extensibility_UG/GPU_Extensibility.md +++ b/docs/Extensibility_UG/GPU_Extensibility.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn the details of custom kernel support for the GPU device to + enable operations not supported by OpenVINO. + + To enable operations not supported by OpenVINO™ out of the box, you may need an extension for OpenVINO operation set, and a custom kernel for the device you will target. This article describes custom kernel support for the GPU device. The GPU codepath abstracts many details about OpenCL. You need to provide the kernel code in OpenCL C and an XML configuration file that connects the kernel and its parameters to the parameters of the operation. diff --git a/docs/Extensibility_UG/Intro.md b/docs/Extensibility_UG/Intro.md index 2ea2cb2f37d..beeb87aa395 100644 --- a/docs/Extensibility_UG/Intro.md +++ b/docs/Extensibility_UG/Intro.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore OpenVINO™ Extensibility API, which allows adding + support for models with custom operations and their further implementation + in applications. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/Extensibility_UG/add_openvino_ops.md b/docs/Extensibility_UG/add_openvino_ops.md index ab32fd5c0a0..16186106ff1 100644 --- a/docs/Extensibility_UG/add_openvino_ops.md +++ b/docs/Extensibility_UG/add_openvino_ops.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore OpenVINO™ Extension API which enables registering + custom operations to support models with operations + not supported by OpenVINO. + OpenVINO™ Extension API allows you to register custom operations to support models with operations which OpenVINO™ does not support out-of-the-box. This capability requires writing code in C++, so if you are using Python to develop your application you need to build a separate shared library implemented in C++ first and load it in Python using ``add_extension`` API. Please refer to :ref:`Create library with extensions ` for more details on library creation and usage. The remining part of this document describes how to implement an operation class. Operation Class diff --git a/docs/Extensibility_UG/frontend_extensions.md b/docs/Extensibility_UG/frontend_extensions.md index 6d4023f6279..8f6c4876033 100644 --- a/docs/Extensibility_UG/frontend_extensions.md +++ b/docs/Extensibility_UG/frontend_extensions.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to use frontend extension classes to facilitate the mapping + of custom operations from the framework model representation to the OpenVINO + representation. + + The goal of this chapter is to explain how to use Frontend extension classes to facilitate mapping of custom operations from framework model representation to OpenVINO representation. Refer to :doc:`Introduction to OpenVINO Extension ` to diff --git a/docs/Extensibility_UG/graph_rewrite_pass.md b/docs/Extensibility_UG/graph_rewrite_pass.md index 6bcb0533a27..4e8480ed84a 100644 --- a/docs/Extensibility_UG/graph_rewrite_pass.md +++ b/docs/Extensibility_UG/graph_rewrite_pass.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Get to know how Graph Rewrite handles running multiple matcher passes on + ov::Model in a single graph traversal. + + ``:ref:`ov::pass::GraphRewrite ``` serves for running multiple matcher passes on ``:ref:`ov::Model ``` in a single graph traversal. Example: diff --git a/docs/Extensibility_UG/matcher_pass.md b/docs/Extensibility_UG/matcher_pass.md index b898e2d0baa..e9c48aaeb90 100644 --- a/docs/Extensibility_UG/matcher_pass.md +++ b/docs/Extensibility_UG/matcher_pass.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to create a pattern, implement a callback, register + the pattern and Matcher to execute MatcherPass transformation + on a model. + ``:ref:`ov::pass::MatcherPass ``` is used for pattern-based transformations. Template for MatcherPass transformation class diff --git a/docs/Extensibility_UG/model_pass.md b/docs/Extensibility_UG/model_pass.md index 163e5ef2f88..d98c31663fc 100644 --- a/docs/Extensibility_UG/model_pass.md +++ b/docs/Extensibility_UG/model_pass.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to use Model Pass transformation class to take entire + ov::Model as input and process it. + + ``:ref:`ov::pass::ModelPass ``` is used for transformations that take entire ``:ref:`ov::Model ``` as an input and process it. Template for ModelPass transformation class diff --git a/docs/Extensibility_UG/ov_transformations.md b/docs/Extensibility_UG/ov_transformations.md index a108a8beb32..9f0e2b36dad 100644 --- a/docs/Extensibility_UG/ov_transformations.md +++ b/docs/Extensibility_UG/ov_transformations.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to apply additional model optimizations or transform + unsupported subgraphs and operations, using OpenVINO™ Transformations API. + + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/IE_PLUGIN_DG/AsyncInferRequest.md b/docs/IE_PLUGIN_DG/AsyncInferRequest.md index b6f91f914bc..eee38c4d931 100644 --- a/docs/IE_PLUGIN_DG/AsyncInferRequest.md +++ b/docs/IE_PLUGIN_DG/AsyncInferRequest.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Use the base ov::IAsyncInferRequest class to implement a custom asynchronous inference request in OpenVINO. + Asynchronous Inference Request runs an inference pipeline asynchronously in one or several task executors depending on a device pipeline structure. OpenVINO Runtime Plugin API provides the base ov::IAsyncInferRequest class: diff --git a/docs/IE_PLUGIN_DG/Building.md b/docs/IE_PLUGIN_DG/Building.md index 4d562d9f801..acb8d6e7c56 100644 --- a/docs/IE_PLUGIN_DG/Building.md +++ b/docs/IE_PLUGIN_DG/Building.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to build a plugin using CMake and OpenVINO Developer Package. + + OpenVINO build infrastructure provides the OpenVINO Developer Package for plugin development. OpenVINO Developer Package diff --git a/docs/IE_PLUGIN_DG/CompiledModel.md b/docs/IE_PLUGIN_DG/CompiledModel.md index c8630df49b9..0376f59a126 100644 --- a/docs/IE_PLUGIN_DG/CompiledModel.md +++ b/docs/IE_PLUGIN_DG/CompiledModel.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Use the ov::CompiledModel class as the base class for a compiled + model and to create an arbitrary number of ov::InferRequest objects. + ov::CompiledModel class functionality: * Compile an ov::Model instance to a backend specific graph representation diff --git a/docs/IE_PLUGIN_DG/InferRequest.md b/docs/IE_PLUGIN_DG/InferRequest.md index 240c2ffa58e..3130bbf3688 100644 --- a/docs/IE_PLUGIN_DG/InferRequest.md +++ b/docs/IE_PLUGIN_DG/InferRequest.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Use the ov::ISyncInferRequest interface as the base class to implement a synchronous inference request in OpenVINO. + + ``InferRequest`` class functionality: * Allocate input and output tensors needed for a backend-dependent network inference. diff --git a/docs/IE_PLUGIN_DG/Intro.md b/docs/IE_PLUGIN_DG/Intro.md index 39e5ef0c6d7..80c01aa8af8 100644 --- a/docs/IE_PLUGIN_DG/Intro.md +++ b/docs/IE_PLUGIN_DG/Intro.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Develop and implement independent inference solutions for + different devices with the components of plugin architecture + of OpenVINO. + + .. toctree:: :maxdepth: 1 :caption: Converting and Preparing Models diff --git a/docs/IE_PLUGIN_DG/Plugin.md b/docs/IE_PLUGIN_DG/Plugin.md index 85a3fdce1c9..23ae3c138ac 100644 --- a/docs/IE_PLUGIN_DG/Plugin.md +++ b/docs/IE_PLUGIN_DG/Plugin.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore OpenVINO Plugin API, which includes functions and + helper classes that simplify the development of new plugins. + + OpenVINO Plugin usually represents a wrapper around a backend. Backends can be: * OpenCL-like backend (e.g. clDNN library) for GPU devices. diff --git a/docs/IE_PLUGIN_DG/PluginTesting.md b/docs/IE_PLUGIN_DG/PluginTesting.md index d43cb4769e3..c5920c34b1c 100644 --- a/docs/IE_PLUGIN_DG/PluginTesting.md +++ b/docs/IE_PLUGIN_DG/PluginTesting.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Use the openvino::funcSharedTests library, which includes + a predefined set of functional tests and utilities to verify a plugin. + + OpenVINO tests infrastructure provides a predefined set of functional tests and utilities. They are used to verify a plugin using the OpenVINO public API. All the tests are written in the `Google Test C++ framework `__. diff --git a/docs/IE_PLUGIN_DG/Properties.md b/docs/IE_PLUGIN_DG/Properties.md index d3fcb027b80..842ed6a297c 100644 --- a/docs/IE_PLUGIN_DG/Properties.md +++ b/docs/IE_PLUGIN_DG/Properties.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Use the ov::Property class to define access rights and + specific properties of an OpenVINO plugin. + + Plugin can provide own device-specific properties. Property Class diff --git a/docs/IE_PLUGIN_DG/QuantizedNetworks.md b/docs/IE_PLUGIN_DG/QuantizedNetworks.md index 591f2e0c18c..fdbe6b23a0d 100644 --- a/docs/IE_PLUGIN_DG/QuantizedNetworks.md +++ b/docs/IE_PLUGIN_DG/QuantizedNetworks.md @@ -3,6 +3,11 @@ @sphinxdirective +.. meta:: + :description: Learn about the support for quantized models with different + precisions and the FakeQuantize operation used to express + quantization rules. + One of the feature of OpenVINO is the support of quantized models with different precisions: INT8, INT4, etc. However, it is up to the plugin to define what exact precisions are supported by the particular HW. All quantized models which can be expressed in IR have a unified representation by means of *FakeQuantize* operation. diff --git a/docs/IE_PLUGIN_DG/RemoteContext.md b/docs/IE_PLUGIN_DG/RemoteContext.md index 81cc6652d6e..79431f5d008 100644 --- a/docs/IE_PLUGIN_DG/RemoteContext.md +++ b/docs/IE_PLUGIN_DG/RemoteContext.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Use the ov::RemoteContext class as the base class for a plugin-specific remote context. + + ov::RemoteContext class functionality: * Represents device-specific inference context. diff --git a/docs/IE_PLUGIN_DG/RemoteTensor.md b/docs/IE_PLUGIN_DG/RemoteTensor.md index f88bf04e132..c586b907719 100644 --- a/docs/IE_PLUGIN_DG/RemoteTensor.md +++ b/docs/IE_PLUGIN_DG/RemoteTensor.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Use the ov::IRemoteTensor interface as a base class for device-specific remote tensors. + + ov::RemoteTensor class functionality: * Provides an interface to work with device-specific memory. diff --git a/docs/IE_PLUGIN_DG/detailed_guides.md b/docs/IE_PLUGIN_DG/detailed_guides.md index 2fbca79fd10..8677d779e8f 100644 --- a/docs/IE_PLUGIN_DG/detailed_guides.md +++ b/docs/IE_PLUGIN_DG/detailed_guides.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn more about plugin development and specific features in + OpenVINO: precision transformations and support for quantized + models with different precisions. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/IE_PLUGIN_DG/dev_api_references.md b/docs/IE_PLUGIN_DG/dev_api_references.md index cec46b75727..5e6cc22c57d 100644 --- a/docs/IE_PLUGIN_DG/dev_api_references.md +++ b/docs/IE_PLUGIN_DG/dev_api_references.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about extra API references required for the development of + plugins in OpenVINO. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/avg_pool_precision_preserved.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/avg_pool_precision_preserved.md index 6e4428d684d..c12ba6adf28 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/avg_pool_precision_preserved.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/avg_pool_precision_preserved.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about AvgPoolPrecisionPreserved attribute used only during AvgPool operation. + :ref:`ngraph::AvgPoolPrecisionPreservedAttribute ` class represents the ``AvgPoolPrecisionPreserved`` attribute. Utility attribute, which is used only during ``AvgPool`` operation, precision preserved property definition. diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/intervals_alignment.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/intervals_alignment.md index d7a1024b498..989e756c89e 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/intervals_alignment.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/intervals_alignment.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about IntervalsAlignment attribute, which describes a subgraph with the same quantization intervals alignment. + + :ref:`ngraph::IntervalsAlignmentAttribute ` class represents the ``IntervalsAlignment`` attribute. The attribute defines a subgraph with the same quantization intervals alignment. ``FakeQuantize`` operations are included. The attribute is used by quantization operations. diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/precision_preserved.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/precision_preserved.md index b0fc68ae949..8d942a61ac6 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/precision_preserved.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/precision_preserved.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about PrecisionPreserved attribute, which describes a precision preserved operation. + + :ref:`ngraph::PrecisionPreservedAttribute ` class represents the ``PrecisionPreserved`` attribute. The attribute defines a precision preserved operation. If the attribute is absent, then an operation is not precision preserved. diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/precisions.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/precisions.md index 1e3d356273c..a2e71742b27 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/precisions.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/precisions.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Precisions attribute, which describes the precision required for an input/output port or an operation. + + :ref:`ngraph::PrecisionsAttribute ` class represents the ``Precisions`` attribute. The attribute defines precision which is required for input/output port or an operation. diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/quantization_alignment.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/quantization_alignment.md index 8ae8517b6fa..7580a9752c4 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/quantization_alignment.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/quantization_alignment.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about QuantizationAlignment attribute, which describes a subgraph with the same quantization alignment. + + :ref:`ngraph::QuantizationAlignmentAttribute ` class represents the ``QuantizationAlignment`` attribute. The attribute defines a subgraph with the same quantization alignment. ``FakeQuantize`` operations are not included. The attribute is used by quantization operations. diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/quantization_granularity.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/quantization_granularity.md index 7bd44c144ca..fd35080c71a 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/quantization_granularity.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/attributes/quantization_granularity.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about QuantizationGranularity attribute, which describes quantization granularity of operation inputs. + + ngraph::QuantizationAttribute class represents the ``QuantizationGranularity`` attribute. The attribute defines quantization granularity of operation inputs. diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt.md index 3fed6f897a9..ef29530fc22 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about low precision transformations used to infer a quantized model in low precision with the maximum performance on Intel CPU, GPU, and ARM platforms. + .. toctree:: :maxdepth: 1 :caption: Low Precision Transformations diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt_attributes.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt_attributes.md index efef98915a6..441afed3361 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt_attributes.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt_attributes.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Check the lists of attributes created or used by model transformations. + + .. toctree:: :maxdepth: 1 :caption: Attributes diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step1_prerequisites.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step1_prerequisites.md index fc0f79cec82..38258c24660 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step1_prerequisites.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step1_prerequisites.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about optional Prerequisites transformations, that + prepare a model before applying other low precision transformations. + Prerequisites transformations are optional. The transformations prepare a model before running other low precision transformations. The transformations do not operate with dequantization operations or update precisions. Prerequisites transformations include: * :doc:`PullReshapeThroughDequantization ` diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step2_markup.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step2_markup.md index 98a79665ae6..92f444a6aac 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step2_markup.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step2_markup.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about markup transformations, which are used to create + attributes for input and output ports and operations during runtime. + This step defines the optimal ``FakeQuantize`` decomposition precisions for the best inference performance via operations markup with runtime attribute instances. Attributes are created for input and output ports and operations. Transformations do not change the operation output port precisions. A model markup low precision logic is decomposed and implemented into the following common markup transformations. The order of transformations is important: 1. :doc:`MarkupBias ` diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step3_main.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step3_main.md index b02388871f1..da8688ba7a7 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step3_main.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step3_main.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn about main transformations, which are mostly low + precision transformations that handle decomposition and + dequantization operations. + + Main transformations are the majority of low precision transformations. Transformations operate with dequantization operations. Main transformations include: * :doc:`AddTransformation ` diff --git a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step4_cleanup.md b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step4_cleanup.md index b5ae6ba93bf..fd9a2d638df 100644 --- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step4_cleanup.md +++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step4_cleanup.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Check the list of transformations used to clean up the + resulting model to avoid unhandled dequantization operations. + * :doc:`EliminateFakeQuantizeTransformation ` * :doc:`FoldConvertTransformation ` * :doc:`FoldFakeQuantizeTransformation ` diff --git a/docs/Legal_Information.md b/docs/Legal_Information.md index 6a32360d26d..d23567a6584 100644 --- a/docs/Legal_Information.md +++ b/docs/Legal_Information.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about legal information and policies related to the use + of Intel® Distribution of OpenVINO™ toolkit. + Performance varies by use, configuration and other factors. Learn more at [www.intel.com/PerformanceIndex](https://www.intel.com/PerformanceIndex). diff --git a/docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md b/docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md index a4e07d076b2..edb9e8385ac 100644 --- a/docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md +++ b/docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md @@ -15,6 +15,11 @@ openvino_docs_MO_DG_Python_API openvino_docs_MO_DG_prepare_model_Model_Optimizer_FAQ +.. meta:: + :description: Model conversion (MO) furthers the transition between training and + deployment environments, it adjusts deep learning models for + optimal execution on target devices. + To convert a model to OpenVINO model format (``ov.Model``), you can use the following command: diff --git a/docs/MO_DG/IR_and_opsets.md b/docs/MO_DG/IR_and_opsets.md index 05b6b1249aa..f0692bd2b92 100644 --- a/docs/MO_DG/IR_and_opsets.md +++ b/docs/MO_DG/IR_and_opsets.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn the essentials of representing deep learning models in OpenVINO + IR format and the use of supported operation sets. + .. toctree:: :maxdepth: 1 :hidden: @@ -9,7 +13,7 @@ openvino_docs_ops_opset openvino_docs_operations_specifications openvino_docs_ops_broadcast_rules - + This article provides essential information on the format used for representation of deep learning models in OpenVINO toolkit and supported operation sets. diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md index 1a60a663614..b6f6a820d31 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a model from the + Caffe format to the OpenVINO Intermediate Representation. + .. warning:: diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md index 89113e2a249..0446573a56c 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a model from the + Kaldi format to the OpenVINO Intermediate Representation. + .. warning:: diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md index 8b0e2e1d51c..85123ce8d34 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a model from the + MXNet format to the OpenVINO Intermediate Representation. + .. warning:: @@ -14,7 +18,7 @@ To convert an MXNet model, run Model Optimizer with the path to the ``.params`` mo --input_model model-file-0000.params -Using MXNet-Specific Conversion Parameters +Using MXNet-Specific Conversion Parameters ########################################## The following list provides the MXNet-specific parameters. @@ -40,7 +44,7 @@ The following list provides the MXNet-specific parameters. Use only if your topology is one of ssd gluoncv topologies -.. note:: +.. note:: By default, model conversion API does not use the Apache MXNet loader. It transforms the topology to another format which is compatible with the latest version of Apache MXNet. However, the Apache MXNet loader is required for models trained with lower version of Apache MXNet. If your model was trained with an Apache MXNet version lower than 1.0.0, specify the ``--legacy_mxnet_model`` key to enable the Apache MXNet loader. Note that the loader does not support models with custom layers. In this case, you must manually recompile Apache MXNet with custom layers and install it in your environment. @@ -77,4 +81,3 @@ See the :doc:`Model Conversion Tutorials ` @endsphinxdirective - diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_ONNX.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_ONNX.md index 7caaa518121..724214c2d15 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_ONNX.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_ONNX.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a model from the + ONNX format to the OpenVINO Intermediate Representation. + + Introduction to ONNX #################### diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md index b61bb20b7ba..7221572022a 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a model from the + PaddlePaddle format to the OpenVINO Intermediate Representation. + + This page provides general instructions on how to convert a model from a PaddlePaddle format to the OpenVINO IR format using Model Optimizer. The instructions are different depending on PaddlePaddle model format. .. note:: PaddlePaddle models are supported via FrontEnd API. You may skip conversion to IR and read models directly by OpenVINO runtime API. Refer to the :doc:`inference example ` for more details. Using ``convert_model`` is still necessary in more complex cases, such as new custom inputs/outputs in model pruning, adding pre-processing, or using Python conversion extensions. @@ -11,6 +16,7 @@ Converting PaddlePaddle Model Inference Format PaddlePaddle inference model includes ``.pdmodel`` (storing model structure) and ``.pdiparams`` (storing model weight). For how to export PaddlePaddle inference model, please refer to the `Exporting PaddlePaddle Inference Model `__ Chinese guide. + To convert a PaddlePaddle model, use the ``mo`` script and specify the path to the input ``.pdmodel`` model file: .. code-block:: sh diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md index 0d3931c400e..ad59e8f3cc2 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a model from the + PyTorch format to the OpenVINO Intermediate Representation. + + This page provides instructions on how to convert a model from the PyTorch format to the OpenVINO IR format using Model Optimizer. Model Optimizer Python API allows the conversion of PyTorch models using the ``convert_model()`` method. diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md index 623755d9c67..13b5586dc80 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a model from a + TensorFlow format to the OpenVINO Intermediate Representation. + + This page provides general instructions on how to run model conversion from a TensorFlow format to the OpenVINO IR format. The instructions are different depending on whether your model was created with TensorFlow v1.X or TensorFlow v2.X. .. note:: TensorFlow models are supported via :doc:`FrontEnd API `. You may skip conversion to IR and read models directly by OpenVINO runtime API. Refer to the :doc:`inference example ` for more details. Using ``convert_model`` is still necessary in more complex cases, such as new custom inputs/outputs in model pruning, adding pre-processing, or using Python conversion extensions. diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow_Lite.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow_Lite.md index 1987ad25ef2..24db071c714 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow_Lite.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow_Lite.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a model from a + TensorFlow Lite format to the OpenVINO Intermediate Representation. + + To convert a TensorFlow Lite model, use the ``mo`` script and specify the path to the input ``.tflite`` model file: .. code-block:: sh diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_Tutorials.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_Tutorials.md index 18708a3a768..2eca161d140 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_Tutorials.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_Tutorials.md @@ -35,6 +35,8 @@ openvino_docs_MO_DG_prepare_model_convert_model_mxnet_specific_Convert_Style_Transfer_From_MXNet openvino_docs_MO_DG_prepare_model_convert_model_kaldi_specific_Aspire_Tdnn_Model +.. meta:: + :description: Get to know conversion methods for specific TensorFlow, ONNX, PyTorch, MXNet, and Kaldi models. This section provides a set of tutorials that demonstrate conversion methods for specific diff --git a/docs/MO_DG/prepare_model/convert_model/Converting_Model.md b/docs/MO_DG/prepare_model/convert_model/Converting_Model.md index 7068a3b33a0..664b5508317 100644 --- a/docs/MO_DG/prepare_model/convert_model/Converting_Model.md +++ b/docs/MO_DG/prepare_model/convert_model/Converting_Model.md @@ -4,6 +4,10 @@ With model conversion API you can increase your model's efficiency by providing @sphinxdirective +.. meta:: + :description: Learn how to increase the efficiency of a model with MO by providing an additional shape definition with the input_shape and static_shape parameters. + + .. _when_to_specify_input_shapes: diff --git a/docs/MO_DG/prepare_model/convert_model/IR_suitable_for_INT8_inference.md b/docs/MO_DG/prepare_model/convert_model/IR_suitable_for_INT8_inference.md index c8d5cbc8ade..0f5304287e0 100644 --- a/docs/MO_DG/prepare_model/convert_model/IR_suitable_for_INT8_inference.md +++ b/docs/MO_DG/prepare_model/convert_model/IR_suitable_for_INT8_inference.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to generate a Low Precision IR - Intermediate + Representation suitable for INT8 low precision inference on CPU + and GPU devices. + Introduction ############ diff --git a/docs/MO_DG/prepare_model/convert_model/kaldi_specific/Aspire_Tdnn_Model.md b/docs/MO_DG/prepare_model/convert_model/kaldi_specific/Aspire_Tdnn_Model.md index 4d9bff1a8aa..c5002f9a62d 100644 --- a/docs/MO_DG/prepare_model/convert_model/kaldi_specific/Aspire_Tdnn_Model.md +++ b/docs/MO_DG/prepare_model/convert_model/kaldi_specific/Aspire_Tdnn_Model.md @@ -2,11 +2,15 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert an ASpIRE Chain TDNN + model from Kaldi to the OpenVINO Intermediate Representation. + + .. warning:: Note that OpenVINO support for Kaldi is currently being deprecated and will be removed entirely in the future. - At the beginning, you should `download a pre-trained model `__ for the ASpIRE Chain Time Delay Neural Network (TDNN) from the Kaldi project official website. diff --git a/docs/MO_DG/prepare_model/convert_model/mxnet_specific/Convert_GluonCV_Models.md b/docs/MO_DG/prepare_model/convert_model/mxnet_specific/Convert_GluonCV_Models.md index ec9687d1655..124bb40861c 100644 --- a/docs/MO_DG/prepare_model/convert_model/mxnet_specific/Convert_GluonCV_Models.md +++ b/docs/MO_DG/prepare_model/convert_model/mxnet_specific/Convert_GluonCV_Models.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert GluonCV models + from MXNet to the OpenVINO Intermediate Representation. + + .. warning:: Note that OpenVINO support for Apache MXNet is currently being deprecated and will be removed entirely in the future. diff --git a/docs/MO_DG/prepare_model/convert_model/mxnet_specific/Convert_Style_Transfer_From_MXNet.md b/docs/MO_DG/prepare_model/convert_model/mxnet_specific/Convert_Style_Transfer_From_MXNet.md index 9bda86922dc..7f596b90864 100644 --- a/docs/MO_DG/prepare_model/convert_model/mxnet_specific/Convert_Style_Transfer_From_MXNet.md +++ b/docs/MO_DG/prepare_model/convert_model/mxnet_specific/Convert_Style_Transfer_From_MXNet.md @@ -2,13 +2,15 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a Style Transfer + model from MXNet to the OpenVINO Intermediate Representation. + .. warning:: Note that OpenVINO support for Apache MXNet is currently being deprecated and will be removed entirely in the future. - - This article provides instructions on how to generate a model for style transfer, using the public MXNet neural style transfer sample. **Step 1**: Download or clone the repository `Zhaw's Neural Style Transfer repository `__ with an MXNet neural style transfer sample. diff --git a/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_Faster_RCNN.md b/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_Faster_RCNN.md index 2d226182a53..fc6a375bef8 100644 --- a/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_Faster_RCNN.md +++ b/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_Faster_RCNN.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a Faster R-CNN model + from ONNX to the OpenVINO Intermediate Representation. + + The instructions below are applicable **only** to the Faster R-CNN model converted to the ONNX file format from the `maskrcnn-benchmark model `__: 1. Download the pretrained model file from `onnx/models `__ (commit-SHA: 8883e49e68de7b43e263d56b9ed156dfa1e03117). diff --git a/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_GPT2.md b/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_GPT2.md index d75a22d8b01..1f6c0bd92f1 100644 --- a/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_GPT2.md +++ b/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_GPT2.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a pre-trained GPT-2 + model from ONNX to the OpenVINO Intermediate Representation. + + `Public pre-trained GPT-2 model `__ is a large transformer-based language model with a simple objective: predict the next word, given all of the previous words within some text. diff --git a/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_Mask_RCNN.md b/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_Mask_RCNN.md index 671a37face1..97fee0df826 100644 --- a/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_Mask_RCNN.md +++ b/docs/MO_DG/prepare_model/convert_model/onnx_specific/Convert_Mask_RCNN.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a pre-trained Mask + R-CNN model from ONNX to the OpenVINO Intermediate Representation. + + The instructions below are applicable **only** to the Mask R-CNN model converted to the ONNX file format from the `maskrcnn-benchmark model `__. 1. Download the pretrained model file from `onnx/models `__ (commit-SHA: 8883e49e68de7b43e263d56b9ed156dfa1e03117). diff --git a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Bert_ner.md b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Bert_ner.md index 96216555339..5b49a90def8 100644 --- a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Bert_ner.md +++ b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Bert_ner.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a BERT-NER model + from Pytorch to the OpenVINO Intermediate Representation. + + The goal of this article is to present a step-by-step guide on how to convert PyTorch BERT-NER model to OpenVINO IR. First, you need to download the model and convert it to ONNX. diff --git a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Cascade_RCNN_res101.md b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Cascade_RCNN_res101.md index 2a6890650de..174cf5cebc3 100644 --- a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Cascade_RCNN_res101.md +++ b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Cascade_RCNN_res101.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a Cascade RCNN R-101 + model from Pytorch to the OpenVINO Intermediate Representation. + + The goal of this article is to present a step-by-step guide on how to convert a PyTorch Cascade RCNN R-101 model to OpenVINO IR. First, you need to download the model and convert it to ONNX. Downloading and Converting Model to ONNX diff --git a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_F3Net.md b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_F3Net.md index d8be169689c..934eca8652a 100644 --- a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_F3Net.md +++ b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_F3Net.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a F3Net model + from Pytorch to the OpenVINO Intermediate Representation. + + `F3Net `__ : Fusion, Feedback and Focus for Salient Object Detection Cloning the F3Net Repository diff --git a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_QuartzNet.md b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_QuartzNet.md index 3942f0ca0fb..9276f3fe8ba 100644 --- a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_QuartzNet.md +++ b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_QuartzNet.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a QuartzNet model + from Pytorch to the OpenVINO Intermediate Representation. + + `NeMo project `__ provides the QuartzNet model. Downloading the Pre-trained QuartzNet Model diff --git a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RCAN.md b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RCAN.md index 3e89de179d4..f736befd64e 100644 --- a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RCAN.md +++ b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RCAN.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a RCAN model + from Pytorch to the OpenVINO Intermediate Representation. + + `RCAN `__ : Image Super-Resolution Using Very Deep Residual Channel Attention Networks Downloading and Converting the Model to ONNX diff --git a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RNNT.md b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RNNT.md index 822df82fff5..a8d11b7338c 100644 --- a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RNNT.md +++ b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RNNT.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a RNN-T model + from Pytorch to the OpenVINO Intermediate Representation. + + This guide covers conversion of RNN-T model from `MLCommons `__ repository. Follow the instructions below to export a PyTorch model into ONNX, before converting it to IR: diff --git a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_YOLACT.md b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_YOLACT.md index 36c45ff8f54..75957a756f1 100644 --- a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_YOLACT.md +++ b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_YOLACT.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a YOLACT model + from Pytorch to the OpenVINO Intermediate Representation. + + You Only Look At CoefficienTs (YOLACT) is a simple, fully convolutional model for real-time instance segmentation. The PyTorch implementation is publicly available in `this GitHub repository `__. The YOLACT++ model is not supported, because it uses deformable convolutional layers that cannot be represented in ONNX format. diff --git a/docs/MO_DG/prepare_model/convert_model/supported_model_formats.md b/docs/MO_DG/prepare_model/convert_model/supported_model_formats.md index ae63aaf9b78..ce509ad059c 100644 --- a/docs/MO_DG/prepare_model/convert_model/supported_model_formats.md +++ b/docs/MO_DG/prepare_model/convert_model/supported_model_formats.md @@ -16,6 +16,10 @@ openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_Kaldi openvino_docs_MO_DG_prepare_model_convert_model_tutorials +.. meta:: + :description: In OpenVINO, ONNX, PaddlePaddle, TensorFlow and TensorFlow Lite + models do not require any prior conversion, while MxNet, Caffe and Kaldi do. + **OpenVINO IR (Intermediate Representation)** - the proprietary format of OpenVINO™, benefiting from the full extent of its features. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_AttentionOCR_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_AttentionOCR_From_Tensorflow.md index 42903fbd86f..e939fa70a19 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_AttentionOCR_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_AttentionOCR_From_Tensorflow.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert the Attention OCR + model from the TensorFlow Attention OCR repository to the + OpenVINO Intermediate Representation. + + This tutorial explains how to convert the Attention OCR (AOCR) model from the `TensorFlow Attention OCR repository `__ to the Intermediate Representation (IR). Extracting a Model from ``aocr`` Library diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_BERT_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_BERT_From_Tensorflow.md index 0bbf0f7c825..052805922e2 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_BERT_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_BERT_From_Tensorflow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a BERT model + from TensorFlow to the OpenVINO Intermediate Representation. + + Pretrained models for BERT (Bidirectional Encoder Representations from Transformers) are `publicly available `__. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_CRNN_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_CRNN_From_Tensorflow.md index 251ac8da42b..f697b432408 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_CRNN_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_CRNN_From_Tensorflow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a CRNN model + from TensorFlow to the OpenVINO Intermediate Representation. + + This tutorial explains how to convert a CRNN model to OpenVINO™ Intermediate Representation (IR). There are several public versions of TensorFlow CRNN model implementation available on GitHub. This tutorial explains how to convert the model from diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_DeepSpeech_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_DeepSpeech_From_Tensorflow.md index 1b224bb21af..e982cbfc0e3 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_DeepSpeech_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_DeepSpeech_From_Tensorflow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a DeepSpeech model + from TensorFlow to the OpenVINO Intermediate Representation. + + `DeepSpeech project `__ provides an engine to train speech-to-text models. Downloading the Pretrained DeepSpeech Model diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_EfficientDet_Models.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_EfficientDet_Models.md index fca2f79570e..fee8b70d276 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_EfficientDet_Models.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_EfficientDet_Models.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert an EfficientDet model + from TensorFlow to the OpenVINO Intermediate Representation. + + This tutorial explains how to convert EfficientDet public object detection models to the Intermediate Representation (IR). .. _efficientdet-to-ir: diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_FaceNet_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_FaceNet_From_Tensorflow.md index 5adb6b87224..85dd3cc4691 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_FaceNet_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_FaceNet_From_Tensorflow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a FaceNet model + from TensorFlow to the OpenVINO Intermediate Representation. + + `Public pre-trained FaceNet models `__ contain both training and inference part of graph. Switch between this two states is manageable with placeholder value. Intermediate Representation (IR) models are intended for inference, which means that train part is redundant. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_GNMT_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_GNMT_From_Tensorflow.md index d56d29b4c6b..59d95dbe571 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_GNMT_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_GNMT_From_Tensorflow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a GNMT model + from TensorFlow to the OpenVINO Intermediate Representation. + + This tutorial explains how to convert Google Neural Machine Translation (GNMT) model to the Intermediate Representation (IR). There are several public versions of TensorFlow GNMT model implementation available on GitHub. This tutorial explains how to convert the GNMT model from the `TensorFlow Neural Machine Translation (NMT) repository `__ to the IR. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_NCF_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_NCF_From_Tensorflow.md index b427b2f0084..3d4c4192c5e 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_NCF_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_NCF_From_Tensorflow.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a Neural Collaborative + Filtering Model from TensorFlow to the OpenVINO Intermediate + Representation. + + This tutorial explains how to convert Neural Collaborative Filtering (NCF) model to the OpenVINO Intermediate Representation. `Public TensorFlow NCF model `__ does not contain pre-trained weights. To convert this model to the IR: diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Object_Detection_API_Models.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Object_Detection_API_Models.md index 15b72442454..77fb543c2ca 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Object_Detection_API_Models.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Object_Detection_API_Models.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert Object Detection + API Models from TensorFlow to the OpenVINO Intermediate + Representation. + + * Starting with the 2022.1 release, model conversion API can convert the TensorFlow Object Detection API Faster and Mask RCNNs topologies differently. By default, model conversion adds operation "Proposal" to the generated IR. This operation needs an additional input to the model with name "image_info" which should be fed with several values describing the preprocessing applied to the input image (refer to the :doc:`Proposal ` operation specification for more information). However, this input is redundant for the models trained and inferred with equal size images. Model conversion API can generate IR for such models and insert operation :doc:`DetectionOutput ` instead of ``Proposal``. The `DetectionOutput` operation does not require additional model input "image_info". Moreover, for some models the produced inference results are closer to the original TensorFlow model. In order to trigger new behavior, the attribute "operation_to_add" in the corresponding JSON transformation configuration file should be set to value "DetectionOutput" instead of default one "Proposal". * Starting with the 2021.1 release, model conversion API converts the TensorFlow Object Detection API SSDs, Faster and Mask RCNNs topologies keeping shape-calculating sub-graphs by default, so topologies can be re-shaped in the OpenVINO Runtime using dedicated reshape API. Refer to the :doc:`Using Shape Inference ` guide for more information on how to use this feature. It is possible to change the both spatial dimensions of the input image and batch size. * To generate IRs for TF 1 SSD topologies, model conversion API creates a number of ``PriorBoxClustered`` operations instead of a constant node with prior boxes calculated for the particular input image size. This change allows you to reshape the topology in the OpenVINO Runtime using dedicated API. The reshaping is supported for all SSD topologies except FPNs, which contain hardcoded shapes for some operations preventing from changing topology input shape. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_RetinaNet_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_RetinaNet_From_Tensorflow.md index 03655d571b7..908135935e0 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_RetinaNet_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_RetinaNet_From_Tensorflow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a RetinaNet model + from TensorFlow to the OpenVINO Intermediate Representation. + + This tutorial explains how to convert a RetinaNet model to the Intermediate Representation (IR). `Public RetinaNet model `__ does not contain pretrained TensorFlow weights. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Slim_Library_Models.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Slim_Library_Models.md index 2e3a31c2a5b..ead9b587ed6 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Slim_Library_Models.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Slim_Library_Models.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a Slim Image + Classification model from TensorFlow to the OpenVINO + Intermediate Representation. + + `TensorFlow-Slim Image Classification Model Library `__ is a library to define, train and evaluate classification models in TensorFlow. The library contains Python scripts defining the classification topologies together with checkpoint files for several pre-trained classification topologies. To convert a TensorFlow-Slim library model, complete the following steps: 1. Download the TensorFlow-Slim models `git repository `__. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_WideAndDeep_Family_Models.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_WideAndDeep_Family_Models.md index 9a632c26471..017a3019394 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_WideAndDeep_Family_Models.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_WideAndDeep_Family_Models.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert Wide and Deep Family + models from TensorFlow to the OpenVINO Intermediate Representation. + + The Wide and Deep models is a combination of wide and deep parts for memorization and generalization of object features respectively. These models can contain different types of object features such as numerical, categorical, sparse and sequential features. These feature types are specified through Tensorflow tf.feature_column API. Table below presents what feature types are supported by the OpenVINO toolkit. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_XLNet_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_XLNet_From_Tensorflow.md index 2877f0515d3..cb0be7d770a 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_XLNet_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_XLNet_From_Tensorflow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert an XLNet model from + TensorFlow to the OpenVINO Intermediate Representation. + + Pretrained models for XLNet (Bidirectional Encoder Representations from Transformers) are `publicly available `__. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_YOLO_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_YOLO_From_Tensorflow.md index 51e20baf61d..bd5a49acc6a 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_YOLO_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_YOLO_From_Tensorflow.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert YOLO models from + TensorFlow to the OpenVINO Intermediate Representation. + + This document explains how to convert real-time object detection YOLOv1, YOLOv2, YOLOv3 and YOLOv4 public models to the Intermediate Representation (IR). All YOLO models are originally implemented in the DarkNet framework and consist of two files: * The ``.cfg`` file with model configurations diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_lm_1b_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_lm_1b_From_Tensorflow.md index b0b9bab98e9..f2433f3175e 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_lm_1b_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_lm_1b_From_Tensorflow.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to convert a TensorFlow Language + Model on One Billion Word Benchmark to the OpenVINO Intermediate + Representation. + + Downloading a Pre-trained Language Model on One Billion Word Benchmark ###################################################################### diff --git a/docs/MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md b/docs/MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md index 42315f55d7f..d2f86b2e607 100644 --- a/docs/MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md +++ b/docs/MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md @@ -2,6 +2,7 @@ @sphinxdirective + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/MO_DG/prepare_model/customize_model_optimizer/Extending_Model_Optimizer_with_Caffe_Python_Layers.md b/docs/MO_DG/prepare_model/customize_model_optimizer/Extending_Model_Optimizer_with_Caffe_Python_Layers.md index 5d558c02b72..62fce957aba 100644 --- a/docs/MO_DG/prepare_model/customize_model_optimizer/Extending_Model_Optimizer_with_Caffe_Python_Layers.md +++ b/docs/MO_DG/prepare_model/customize_model_optimizer/Extending_Model_Optimizer_with_Caffe_Python_Layers.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to extract operator attributes in Model Optimizer to + support a custom Caffe operation written only in Python. + .. danger:: The code described here has been **deprecated!** Do not use it to avoid working with a legacy solution. It will be kept for some time to ensure backwards compatibility, but **you should not use** it in contemporary applications. diff --git a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Extensions.md b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Extensions.md index 6c67748c760..6da9bbe4c78 100644 --- a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Extensions.md +++ b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Extensions.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about deprecated extensions, which enable injecting logic + to the model conversion pipeline without changing the Model + Optimizer core code. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Extractor.md b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Extractor.md index 8e3b3d9648d..0de73245841 100644 --- a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Extractor.md +++ b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Extractor.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn about a deprecated generic extension in Model Optimizer, + which provides the operation extractor usable for all model + frameworks. + + .. danger:: The code described here has been **deprecated!** Do not use it to avoid working with a legacy solution. It will be kept for some time to ensure backwards compatibility, but **you should not use** it in contemporary applications. diff --git a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Operation.md b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Operation.md index 4f3ed1ba48f..0de74fbd6ff 100644 --- a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Operation.md +++ b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Operation.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about the Op class, that contains operation attributes, + which are set to a node of the graph created during model + conversion with Model Optimizer. + .. danger:: The code described here has been **deprecated!** Do not use it to avoid working with a legacy solution. It will be kept for some time to ensure backwards compatibility, but **you should not use** it in contemporary applications. diff --git a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Ports_Connections.md b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Ports_Connections.md index 45379032b50..e8777b2ff93 100644 --- a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Ports_Connections.md +++ b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Ports_Connections.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about deprecated APIs and the Port and Connection classes + in Model Optimizer used for graph traversal and transformation. + .. danger:: The code described here has been **deprecated!** Do not use it to avoid working with a legacy solution. It will be kept for some time to ensure backwards compatibility, but **you should not use** it in contemporary applications. diff --git a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Transformation_Extensions.md b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Transformation_Extensions.md index 749bc459cae..4cf8304f8d5 100644 --- a/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Transformation_Extensions.md +++ b/docs/MO_DG/prepare_model/customize_model_optimizer/Model_Optimizer_Transformation_Extensions.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about various base classes for front, middle and back phase + transformations applied during model conversion with Model Optimizer. + .. danger:: The code described here has been **deprecated!** Do not use it to avoid working with a legacy solution. It will be kept for some time to ensure backwards compatibility, but **you should not use** it in contemporary applications. diff --git a/docs/OV_Runtime_UG/AutoPlugin_Debugging.md b/docs/OV_Runtime_UG/AutoPlugin_Debugging.md index 83666156257..25041105185 100644 --- a/docs/OV_Runtime_UG/AutoPlugin_Debugging.md +++ b/docs/OV_Runtime_UG/AutoPlugin_Debugging.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: In OpenVINO Runtime, you can enable Instrumentation and Tracing Technology API (ITT API) of Intel® VTune™ + Profiler to control trace data during execution of AUTO plugin. + + Using Debug Log ############### diff --git a/docs/OV_Runtime_UG/Model_caching_overview.md b/docs/OV_Runtime_UG/Model_caching_overview.md index 0cbe9c52ea0..9b47de322e3 100644 --- a/docs/OV_Runtime_UG/Model_caching_overview.md +++ b/docs/OV_Runtime_UG/Model_caching_overview.md @@ -1,7 +1,13 @@ # Model Caching Overview {#openvino_docs_OV_UG_Model_caching_overview} @sphinxdirective - + +.. meta:: + :description: Enabling model caching to export compiled model + automatically and reusing it can significantly + reduce duration of model compilation on application startup. + + As described in :doc:`Integrate OpenVINO™ with Your Application `, a common application flow consists of the following steps: diff --git a/docs/OV_Runtime_UG/Operations_specifications.md b/docs/OV_Runtime_UG/Operations_specifications.md index 2558522fe74..8d195896037 100644 --- a/docs/OV_Runtime_UG/Operations_specifications.md +++ b/docs/OV_Runtime_UG/Operations_specifications.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operations supported in OpenVINO™ toolkit. + .. toctree:: :maxdepth: 1 diff --git a/docs/OV_Runtime_UG/Python_API_exclusives.md b/docs/OV_Runtime_UG/Python_API_exclusives.md index c1824186fef..bf2d645d2de 100644 --- a/docs/OV_Runtime_UG/Python_API_exclusives.md +++ b/docs/OV_Runtime_UG/Python_API_exclusives.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: OpenVINO™ Runtime Python API includes additional features to + improve user experience and provide simple yet powerful tool + for Python users. + + OpenVINO™ Runtime Python API offers additional features and helpers to enhance user experience. The main goal of Python API is to provide user-friendly and simple yet powerful tool for Python users. Easier Model Compilation diff --git a/docs/OV_Runtime_UG/Python_API_inference.md b/docs/OV_Runtime_UG/Python_API_inference.md index 6638ae4e6f9..94811530e29 100644 --- a/docs/OV_Runtime_UG/Python_API_inference.md +++ b/docs/OV_Runtime_UG/Python_API_inference.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: OpenVINO™ Runtime Python API enables you to share memory on inputs, hide + the latency with asynchronous calls and implement "postponed return". + + .. warning:: All mentioned methods are very dependent on a specific hardware and software set-up. diff --git a/docs/OV_Runtime_UG/Samples_Overview.md b/docs/OV_Runtime_UG/Samples_Overview.md index 6643ad28810..4a9ce9df2ac 100644 --- a/docs/OV_Runtime_UG/Samples_Overview.md +++ b/docs/OV_Runtime_UG/Samples_Overview.md @@ -4,6 +4,12 @@ .. _code samples: +.. meta:: + :description: OpenVINO™ samples include a collection of simple console applications + that explain how to implement the capabilities and features of + OpenVINO API into an application. + + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/OV_Runtime_UG/ShapeInference.md b/docs/OV_Runtime_UG/ShapeInference.md index 823e1c383fa..befb89d2558 100644 --- a/docs/OV_Runtime_UG/ShapeInference.md +++ b/docs/OV_Runtime_UG/ShapeInference.md @@ -8,6 +8,9 @@ troubleshooting_reshape_errors +.. meta:: + :description: OpenVINO™ allows changing model input shape during the runtime when the provided input has a different size than the model's input shape. + OpenVINO™ enables you to change model input shape during the application runtime. It may be useful when you want to feed the model an input that has different size than the model input shape. diff --git a/docs/OV_Runtime_UG/Troubleshooting_ReshapeMethod.md b/docs/OV_Runtime_UG/Troubleshooting_ReshapeMethod.md index f1b9ce95f66..450c61a691b 100644 --- a/docs/OV_Runtime_UG/Troubleshooting_ReshapeMethod.md +++ b/docs/OV_Runtime_UG/Troubleshooting_ReshapeMethod.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: In OpenVINO™, you can use several methods to address the issues + of non-reshape-able models and shape collision, which prevent + normal shape propagation. + + How To Avoid Shape Collision ############################ diff --git a/docs/OV_Runtime_UG/auto_device_selection.md b/docs/OV_Runtime_UG/auto_device_selection.md index a1dd7fd2b37..c2a228b3d74 100644 --- a/docs/OV_Runtime_UG/auto_device_selection.md +++ b/docs/OV_Runtime_UG/auto_device_selection.md @@ -8,6 +8,11 @@ Debugging Auto-Device Plugin +.. meta:: + :description: The Automatic Device Selection mode in OpenVINO™ Runtime + detects available devices and selects the optimal processing + unit for inference automatically. + This article introduces how Automatic Device Selection works and how to use it for inference. diff --git a/docs/OV_Runtime_UG/automatic_batching.md b/docs/OV_Runtime_UG/automatic_batching.md index 618a7644eeb..ee43cbcaf82 100644 --- a/docs/OV_Runtime_UG/automatic_batching.md +++ b/docs/OV_Runtime_UG/automatic_batching.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: The Automatic Batching Execution mode in OpenVINO Runtime + performs automatic batching to improve device utilization + by grouping inference requests. + + The Automatic Batching Execution mode (or Auto-batching for short) performs automatic batching on-the-fly to improve device utilization by grouping inference requests together, without programming effort from the user. With Automatic Batching, gathering the input and scattering the output from the individual inference requests required for the batch happen transparently, without affecting the application code. diff --git a/docs/OV_Runtime_UG/deployment/deployment-manager-tool.md b/docs/OV_Runtime_UG/deployment/deployment-manager-tool.md index 431234e90d2..57c189e79cf 100644 --- a/docs/OV_Runtime_UG/deployment/deployment-manager-tool.md +++ b/docs/OV_Runtime_UG/deployment/deployment-manager-tool.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: OpenVINO™ Deployment Manager assembles the model, OpenVINO IR + files, your application, dependencies and creates a deployment + package for a target device. + + The OpenVINO™ Deployment Manager is a Python command-line tool that creates a deployment package by assembling the model, OpenVINO IR files, your application, and associated dependencies into a runtime package for your target device. This tool is delivered within the Intel® Distribution of OpenVINO™ toolkit for Linux, Windows and macOS release packages. It is available in the ``/tools/deployment_manager`` directory after installation. This article provides instructions on how to create a package with Deployment Manager and then deploy the package to your target systems. diff --git a/docs/OV_Runtime_UG/deployment/deployment_intro.md b/docs/OV_Runtime_UG/deployment/deployment_intro.md index 6b7c925942a..f54558b62ff 100644 --- a/docs/OV_Runtime_UG/deployment/deployment_intro.md +++ b/docs/OV_Runtime_UG/deployment/deployment_intro.md @@ -10,6 +10,10 @@ Local Distribution Libraries Optimize Binaries Size +.. meta:: + :description: There are several ways of deploying OpenVINO™ application once + its development has been finished. + .. note:: diff --git a/docs/OV_Runtime_UG/deployment/local-distribution.md b/docs/OV_Runtime_UG/deployment/local-distribution.md index 06accf83c4c..e88fd54d176 100644 --- a/docs/OV_Runtime_UG/deployment/local-distribution.md +++ b/docs/OV_Runtime_UG/deployment/local-distribution.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: A local distribution will have its own copies of OpenVINO + Runtime binaries along with a set of required libraries + needed to deploy the application. + + With local distribution, each C or C++ application/installer has its own copies of OpenVINO Runtime binaries. However, OpenVINO has a scalable plugin-based architecture, which means that some components can be loaded in runtime only when they are really needed. This guide helps you understand what minimal set of libraries is required to deploy the application. Local distribution is also suitable for OpenVINO binaries built from source using `Build instructions `__, diff --git a/docs/OV_Runtime_UG/hetero_execution.md b/docs/OV_Runtime_UG/hetero_execution.md index 1cfc8093017..701ad34dd17 100644 --- a/docs/OV_Runtime_UG/hetero_execution.md +++ b/docs/OV_Runtime_UG/hetero_execution.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Heterogeneous execution mode in OpenVINO Runtime enables + the inference of one model on several computing devices. + + Heterogeneous execution enables executing inference of one model on several devices. Its purpose is to: * Utilize the power of accelerators to process the heaviest parts of the model and to execute unsupported operations on fallback devices, like the CPU. diff --git a/docs/OV_Runtime_UG/integrate_with_your_application.md b/docs/OV_Runtime_UG/integrate_with_your_application.md index b7679941170..c102709bed2 100644 --- a/docs/OV_Runtime_UG/integrate_with_your_application.md +++ b/docs/OV_Runtime_UG/integrate_with_your_application.md @@ -12,6 +12,12 @@ openvino_docs_OV_UG_Python_API_exclusives openvino_docs_MO_DG_TensorFlow_Frontend + +.. meta:: + :description: Learn how to implement a typical inference pipeline of OpenVINO™ + Runtime in an application. + + Following these steps, you can implement a typical OpenVINO™ Runtime inference pipeline in your application. Before proceeding, make sure you have :doc:`installed OpenVINO Runtime ` and set environment variables (run ``/setupvars.sh`` for Linux or ``setupvars.bat`` for Windows, otherwise, the ``OpenVINO_DIR`` variable won't be configured properly to pass ``find_package`` calls). diff --git a/docs/OV_Runtime_UG/layout_overview.md b/docs/OV_Runtime_UG/layout_overview.md index db305729420..40a8eabba8a 100644 --- a/docs/OV_Runtime_UG/layout_overview.md +++ b/docs/OV_Runtime_UG/layout_overview.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: The layout enables the application to interpret each particular + dimension of input/ output tensor properly and the input size + can be resized to fit the model. + The concept of layout helps you (and your application) to understand what each particular dimension of input/output tensor means. For example, if your input has the ``{1, 3, 720, 1280}`` shape and the ``NCHW`` layout, it is clear that ``N(batch) = 1``, ``C(channels) = 3``, ``H(height) = 720``, and ``W(width) = 1280``. Without the layout information, the ``{1, 3, 720, 1280}`` tuple does not give any idea to your application on what these numbers mean and how to resize the input image to fit the expectations of the model. diff --git a/docs/OV_Runtime_UG/lowlatency2.md b/docs/OV_Runtime_UG/lowlatency2.md index 6e14d0ea8ae..4bfc58b35b4 100644 --- a/docs/OV_Runtime_UG/lowlatency2.md +++ b/docs/OV_Runtime_UG/lowlatency2.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: The LowLatency2 transformation in OpenVINO Runtime enables restructuring + of stateful networks by inserting Assign/ ReadValue layers. + + The LowLatency2 transformation changes the structure of the network containing :doc:`TensorIterator ` and :doc:`Loop ` by adding the ability to work with the state, inserting the :doc:`Assign ` / :doc:`ReadValue ` layers as it is shown in the picture below. The Differences between the LowLatency and the LowLatency2: diff --git a/docs/OV_Runtime_UG/migration_ov_2_0/common_inference_pipeline.md b/docs/OV_Runtime_UG/migration_ov_2_0/common_inference_pipeline.md index fdc02bc920f..5e94c7bd46a 100644 --- a/docs/OV_Runtime_UG/migration_ov_2_0/common_inference_pipeline.md +++ b/docs/OV_Runtime_UG/migration_ov_2_0/common_inference_pipeline.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: The inference pipeline is a set of steps to be + performed in a specific order to infer models with OpenVINO™ + Runtime. + + To infer models with OpenVINO™ Runtime, you usually need to perform the following steps in the application pipeline: 1. `Create a Core object <#create-a-core-object>`__. diff --git a/docs/OV_Runtime_UG/migration_ov_2_0/configure_devices.md b/docs/OV_Runtime_UG/migration_ov_2_0/configure_devices.md index b31deb054c6..dcf15a71e5b 100644 --- a/docs/OV_Runtime_UG/migration_ov_2_0/configure_devices.md +++ b/docs/OV_Runtime_UG/migration_ov_2_0/configure_devices.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Openvino Runtime API 2.0 has introduced properties that unify + metrics and configuration key concepts, which simplifies the + configuration of inference devices. + + The Inference Engine API provides the ability to configure devices with configuration keys and obtain device-specific metrics. The values retrived from `InferenceEngine::Core::GetConfig `__ are requested by the string name, while the return type is `InferenceEngine::Parameter `__ , which results in users not knowing what the actual type is stored in this parameter. API 2.0 solves these issues by introducing :doc:`properties `, which unify metrics and configuration key concepts. The main advantage is that they have the C++ type: diff --git a/docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md b/docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md index cbaf8ae5873..38b80e59b9f 100644 --- a/docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md +++ b/docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: OpenVINO™ API 2.0 focuses on the use of development tools and + deployment of applications, it also simplifies migration from + different frameworks to OpenVINO. + + One of the main concepts for OpenVINO™ API 2.0 is being "easy to use", which includes: * Simplification of migration from different frameworks to OpenVINO. diff --git a/docs/OV_Runtime_UG/migration_ov_2_0/graph_construction.md b/docs/OV_Runtime_UG/migration_ov_2_0/graph_construction.md index c26fc3611dc..23b61385a72 100644 --- a/docs/OV_Runtime_UG/migration_ov_2_0/graph_construction.md +++ b/docs/OV_Runtime_UG/migration_ov_2_0/graph_construction.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Model creation in OpenVINO™ Runtime API 2.0 is performed with + nGraph engine that has been preserved in the new API and its + namespace has been changed to 'ov'. + + OpenVINO™ Runtime with API 2.0 includes the nGraph engine as a common part. The ``ngraph`` namespace has been changed to ``ov``, but all other parts of the ngraph API have been preserved. The code snippets below show how to change the application code for migration to API 2.0. diff --git a/docs/OV_Runtime_UG/migration_ov_2_0/intro.md b/docs/OV_Runtime_UG/migration_ov_2_0/intro.md index 51d9718c7e4..cd9d439dfd1 100644 --- a/docs/OV_Runtime_UG/migration_ov_2_0/intro.md +++ b/docs/OV_Runtime_UG/migration_ov_2_0/intro.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: A detailed information on a new version of OpenVINO™ API 2.0, + as well as the new OpenVINO IR model format: IR v11. + + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/OV_Runtime_UG/migration_ov_2_0/preprocessing.md b/docs/OV_Runtime_UG/migration_ov_2_0/preprocessing.md index cb4f4fa62e4..fb9958b0a04 100644 --- a/docs/OV_Runtime_UG/migration_ov_2_0/preprocessing.md +++ b/docs/OV_Runtime_UG/migration_ov_2_0/preprocessing.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: In OpenVINO™ API 2.0 each preprocessing or post-processing + operation is integrated directly into the model and compiled + together with the inference graph. + + This guide introduces how preprocessing works in API 2.0 by a comparison with preprocessing in the previous Inference Engine API. It also demonstrates how to migrate preprocessing scenarios from Inference Engine to API 2.0 via code samples. How Preprocessing Works in API 2.0 diff --git a/docs/OV_Runtime_UG/model_representation.md b/docs/OV_Runtime_UG/model_representation.md index ca4cf618512..2b00be705a6 100644 --- a/docs/OV_Runtime_UG/model_representation.md +++ b/docs/OV_Runtime_UG/model_representation.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: In OpenVINO™ Runtime a model is represented by special classes to work with model data types and shapes. + + In OpenVINO™ Runtime, a model is represented by the ``:ref:`ov::Model ``` class. The ``:ref:`ov::Model ``` object stores shared pointers to ``:ref:`ov::op::v0::Parameter ```, ``:ref:`ov::op::v0::Result ```, and ``:ref:`ov::op::Sink ``` operations, which are inputs, outputs, and sinks of the graph. Sinks of the graph have no consumers and are not included in the results vector. All other operations hold each other via shared pointers, in which a child operation holds its parent via a hard link. If an operation has no consumers and is neither the ``Result`` nor the ``Sink`` operation whose shared pointer counter is zero, the operation will be destructed and not be accessible anymore. diff --git a/docs/OV_Runtime_UG/model_state_intro.md b/docs/OV_Runtime_UG/model_state_intro.md index d45ee927249..eca22cc6eb9 100644 --- a/docs/OV_Runtime_UG/model_state_intro.md +++ b/docs/OV_Runtime_UG/model_state_intro.md @@ -8,6 +8,11 @@ openvino_docs_OV_UG_lowlatency2 +.. meta:: + :description: OpenVINO Runtime includes a special API to work with stateful + networks, where a state can be automatically read, set, saved + or reset between inferences. + Several use cases require processing of data sequences. When length of a sequence is known and small enough, it can be processed with RNN like models that contain a cycle inside. However, in some cases (e.g., online speech recognition of time series diff --git a/docs/OV_Runtime_UG/multi_device.md b/docs/OV_Runtime_UG/multi_device.md index 4658fc89f8f..4cfb4078915 100644 --- a/docs/OV_Runtime_UG/multi_device.md +++ b/docs/OV_Runtime_UG/multi_device.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: The Multi-Device execution mode in OpenVINO Runtime assigns + multiple available computing devices to particular inference + requests to execute in parallel. + + To run inference on multiple devices, you can choose either of the following ways: - Use the :ref:`CUMULATIVE_THROUGHPUT option ` of the Automatic Device Selection mode. This way, you can use all available devices in the system without the need to specify them. diff --git a/docs/OV_Runtime_UG/openvino_intro.md b/docs/OV_Runtime_UG/openvino_intro.md index 90c8db21dbc..79395a748b4 100644 --- a/docs/OV_Runtime_UG/openvino_intro.md +++ b/docs/OV_Runtime_UG/openvino_intro.md @@ -16,6 +16,11 @@ openvino_docs_OV_UG_model_state_intro Optimize Inference +.. meta:: + :description: OpenVINO Runtime is an API comprised of a set of C++ libraries + with C and Python bindings and it delivers inference solutions + on different platforms. + OpenVINO Runtime is a set of C++ libraries with C and Python bindings providing a common API to deliver inference solutions on the platform of your choice. Use the OpenVINO Runtime API to read an Intermediate Representation (IR), TensorFlow, TensorFlow Lite, ONNX, or PaddlePaddle model and execute it on preferred devices. diff --git a/docs/OV_Runtime_UG/ov_dynamic_shapes.md b/docs/OV_Runtime_UG/ov_dynamic_shapes.md index f689624ee6b..a07b2597fdc 100644 --- a/docs/OV_Runtime_UG/ov_dynamic_shapes.md +++ b/docs/OV_Runtime_UG/ov_dynamic_shapes.md @@ -8,6 +8,11 @@ openvino_docs_OV_UG_NoDynamicShapes +.. meta:: + :description: The Reshape method in OpenVINO Runtime API can handle dynamic + shapes of models that support changing input shapes before + model compilation. + As it was demonstrated in the :doc:`Changing Input Shapes ` article, there are models that support changing input shapes before model compilation in ``Core::compile_model``. Reshaping models provides an ability to customize the model input shape for the exact size required in the end application. diff --git a/docs/OV_Runtime_UG/ov_infer_request.md b/docs/OV_Runtime_UG/ov_infer_request.md index 1decebf824a..ad5723e72c4 100644 --- a/docs/OV_Runtime_UG/ov_infer_request.md +++ b/docs/OV_Runtime_UG/ov_infer_request.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Infer Request mechanism in OpenVINO™ Runtime allows inferring + models on different devices in asynchronous or synchronous + modes of inference. + + OpenVINO™ Runtime uses Infer Request mechanism which allows running models on different devices in asynchronous or synchronous manners. The ``ov::InferRequest`` class is used for this purpose inside the OpenVINO™ Runtime. This class allows you to set and get data for model inputs, outputs and run inference for the model. diff --git a/docs/OV_Runtime_UG/ov_without_dynamic_shapes.md b/docs/OV_Runtime_UG/ov_without_dynamic_shapes.md index 91d14b219e8..479bd1f6a26 100644 --- a/docs/OV_Runtime_UG/ov_without_dynamic_shapes.md +++ b/docs/OV_Runtime_UG/ov_without_dynamic_shapes.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: The methods to emulate dynamic shapes are applied only if the + native dynamic shape API does not work or does not perform + as expected. + + Several approaches to emulate dynamic shapes are considered in this article. Apply the following methods only if the :doc:`native dynamic shape API ` does not work or does not perform as expected. diff --git a/docs/OV_Runtime_UG/performance_hints.md b/docs/OV_Runtime_UG/performance_hints.md index e5fe47d306c..71077748ab5 100644 --- a/docs/OV_Runtime_UG/performance_hints.md +++ b/docs/OV_Runtime_UG/performance_hints.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: OpenVINO Runtime offers two dedicated high-level performance + hints, namely throughput and latency, that help to configure + an inference device. + + Even though all :doc:`supported devices ` in OpenVINO™ offer low-level performance settings, utilizing them is not recommended outside of very few cases. The preferred way to configure performance in OpenVINO Runtime is using performance hints. This is a future-proof solution fully compatible with the :doc:`automatic device selection inference mode ` and designed with *portability* in mind. diff --git a/docs/OV_Runtime_UG/preprocessing_details.md b/docs/OV_Runtime_UG/preprocessing_details.md index 2f1b48e6fcc..414eaf972d1 100644 --- a/docs/OV_Runtime_UG/preprocessing_details.md +++ b/docs/OV_Runtime_UG/preprocessing_details.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn the details on capabilities of pre-processing API and post-processing. + + The purpose of this article is to present details on preprocessing API, such as its capabilities and post-processing. Pre-processing Capabilities diff --git a/docs/OV_Runtime_UG/preprocessing_overview.md b/docs/OV_Runtime_UG/preprocessing_overview.md index 6892f387eb6..5ab2b7021be 100644 --- a/docs/OV_Runtime_UG/preprocessing_overview.md +++ b/docs/OV_Runtime_UG/preprocessing_overview.md @@ -10,6 +10,10 @@ openvino_docs_OV_UG_Layout_Overview openvino_docs_OV_UG_Preprocess_Usecase_save +.. meta:: + :description: The preprocessing entails additional operations to transform + the input data that does not fit the model input tensor. + Introduction #################### diff --git a/docs/OV_Runtime_UG/preprocessing_usecase_save.md b/docs/OV_Runtime_UG/preprocessing_usecase_save.md index 492fa85dc62..bada7e04147 100644 --- a/docs/OV_Runtime_UG/preprocessing_usecase_save.md +++ b/docs/OV_Runtime_UG/preprocessing_usecase_save.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Once a model is read, the preprocessing/ postprocessing steps + can be added and then the resulting model can be saved to + OpenVINO Intermediate Representation. + + Previous sections covered the topic of the :doc:`preprocessing steps ` and the overview of :doc:`Layout ` API. diff --git a/docs/OV_Runtime_UG/protecting_model_guide.md b/docs/OV_Runtime_UG/protecting_model_guide.md index 38c961c1d6a..9f54a84d4bc 100644 --- a/docs/OV_Runtime_UG/protecting_model_guide.md +++ b/docs/OV_Runtime_UG/protecting_model_guide.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to encrypt and optimize a model before its deployment + to the edge device to ensure inference integrity and + provide copyright protection. + Deploying deep-learning capabilities to edge devices can present security challenges like ensuring inference integrity, or providing copyright protection of your deep-learning models. One possible solution is to use cryptography to protect models as they are deployed and stored on edge devices. Model encryption, decryption and authentication are not provided by OpenVINO but can be implemented with third-party tools (i.e., OpenSSL). While implementing encryption, ensure that the latest versions of tools are used and follow cryptography best practices. diff --git a/docs/OV_Runtime_UG/supported_plugins/CPU.md b/docs/OV_Runtime_UG/supported_plugins/CPU.md index f7329449c81..a2fc5a60ed2 100644 --- a/docs/OV_Runtime_UG/supported_plugins/CPU.md +++ b/docs/OV_Runtime_UG/supported_plugins/CPU.md @@ -1,10 +1,13 @@ # CPU Device {#openvino_docs_OV_UG_supported_plugins_CPU} - - @sphinxdirective +.. meta:: + :description: The CPU plugin in the Intel® Distribution of OpenVINO™ toolkit + is developed to achieve high performance inference of neural + networks on Intel® x86-64 and Arm® CPUs. + The CPU plugin is a part of the Intel® Distribution of OpenVINO™ toolkit. It is developed to achieve high performance inference of neural networks on Intel® x86-64 and Arm® CPUs. The newer 11th generation and later Intel® CPUs provide even further performance boost, especially with INT8 models. For an in-depth description of CPU plugin, see: diff --git a/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md b/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md index dffa2edac1e..6dd12cdfcc5 100644 --- a/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md +++ b/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md @@ -11,6 +11,11 @@ openvino_docs_OV_UG_supported_plugins_GPU openvino_docs_OV_UG_supported_plugins_GNA +.. meta:: + :description: The list of types of devices and corresponding plugins which + are compatible with OpenVINO Runtime and support inference + of deep learning models. + OpenVINO™ Runtime can infer deep learning models using the following device types: diff --git a/docs/OV_Runtime_UG/supported_plugins/GNA.md b/docs/OV_Runtime_UG/supported_plugins/GNA.md index 8bd0537ed3a..ab543b29872 100644 --- a/docs/OV_Runtime_UG/supported_plugins/GNA.md +++ b/docs/OV_Runtime_UG/supported_plugins/GNA.md @@ -3,6 +3,11 @@ @sphinxdirective +.. meta:: + :description: The GNA plugin in OpenVINO™ Runtime enables running inference + on Intel® Gaussian & Neural Accelerator (GNA) and in the + software execution mode on CPU. + The Intel® Gaussian & Neural Accelerator (GNA) is a low-power neural coprocessor for continuous inference at the edge. diff --git a/docs/OV_Runtime_UG/supported_plugins/GPU.md b/docs/OV_Runtime_UG/supported_plugins/GPU.md index df4cb4049c8..cd51350cc7d 100644 --- a/docs/OV_Runtime_UG/supported_plugins/GPU.md +++ b/docs/OV_Runtime_UG/supported_plugins/GPU.md @@ -8,6 +8,11 @@ openvino_docs_OV_UG_supported_plugins_GPU_RemoteTensor_API +.. meta:: + :description: The GPU plugin in the Intel® Distribution of OpenVINO™ toolkit + is an OpenCL based plugin for inference of deep neural + networks on Intel® GPus. + The GPU plugin is an OpenCL based plugin for inference of deep neural networks on Intel GPUs, both integrated and discrete ones. For an in-depth description of the GPU plugin, see: diff --git a/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md b/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md index 8e85e0f7ca6..cf675115abe 100644 --- a/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md +++ b/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: The Remote Tensor API of GPU plugin in OpenVINO™ supports + interoperability with existing native APIs, such as OpenCL, + Microsoft DirectX, or VAAPI. + The GPU plugin implementation of the ``ov::RemoteContext`` and ``ov::RemoteTensor`` interfaces supports GPU pipeline developers who need video memory sharing and interoperability with existing native APIs, diff --git a/docs/OV_Runtime_UG/supported_plugins/config_properties.md b/docs/OV_Runtime_UG/supported_plugins/config_properties.md index c7da42fca1f..8bddb0d0358 100644 --- a/docs/OV_Runtime_UG/supported_plugins/config_properties.md +++ b/docs/OV_Runtime_UG/supported_plugins/config_properties.md @@ -3,6 +3,10 @@ @sphinxdirective +.. meta:: + :description: Learn the details on the process of querying different device + properties and configuration values at runtime. + The OpenVINO™ toolkit supports inference with several types of devices (processors or accelerators). This section provides a high-level description of the process of querying of different device properties and configuration values at runtime. diff --git a/docs/api/api_reference.rst b/docs/api/api_reference.rst index 05a52240f28..6db9de2df02 100644 --- a/docs/api/api_reference.rst +++ b/docs/api/api_reference.rst @@ -3,6 +3,10 @@ API Reference ------------- +.. meta:: + :description: Explore the features of Python, C, C++ APIs in Intel® Distribution of OpenVINO™ Toolkit. + + The OpenVINO toolkit has APIs available for Python, C, and C++. Most features exist for all APIs, but there are some differences. The C++ API is the most comprehensive. API references available: diff --git a/docs/api/ie_python_api/api.rst b/docs/api/ie_python_api/api.rst index 5faa85f4e05..cd9cb49ddd0 100644 --- a/docs/api/ie_python_api/api.rst +++ b/docs/api/ie_python_api/api.rst @@ -1,6 +1,10 @@ OpenVINO Python API =================== +.. meta:: + :description: Explore Python API and implementation of its features in Intel® Distribution of OpenVINO™ Toolkit. + + .. autosummary:: :toctree: _autosummary :template: custom-module-template.rst diff --git a/docs/api/ie_python_api/compatibility.rst b/docs/api/ie_python_api/compatibility.rst index 54ba2f3eb50..d1001843caa 100644 --- a/docs/api/ie_python_api/compatibility.rst +++ b/docs/api/ie_python_api/compatibility.rst @@ -1,6 +1,10 @@ OpenVINO Python API - Compatibility =================================== +.. meta:: + :description: Get to know Python API features, including openvino.inference_engine, ngraph and _pyngraph modules. + + .. autosummary:: :toctree: _autosummary :template: custom-module-template.rst diff --git a/docs/benchmarks/performance_benchmarks.md b/docs/benchmarks/performance_benchmarks.md index f36eff122b5..a302be3453b 100644 --- a/docs/benchmarks/performance_benchmarks.md +++ b/docs/benchmarks/performance_benchmarks.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Use the benchmark results for Intel® Distribution of OpenVINO™ + toolkit, that may help you decide what hardware to use or how + to plan the workload. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/benchmarks/performance_benchmarks_faq.md b/docs/benchmarks/performance_benchmarks_faq.md index 92ebe0cb0dc..12dfb52e03c 100644 --- a/docs/benchmarks/performance_benchmarks_faq.md +++ b/docs/benchmarks/performance_benchmarks_faq.md @@ -3,6 +3,10 @@ @sphinxdirective +.. meta:: + :description: Check the F.A.Q. for performance benchmarks in Intel® Distribution of OpenVINO™ toolkit. + + .. dropdown:: How often do performance benchmarks get updated? New performance benchmarks are typically published on every diff --git a/docs/benchmarks/performance_int8_vs_fp32.md b/docs/benchmarks/performance_int8_vs_fp32.md index c61da39fdbc..b28cb4e0d97 100644 --- a/docs/benchmarks/performance_int8_vs_fp32.md +++ b/docs/benchmarks/performance_int8_vs_fp32.md @@ -3,6 +3,11 @@ @sphinxdirective +.. meta:: + :description: Learn about the differences in absolute accuracy drop for INT8, + FP32 and FP16 representations of models inferred with OpenVINO + on three different platforms. + The following two tables present the absolute accuracy drop calculated as the accuracy difference between OV-accuracy and the original frame work accuracy for FP32, and the same for INT8 and FP16 representations of a model on three platform architectures. Please also refer to notes below table diff --git a/docs/dlstreamer.md b/docs/dlstreamer.md index 13214a98a60..8f5a86cc4d1 100644 --- a/docs/dlstreamer.md +++ b/docs/dlstreamer.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore Intel® DL Streamer - a framework used to analyze audio + and video streams to detect, classify, track, identify and count + objects, events and people. + Intel® DL Streamer is a streaming media analytics framework, based on GStreamer* multimedia framework, for creating complex media analytics pipelines. Intel® DL Streamer makes Media analytics easy: diff --git a/docs/documentation.md b/docs/documentation.md index 8932f51726d..e3648a2a654 100644 --- a/docs/documentation.md +++ b/docs/documentation.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the OpenVINO toolkit workflow that entails preparing, + optimizing and deploying models in deep learning applications. + + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/gapi/face_beautification.md b/docs/gapi/face_beautification.md index 2097a980d1f..b5201f19561 100644 --- a/docs/gapi/face_beautification.md +++ b/docs/gapi/face_beautification.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to use a simple face beautification algorithm in a + pipeline with G-API that can be run on a video stream. + Introduction ############ diff --git a/docs/gapi/gapi_face_analytics_pipeline.md b/docs/gapi/gapi_face_analytics_pipeline.md index 4298c2cdaf6..e1c25c7d134 100644 --- a/docs/gapi/gapi_face_analytics_pipeline.md +++ b/docs/gapi/gapi_face_analytics_pipeline.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to integrate a deep learning inference in a G-API + graph that can be run on a video stream to obtain data. + + Overview ######## diff --git a/docs/gapi/gapi_intro.md b/docs/gapi/gapi_intro.md index c24b6cc9dd5..3abd4cdf999 100644 --- a/docs/gapi/gapi_intro.md +++ b/docs/gapi/gapi_intro.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about OpenCV Graph API (G-API) which is used to accelerate + regular image and video processing and ensure its portability. + + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/gapi/kernel_api.md b/docs/gapi/kernel_api.md index df4e183f524..05e3bc188f0 100644 --- a/docs/gapi/kernel_api.md +++ b/docs/gapi/kernel_api.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn how to build a pipeline with Graph API (G-API) and ensure its portability, using custom kernel interfaces. + The core idea behind Graph API (G-API) is portability – a pipeline built with G-API must be portable (or at least able to be portable). It means that either it works out-of-the box when compiled for new platform, or G-API provides necessary tools to make it running there, with little-to-no changes in the algorithm itself. This idea can be achieved by separating kernel interface from its implementation. Once a pipeline is built using kernel interfaces, it becomes implementation-neutral – the implementation details (i.e. which kernels to use) are passed on a separate stage (graph compilation). diff --git a/docs/get_started.md b/docs/get_started.md index 37670b7a8fd..5e668ad3076 100644 --- a/docs/get_started.md +++ b/docs/get_started.md @@ -2,10 +2,15 @@ @sphinxdirective +.. meta:: + :description: Learn how to install Intel® Distribution of OpenVINO™ toolkit + on Windows, macOS, and Linux operating systems, using various + installation methods. + .. toctree:: :maxdepth: 1 :hidden: - + Installing OpenVINO Additional Configurations Uninstalling @@ -15,7 +20,7 @@ .. raw:: html - +

Welcome to OpenVINO! This guide introduces installation and learning materials for Intel® Distribution of OpenVINO™ toolkit. The guide walks through the following steps:
Quick Start Example Install OpenVINO diff --git a/docs/get_started/get_started_demos.md b/docs/get_started/get_started_demos.md index cb815157c3f..cecb009be0f 100644 --- a/docs/get_started/get_started_demos.md +++ b/docs/get_started/get_started_demos.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn the details on the workflow of Intel® Distribution of OpenVINO™ + toolkit, and how to run inference, using provided code samples. + + The guide presents a basic workflow for building and running C++ code samples in OpenVINO. Note that these steps will not work with the Python samples. To get started, you must first install OpenVINO Runtime, install OpenVINO Development tools, and build the sample applications. See the :ref:`Prerequisites ` section for instructions. diff --git a/docs/glossary.md b/docs/glossary.md index 87da40f7c98..04834859c09 100644 --- a/docs/glossary.md +++ b/docs/glossary.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Check the list of acronyms, abbreviations and terms used in + Intel® Distribution of OpenVINO™ toolkit. + Acronyms and Abbreviations ################################################# diff --git a/docs/install_guides/configurations-for-intel-gna.md b/docs/install_guides/configurations-for-intel-gna.md index 157a33ed4d5..5e639092e82 100644 --- a/docs/install_guides/configurations-for-intel-gna.md +++ b/docs/install_guides/configurations-for-intel-gna.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to provide additional configuration for Intel® + Gaussian & Neural Accelerator (GNA) to work with Intel® + Distribution of OpenVINO™ toolkit on your system. + + .. note:: On platforms where Intel® GNA is not enabled in the BIOS, the driver cannot be installed, so the GNA plugin uses the software emulation mode only. diff --git a/docs/install_guides/configurations-for-intel-gpu.md b/docs/install_guides/configurations-for-intel-gpu.md index 6d2313fdedc..dc30080a11f 100644 --- a/docs/install_guides/configurations-for-intel-gpu.md +++ b/docs/install_guides/configurations-for-intel-gpu.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to provide additional configuration for Intel® + Processor Graphics (GPU) to work with Intel® Distribution of + OpenVINO™ toolkit on your system. + + .. _gpu guide: To use the OpenVINO™ GPU plug-in and transfer the inference to the graphics of the Intel® processor (GPU), the Intel® graphics driver must be properly configured on the system. diff --git a/docs/install_guides/configurations-header.md b/docs/install_guides/configurations-header.md index 3e287fd3411..4b7b603e003 100644 --- a/docs/install_guides/configurations-header.md +++ b/docs/install_guides/configurations-header.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to create additional configurations for your devices + to work with Intel® Distribution of OpenVINO™ toolkit. + .. _additional configurations: .. toctree:: diff --git a/docs/install_guides/installing-model-dev-tools.md b/docs/install_guides/installing-model-dev-tools.md index cf04b966242..2227e0c1825 100644 --- a/docs/install_guides/installing-model-dev-tools.md +++ b/docs/install_guides/installing-model-dev-tools.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Development Tools on Windows, + Linux, and macOS operating systems, using a PyPi package. + OpenVINO Development Tools is a set of utilities that make it easy to develop and optimize models and applications for OpenVINO. It provides the following tools: * Model conversion API diff --git a/docs/install_guides/installing-openvino-apt.md b/docs/install_guides/installing-openvino-apt.md index 60073776d01..79f9f21ea1d 100644 --- a/docs/install_guides/installing-openvino-apt.md +++ b/docs/install_guides/installing-openvino-apt.md @@ -4,6 +4,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Linux operating + system, using the APT repository, which is a recommended + installation method for C++ developers. + + With the OpenVINO™ 2023.0 release, you can install OpenVINO Runtime on Linux using the APT repository. OpenVINO™ Development Tools can be installed via PyPI only. See `Installing Additional Components `__ for more information. diff --git a/docs/install_guides/installing-openvino-brew.md b/docs/install_guides/installing-openvino-brew.md index b3030f83e28..277012e02c2 100644 --- a/docs/install_guides/installing-openvino-brew.md +++ b/docs/install_guides/installing-openvino-brew.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Linux and macOS + operating systems, using Homebrew, which is a recommended + installation method for C++ developers. + + .. note:: Installing OpenVINO Runtime from Homebrew is recommended for C++ developers. diff --git a/docs/install_guides/installing-openvino-conda.md b/docs/install_guides/installing-openvino-conda.md index 9504402ce0e..7c206d2d6d3 100644 --- a/docs/install_guides/installing-openvino-conda.md +++ b/docs/install_guides/installing-openvino-conda.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Windows, Linux, and + macOS operating systems, using Conda Forge - a recommended + installation method for C++ developers. + + .. note:: Installing OpenVINO Runtime from Conda Forge is recommended for C++ developers, as it provides only the C++ Runtime API. diff --git a/docs/install_guides/installing-openvino-docker-linux.md b/docs/install_guides/installing-openvino-docker-linux.md index 3706ce162ca..2a3db6546ff 100644 --- a/docs/install_guides/installing-openvino-docker-linux.md +++ b/docs/install_guides/installing-openvino-docker-linux.md @@ -2,7 +2,12 @@ @sphinxdirective -Supported operating systems for the Docker Base image: +.. meta:: + :description: Learn how to use a prebuilt Docker image or create an image + manually to install OpenVINO™ Runtime on Linux and Windows operating systems. + + +Supported operating systems for the Docker Base image: - Ubuntu 22.04 LTS - Ubuntu 20.04 LTS diff --git a/docs/install_guides/installing-openvino-from-archive-linux.md b/docs/install_guides/installing-openvino-from-archive-linux.md index 04c294bd7ca..0469fe344fe 100644 --- a/docs/install_guides/installing-openvino-from-archive-linux.md +++ b/docs/install_guides/installing-openvino-from-archive-linux.md @@ -3,6 +3,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Linux operating + system, using an archive file, which is a recommended + installation method for C++ developers. + + Installing OpenVINO Runtime from archive files is recommended for C++ developers. It will contain code samples, as well as pre-built binaries and library files needed for OpenVINO Runtime. If you work with Python, the PyPI package may be a better choice. See the :doc:`Install OpenVINO from PyPI ` diff --git a/docs/install_guides/installing-openvino-from-archive-macos.md b/docs/install_guides/installing-openvino-from-archive-macos.md index abf3c8e45b6..b6b4d684095 100644 --- a/docs/install_guides/installing-openvino-from-archive-macos.md +++ b/docs/install_guides/installing-openvino-from-archive-macos.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on macOS operating + system, using an archive file, which is a recommended + installation method for C++ developers. + With the OpenVINO™ 2023.0 release, you can download and use archive files to install OpenVINO Runtime. The archive files contain pre-built binaries and library files needed for OpenVINO Runtime, as well as code samples. Installing OpenVINO Runtime from archive files is recommended for C++ developers. If you are working with Python, the PyPI package has everything needed for Python development and deployment on CPU and GPUs. Visit the :doc:`Install OpenVINO from PyPI ` page for instructions on how to install OpenVINO Runtime for Python using PyPI. diff --git a/docs/install_guides/installing-openvino-from-archive-windows.md b/docs/install_guides/installing-openvino-from-archive-windows.md index d3fb44c5b75..6ce9d324a2c 100644 --- a/docs/install_guides/installing-openvino-from-archive-windows.md +++ b/docs/install_guides/installing-openvino-from-archive-windows.md @@ -1,7 +1,13 @@ # Install OpenVINO™ Runtime on Windows from an Archive File {#openvino_docs_install_guides_installing_openvino_from_archive_windows} @sphinxdirective - + +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Windows operating + system, using an archive file, which is a recommended + installation method for C++ developers. + + With the OpenVINO™ 2023.0 release, you can download and use archive files to install OpenVINO Runtime. The archive files contain pre-built binaries and library files needed for OpenVINO Runtime, as well as code samples. Installing OpenVINO Runtime from archive files is recommended for C++ developers. If you are working with Python, the PyPI package has everything needed for Python development and deployment on CPU and GPUs. See the :doc:`Install OpenVINO from PyPI ` page for instructions on how to install OpenVINO Runtime for Python using PyPI. diff --git a/docs/install_guides/installing-openvino-linux-header.md b/docs/install_guides/installing-openvino-linux-header.md index 75c65503f52..27c0b69872f 100644 --- a/docs/install_guides/installing-openvino-linux-header.md +++ b/docs/install_guides/installing-openvino-linux-header.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Linux operating system. + You can use an archive, a PyPi package, APT, YUM, Conda Forge, + Homebrew or a Docker image. + + .. toctree:: :maxdepth: 3 :hidden: diff --git a/docs/install_guides/installing-openvino-macos-header.md b/docs/install_guides/installing-openvino-macos-header.md index 94b9af3a4d4..8a8f710e6a7 100644 --- a/docs/install_guides/installing-openvino-macos-header.md +++ b/docs/install_guides/installing-openvino-macos-header.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on macOS operating + system. You can use an archive, a PyPi package, Conda Forge + or Homebrew. + + .. toctree:: :maxdepth: 3 :hidden: diff --git a/docs/install_guides/installing-openvino-overview.md b/docs/install_guides/installing-openvino-overview.md index bf846259d9c..34b4db10880 100644 --- a/docs/install_guides/installing-openvino-overview.md +++ b/docs/install_guides/installing-openvino-overview.md @@ -2,10 +2,16 @@ @sphinxdirective +.. meta:: + :description: You can choose to install OpenVINO Runtime package - a core set + of libraries or OpenVINO Development Tools - a set of utilities + for working with OpenVINO. + + .. toctree:: :maxdepth: 3 :hidden: - + OpenVINO Runtime OpenVINO Development Tools Build from Source diff --git a/docs/install_guides/installing-openvino-pip.md b/docs/install_guides/installing-openvino-pip.md index 216081ae135..2932b764048 100644 --- a/docs/install_guides/installing-openvino-pip.md +++ b/docs/install_guides/installing-openvino-pip.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Windows, Linux, and + macOS operating systems, using a PyPi package. + + Using the PyPI repository, you can install either OpenVINO™ Runtime or OpenVINO Development Tools on Windows, Linux, and macOS systems. This article focuses on OpenVINO™ Runtime. diff --git a/docs/install_guides/installing-openvino-runtime.md b/docs/install_guides/installing-openvino-runtime.md index dcbd414a543..027126f6248 100644 --- a/docs/install_guides/installing-openvino-runtime.md +++ b/docs/install_guides/installing-openvino-runtime.md @@ -2,10 +2,15 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Windows, macOS, and + Linux operating systems, using various installation methods. + + .. toctree:: :maxdepth: 2 :hidden: - + Linux Windows macOS diff --git a/docs/install_guides/installing-openvino-windows-header.md b/docs/install_guides/installing-openvino-windows-header.md index 9b4b547bb75..8340ebdcd42 100644 --- a/docs/install_guides/installing-openvino-windows-header.md +++ b/docs/install_guides/installing-openvino-windows-header.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Windows operating + system. You can use an archive, a PyPi package, Conda Forge, + or a Docker image. + + .. toctree:: :maxdepth: 3 :hidden: diff --git a/docs/install_guides/installing-openvino-yocto.md b/docs/install_guides/installing-openvino-yocto.md index c60ba26ce81..4c304e69fc5 100644 --- a/docs/install_guides/installing-openvino-yocto.md +++ b/docs/install_guides/installing-openvino-yocto.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to create a Yocto image with Intel® Distribution of + OpenVINO™ toolkit on your host machine. + This document provides instructions for creating a Yocto image with Intel® Distribution of OpenVINO™ toolkit. System Requirements diff --git a/docs/install_guides/installing-openvino-yum.md b/docs/install_guides/installing-openvino-yum.md index 0c9176f8a57..2dfb8749cd7 100644 --- a/docs/install_guides/installing-openvino-yum.md +++ b/docs/install_guides/installing-openvino-yum.md @@ -4,6 +4,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to install OpenVINO™ Runtime on Linux operating + system, using the YUM repository, which is a recommended + installation method for C++ developers. + + With the OpenVINO™ 2023.0 release, you can install OpenVINO Runtime on Linux using the YUM repository. OpenVINO™ Development Tools can be installed via PyPI only. See `Installing Additional Components <#step-3-optional-install-additional-components>`__ for more information. diff --git a/docs/install_guides/troubleshooting-issues.md b/docs/install_guides/troubleshooting-issues.md index a381f0f46c1..4f5b3020a85 100644 --- a/docs/install_guides/troubleshooting-issues.md +++ b/docs/install_guides/troubleshooting-issues.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Get to know solutions for possible problems that may occur during + the installation and configuration of OpenVINO™ on your system. + This page lists issues that you may encounter during the installation and configuration of OpenVINO™, as well as their possible solutions. .. _install_for_prc: diff --git a/docs/install_guides/troubleshooting-steps.md b/docs/install_guides/troubleshooting-steps.md index f3c8ebdb5e3..7174a92de2d 100644 --- a/docs/install_guides/troubleshooting-steps.md +++ b/docs/install_guides/troubleshooting-steps.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn what checks you may perform after encountering problems during + the installation and configuration of OpenVINO™ on your system. + + If you run into issues while installing or configuring OpenVINO™, you can try the following methods to do some quick checks first. Check the versions of OpenVINO Runtime and Development Tools diff --git a/docs/install_guides/troubleshooting.md b/docs/install_guides/troubleshooting.md index 99e3fd7ca8e..986430ee13d 100644 --- a/docs/install_guides/troubleshooting.md +++ b/docs/install_guides/troubleshooting.md @@ -2,10 +2,16 @@ @sphinxdirective +.. meta:: + :description: A collection of troubleshooting steps and solutions to possible + problems that may occur during the installation and configuration + of OpenVINO™ on your system. + + .. toctree:: :maxdepth: 2 :hidden: - + Issues & Solutions Troubleshooting Steps diff --git a/docs/install_guides/uninstalling-openvino.md b/docs/install_guides/uninstalling-openvino.md index daec6910139..bd9fdbf768d 100644 --- a/docs/install_guides/uninstalling-openvino.md +++ b/docs/install_guides/uninstalling-openvino.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to uninstall Intel® Distribution of OpenVINO™ Toolkit from your + operating system. + + .. note:: Uninstallation procedures remove all Intel® Distribution of OpenVINO™ Toolkit component files but don't affect user files in the installation directory. diff --git a/docs/learn_openvino.md b/docs/learn_openvino.md index 61445051983..7d5f3c41234 100644 --- a/docs/learn_openvino.md +++ b/docs/learn_openvino.md @@ -2,14 +2,21 @@ @sphinxdirective +.. meta:: + :description: Explore learning materials, including interactive + Python tutorials and sample console applications that explain + how to use OpenVINO features. + + .. toctree:: :maxdepth: 1 :hidden: - + Interactive Tutorials (Python) Sample Applications (Python & C++) OpenVINO API 2.0 Transition + This section will help you get a hands-on experience with OpenVINO even if you are just starting to learn what OpenVINO is and how it works. It includes various types of learning materials accommodating different learning needs, which means you should find it useful if you are a beginning, diff --git a/docs/notebooks-installation.md b/docs/notebooks-installation.md index 70d4a836001..836981f3bbe 100644 --- a/docs/notebooks-installation.md +++ b/docs/notebooks-installation.md @@ -9,9 +9,6 @@ :description: An installation guide for Jupyter notebooks on which Python tutorials run. The tutorials serve as introduction to the OpenVINO™ toolkit. - :keywords: OpenVINO™ toolkit, Jupyter notebooks, Jupyter, Python, Python API, - installation guide, tutorials, install notebooks, local - installation, OpenVINO™ Notebooks, run notebooks The notebooks run almost anywhere, from browsers and desktops to even a cloud VM or a Docker container. diff --git a/docs/ops/activation/Clamp_1.md b/docs/ops/activation/Clamp_1.md index c32bc3f5ba0..371a2619138 100644 --- a/docs/ops/activation/Clamp_1.md +++ b/docs/ops/activation/Clamp_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Clamp-1 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Clamp-1* **Category**: *Activation function* diff --git a/docs/ops/activation/Elu_1.md b/docs/ops/activation/Elu_1.md index df95b8ddf04..7998368ceea 100644 --- a/docs/ops/activation/Elu_1.md +++ b/docs/ops/activation/Elu_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Elu-1 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Elu-1* **Category**: *Activation function* diff --git a/docs/ops/activation/Exp_1.md b/docs/ops/activation/Exp_1.md index 0576de59e5d..fe11978bbbc 100644 --- a/docs/ops/activation/Exp_1.md +++ b/docs/ops/activation/Exp_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Exp-1 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Exp-1* **Category**: *Activation function* diff --git a/docs/ops/activation/GELU_2.md b/docs/ops/activation/GELU_2.md index 62d2dffdd60..b3eb3daa0d8 100644 --- a/docs/ops/activation/GELU_2.md +++ b/docs/ops/activation/GELU_2.md @@ -3,6 +3,9 @@ @sphinxdirective +.. meta:: + :description: Learn about Gelu-2 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. **Versioned name**: *Gelu-2* diff --git a/docs/ops/activation/GELU_7.md b/docs/ops/activation/GELU_7.md index a2738e0a59d..e69c1de5b0b 100644 --- a/docs/ops/activation/GELU_7.md +++ b/docs/ops/activation/GELU_7.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about Gelu-7 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. **Versioned name**: *Gelu-7* diff --git a/docs/ops/activation/HSigmoid_5.md b/docs/ops/activation/HSigmoid_5.md index d208cb71b84..2fb93070dfe 100644 --- a/docs/ops/activation/HSigmoid_5.md +++ b/docs/ops/activation/HSigmoid_5.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about HSigmoid-5 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *HSigmoid-5* **Category**: *Activation function* diff --git a/docs/ops/activation/HSwish_4.md b/docs/ops/activation/HSwish_4.md index d06e13efb6f..a1bc89897b7 100644 --- a/docs/ops/activation/HSwish_4.md +++ b/docs/ops/activation/HSwish_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about HSwish-4 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *HSwish-4* **Category**: *Activation function* diff --git a/docs/ops/activation/HardSigmoid_1.md b/docs/ops/activation/HardSigmoid_1.md index 7aa101bd1da..7f5ef3b8e67 100644 --- a/docs/ops/activation/HardSigmoid_1.md +++ b/docs/ops/activation/HardSigmoid_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about HardSigmoid-1 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *HardSigmoid-1* **Category**: *Activation function* diff --git a/docs/ops/activation/LogSoftmax_5.md b/docs/ops/activation/LogSoftmax_5.md index a6f2a0fabc4..dfaccffed86 100644 --- a/docs/ops/activation/LogSoftmax_5.md +++ b/docs/ops/activation/LogSoftmax_5.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about LogSoftmax-5 - an activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *LogSoftmax-5* **Category**: *Activation function* diff --git a/docs/ops/activation/Mish_4.md b/docs/ops/activation/Mish_4.md index 3198edc2386..826a21134fa 100644 --- a/docs/ops/activation/Mish_4.md +++ b/docs/ops/activation/Mish_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Mish-4 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Mish-4* **Category**: *Activation function* diff --git a/docs/ops/activation/PReLU_1.md b/docs/ops/activation/PReLU_1.md index b99d7b73936..4271ac94d78 100644 --- a/docs/ops/activation/PReLU_1.md +++ b/docs/ops/activation/PReLU_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about PReLU-1 -an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *PReLU-1* **Category**: *Activation function* diff --git a/docs/ops/activation/ReLU_1.md b/docs/ops/activation/ReLU_1.md index d1165d945bc..94e54e9ed9a 100644 --- a/docs/ops/activation/ReLU_1.md +++ b/docs/ops/activation/ReLU_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReLU-1 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *ReLU-1* **Category**: *Activation function* diff --git a/docs/ops/activation/Selu_1.md b/docs/ops/activation/Selu_1.md index 11131503f8d..0f5058cad03 100644 --- a/docs/ops/activation/Selu_1.md +++ b/docs/ops/activation/Selu_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about SeLU-1 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Selu-1* **Category**: *Activation function* diff --git a/docs/ops/activation/Sigmoid_1.md b/docs/ops/activation/Sigmoid_1.md index b072babbf08..f8078da39ee 100644 --- a/docs/ops/activation/Sigmoid_1.md +++ b/docs/ops/activation/Sigmoid_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Sigmoid-1 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Sigmoid-1* **Category**: *Activation function* diff --git a/docs/ops/activation/SoftMax_1.md b/docs/ops/activation/SoftMax_1.md index db638fdc27e..3864d7cb179 100644 --- a/docs/ops/activation/SoftMax_1.md +++ b/docs/ops/activation/SoftMax_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about SoftMax-1 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *SoftMax-1* **Category**: *Activation function* diff --git a/docs/ops/activation/SoftMax_8.md b/docs/ops/activation/SoftMax_8.md index 7c12d9fe4af..519f549b8e6 100644 --- a/docs/ops/activation/SoftMax_8.md +++ b/docs/ops/activation/SoftMax_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about SoftMax-8 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *SoftMax-8* **Category**: *Activation function* diff --git a/docs/ops/activation/SoftPlus_4.md b/docs/ops/activation/SoftPlus_4.md index e47a29e6247..e4897ee6f0e 100644 --- a/docs/ops/activation/SoftPlus_4.md +++ b/docs/ops/activation/SoftPlus_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about SoftPlus-4 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *SoftPlus-4* **Category**: *Activation function* diff --git a/docs/ops/activation/SoftSign_9.md b/docs/ops/activation/SoftSign_9.md index 5ad643a9333..bf8fbaee1f1 100644 --- a/docs/ops/activation/SoftSign_9.md +++ b/docs/ops/activation/SoftSign_9.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about SoftSign-9 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *SoftSign-9* **Category**: *Activation function* diff --git a/docs/ops/activation/Swish_4.md b/docs/ops/activation/Swish_4.md index 7ad02614378..f460915b21e 100644 --- a/docs/ops/activation/Swish_4.md +++ b/docs/ops/activation/Swish_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Swish-4 - an element-wise, activation operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Swish-4* **Category**: *Activation function* diff --git a/docs/ops/arithmetic/Abs_1.md b/docs/ops/arithmetic/Abs_1.md index b727a635bce..c49574fca69 100644 --- a/docs/ops/arithmetic/Abs_1.md +++ b/docs/ops/arithmetic/Abs_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Abs-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Abs-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Acos_1.md b/docs/ops/arithmetic/Acos_1.md index 6018bacb163..5e9b33c0d7a 100644 --- a/docs/ops/arithmetic/Acos_1.md +++ b/docs/ops/arithmetic/Acos_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Acos-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Acos-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Acosh_3.md b/docs/ops/arithmetic/Acosh_3.md index f0dfc62179b..c52b86f8551 100644 --- a/docs/ops/arithmetic/Acosh_3.md +++ b/docs/ops/arithmetic/Acosh_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Acosh-3 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Acosh-3* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Add_1.md b/docs/ops/arithmetic/Add_1.md index 8bb833c7e35..8a57d0bd7ec 100644 --- a/docs/ops/arithmetic/Add_1.md +++ b/docs/ops/arithmetic/Add_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Add-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Add-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Asin_1.md b/docs/ops/arithmetic/Asin_1.md index becea7827dd..224645366f9 100644 --- a/docs/ops/arithmetic/Asin_1.md +++ b/docs/ops/arithmetic/Asin_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Asin-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Asin-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Asinh_3.md b/docs/ops/arithmetic/Asinh_3.md index 4ff0f72b635..be50df73113 100644 --- a/docs/ops/arithmetic/Asinh_3.md +++ b/docs/ops/arithmetic/Asinh_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Asinh-3 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Asinh-3* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Atan_1.md b/docs/ops/arithmetic/Atan_1.md index e9fa48afb47..df6be295676 100644 --- a/docs/ops/arithmetic/Atan_1.md +++ b/docs/ops/arithmetic/Atan_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Atan-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Atan-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Atanh_3.md b/docs/ops/arithmetic/Atanh_3.md index 1790b4f6610..e70fd71c2a4 100644 --- a/docs/ops/arithmetic/Atanh_3.md +++ b/docs/ops/arithmetic/Atanh_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Atanh-3 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Atanh-3* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Ceiling_1.md b/docs/ops/arithmetic/Ceiling_1.md index 6c2139ff741..312d5c114fa 100644 --- a/docs/ops/arithmetic/Ceiling_1.md +++ b/docs/ops/arithmetic/Ceiling_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Ceiling-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Ceiling-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Cos_1.md b/docs/ops/arithmetic/Cos_1.md index 585d9bb48f9..fb6a99147d2 100644 --- a/docs/ops/arithmetic/Cos_1.md +++ b/docs/ops/arithmetic/Cos_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Cos-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Cos-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Cosh_1.md b/docs/ops/arithmetic/Cosh_1.md index 5622ef1d2ff..b2e84a78452 100644 --- a/docs/ops/arithmetic/Cosh_1.md +++ b/docs/ops/arithmetic/Cosh_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Cosh-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Cosh-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/CumSum_3.md b/docs/ops/arithmetic/CumSum_3.md index 0e07383583a..3c8d73dbc00 100644 --- a/docs/ops/arithmetic/CumSum_3.md +++ b/docs/ops/arithmetic/CumSum_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about CumSum-3 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *CumSum-3* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Divide_1.md b/docs/ops/arithmetic/Divide_1.md index 898fc93bdff..ec0cf6d52d2 100644 --- a/docs/ops/arithmetic/Divide_1.md +++ b/docs/ops/arithmetic/Divide_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Divide-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Divide-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Erf_1.md b/docs/ops/arithmetic/Erf_1.md index 9f4911c0afc..bbd934813a1 100644 --- a/docs/ops/arithmetic/Erf_1.md +++ b/docs/ops/arithmetic/Erf_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Erf-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Erf-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/FloorMod_1.md b/docs/ops/arithmetic/FloorMod_1.md index 332ab19520d..dca84d6a7ac 100644 --- a/docs/ops/arithmetic/FloorMod_1.md +++ b/docs/ops/arithmetic/FloorMod_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about FloorMod-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *FloorMod-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Floor_1.md b/docs/ops/arithmetic/Floor_1.md index 811ad3ecbc8..02b5f6b7c34 100644 --- a/docs/ops/arithmetic/Floor_1.md +++ b/docs/ops/arithmetic/Floor_1.md @@ -1,7 +1,10 @@ # Floor {#openvino_docs_ops_arithmetic_Floor_1} - + @sphinxdirective +.. meta:: + :description: Learn about Floor-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. **Versioned name**: *Floor-1* diff --git a/docs/ops/arithmetic/Log_1.md b/docs/ops/arithmetic/Log_1.md index 6d02fb5e7e7..f505670c6d7 100644 --- a/docs/ops/arithmetic/Log_1.md +++ b/docs/ops/arithmetic/Log_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Log-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Log-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Maximum_1.md b/docs/ops/arithmetic/Maximum_1.md index 9a7ce83c5eb..db85ac1c7cf 100644 --- a/docs/ops/arithmetic/Maximum_1.md +++ b/docs/ops/arithmetic/Maximum_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Maximum-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Maximum-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Minimum_1.md b/docs/ops/arithmetic/Minimum_1.md index db4dc01309a..a17268837d6 100644 --- a/docs/ops/arithmetic/Minimum_1.md +++ b/docs/ops/arithmetic/Minimum_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Minimum-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Minimum-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Mod_1.md b/docs/ops/arithmetic/Mod_1.md index 1760f8baafa..31ca65b4ecd 100644 --- a/docs/ops/arithmetic/Mod_1.md +++ b/docs/ops/arithmetic/Mod_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Mod-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Mod-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Multiply_1.md b/docs/ops/arithmetic/Multiply_1.md index 969c88037a3..b06fd4aa97c 100644 --- a/docs/ops/arithmetic/Multiply_1.md +++ b/docs/ops/arithmetic/Multiply_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Multiply-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Multiply-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Negative_1.md b/docs/ops/arithmetic/Negative_1.md index 9a30ba38cdb..61ba7b73c01 100644 --- a/docs/ops/arithmetic/Negative_1.md +++ b/docs/ops/arithmetic/Negative_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Negative-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Negative-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Power_1.md b/docs/ops/arithmetic/Power_1.md index f91b02d4d7e..8188afd6a64 100644 --- a/docs/ops/arithmetic/Power_1.md +++ b/docs/ops/arithmetic/Power_1.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about Power-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. **Versioned name**: *Power-1* diff --git a/docs/ops/arithmetic/Round_5.md b/docs/ops/arithmetic/Round_5.md index 292bb6085af..d11cd8f1c50 100644 --- a/docs/ops/arithmetic/Round_5.md +++ b/docs/ops/arithmetic/Round_5.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Round-5 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Round-5* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Sign_1.md b/docs/ops/arithmetic/Sign_1.md index e95688e007f..38226a26405 100644 --- a/docs/ops/arithmetic/Sign_1.md +++ b/docs/ops/arithmetic/Sign_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Sign-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Sign-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Sin_1.md b/docs/ops/arithmetic/Sin_1.md index 9b8ea5e7fba..fe9ae89402d 100644 --- a/docs/ops/arithmetic/Sin_1.md +++ b/docs/ops/arithmetic/Sin_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Sin-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Sin-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Sinh_1.md b/docs/ops/arithmetic/Sinh_1.md index 0b58feadcf1..07d9db6d914 100644 --- a/docs/ops/arithmetic/Sinh_1.md +++ b/docs/ops/arithmetic/Sinh_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Sinh-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Sinh-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Sqrt_1.md b/docs/ops/arithmetic/Sqrt_1.md index 759a07061e7..d2247e3e2ae 100644 --- a/docs/ops/arithmetic/Sqrt_1.md +++ b/docs/ops/arithmetic/Sqrt_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Sqrt-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Sqrt-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/SquaredDifference_1.md b/docs/ops/arithmetic/SquaredDifference_1.md index 523a709a379..5744eee835f 100644 --- a/docs/ops/arithmetic/SquaredDifference_1.md +++ b/docs/ops/arithmetic/SquaredDifference_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about SquaredDifference-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *SquaredDifference-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Subtract_1.md b/docs/ops/arithmetic/Subtract_1.md index 2398bc9824f..704aa7818ad 100644 --- a/docs/ops/arithmetic/Subtract_1.md +++ b/docs/ops/arithmetic/Subtract_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Subtract-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Subtract-1* **Category**: *Arithmetic binary* diff --git a/docs/ops/arithmetic/Tan_1.md b/docs/ops/arithmetic/Tan_1.md index d3b8d07f79f..b2f0e1aa3b9 100644 --- a/docs/ops/arithmetic/Tan_1.md +++ b/docs/ops/arithmetic/Tan_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Tan-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Tan-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/arithmetic/Tanh_1.md b/docs/ops/arithmetic/Tanh_1.md index a0e523422fc..8c3cb77b4e8 100644 --- a/docs/ops/arithmetic/Tanh_1.md +++ b/docs/ops/arithmetic/Tanh_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Tanh-1 - an element-wise, arithmetic operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *Tanh-1* **Category**: *Arithmetic unary* diff --git a/docs/ops/broadcast_rules.md b/docs/ops/broadcast_rules.md index b63379f2944..18b241fd3d5 100644 --- a/docs/ops/broadcast_rules.md +++ b/docs/ops/broadcast_rules.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about Numpy and PDPD broadcast types in OpenVINO, that + enable performing element-wise operation for inputs of arbitrary + number of dimensions. + The purpose of this document is to provide a set of common rules which are applicable for ops using broadcasting. Description diff --git a/docs/ops/comparison/Equal_1.md b/docs/ops/comparison/Equal_1.md index fdbee520c5c..d827d7b152b 100644 --- a/docs/ops/comparison/Equal_1.md +++ b/docs/ops/comparison/Equal_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Equal-1 - an element-wise, comparison operation, which + can be performed on two given tensors in OpenVINO. + **Versioned name**: *Equal-1* **Category**: *Comparison binary* diff --git a/docs/ops/comparison/GreaterEqual_1.md b/docs/ops/comparison/GreaterEqual_1.md index e07442eb44f..250f6e8b36f 100644 --- a/docs/ops/comparison/GreaterEqual_1.md +++ b/docs/ops/comparison/GreaterEqual_1.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about GreaterEqual-1 - an element-wise, comparison operation, which + can be performed on two given tensors in OpenVINO. **Versioned name**: *GreaterEqual-1* diff --git a/docs/ops/comparison/Greater_1.md b/docs/ops/comparison/Greater_1.md index 367db99fb55..7089540794c 100644 --- a/docs/ops/comparison/Greater_1.md +++ b/docs/ops/comparison/Greater_1.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about Greater-1 - an element-wise, comparison operation, which + can be performed on two given tensors in OpenVINO. **Versioned name**: *Greater-1* diff --git a/docs/ops/comparison/IsFinite_10.md b/docs/ops/comparison/IsFinite_10.md index c26d92d8bb0..5b4eed0ac8a 100644 --- a/docs/ops/comparison/IsFinite_10.md +++ b/docs/ops/comparison/IsFinite_10.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about IsFinite-10 - an element-wise, comparison operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *IsFinite-10* **Category**: *Comparison* diff --git a/docs/ops/comparison/IsInf_10.md b/docs/ops/comparison/IsInf_10.md index fc0d78fb458..77d148d0255 100644 --- a/docs/ops/comparison/IsInf_10.md +++ b/docs/ops/comparison/IsInf_10.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about IsInf - an element-wise, comparison operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *IsInf-10* **Category**: *Comparison* diff --git a/docs/ops/comparison/IsNaN_10.md b/docs/ops/comparison/IsNaN_10.md index aa2cfd9e1c4..ee2f81ee187 100644 --- a/docs/ops/comparison/IsNaN_10.md +++ b/docs/ops/comparison/IsNaN_10.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about IsNaN-10 - an element-wise, comparison operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *IsNaN-10* **Category**: *Comparison* diff --git a/docs/ops/comparison/LessEqual_1.md b/docs/ops/comparison/LessEqual_1.md index 762007213e5..8af844849c3 100644 --- a/docs/ops/comparison/LessEqual_1.md +++ b/docs/ops/comparison/LessEqual_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about LessEqual-1 - an element-wise, comparison operation, which + can be performed on two given tensors in OpenVINO. + **Versioned name**: *LessEqual-1* **Category**: *Comparison binary* diff --git a/docs/ops/comparison/Less_1.md b/docs/ops/comparison/Less_1.md index e38ad8b4245..183997d6de8 100644 --- a/docs/ops/comparison/Less_1.md +++ b/docs/ops/comparison/Less_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Less-1 - an element-wise, comparison operation, which + can be performed on two given tensors in OpenVINO. + **Versioned name**: *Less-1* **Category**: *Comparison binary* diff --git a/docs/ops/comparison/NotEqual_1.md b/docs/ops/comparison/NotEqual_1.md index 0b6f7b77e17..7ef57f2523f 100644 --- a/docs/ops/comparison/NotEqual_1.md +++ b/docs/ops/comparison/NotEqual_1.md @@ -1,21 +1,29 @@ # NotEqual {#openvino_docs_ops_comparison_NotEqual_1} +@sphinxdirective + +.. meta:: + :description: Learn about LessEqual-1 - an element-wise, comparison operation, which + can be performed on two given tensors in OpenVINO. + **Versioned name**: *NotEqual-1* **Category**: *Comparison binary* **Short description**: *NotEqual* performs element-wise comparison operation with two given tensors applying -multi-directional broadcast rules specified in the `auto_broadcast` attribute. +multi-directional broadcast rules specified in the ``auto_broadcast`` attribute. **Detailed description** + Before performing comparison operation, input tensors *a* and *b* are broadcasted if their shapes are different. -Broadcasting is performed according to `auto_broadcast` value. +Broadcasting is performed according to ``auto_broadcast`` value. After broadcasting, *NotEqual* does the following with the input tensors *a* and *b*: -\f[ -o_{i} = a_{i} != b_{i} -\f] +.. math:: + + o_{i} = a_{i} != b_{i} + **Attributes**: @@ -23,9 +31,11 @@ o_{i} = a_{i} != b_{i} * **Description**: specifies rules used for auto-broadcasting of input tensors. * **Range of values**: + * *none* - no auto-broadcasting is allowed, all input shapes should match - * *numpy* - numpy broadcasting rules, description is available in [Broadcast Rules For Elementwise Operations](../broadcast_rules.md), - * *pdpd* - PaddlePaddle-style implicit broadcasting, description is available in [Broadcast Rules For Elementwise Operations](../broadcast_rules.md). + * *numpy* - numpy broadcasting rules, description is available in :doc:`Broadcast Rules For Elementwise Operations `, + * *pdpd* - PaddlePaddle-style implicit broadcasting, description is available in :doc:`Broadcast Rules For Elementwise Operations `. + * **Type**: string * **Default value**: "numpy" * **Required**: *no* @@ -47,50 +57,55 @@ o_{i} = a_{i} != b_{i} *Example 1* -```xml - - - - 256 - 56 - - - 256 - 56 - - - - - 256 - 56 - - - -``` +.. code-block:: cpp + + + + + 256 + 56 + + + 256 + 56 + + + + + 256 + 56 + + + + *Example 2: broadcast* -```xml - - - - 8 - 1 - 6 - 1 - - - 7 - 1 - 5 - - - - - 8 - 7 - 6 - 5 - - - -``` + +.. code-block:: cpp + + + + + 8 + 1 + 6 + 1 + + + 7 + 1 + 5 + + + + + 8 + 7 + 6 + 5 + + + + + +@endsphinxdirective diff --git a/docs/ops/condition/Bucketize_3.md b/docs/ops/condition/Bucketize_3.md index 6bcec80aceb..e2015fff391 100644 --- a/docs/ops/condition/Bucketize_3.md +++ b/docs/ops/condition/Bucketize_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Bucketize-3 - an element-wise, condition operation, which + can be performed on two given tensors in OpenVINO. + **Versioned name**: *Bucketize-3* **Category**: *Condition* diff --git a/docs/ops/condition/If_8.md b/docs/ops/condition/If_8.md index 378d3beaa9f..6a12fbdfb2e 100644 --- a/docs/ops/condition/If_8.md +++ b/docs/ops/condition/If_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about If-8 - an element-wise, condition operation, which + can be performed on multiple tensors in OpenVINO. + **Versioned name**: *If-8* **Category**: *Condition* diff --git a/docs/ops/condition/NonZero_3.md b/docs/ops/condition/NonZero_3.md index 6ec1e70c0b5..086439f8422 100644 --- a/docs/ops/condition/NonZero_3.md +++ b/docs/ops/condition/NonZero_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about NonZero-3 - an element-wise, condition operation, which + can be performed on a single tensor in OpenVINO. + **Versioned name**: *NonZero-3* **Category**: *Condition* diff --git a/docs/ops/condition/Select_1.md b/docs/ops/condition/Select_1.md index 0fa04a72f60..56297d08dda 100644 --- a/docs/ops/condition/Select_1.md +++ b/docs/ops/condition/Select_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Select-1 - an element-wise, condition operation, which + can be performed on three given tensors in OpenVINO. + **Versioned name**: *Select-1* **Category**: *Condition* diff --git a/docs/ops/convolution/BinaryConvolution_1.md b/docs/ops/convolution/BinaryConvolution_1.md index 5c94d01d739..e248f85ce02 100644 --- a/docs/ops/convolution/BinaryConvolution_1.md +++ b/docs/ops/convolution/BinaryConvolution_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about BinaryConvolution-1 - a 2D convolution operation, which + can be performed on binary input and binary kernel tensors in OpenVINO. + **Versioned name**: *BinaryConvolution-1* **Category**: *Convolution* diff --git a/docs/ops/convolution/ConvolutionBackpropData_1.md b/docs/ops/convolution/ConvolutionBackpropData_1.md index ac612c3a445..c6415372511 100644 --- a/docs/ops/convolution/ConvolutionBackpropData_1.md +++ b/docs/ops/convolution/ConvolutionBackpropData_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ConvolutionBackpropData-1 - a 1D, 2D or 3D convolution operation, which + can be performed on input and kernel tensors in OpenVINO. + **Versioned name**: *ConvolutionBackpropData-1* **Category**: *Convolution* diff --git a/docs/ops/convolution/Convolution_1.md b/docs/ops/convolution/Convolution_1.md index 8fb3554eb73..2203f65e5a7 100644 --- a/docs/ops/convolution/Convolution_1.md +++ b/docs/ops/convolution/Convolution_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Convolution-1 - a 1D, 2D or 3D convolution operation, which + can be performed on input and kernel tensors in OpenVINO. + **Versioned name**: *Convolution-1* **Category**: *Convolution* diff --git a/docs/ops/convolution/DeformableConvolution_1.md b/docs/ops/convolution/DeformableConvolution_1.md index 60f3db73ea9..9ea23519705 100644 --- a/docs/ops/convolution/DeformableConvolution_1.md +++ b/docs/ops/convolution/DeformableConvolution_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about DeformableConvolution-1 - a 2D, deformable, convolution operation, which + can be performed on input and kernel tensors in OpenVINO. + **Versioned name**: *DeformableConvolution-1* **Category**: *Convolution* diff --git a/docs/ops/convolution/DeformableConvolution_8.md b/docs/ops/convolution/DeformableConvolution_8.md index 193e558e6ef..b582dd02257 100644 --- a/docs/ops/convolution/DeformableConvolution_8.md +++ b/docs/ops/convolution/DeformableConvolution_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about DeformableConvolution-1 - a 2D, deformable, convolution operation, which + can be performed on input and kernel tensors in OpenVINO. + **Versioned name**: *DeformableConvolution-8* **Category**: *Convolution* diff --git a/docs/ops/convolution/GroupConvolutionBackpropData_1.md b/docs/ops/convolution/GroupConvolutionBackpropData_1.md index ca92a8221e6..884ee39cef5 100644 --- a/docs/ops/convolution/GroupConvolutionBackpropData_1.md +++ b/docs/ops/convolution/GroupConvolutionBackpropData_1.md @@ -3,6 +3,9 @@ @sphinxdirective +.. meta:: + :description: Learn about GroupConvolutionBackpropData-1 - a 1D, 2D or 3D convolution operation, which + can be performed on input and kernel tensors in OpenVINO. **Versioned name**: *GroupConvolutionBackpropData-1* diff --git a/docs/ops/convolution/GroupConvolution_1.md b/docs/ops/convolution/GroupConvolution_1.md index 3327a57c655..3a2024c96cb 100644 --- a/docs/ops/convolution/GroupConvolution_1.md +++ b/docs/ops/convolution/GroupConvolution_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GroupConvolution-1 - a 1D, 2D or 3D, convolution operation, which + can be performed on input and kernel tensors in OpenVINO. + **Versioned name**: *GroupConvolution-1* **Category**: *Convolution* diff --git a/docs/ops/detection/DeformablePSROIPooling_1.md b/docs/ops/detection/DeformablePSROIPooling_1.md index e3a66677161..e58d4b9b841 100644 --- a/docs/ops/detection/DeformablePSROIPooling_1.md +++ b/docs/ops/detection/DeformablePSROIPooling_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about DeformablePSROIPooling-1 - an object detection operation, which + can be performed on two or three input tensors in OpenVINO. + **Versioned name**: *DeformablePSROIPooling-1* **Category**: *Object detection* diff --git a/docs/ops/detection/DetectionOutput_1.md b/docs/ops/detection/DetectionOutput_1.md index 771c62249dc..9817c6e0633 100644 --- a/docs/ops/detection/DetectionOutput_1.md +++ b/docs/ops/detection/DetectionOutput_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about DetectionOutput-1 - an object detection operation, which + can be performed on three mandatory and two additional input tensors in OpenVINO. + **Versioned name**: *DetectionOutput-1* **Category**: *Object detection* diff --git a/docs/ops/detection/DetectionOutput_8.md b/docs/ops/detection/DetectionOutput_8.md index 8179e507061..891e9e0d500 100644 --- a/docs/ops/detection/DetectionOutput_8.md +++ b/docs/ops/detection/DetectionOutput_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about DetectionOutput-8 - an object detection operation, which + can be performed on three mandatory and two additional tensors in OpenVINO. + **Versioned name**: *DetectionOutput-8* **Category**: *Object detection* diff --git a/docs/ops/detection/ExperimentalDetectronDetectionOutput_6.md b/docs/ops/detection/ExperimentalDetectronDetectionOutput_6.md index cebc9594d61..6e0cf618c03 100644 --- a/docs/ops/detection/ExperimentalDetectronDetectionOutput_6.md +++ b/docs/ops/detection/ExperimentalDetectronDetectionOutput_6.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about ExperimentalDetectronDetectionOutput-6 - an object + detection operation, which can be performed on four required + input tensors in OpenVINO. + **Versioned name**: *ExperimentalDetectronDetectionOutput-6* **Category**: *Object detection* diff --git a/docs/ops/detection/ExperimentalDetectronGenerateProposalsSingleImage_6.md b/docs/ops/detection/ExperimentalDetectronGenerateProposalsSingleImage_6.md index 64c9e5ccca9..6c5364fb743 100644 --- a/docs/ops/detection/ExperimentalDetectronGenerateProposalsSingleImage_6.md +++ b/docs/ops/detection/ExperimentalDetectronGenerateProposalsSingleImage_6.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about ExperimentalDetectronGenerateProposalsSingleImage-6 - + an object detection operation, which can be performed on four + required input tensors. + **Versioned name**: *ExperimentalDetectronGenerateProposalsSingleImage-6* **Category**: *Object detection* diff --git a/docs/ops/detection/ExperimentalDetectronPriorGridGenerator_6.md b/docs/ops/detection/ExperimentalDetectronPriorGridGenerator_6.md index 62ddba5f461..6fd83f7e72f 100644 --- a/docs/ops/detection/ExperimentalDetectronPriorGridGenerator_6.md +++ b/docs/ops/detection/ExperimentalDetectronPriorGridGenerator_6.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about ExperimentalDetectronPriorGridGenerator-6 - + an object detection operation, which can be performed on three + required input tensors. + **Versioned name**: *ExperimentalDetectronPriorGridGenerator-6* **Category**: *Object detection* diff --git a/docs/ops/detection/ExperimentalDetectronROIFeatureExtractor_6.md b/docs/ops/detection/ExperimentalDetectronROIFeatureExtractor_6.md index ad4a10e7e6f..3a5440e0965 100644 --- a/docs/ops/detection/ExperimentalDetectronROIFeatureExtractor_6.md +++ b/docs/ops/detection/ExperimentalDetectronROIFeatureExtractor_6.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about ExperimentalDetectronROIFeatureExtractor-6 - + an object detection operation, which can be performed on two + required input tensors. + **Versioned name**: *ExperimentalDetectronROIFeatureExtractor-6* **Category**: *Object detection* diff --git a/docs/ops/detection/GenerateProposals_9.md b/docs/ops/detection/GenerateProposals_9.md index 650e8720845..b2f3b7fc9b8 100644 --- a/docs/ops/detection/GenerateProposals_9.md +++ b/docs/ops/detection/GenerateProposals_9.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GenerateProposals-9 - an object detection operation, + which can be performed on four required input tensors. + **Versioned name**: *GenerateProposals-9* **Category**: *Object detection* diff --git a/docs/ops/detection/PSROIPooling_1.md b/docs/ops/detection/PSROIPooling_1.md index bfc20c255ed..257316110b6 100644 --- a/docs/ops/detection/PSROIPooling_1.md +++ b/docs/ops/detection/PSROIPooling_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about PSROIPooling-1 - an object detection operation, + which can be performed on two required input tensors. + **Versioned name**: *PSROIPooling-1* **Category**: *Object detection* diff --git a/docs/ops/detection/PriorBoxClustered_1.md b/docs/ops/detection/PriorBoxClustered_1.md index 75dbd7f9b0f..16ecadafc00 100644 --- a/docs/ops/detection/PriorBoxClustered_1.md +++ b/docs/ops/detection/PriorBoxClustered_1.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about PriorBoxClustered-1 - an object detection operation, + which can be performed on two 1D input tensors. **Versioned name**: *PriorBoxClustered-1* diff --git a/docs/ops/detection/PriorBox_1.md b/docs/ops/detection/PriorBox_1.md index f28a92a949b..f554ae24aa8 100644 --- a/docs/ops/detection/PriorBox_1.md +++ b/docs/ops/detection/PriorBox_1.md @@ -3,6 +3,10 @@ @sphinxdirective +.. meta:: + :description: Learn about PriorBox-1 - an object detection operation, + which can be performed on two required input tensors. + **Versioned name**: *PriorBox-1* **Category**: *Object detection* diff --git a/docs/ops/detection/PriorBox_8.md b/docs/ops/detection/PriorBox_8.md index 74f4ec1e4a6..c636954fc33 100644 --- a/docs/ops/detection/PriorBox_8.md +++ b/docs/ops/detection/PriorBox_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about PriorBox-8 - an object detection operation, + which can be performed on two required input tensors. + **Versioned name**: *PriorBox-8* **Category**: *Object detection* diff --git a/docs/ops/detection/Proposal_1.md b/docs/ops/detection/Proposal_1.md index d06794776bb..0c9ed9f5d25 100644 --- a/docs/ops/detection/Proposal_1.md +++ b/docs/ops/detection/Proposal_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Proposal-1 - an object detection operation, + which can be performed on three required input tensors. + **Versioned name**: *Proposal-1* **Category**: *Object detection* diff --git a/docs/ops/detection/Proposal_4.md b/docs/ops/detection/Proposal_4.md index 0b57e4073e2..341b6396a8e 100644 --- a/docs/ops/detection/Proposal_4.md +++ b/docs/ops/detection/Proposal_4.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about Proposal-4 - an object detection operation, + which can be performed on three required input tensors. **Versioned name**: *Proposal-4* diff --git a/docs/ops/detection/ROIAlign_3.md b/docs/ops/detection/ROIAlign_3.md index 8be586978c0..4c33a9786a3 100644 --- a/docs/ops/detection/ROIAlign_3.md +++ b/docs/ops/detection/ROIAlign_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ROIAlign-3 - an object detection operation, + which can be performed on three required input tensors. + **Versioned name**: *ROIAlign-3* **Category**: *Object detection* diff --git a/docs/ops/detection/ROIAlign_9.md b/docs/ops/detection/ROIAlign_9.md index 5cccbbe981e..9f0185c2808 100644 --- a/docs/ops/detection/ROIAlign_9.md +++ b/docs/ops/detection/ROIAlign_9.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about ROIAlign-9 - an object detection operation, + which can be performed on three required input tensors. + + **Versioned name**: *ROIAlign-9* **Category**: *Object detection* diff --git a/docs/ops/detection/ROIPooling_1.md b/docs/ops/detection/ROIPooling_1.md index 3e929633caf..e837a6bb124 100644 --- a/docs/ops/detection/ROIPooling_1.md +++ b/docs/ops/detection/ROIPooling_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ROIPooling-1 - an object detection operation, + which can be performed on two required input tensors. + **Versioned name**: *ROIPooling-1* **Category**: *Object detection* diff --git a/docs/ops/detection/RegionYolo_1.md b/docs/ops/detection/RegionYolo_1.md index 73ea40a5695..70d8c2ab205 100644 --- a/docs/ops/detection/RegionYolo_1.md +++ b/docs/ops/detection/RegionYolo_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about RegionYolo-1 - an object detection operation, + which can be performed on a 4D input tensor. + **Versioned name**: *RegionYolo-1* **Category**: *Object detection* diff --git a/docs/ops/detection/ReorgYolo_1.md b/docs/ops/detection/ReorgYolo_1.md index 064586e6900..4a33916d2f1 100644 --- a/docs/ops/detection/ReorgYolo_1.md +++ b/docs/ops/detection/ReorgYolo_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReorgYolo-1 - an object detection operation, + which can be performed on a 4D input tensor. + **Versioned name**: *ReorgYolo-1* **Category**: *Object detection* diff --git a/docs/ops/generation/Eye_9.md b/docs/ops/generation/Eye_9.md index 7fd6f516fb3..2e6f43aad55 100644 --- a/docs/ops/generation/Eye_9.md +++ b/docs/ops/generation/Eye_9.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Eye-9 - a generation operation, which can be + performed on three required and one optional input tensors. + **Versioned name**: *Eye-9* **Category**: *Generation* diff --git a/docs/ops/generation/RandomUniform_8.md b/docs/ops/generation/RandomUniform_8.md index cb94d35043b..07648fa7d3f 100644 --- a/docs/ops/generation/RandomUniform_8.md +++ b/docs/ops/generation/RandomUniform_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about RandomUniform-8 - a generation operation, which can be + performed on three required input tensors. + **Versioned name**: *RandomUniform-8* **Category**: *Generation* diff --git a/docs/ops/generation/Range_1.md b/docs/ops/generation/Range_1.md index 36a6b3ee3bb..12833c994a3 100644 --- a/docs/ops/generation/Range_1.md +++ b/docs/ops/generation/Range_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Range-1 - a generation operation, which can be + performed on three required input tensors. + **Versioned name**: *Range-1* **Category**: *Generation* diff --git a/docs/ops/generation/Range_4.md b/docs/ops/generation/Range_4.md index 255ba65d9f4..9aedf7af68e 100644 --- a/docs/ops/generation/Range_4.md +++ b/docs/ops/generation/Range_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Range-4 - a generation operation, which can be + performed on three required input tensors. + **Versioned name**: *Range-4* **Category**: *Generation* diff --git a/docs/ops/image/GridSample_9.md b/docs/ops/image/GridSample_9.md index 3ef8e9c190a..b6664e0b05c 100644 --- a/docs/ops/image/GridSample_9.md +++ b/docs/ops/image/GridSample_9.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GridSample-9 - an image processing operation, which + can be performed on two required input tensors. + **Versioned name:** *GridSample-9* **Category:** *Image processing* diff --git a/docs/ops/image/I420toBGR_8.md b/docs/ops/image/I420toBGR_8.md index fe63dd27fbe..c619e0e420a 100644 --- a/docs/ops/image/I420toBGR_8.md +++ b/docs/ops/image/I420toBGR_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about I420toBGR-8 - an image processing operation, which + can be performed to convert image from I420 to BGR format. + **Versioned name**: *I420toBGR-8* **Category**: *Image processing* diff --git a/docs/ops/image/I420toRGB_8.md b/docs/ops/image/I420toRGB_8.md index bf54753d437..8a4d42c9e5c 100644 --- a/docs/ops/image/I420toRGB_8.md +++ b/docs/ops/image/I420toRGB_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about I420toRGB-8 - an image processing operation, which + can be performed to convert image from I420 to RGB format. + **Versioned name**: *I420toRGB-8* **Category**: *Image processing* diff --git a/docs/ops/image/Interpolate_1.md b/docs/ops/image/Interpolate_1.md index 5acecd1648e..59770281846 100644 --- a/docs/ops/image/Interpolate_1.md +++ b/docs/ops/image/Interpolate_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about I420toRGB-8 - an image processing operation, which + can be performed on two required tensors. + **Versioned name**: *Interpolate-1* **Category**: *Image processing* diff --git a/docs/ops/image/Interpolate_11.md b/docs/ops/image/Interpolate_11.md index e86adb4aff9..92585a5c5ef 100644 --- a/docs/ops/image/Interpolate_11.md +++ b/docs/ops/image/Interpolate_11.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Interpolate-11 - an image processing operation, which + can be performed on two required and one optional tensor. + **Versioned name**: *Interpolate-11* **Category**: *Image processing* diff --git a/docs/ops/image/Interpolate_4.md b/docs/ops/image/Interpolate_4.md index eef43ee4751..2fb4a37edb0 100644 --- a/docs/ops/image/Interpolate_4.md +++ b/docs/ops/image/Interpolate_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Interpolate-4 - an image processing operation, which + can be performed on three required and one optional tensor. + **Versioned name**: *Interpolate-4* **Category**: *Image processing* diff --git a/docs/ops/image/NV12toBGR_8.md b/docs/ops/image/NV12toBGR_8.md index 10e7236320d..0c9cf5f2825 100644 --- a/docs/ops/image/NV12toBGR_8.md +++ b/docs/ops/image/NV12toBGR_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about NV12toBGR-8 - an image processing operation, which + can be performed to convert an image from NV12 to BGR format. + **Versioned name**: *NV12toBGR-8* **Category**: *Image processing* diff --git a/docs/ops/image/NV12toRGB_8.md b/docs/ops/image/NV12toRGB_8.md index 6d583cb93c1..3b5c94e6631 100644 --- a/docs/ops/image/NV12toRGB_8.md +++ b/docs/ops/image/NV12toRGB_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about NV12toRGB-8 - an image processing operation, which + can be performed to convert an image from NV12 to RGB format. + **Versioned name**: *NV12toRGB-8* **Category**: *Image processing* diff --git a/docs/ops/infrastructure/Assign_3.md b/docs/ops/infrastructure/Assign_3.md index bb0a5d02660..55b2409494f 100644 --- a/docs/ops/infrastructure/Assign_3.md +++ b/docs/ops/infrastructure/Assign_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Assign-3 - an infrastructure operation, which + can be performed on a single input tensor to set a value to variable_id. + **Versioned name**: *Assign-3* **Category**: *Infrastructure* diff --git a/docs/ops/infrastructure/Constant_1.md b/docs/ops/infrastructure/Constant_1.md index 790cf37b80b..85ff739809e 100644 --- a/docs/ops/infrastructure/Constant_1.md +++ b/docs/ops/infrastructure/Constant_1.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about Constant-1 - an infrastructure operation, which + can be performed to produce a tensor with content read from + binary file by offset and size. + **Versioned name**: *Constant-1* **Category**: *Infrastructure* diff --git a/docs/ops/infrastructure/Loop_5.md b/docs/ops/infrastructure/Loop_5.md index c5921bfc842..6ac4306bf22 100644 --- a/docs/ops/infrastructure/Loop_5.md +++ b/docs/ops/infrastructure/Loop_5.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Loop-5 - an infrastructure operation, which + can be performed on two required and one optional input tensor. + **Versioned name**: *Loop-5* **Category**: *Infrastructure* diff --git a/docs/ops/infrastructure/Parameter_1.md b/docs/ops/infrastructure/Parameter_1.md index 5f7deefb029..57fa733fbaf 100644 --- a/docs/ops/infrastructure/Parameter_1.md +++ b/docs/ops/infrastructure/Parameter_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Parameter-1 - an infrastructure operation, which + can be performed to specify input to the model. + **Versioned name**: *Parameter-1* **Category**: *Infrastructure* diff --git a/docs/ops/infrastructure/ReadValue_3.md b/docs/ops/infrastructure/ReadValue_3.md index de19755b5e1..e2dd6911369 100644 --- a/docs/ops/infrastructure/ReadValue_3.md +++ b/docs/ops/infrastructure/ReadValue_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReadValue-3 - an infrastructure operation, which + can be performed on a single input tensor to return the value of variable_id. + **Versioned name**: *ReadValue-3* **Category**: *Infrastructure* diff --git a/docs/ops/infrastructure/Result_1.md b/docs/ops/infrastructure/Result_1.md index d65eab08419..71050a310c3 100644 --- a/docs/ops/infrastructure/Result_1.md +++ b/docs/ops/infrastructure/Result_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Result-1 - an infrastructure operation, which + can be performed on a single input tensor to specify output of the model. + **Versioned name**: *Result-1* **Category**: *Infrastructure* diff --git a/docs/ops/infrastructure/TensorIterator_1.md b/docs/ops/infrastructure/TensorIterator_1.md index aa23e909652..3ff7c03ecc5 100644 --- a/docs/ops/infrastructure/TensorIterator_1.md +++ b/docs/ops/infrastructure/TensorIterator_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about TensorIterator-1 - an infrastructure operation, which + can be performed on multiple input tensors of any supported type and shape. + **Versioned name**: *TensorIterator-1* **Category**: *Infrastructure* diff --git a/docs/ops/logical/LogicalAnd_1.md b/docs/ops/logical/LogicalAnd_1.md index 780ee06d277..97ebb1f4d44 100644 --- a/docs/ops/logical/LogicalAnd_1.md +++ b/docs/ops/logical/LogicalAnd_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about LogicalAnd-1 - an element-wise, logical binary + operation, which can be performed on two required input tensors. + **Versioned name**: *LogicalAnd-1* **Category**: *Logical binary* diff --git a/docs/ops/logical/LogicalNot_1.md b/docs/ops/logical/LogicalNot_1.md index 989caa42130..e41a0d5b600 100644 --- a/docs/ops/logical/LogicalNot_1.md +++ b/docs/ops/logical/LogicalNot_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about LogicalNot-1 - an element-wise, logical binary + operation, which can be performed on a single input tensor. + **Versioned name**: *LogicalNot-1* **Category**: *Logical unary* diff --git a/docs/ops/logical/LogicalOr_1.md b/docs/ops/logical/LogicalOr_1.md index 30bec35d571..c89985a68da 100644 --- a/docs/ops/logical/LogicalOr_1.md +++ b/docs/ops/logical/LogicalOr_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about LogicalOr-1 - an element-wise, logical binary + operation, which can be performed on two required input tensors. + **Versioned name**: *LogicalOr-1* **Category**: *Logical binary* diff --git a/docs/ops/logical/LogicalXor_1.md b/docs/ops/logical/LogicalXor_1.md index 24c93fb7c7c..139ae64b488 100644 --- a/docs/ops/logical/LogicalXor_1.md +++ b/docs/ops/logical/LogicalXor_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about LogicalXor-1 - an element-wise, logical binary + operation, which can be performed on two required input tensors. + **Versioned name**: *LogicalXor-1* **Category**: *Logical binary* diff --git a/docs/ops/matrix/Einsum_7.md b/docs/ops/matrix/Einsum_7.md index 4955cbe206d..45938a9352d 100644 --- a/docs/ops/matrix/Einsum_7.md +++ b/docs/ops/matrix/Einsum_7.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Einsum-7 - a matrix multiplication operation, + which can be performed on multiple input tensors of different shape. + **Versioned name**: *Einsum-7* **Category**: *Matrix multiplication* diff --git a/docs/ops/matrix/MatMul_1.md b/docs/ops/matrix/MatMul_1.md index 92f00aa758c..0a96ed48b18 100644 --- a/docs/ops/matrix/MatMul_1.md +++ b/docs/ops/matrix/MatMul_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about MatMul-1 - a matrix multiplication operation, + which can be performed on two required input tensors. + **Versioned name**: *MatMul-1* **Category**: *Matrix multiplication* diff --git a/docs/ops/movement/BatchToSpace_2.md b/docs/ops/movement/BatchToSpace_2.md index 68ee6790c32..e1b7408ddfc 100644 --- a/docs/ops/movement/BatchToSpace_2.md +++ b/docs/ops/movement/BatchToSpace_2.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about BatchToSpace-2 - a data movement operation, + which can be performed on four required input tensors. + **Versioned name**: *BatchToSpace-2* **Category**: *Data movement* diff --git a/docs/ops/movement/Broadcast_1.md b/docs/ops/movement/Broadcast_1.md index 6da528b627e..e7d0caaecec 100644 --- a/docs/ops/movement/Broadcast_1.md +++ b/docs/ops/movement/Broadcast_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Broadcast-1 - a data movement operation, + which can be performed on two required and one optional input tensor. + **Versioned name**: *Broadcast-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Broadcast_3.md b/docs/ops/movement/Broadcast_3.md index 0e1a2579a42..ab901ff28a2 100644 --- a/docs/ops/movement/Broadcast_3.md +++ b/docs/ops/movement/Broadcast_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Broadcast-3 - a data movement operation, + which can be performed on two required and one optional input tensor. + **Versioned name**: *Broadcast-3* **Category**: *Data movement* diff --git a/docs/ops/movement/Concat_1.md b/docs/ops/movement/Concat_1.md index cad367213d3..8029e485c83 100644 --- a/docs/ops/movement/Concat_1.md +++ b/docs/ops/movement/Concat_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Concat-1 - a data movement operation, + which can be performed on arbitrary number of input tensors. + **Versioned name**: *Concat-1* **Category**: *Data movement* diff --git a/docs/ops/movement/DepthToSpace_1.md b/docs/ops/movement/DepthToSpace_1.md index d46612a9aec..2d971f0d46a 100644 --- a/docs/ops/movement/DepthToSpace_1.md +++ b/docs/ops/movement/DepthToSpace_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about DepthToSpace-1 - a data movement operation, + which can be performed on a single input tensor. + **Versioned name**: *DepthToSpace-1* **Category**: *Data movement* diff --git a/docs/ops/movement/ExtractImagePatches_3.md b/docs/ops/movement/ExtractImagePatches_3.md index 764f2a6bc71..7a8d3412cdd 100644 --- a/docs/ops/movement/ExtractImagePatches_3.md +++ b/docs/ops/movement/ExtractImagePatches_3.md @@ -1,5 +1,11 @@ # ExtractImagePatches {#openvino_docs_ops_movement_ExtractImagePatches_3} +@sphinxdirective + +.. meta:: + :description: Learn about ExtractImagePatches-3 - a data movement operation, + which can be performed on a 4D input tensor. + **Versioned name**: *ExtractImagePatches-3* **Category**: *Data movement* diff --git a/docs/ops/movement/GatherElements_6.md b/docs/ops/movement/GatherElements_6.md index ee45130fe4f..8957420fe7d 100644 --- a/docs/ops/movement/GatherElements_6.md +++ b/docs/ops/movement/GatherElements_6.md @@ -3,6 +3,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GatherElements-6 - a data movement operation, + which can be performed on two required input tensors. + **Versioned name**: *GatherElements-6* **Category**: *Data movement* diff --git a/docs/ops/movement/GatherND_5.md b/docs/ops/movement/GatherND_5.md index 020b77059f9..e6e9e4ba1fb 100644 --- a/docs/ops/movement/GatherND_5.md +++ b/docs/ops/movement/GatherND_5.md @@ -3,6 +3,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GatherND-5 - a data movement operation, + which can be performed on two required input tensors. + **Versioned name**: *GatherND-5* **Category**: *Data movement* diff --git a/docs/ops/movement/GatherND_8.md b/docs/ops/movement/GatherND_8.md index 6dc0d219242..e383fa9169a 100644 --- a/docs/ops/movement/GatherND_8.md +++ b/docs/ops/movement/GatherND_8.md @@ -3,7 +3,9 @@ @sphinxdirective - +.. meta:: + :description: Learn about GatherND-8 - a data movement operation, + which can be performed on two required input tensors. **Versioned name**: *GatherND-8* diff --git a/docs/ops/movement/GatherTree_1.md b/docs/ops/movement/GatherTree_1.md index d72339520d8..b3660facfdd 100644 --- a/docs/ops/movement/GatherTree_1.md +++ b/docs/ops/movement/GatherTree_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GatherTree-1 - a data movement operation, + which can be performed on four required input tensors. + **Versioned name**: *GatherTree-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Gather_1.md b/docs/ops/movement/Gather_1.md index 3645129f8a0..6fb170e9c92 100644 --- a/docs/ops/movement/Gather_1.md +++ b/docs/ops/movement/Gather_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Gather-1 - a data movement operation, + which can be performed on three required input tensors. + **Versioned name:** *Gather-1* **Category:** *Data movement* diff --git a/docs/ops/movement/Gather_7.md b/docs/ops/movement/Gather_7.md index ee6cda251ea..411079cfb2b 100644 --- a/docs/ops/movement/Gather_7.md +++ b/docs/ops/movement/Gather_7.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Gather-7 - a data movement operation, + which can be performed on three required input tensors. + **Versioned name**: *Gather-7* **Category**: *Data movement* diff --git a/docs/ops/movement/Gather_8.md b/docs/ops/movement/Gather_8.md index bd230242141..346f5c3635d 100644 --- a/docs/ops/movement/Gather_8.md +++ b/docs/ops/movement/Gather_8.md @@ -3,6 +3,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Gather-8 - a data movement operation, + which can be performed on three required input tensors. + **Versioned name**: *Gather-8* **Category**: *Data movement* diff --git a/docs/ops/movement/Pad_1.md b/docs/ops/movement/Pad_1.md index 2faf0423353..ba7a89dfd40 100644 --- a/docs/ops/movement/Pad_1.md +++ b/docs/ops/movement/Pad_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Pad-1 - a data movement operation, + which can be performed on three required and one optional input tensor. + **Versioned name**: *Pad-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Pad_12.md b/docs/ops/movement/Pad_12.md index c9be5b4f06b..647e799b826 100644 --- a/docs/ops/movement/Pad_12.md +++ b/docs/ops/movement/Pad_12.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Pad-12 - a data movement operation, + which can be performed on three required and one optional input tensor. + **Versioned name**: *Pad-12* **Category**: *Data movement* diff --git a/docs/ops/movement/ReverseSequence_1.md b/docs/ops/movement/ReverseSequence_1.md index f048d89b3c0..03389f373d6 100644 --- a/docs/ops/movement/ReverseSequence_1.md +++ b/docs/ops/movement/ReverseSequence_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReverseSequence-1 - a data movement operation, + which can be performed on two required input tensors. + **Versioned name**: *ReverseSequence-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Reverse_1.md b/docs/ops/movement/Reverse_1.md index 5b0fe9b4e3c..442bc8cbc96 100644 --- a/docs/ops/movement/Reverse_1.md +++ b/docs/ops/movement/Reverse_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Reverse-1 - a data movement operation, + which can be performed on one required and one optional input tensor. + **Versioned name**: *Reverse-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Roll_7.md b/docs/ops/movement/Roll_7.md index a6b632775f6..57dc015573c 100644 --- a/docs/ops/movement/Roll_7.md +++ b/docs/ops/movement/Roll_7.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Roll-7 - a data movement operation, which can be + performed on three required input tensors. + **Versioned name**: *Roll-7* **Category**: *Data movement* diff --git a/docs/ops/movement/ScatterElementsUpdate_3.md b/docs/ops/movement/ScatterElementsUpdate_3.md index 66d7eeebcbb..cc93ab4facc 100644 --- a/docs/ops/movement/ScatterElementsUpdate_3.md +++ b/docs/ops/movement/ScatterElementsUpdate_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ScatterElementsUpdate-3 - a data movement operation, which can be + performed on four required input tensors. + **Versioned name**: *ScatterElementsUpdate-3* **Category**: *Data movement* diff --git a/docs/ops/movement/ScatterNDUpdate_3.md b/docs/ops/movement/ScatterNDUpdate_3.md index 6248673c4a7..48a2eb9b1ec 100644 --- a/docs/ops/movement/ScatterNDUpdate_3.md +++ b/docs/ops/movement/ScatterNDUpdate_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ScatterNDUpdate-3 - a data movement operation, which can be + performed on three required input tensors. + **Versioned name**: *ScatterNDUpdate-3* **Category**: *Data movement* diff --git a/docs/ops/movement/ScatterUpdate_3.md b/docs/ops/movement/ScatterUpdate_3.md index 976da815d11..1b4e57700e3 100644 --- a/docs/ops/movement/ScatterUpdate_3.md +++ b/docs/ops/movement/ScatterUpdate_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ScatterUpdate-3 - a data movement operation, which can be + performed on four required input tensors. + **Versioned name**: *ScatterUpdate-3* **Category**: *Data movement* diff --git a/docs/ops/movement/ShuffleChannels_1.md b/docs/ops/movement/ShuffleChannels_1.md index 9201cbb32c3..23c5fa7bd0c 100644 --- a/docs/ops/movement/ShuffleChannels_1.md +++ b/docs/ops/movement/ShuffleChannels_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ShuffleChannels-1 - a data movement operation, + which can be performed on a single input tensor. + **Versioned name**: *ShuffleChannels-1* **Name**: *ShuffleChannels* diff --git a/docs/ops/movement/Slice_8.md b/docs/ops/movement/Slice_8.md index ddb347af1c1..8b093babb33 100644 --- a/docs/ops/movement/Slice_8.md +++ b/docs/ops/movement/Slice_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Slice-8 - a data movement operation, + which can be performed on four required and one optional input tensor. + **Versioned name**: *Slice-8* **Category**: *Data movement* diff --git a/docs/ops/movement/SpaceToBatch_2.md b/docs/ops/movement/SpaceToBatch_2.md index bd05575d149..1abdbecd45a 100644 --- a/docs/ops/movement/SpaceToBatch_2.md +++ b/docs/ops/movement/SpaceToBatch_2.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about SpaceToBatch-2 - a data movement operation, + which can be performed on four required input tensors. + **Versioned name**: *SpaceToBatch-2* **Category**: *Data movement* diff --git a/docs/ops/movement/SpaceToDepth_1.md b/docs/ops/movement/SpaceToDepth_1.md index f20b6187ab0..e0c36f0eb19 100644 --- a/docs/ops/movement/SpaceToDepth_1.md +++ b/docs/ops/movement/SpaceToDepth_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about SpaceToDepth-1 - a data movement operation, + which can be performed on a single input tensor. + **Versioned name**: *SpaceToDepth-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Split_1.md b/docs/ops/movement/Split_1.md index c6895ba15b7..9821155fb3a 100644 --- a/docs/ops/movement/Split_1.md +++ b/docs/ops/movement/Split_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Split-1 - a data movement operation, + which can be performed on two required input tensors. + **Versioned name**: *Split-1* **Category**: *Data movement* diff --git a/docs/ops/movement/StridedSlice_1.md b/docs/ops/movement/StridedSlice_1.md index 57198bd3c75..fc1cec4f25e 100644 --- a/docs/ops/movement/StridedSlice_1.md +++ b/docs/ops/movement/StridedSlice_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about StridedSlice-1 - a data movement operation, + which can be performed on three required and one optional input tensor. + **Versioned name**: *StridedSlice-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Tile_1.md b/docs/ops/movement/Tile_1.md index e4ebfc1fac2..fd661e54251 100644 --- a/docs/ops/movement/Tile_1.md +++ b/docs/ops/movement/Tile_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Tile-1 - a data movement operation, which can be + performed on two required input tensors. + **Versioned name**: *Tile-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Transpose_1.md b/docs/ops/movement/Transpose_1.md index 29598fc75d7..1af2e84ac95 100644 --- a/docs/ops/movement/Transpose_1.md +++ b/docs/ops/movement/Transpose_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Transpose-1 - a data movement operation, which can be + performed on two required input tensors. + **Versioned name**: *Transpose-1* **Category**: *Data movement* diff --git a/docs/ops/movement/Unique_10.md b/docs/ops/movement/Unique_10.md index e45a5e510e0..249daac8fcf 100644 --- a/docs/ops/movement/Unique_10.md +++ b/docs/ops/movement/Unique_10.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Unique-10 - a data movement operation, which can be + performed on one required and one optional input tensor. + **Versioned name**: *Unique-10* **Category**: *Data movement* diff --git a/docs/ops/movement/VariadicSplit_1.md b/docs/ops/movement/VariadicSplit_1.md index afacc61bf44..0479c0b2b52 100644 --- a/docs/ops/movement/VariadicSplit_1.md +++ b/docs/ops/movement/VariadicSplit_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about VariadicSplit-1 - a data movement operation, which can be + performed on three required input tensors. + **Versioned name**: *VariadicSplit-1* **Category**: *Data movement* diff --git a/docs/ops/normalization/BatchNormInference_1.md b/docs/ops/normalization/BatchNormInference_1.md index 16977a84c1b..928d2389842 100644 --- a/docs/ops/normalization/BatchNormInference_1.md +++ b/docs/ops/normalization/BatchNormInference_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about BatchNormInference-5 - a normalization operation, which can be + performed on five required input tensors. + **Versioned name**: *BatchNormInference-5* **Category**: *Normalization* diff --git a/docs/ops/normalization/BatchNormInference_5.md b/docs/ops/normalization/BatchNormInference_5.md index 420da313e5f..aa090de94da 100644 --- a/docs/ops/normalization/BatchNormInference_5.md +++ b/docs/ops/normalization/BatchNormInference_5.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about BatchNormInference-5 - a normalization operation, which can be + performed on five required input tensors. + **Versioned name**: *BatchNormInference-5* **Category**: *Normalization* diff --git a/docs/ops/normalization/GRN_1.md b/docs/ops/normalization/GRN_1.md index 50087a9e3cd..ce6a7724646 100644 --- a/docs/ops/normalization/GRN_1.md +++ b/docs/ops/normalization/GRN_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GRN-1 - a normalization operation, which can be + performed on a single input tensor. + **Versioned name**: *GRN-1* **Category**: *Normalization* diff --git a/docs/ops/normalization/GroupNormalization_12.md b/docs/ops/normalization/GroupNormalization_12.md index 70b1acc712a..f8937ed2c6e 100644 --- a/docs/ops/normalization/GroupNormalization_12.md +++ b/docs/ops/normalization/GroupNormalization_12.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GroupNormalization-12 - a normalization operation, + which can be performed on three required input tensors. + **Versioned name**: *GroupNormalization-12* **Category**: *Normalization* diff --git a/docs/ops/normalization/LRN_1.md b/docs/ops/normalization/LRN_1.md index 7859c3f5427..7d7e34a0a8f 100644 --- a/docs/ops/normalization/LRN_1.md +++ b/docs/ops/normalization/LRN_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about LRN-1 - a normalization operation, which can be + performed on two required input tensors. + **Versioned name**: *LRN-1* **Category**: *Normalization* diff --git a/docs/ops/normalization/MVN_1.md b/docs/ops/normalization/MVN_1.md index 2a9ce4b32fd..6d10bd05e7e 100644 --- a/docs/ops/normalization/MVN_1.md +++ b/docs/ops/normalization/MVN_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about MVN-1 - a normalization operation, which can be + performed on a single input tensor. + **Versioned name**: *MVN-1* **Category**: *Normalization* diff --git a/docs/ops/normalization/MVN_6.md b/docs/ops/normalization/MVN_6.md index 6fc5af574f1..aad5414527e 100644 --- a/docs/ops/normalization/MVN_6.md +++ b/docs/ops/normalization/MVN_6.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about MVN-6 - a normalization operation, which can be + performed on two required input tensors. + **Versioned name**: *MVN-6* **Category**: *Normalization* diff --git a/docs/ops/normalization/NormalizeL2_1.md b/docs/ops/normalization/NormalizeL2_1.md index b98da97cbf2..03a14c204da 100644 --- a/docs/ops/normalization/NormalizeL2_1.md +++ b/docs/ops/normalization/NormalizeL2_1.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn about MVN-1 - a normalization operation, which can be + performed on two required input tensors. **Versioned name**: *NormalizeL2-1* diff --git a/docs/ops/opset.md b/docs/ops/opset.md index b09d2f7919b..d4d582dfa15 100644 --- a/docs/ops/opset.md +++ b/docs/ops/opset.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Check the list of available operation sets fully supported in + specific versions of OpenVINO™ toolkit. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/ops/opset1.md b/docs/ops/opset1.md index a1edf63596f..11093f1b4fb 100644 --- a/docs/ops/opset1.md +++ b/docs/ops/opset1.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset1 operation set, supported in OpenVINO™ + toolkit. + This specification document describes ``opset1`` operation set supported in OpenVINO. Support for each particular operation from the list below depends on the capabilities available in a inference plugin and may vary among different hardware platforms and devices. Examples of operation instances are expressed as IR V10 xml diff --git a/docs/ops/opset10.md b/docs/ops/opset10.md index 52c0740940e..45637ce807b 100644 --- a/docs/ops/opset10.md +++ b/docs/ops/opset10.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset10 operation set, supported in OpenVINO™ + toolkit. + 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 V10 xml diff --git a/docs/ops/opset11.md b/docs/ops/opset11.md index 4033324c64a..467781d048f 100644 --- a/docs/ops/opset11.md +++ b/docs/ops/opset11.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset11 operation set, supported in OpenVINO™ + toolkit. + 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 V10 xml diff --git a/docs/ops/opset12.md b/docs/ops/opset12.md index 6494e920ef0..82bc649643a 100644 --- a/docs/ops/opset12.md +++ b/docs/ops/opset12.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset12 operation set, supported in OpenVINO™ + toolkit. + 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 V10 xml diff --git a/docs/ops/opset2.md b/docs/ops/opset2.md index d4ea13e30b6..dc95dee99f4 100644 --- a/docs/ops/opset2.md +++ b/docs/ops/opset2.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset2 operation set, supported in OpenVINO™ + toolkit. + This specification document describes ``opset2`` operation set supported in OpenVINO. Support for each particular operation from the list below depends on the capabilities available in a inference plugin and may vary among different hardware platforms and devices. Examples of operation instances are expressed as IR V10 xml diff --git a/docs/ops/opset3.md b/docs/ops/opset3.md index 3a5d88cae4f..23937c5b9c7 100644 --- a/docs/ops/opset3.md +++ b/docs/ops/opset3.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset3 operation set, supported in OpenVINO™ + toolkit. + This specification document describes ``opset3`` operation set supported in OpenVINO. Support for each particular operation from the list below depends on the capabilities available in a inference plugin and may vary among different hardware platforms and devices. Examples of operation instances are expressed as IR V10 xml diff --git a/docs/ops/opset4.md b/docs/ops/opset4.md index 71afd847105..4d85ec81535 100644 --- a/docs/ops/opset4.md +++ b/docs/ops/opset4.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset4 operation set, supported in OpenVINO™ + toolkit. + This specification document describes ``opset4`` operation set supported in OpenVINO. Support for each particular operation from the list below depends on the capabilities available in a inference plugin and may vary among different hardware platforms and devices. Examples of operation instances are expressed as IR V10 xml diff --git a/docs/ops/opset5.md b/docs/ops/opset5.md index 9d62afd0d66..2dabaded98c 100644 --- a/docs/ops/opset5.md +++ b/docs/ops/opset5.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset5 operation set, supported in OpenVINO™ + toolkit. + This specification document describes ``opset5`` operation set supported in OpenVINO. Support for each particular operation from the list below depends on the capabilities available in a inference plugin and may vary among different hardware platforms and devices. Examples of operation instances are expressed as IR V10 xml diff --git a/docs/ops/opset6.md b/docs/ops/opset6.md index 8d4f89d9a11..78678533ef2 100644 --- a/docs/ops/opset6.md +++ b/docs/ops/opset6.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset6 operation set, supported in OpenVINO™ + toolkit. + This specification document describes ``opset6`` operation set supported in OpenVINO. Support for each particular operation from the list below depends on the capabilities available in a inference plugin and may vary among different hardware platforms and devices. Examples of operation instances are expressed as IR V10 xml diff --git a/docs/ops/opset7.md b/docs/ops/opset7.md index a57d6aae954..3c25151c490 100644 --- a/docs/ops/opset7.md +++ b/docs/ops/opset7.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset7 operation set, supported in OpenVINO™ + toolkit. + This specification document describes the ``opset7`` operation set supported in OpenVINO™. Support for each particular operation from the list below depends on the capabilities available in an inference plugin and may vary among different hardware platforms and devices. Examples of operation instances are provided as IR V10 xml diff --git a/docs/ops/opset8.md b/docs/ops/opset8.md index 6e5fa39ea24..3aae3426f38 100644 --- a/docs/ops/opset8.md +++ b/docs/ops/opset8.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset8 operation set, supported in OpenVINO™ + toolkit. + 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 V10 xml diff --git a/docs/ops/opset9.md b/docs/ops/opset9.md index 34b132e81eb..667d39a0c40 100644 --- a/docs/ops/opset9.md +++ b/docs/ops/opset9.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Explore the examples of operation instances expressed as IR V10 + XML snippets in the opset9 operation set, supported in OpenVINO™ + toolkit. + 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 V10 xml diff --git a/docs/ops/pooling/AdaptiveAvgPool_8.md b/docs/ops/pooling/AdaptiveAvgPool_8.md index 32e6ee098f3..c4eb41dce65 100644 --- a/docs/ops/pooling/AdaptiveAvgPool_8.md +++ b/docs/ops/pooling/AdaptiveAvgPool_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about AdaptiveAvgPool-8 - a pooling operation, which can + be performed on two required input tensors. + **Versioned name**: *AdaptiveAvgPool-8* **Category**: *Pooling* diff --git a/docs/ops/pooling/AdaptiveMaxPool_8.md b/docs/ops/pooling/AdaptiveMaxPool_8.md index 37e46101f85..87ea96d505d 100644 --- a/docs/ops/pooling/AdaptiveMaxPool_8.md +++ b/docs/ops/pooling/AdaptiveMaxPool_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about AdaptiveMaxPool-8 - a pooling operation, which can + be performed on two required input tensors. + **Versioned name**: *AdaptiveMaxPool-8* **Category**: *Pooling* diff --git a/docs/ops/pooling/AvgPool_1.md b/docs/ops/pooling/AvgPool_1.md index b5c222cc477..07fa577e530 100644 --- a/docs/ops/pooling/AvgPool_1.md +++ b/docs/ops/pooling/AvgPool_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about AvgPool-1 - a pooling operation, which can + be performed on a 3D, 4D or 5D input tensor. + **Versioned name**: *AvgPool-1* **Category**: *Pooling* diff --git a/docs/ops/pooling/MaxPool_1.md b/docs/ops/pooling/MaxPool_1.md index 42a6f801401..c1b2dd05ed3 100644 --- a/docs/ops/pooling/MaxPool_1.md +++ b/docs/ops/pooling/MaxPool_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about MaxPool-1 - a pooling operation, which can + be performed on a 3D, 4D or 5D input tensor. + **Versioned name**: *MaxPool-1* **Category**: *Pooling* diff --git a/docs/ops/pooling/MaxPool_8.md b/docs/ops/pooling/MaxPool_8.md index 7fb3e3b0503..c99b371c0bd 100644 --- a/docs/ops/pooling/MaxPool_8.md +++ b/docs/ops/pooling/MaxPool_8.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about MaxPool-8 - a pooling operation, which can + be performed on a 3D, 4D or 5D input tensor. + **Versioned name**: *MaxPool-8* **Category**: *Pooling* diff --git a/docs/ops/quantization/FakeQuantize_1.md b/docs/ops/quantization/FakeQuantize_1.md index 744f59cae63..e1031b90bc4 100644 --- a/docs/ops/quantization/FakeQuantize_1.md +++ b/docs/ops/quantization/FakeQuantize_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about FakeQuantize-1 - a quantization operation, which can + be performed on five required input tensors. + **Versioned name**: *FakeQuantize-1* **Category**: *Quantization* diff --git a/docs/ops/reduction/ReduceL1_4.md b/docs/ops/reduction/ReduceL1_4.md index 62b2dd71af2..bfa3a4c24be 100644 --- a/docs/ops/reduction/ReduceL1_4.md +++ b/docs/ops/reduction/ReduceL1_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceL1-4 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceL1-4* **Category**: *Reduction* diff --git a/docs/ops/reduction/ReduceL2_4.md b/docs/ops/reduction/ReduceL2_4.md index 0ba23297def..ef15e847df7 100644 --- a/docs/ops/reduction/ReduceL2_4.md +++ b/docs/ops/reduction/ReduceL2_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceL2-4 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceL2-4* **Category**: *Reduction* diff --git a/docs/ops/reduction/ReduceLogicalAnd_1.md b/docs/ops/reduction/ReduceLogicalAnd_1.md index 9ef24b02809..f586a5f80a7 100644 --- a/docs/ops/reduction/ReduceLogicalAnd_1.md +++ b/docs/ops/reduction/ReduceLogicalAnd_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceLogicalAnd-1 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceLogicalAnd-1* **Category**: *Reduction* diff --git a/docs/ops/reduction/ReduceLogicalOr_1.md b/docs/ops/reduction/ReduceLogicalOr_1.md index d5646b79c46..553741ead41 100644 --- a/docs/ops/reduction/ReduceLogicalOr_1.md +++ b/docs/ops/reduction/ReduceLogicalOr_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceLogicalOr-1 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceLogicalOr-1* **Category**: *Reduction* diff --git a/docs/ops/reduction/ReduceMax_1.md b/docs/ops/reduction/ReduceMax_1.md index e4a3e142eba..922bd13b226 100644 --- a/docs/ops/reduction/ReduceMax_1.md +++ b/docs/ops/reduction/ReduceMax_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceMax-1 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceMax-1* **Category**: *Reduction* diff --git a/docs/ops/reduction/ReduceMean_1.md b/docs/ops/reduction/ReduceMean_1.md index bdab4dd0734..57497239958 100644 --- a/docs/ops/reduction/ReduceMean_1.md +++ b/docs/ops/reduction/ReduceMean_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceMean-1 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceMean-1* **Category**: *Reduction* diff --git a/docs/ops/reduction/ReduceMin_1.md b/docs/ops/reduction/ReduceMin_1.md index cfdf005cc75..27347cebdbc 100644 --- a/docs/ops/reduction/ReduceMin_1.md +++ b/docs/ops/reduction/ReduceMin_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceMin-1 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceMin-1* **Category**: *Reduction* diff --git a/docs/ops/reduction/ReduceProd_1.md b/docs/ops/reduction/ReduceProd_1.md index b5e5b77ec11..e06392c12a9 100644 --- a/docs/ops/reduction/ReduceProd_1.md +++ b/docs/ops/reduction/ReduceProd_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceProd-1 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceProd-1* **Category**: *Reduction* diff --git a/docs/ops/reduction/ReduceSum_1.md b/docs/ops/reduction/ReduceSum_1.md index 7a09cebf766..37d94466982 100644 --- a/docs/ops/reduction/ReduceSum_1.md +++ b/docs/ops/reduction/ReduceSum_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ReduceSum-1 - a reduction operation, which can be + performed on two required input tensors. + **Versioned name**: *ReduceSum-1* **Category**: *Reduction* diff --git a/docs/ops/sequence/CTCGreedyDecoderSeqLen_6.md b/docs/ops/sequence/CTCGreedyDecoderSeqLen_6.md index 75c39446d93..455d1989b4b 100644 --- a/docs/ops/sequence/CTCGreedyDecoderSeqLen_6.md +++ b/docs/ops/sequence/CTCGreedyDecoderSeqLen_6.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about CTCGreedyDecoderSeqLen-6 - a sequence processing + operation, which can be performed on two required input tensors. + **Versioned name**: *CTCGreedyDecoderSeqLen-6* **Category**: *Sequence processing* diff --git a/docs/ops/sequence/CTCGreedyDecoder_1.md b/docs/ops/sequence/CTCGreedyDecoder_1.md index 738532bf853..cf5b60d8002 100644 --- a/docs/ops/sequence/CTCGreedyDecoder_1.md +++ b/docs/ops/sequence/CTCGreedyDecoder_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about CTCGreedyDecoder-1 - a sequence processing operation, + which can be performed on two required input tensors. + **Versioned name**: *CTCGreedyDecoder-1* **Category**: *Sequence processing* diff --git a/docs/ops/sequence/CTCLoss_4.md b/docs/ops/sequence/CTCLoss_4.md index fddcbbe1256..0e90bb2ca7b 100644 --- a/docs/ops/sequence/CTCLoss_4.md +++ b/docs/ops/sequence/CTCLoss_4.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about CTCLoss-4 - a sequence processing operation, which + can be performed on four required and one optional input tensor. + **Versioned name**: *CTCLoss-4* **Category**: *Sequence processing* diff --git a/docs/ops/sequence/GRUCell_3.md b/docs/ops/sequence/GRUCell_3.md index 2b3e18e202d..2d6747c9b57 100644 --- a/docs/ops/sequence/GRUCell_3.md +++ b/docs/ops/sequence/GRUCell_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GRUCell-3 - a sequence processing operation, which + can be performed on four required and one optional input tensor. + **Versioned name**: *GRUCell-3* **Category**: *Sequence processing* diff --git a/docs/ops/sequence/GRUSequence_5.md b/docs/ops/sequence/GRUSequence_5.md index d27e7c0ca71..d50028359c6 100644 --- a/docs/ops/sequence/GRUSequence_5.md +++ b/docs/ops/sequence/GRUSequence_5.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about GRUSequence-5 - a sequence processing operation, which + can be performed on six required input tensors. + **Versioned name**: *GRUSequence-5* **Category**: *Sequence processing* diff --git a/docs/ops/sequence/LSTMCell_1.md b/docs/ops/sequence/LSTMCell_1.md index 6573f0256c1..948bab39122 100644 --- a/docs/ops/sequence/LSTMCell_1.md +++ b/docs/ops/sequence/LSTMCell_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about LSTMCell-1 - a sequence processing operation, which + can be performed on five required and one optional input tensor. + **Versioned name**: *LSTMCell-1* **Category**: *Sequence processing* diff --git a/docs/ops/sequence/LSTMSequence_1.md b/docs/ops/sequence/LSTMSequence_1.md index 97290a54693..dda0cd1194f 100644 --- a/docs/ops/sequence/LSTMSequence_1.md +++ b/docs/ops/sequence/LSTMSequence_1.md @@ -1,14 +1,20 @@ # LSTMSequence {#openvino_docs_ops_sequence_LSTMSequence_1} +@sphinxdirective + +.. meta:: + :description: Learn about LSTMSequence-1 - a sequence processing operation, which + can be performed on seven required input tensors. + **Versioned name**: *LSTMSequence-1* **Category**: *Sequence processing* -**Short description**: *LSTMSequence* operation represents a series of LSTM cells. Each cell is implemented as LSTMCell operation. +**Short description**: *LSTMSequence* operation represents a series of LSTM cells. Each cell is implemented as ref:`LSTMCell ` operation. **Detailed description** -A single cell in the sequence is implemented in the same way as in LSTMCell operation. *LSTMSequence* represents a sequence of LSTM cells. The sequence can be connected differently depending on `direction` attribute that specifies the direction of traversing of input data along sequence dimension or specifies whether it should be a bidirectional sequence. The most of the attributes are in sync with the specification of ONNX LSTM operator defined LSTMCell. +A single cell in the sequence is implemented in the same way as in ref:`LSTMCell ` operation. *LSTMSequence* represents a sequence of LSTM cells. The sequence can be connected differently depending on ``direction`` attribute that specifies the direction of traversing of input data along sequence dimension or specifies whether it should be a bidirectional sequence. The most of the attributes are in sync with the specification of ONNX LSTM operator defined `LSTMCell `__ . **Attributes** @@ -17,7 +23,7 @@ A single cell in the sequence is implemented in the same way as in - - - - 1 - 4 - 16 - - - 1 - 1 - 128 - - - 1 - 1 - 128 - - - 1 - - - 1 - 512 - 16 - - - 1 - 512 - 128 - - - 1 - 512 - - - - - 1 - 1 - 4 - 128 - - - 1 - 1 - 128 - - - 1 - 1 - 128 - - - -``` + +.. code-block:: cpp + + + + + + 1 + 4 + 16 + + + 1 + 1 + 128 + + + 1 + 1 + 128 + + + 1 + + + 1 + 512 + 16 + + + 1 + 512 + 128 + + + 1 + 512 + + + + + 1 + 1 + 4 + 128 + + + 1 + 1 + 128 + + + 1 + 1 + 128 + + + + +@endsphinxdirective diff --git a/docs/ops/sequence/OneHot_1.md b/docs/ops/sequence/OneHot_1.md index 3a66901aaa2..d0224f04190 100644 --- a/docs/ops/sequence/OneHot_1.md +++ b/docs/ops/sequence/OneHot_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about OneHot-1 - a sequence processing operation, which + can be performed on four required input tensors. + **Versioned name**: *OneHot-1* **Category**: *Sequence processing* diff --git a/docs/ops/sequence/RNNCell_3.md b/docs/ops/sequence/RNNCell_3.md index 3f22409750a..bf8553df88a 100644 --- a/docs/ops/sequence/RNNCell_3.md +++ b/docs/ops/sequence/RNNCell_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about RNNCell-3 - a sequence processing operation, which + can be performed on five required input tensors. + **Versioned name**: *RNNCell-3* **Category**: *Sequence processing* diff --git a/docs/ops/sequence/RNNSequence_5.md b/docs/ops/sequence/RNNSequence_5.md index c8515fe4bfd..959170d803a 100644 --- a/docs/ops/sequence/RNNSequence_5.md +++ b/docs/ops/sequence/RNNSequence_5.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about RNNSequence-5 - a sequence processing operation, which + can be performed on six required input tensors. + **Versioned name**: *RNNSequence-5* **Category**: *Sequence processing* diff --git a/docs/ops/shape/Reshape_1.md b/docs/ops/shape/Reshape_1.md index 3722034b362..dfa5f70764e 100644 --- a/docs/ops/shape/Reshape_1.md +++ b/docs/ops/shape/Reshape_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Reshape-1 - a shape manipulation operation, which + can be performed on two required input tensors. + **Versioned name**: *Reshape-1* **Category**: *Shape manipulation* diff --git a/docs/ops/shape/ShapeOf_1.md b/docs/ops/shape/ShapeOf_1.md index 611fc69bb36..894f173730d 100644 --- a/docs/ops/shape/ShapeOf_1.md +++ b/docs/ops/shape/ShapeOf_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ShapeOf-1 - a shape manipulation operation, which + can be performed on an arbitrary input tensor. + **Versioned name**: *ShapeOf-1* **Category**: *Shape manipulation* diff --git a/docs/ops/shape/ShapeOf_3.md b/docs/ops/shape/ShapeOf_3.md index f75a39bc7b2..824cc1d66f3 100644 --- a/docs/ops/shape/ShapeOf_3.md +++ b/docs/ops/shape/ShapeOf_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ShapeOf-3 - a shape manipulation operation, which + can be performed on an arbitrary input tensor. + **Versioned name**: *ShapeOf-3* **Category**: *Shape manipulation* diff --git a/docs/ops/shape/Squeeze_1.md b/docs/ops/shape/Squeeze_1.md index 2dd443abbd7..2374e6f2ad2 100644 --- a/docs/ops/shape/Squeeze_1.md +++ b/docs/ops/shape/Squeeze_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Squeeze-1 - a shape manipulation operation, which + can be performed on one required and one optional input tensor. + **Versioned name**: *Squeeze-1* **Category**: *Shape manipulation* diff --git a/docs/ops/shape/Unsqueeze_1.md b/docs/ops/shape/Unsqueeze_1.md index acc88e6c0eb..3142466c50b 100644 --- a/docs/ops/shape/Unsqueeze_1.md +++ b/docs/ops/shape/Unsqueeze_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Unsqueeze-1 - a shape manipulation operation, which + can be performed on two required input tensors. + **Versioned name**: *Unsqueeze-1* **Category**: *Shape manipulation* diff --git a/docs/ops/signals/DFT_7.md b/docs/ops/signals/DFT_7.md index 117d20ec444..6d81260d01c 100644 --- a/docs/ops/signals/DFT_7.md +++ b/docs/ops/signals/DFT_7.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about DFT-7 - a signal processing operation, which can be + performed on two required and one optional input tensor. + **Versioned name**: *DFT-7* **Category**: *Signal processing* diff --git a/docs/ops/signals/IDFT_7.md b/docs/ops/signals/IDFT_7.md index 9d129613b72..e4b4c39ad75 100644 --- a/docs/ops/signals/IDFT_7.md +++ b/docs/ops/signals/IDFT_7.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about IDFT-7 - a signal processing operation, which can be + performed on two required and one optional input tensor. + **Versioned name**: *IDFT-7* **Category**: *Signal processing* diff --git a/docs/ops/signals/IRDFT_9.md b/docs/ops/signals/IRDFT_9.md index f8a715c25ee..d6136f84715 100644 --- a/docs/ops/signals/IRDFT_9.md +++ b/docs/ops/signals/IRDFT_9.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about IRDFT-9 - a signal processing operation, which can be + performed on two required and one optional input tensor. + **Versioned name**: *IRDFT-9* **Category**: *Signal processing* diff --git a/docs/ops/signals/RDFT_9.md b/docs/ops/signals/RDFT_9.md index cb5e7d5be04..be87f5f555e 100644 --- a/docs/ops/signals/RDFT_9.md +++ b/docs/ops/signals/RDFT_9.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about RDFT-9 - a signal processing operation, which can be + performed on two required and one optional input tensor. + **Versioned name**: *RDFT-9* **Category**: *Signal processing* diff --git a/docs/ops/sort/ExperimentalDetectronTopKROIs_6.md b/docs/ops/sort/ExperimentalDetectronTopKROIs_6.md index 3b5e888152b..5c0f0e40999 100644 --- a/docs/ops/sort/ExperimentalDetectronTopKROIs_6.md +++ b/docs/ops/sort/ExperimentalDetectronTopKROIs_6.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about ExperimentalDetectronTopKROIs-6 - a sorting and + maximization operation, which can be performed on two required + input tensors. + **Versioned name**: *ExperimentalDetectronTopKROIs-6* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/MatrixNMS_8.md b/docs/ops/sort/MatrixNMS_8.md index f6ccfaca65f..d5e1751ee9e 100644 --- a/docs/ops/sort/MatrixNMS_8.md +++ b/docs/ops/sort/MatrixNMS_8.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about MatrixNonMaxSuppression-8 - a sorting and + maximization operation, which can be performed on two required + input tensors. + **Versioned name**: *MatrixNonMaxSuppression-8* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/MulticlassNonMaxSuppression_8.md b/docs/ops/sort/MulticlassNonMaxSuppression_8.md index 3d8de44815e..d1493044171 100644 --- a/docs/ops/sort/MulticlassNonMaxSuppression_8.md +++ b/docs/ops/sort/MulticlassNonMaxSuppression_8.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about MulticlassNonMaxSuppression-8 - a sorting and + maximization operation, which can be performed on two required + input tensors. + **Versioned name**: *MulticlassNonMaxSuppression-8* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/MulticlassNonMaxSuppression_9.md b/docs/ops/sort/MulticlassNonMaxSuppression_9.md index 0942ef8caa6..37c1c7d2984 100644 --- a/docs/ops/sort/MulticlassNonMaxSuppression_9.md +++ b/docs/ops/sort/MulticlassNonMaxSuppression_9.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about MulticlassNonMaxSuppression-8 - a sorting and + maximization operation, which can be performed on two or three + required input tensors. + **Versioned name**: *MulticlassNonMaxSuppression-9* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/NonMaxSuppression_1.md b/docs/ops/sort/NonMaxSuppression_1.md index f5cfa798770..0c7cd2d7459 100644 --- a/docs/ops/sort/NonMaxSuppression_1.md +++ b/docs/ops/sort/NonMaxSuppression_1.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about NonMaxSuppression-1 - a sorting and maximization + operation, which can be performed on two required and three + optional input tensors. + **Versioned name**: *NonMaxSuppression-1* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/NonMaxSuppression_3.md b/docs/ops/sort/NonMaxSuppression_3.md index f22470e9514..668b7d6f99d 100644 --- a/docs/ops/sort/NonMaxSuppression_3.md +++ b/docs/ops/sort/NonMaxSuppression_3.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about NonMaxSuppression-3 - a sorting and maximization + operation, which can be performed on two required and three + optional input tensors. + **Versioned name**: *NonMaxSuppression-3* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/NonMaxSuppression_4.md b/docs/ops/sort/NonMaxSuppression_4.md index b4bc2a42f0f..0b2027f8412 100644 --- a/docs/ops/sort/NonMaxSuppression_4.md +++ b/docs/ops/sort/NonMaxSuppression_4.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about NonMaxSuppression-4 - a sorting and maximization + operation, which can be performed on two required and three + optional input tensors. + **Versioned name**: *NonMaxSuppression-4* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/NonMaxSuppression_5.md b/docs/ops/sort/NonMaxSuppression_5.md index 4295ce8564c..e5c6da985a2 100644 --- a/docs/ops/sort/NonMaxSuppression_5.md +++ b/docs/ops/sort/NonMaxSuppression_5.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about NonMaxSuppression-5 - a sorting and maximization + operation, which can be performed on two required and four + optional input tensors. + **Versioned name**: *NonMaxSuppression-5* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/NonMaxSuppression_9.md b/docs/ops/sort/NonMaxSuppression_9.md index 131ef2fe4d3..83cd6291e8d 100644 --- a/docs/ops/sort/NonMaxSuppression_9.md +++ b/docs/ops/sort/NonMaxSuppression_9.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about NonMaxSuppression-9 - a sorting and maximization + operation, which can be performed on two required and four + optional input tensors. + **Versioned name**: *NonMaxSuppression-9* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/TopK_1.md b/docs/ops/sort/TopK_1.md index 31b757f32fc..df8b68f4c11 100644 --- a/docs/ops/sort/TopK_1.md +++ b/docs/ops/sort/TopK_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about TopK-1 - a sorting and maximization operation, which + can be performed on one required and on optional input tensor. + **Versioned name**: *TopK-1* **Category**: *Sorting and maximization* diff --git a/docs/ops/sort/TopK_11.md b/docs/ops/sort/TopK_11.md index 449d78575d1..c19a66ebdd6 100644 --- a/docs/ops/sort/TopK_11.md +++ b/docs/ops/sort/TopK_11.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about TopK-11 - a sorting and maximization operation, + which can be performed on two required input tensors. + **Versioned name**: *TopK-11* **Category**: *sorting and maximization* diff --git a/docs/ops/sort/TopK_3.md b/docs/ops/sort/TopK_3.md index 5dca71e9084..dea09f84ea4 100644 --- a/docs/ops/sort/TopK_3.md +++ b/docs/ops/sort/TopK_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about TopK-3 - a sorting and maximization operation, + which can be performed on two required input tensors. + **Versioned name**: *TopK-3* **Category**: *Sorting and maximization* diff --git a/docs/ops/sparse/EmbeddingBagOffsetsSum_3.md b/docs/ops/sparse/EmbeddingBagOffsetsSum_3.md index 719fb2e4483..db6d48321e2 100644 --- a/docs/ops/sparse/EmbeddingBagOffsetsSum_3.md +++ b/docs/ops/sparse/EmbeddingBagOffsetsSum_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about EmbeddingBagOffsetsSum-3 - a sparse operation, which + can be performed on three required and two optional input tensors. + **Versioned name**: *EmbeddingBagOffsetsSum-3* **Category**: *Sparse* diff --git a/docs/ops/sparse/EmbeddingBagPackedSum_3.md b/docs/ops/sparse/EmbeddingBagPackedSum_3.md index 4906c1d10ea..7e91ccced05 100644 --- a/docs/ops/sparse/EmbeddingBagPackedSum_3.md +++ b/docs/ops/sparse/EmbeddingBagPackedSum_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about EmbeddingBagPackedSum-3 - a sparse operation, which + can be performed on two required and one optional input tensor. + **Versioned name**: *EmbeddingBagPackedSum-3* **Category**: *Sparse* diff --git a/docs/ops/sparse/EmbeddingSegmentsSum_3.md b/docs/ops/sparse/EmbeddingSegmentsSum_3.md index 54d6ccdce74..ea584e71d94 100644 --- a/docs/ops/sparse/EmbeddingSegmentsSum_3.md +++ b/docs/ops/sparse/EmbeddingSegmentsSum_3.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about EmbeddingSegmentsSum-3 - a sparse operation, which + can be performed on four required and two optional input tensors. + **Versioned name**: *EmbeddingSegmentsSum-3* **Category**: *Sparse* diff --git a/docs/ops/type/ConvertLike_1.md b/docs/ops/type/ConvertLike_1.md index a08947e09a0..88209deefb0 100644 --- a/docs/ops/type/ConvertLike_1.md +++ b/docs/ops/type/ConvertLike_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about ConvertLike-1 - an element-wise, type conversion + operation, which can be performed two required input tensors. + **Versioned name**: *ConvertLike-1* **Category**: *Type conversion* diff --git a/docs/ops/type/Convert_1.md b/docs/ops/type/Convert_1.md index 90b5deb968b..1b6c95b7a1c 100644 --- a/docs/ops/type/Convert_1.md +++ b/docs/ops/type/Convert_1.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn about Convert-1 - an element-wise, type conversion + operation, which can be performed on a single input tensor. + **Versioned name**: *Convert-1* **Category**: *Type conversion* diff --git a/docs/optimization_guide/dldt_deployment_optimization_common.md b/docs/optimization_guide/dldt_deployment_optimization_common.md index 3430a516d0c..be565df61b6 100644 --- a/docs/optimization_guide/dldt_deployment_optimization_common.md +++ b/docs/optimization_guide/dldt_deployment_optimization_common.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: General optimizations include application-level optimization + methods that improve data pipelining, pre-processing + acceleration and both latency and throughput. + + This article covers application-level optimization techniques, such as asynchronous execution, to improve data pipelining, pre-processing acceleration and so on. While the techniques (e.g. pre-processing) can be specific to end-user applications, the associated performance improvements are general and shall improve any target scenario -- both latency and throughput. diff --git a/docs/optimization_guide/dldt_deployment_optimization_guide.md b/docs/optimization_guide/dldt_deployment_optimization_guide.md index 4bb9cf3c9ff..e3167eb93de 100644 --- a/docs/optimization_guide/dldt_deployment_optimization_guide.md +++ b/docs/optimization_guide/dldt_deployment_optimization_guide.md @@ -16,6 +16,11 @@ openvino_docs_deployment_optimization_guide_internals openvino_docs_memory_optimization_guide +.. meta:: + :description: Improving inference performance involves model and runtime + optimizations that can be done independently. Inference + speed depends on latency and throughput. + Runtime optimization, or deployment optimization, focuses on tuning inference parameters and execution means (e.g., the optimum number of requests executed simultaneously). Unlike model-level optimizations, they are highly specific to the hardware and case they are used for, and often come at a cost. `ov::hint::inference_precision `__ is a "typical runtime configuration" which trades accuracy for performance, allowing ``fp16/bf16`` execution for the layers that remain in ``fp32`` after quantization of the original ``fp32`` model. diff --git a/docs/optimization_guide/dldt_deployment_optimization_internals.md b/docs/optimization_guide/dldt_deployment_optimization_internals.md index ab596e49c98..cd65df349c2 100644 --- a/docs/optimization_guide/dldt_deployment_optimization_internals.md +++ b/docs/optimization_guide/dldt_deployment_optimization_internals.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Automatic Batching moves asynchronicity from individual + requests to groups of requests, and the CPU streams are + inference threads grouped by CPU cores. + + Throughput on the CPU: Internals ################################ diff --git a/docs/optimization_guide/dldt_deployment_optimization_latency.md b/docs/optimization_guide/dldt_deployment_optimization_latency.md index a8702a539e2..3a09d41ac39 100644 --- a/docs/optimization_guide/dldt_deployment_optimization_latency.md +++ b/docs/optimization_guide/dldt_deployment_optimization_latency.md @@ -8,6 +8,10 @@ openvino_docs_OV_UG_Model_caching_overview +.. meta:: + :description: OpenVINO provides methods that help to preserve minimal + latency despite the number of inference requests and + improve throughput without degrading latency. A significant portion of deep learning use cases involve applications loading a single model and using a single input at a time, which is the of typical "consumer" scenario. diff --git a/docs/optimization_guide/dldt_deployment_optimization_tput.md b/docs/optimization_guide/dldt_deployment_optimization_tput.md index b2c796bea01..2bc174148da 100644 --- a/docs/optimization_guide/dldt_deployment_optimization_tput.md +++ b/docs/optimization_guide/dldt_deployment_optimization_tput.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Throughput-oriented approaches in OpenVINO involve + execution of a large number of inference requests + simultaneously which improves the device utilization. + + As described in the section on the :doc:`latency-specific considerations `, one of the possible use cases is *delivering every single request at the minimal delay*. Throughput, on the other hand, is about inference scenarios in which potentially **large number of inference requests are served simultaneously to improve the device utilization**. diff --git a/docs/optimization_guide/dldt_deployment_optimization_tput_advanced.md b/docs/optimization_guide/dldt_deployment_optimization_tput_advanced.md index 48a2f70b65a..eb4e1cd4e41 100644 --- a/docs/optimization_guide/dldt_deployment_optimization_tput_advanced.md +++ b/docs/optimization_guide/dldt_deployment_optimization_tput_advanced.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: With OpenVINO streams a device may handle processing multiple + inference requests and the batching helps to saturate the + device and leads to higher throughput. + + OpenVINO Streams #################### diff --git a/docs/ovsa/ovsa_get_started.md b/docs/ovsa/ovsa_get_started.md index 7119708b23f..e7e47da386a 100644 --- a/docs/ovsa/ovsa_get_started.md +++ b/docs/ovsa/ovsa_get_started.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to setup hardware and virtual machines to use the OpenVINO™ Security Add-on to access and run access controlled models. + + This guide provides instructions for people who use the OpenVINO™ Security Add-on to create, distribute, and use models that are created with the OpenVINO™ toolkit: * **Model Developer**: The Model Developer interacts with the Independent Software Vendor to control the User access to models. This document shows you how to setup hardware and virtual machines to use the OpenVINO™ Security Add-on to define access control to your OpenVINO™ models and then provide the access controlled models to the users. diff --git a/docs/resources/Supported_Devices.md b/docs/resources/Supported_Devices.md index 8c088fe5c8d..3deb707af39 100644 --- a/docs/resources/Supported_Devices.md +++ b/docs/resources/Supported_Devices.md @@ -3,6 +3,10 @@ @sphinxdirective +.. meta:: + :description: Check the list of officially supported models in Intel® + Distribution of OpenVINO™ toolkit. + The OpenVINO runtime can infer various models of different input and output formats. Here, you can find configurations supported by OpenVINO devices, which are CPU, GPU, and GNA (Gaussian Neural Accelerator coprocessor). diff --git a/docs/resources/openvino_ir.md b/docs/resources/openvino_ir.md index 6418ba07639..a9595eac3c8 100644 --- a/docs/resources/openvino_ir.md +++ b/docs/resources/openvino_ir.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: OpenVINO IR, known as Intermediate Representation, is the result + of model conversion in OpenVINO and is represented by two files: + an XML and a binary file. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/resources/prerelease_information.md b/docs/resources/prerelease_information.md index e706f456b35..c9df5aa8a27 100644 --- a/docs/resources/prerelease_information.md +++ b/docs/resources/prerelease_information.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Check the pre-release information that includes a general + changelog for each version of OpenVINO Toolkit published under + the current cycle. + To ensure you can test OpenVINO's upcoming features even before they are officially released, OpenVINO developers continue to roll out pre-release software. On this page you can find a general changelog for each version published under the current cycle. diff --git a/docs/resources/resources.md b/docs/resources/resources.md index bc660ab6ce4..bc4a8240875 100644 --- a/docs/resources/resources.md +++ b/docs/resources/resources.md @@ -3,6 +3,10 @@ @sphinxdirective +.. meta:: + :description: Learn more about OpenVINO from benchmark results, case studies + and lists of supported models, operations and devices. + .. toctree:: :maxdepth: 1 :hidden: diff --git a/docs/resources/supported_models.md b/docs/resources/supported_models.md index f79bf818b15..ccb7771ee7a 100644 --- a/docs/resources/supported_models.md +++ b/docs/resources/supported_models.md @@ -2,6 +2,12 @@ @sphinxdirective + +.. meta:: + :description: Check the list of officially supported models in Intel® + Distribution of OpenVINO™ toolkit. + + The OpenVINO team continues the effort to support as many models out-of-the-box as possible. Based on our research and user feedback, we prioritize the most common models and test them before every release. These models are considered officially supported. diff --git a/docs/resources/supported_operations_framework_frontend.md b/docs/resources/supported_operations_framework_frontend.md index 72f7cdff200..f9ddceff3c9 100644 --- a/docs/resources/supported_operations_framework_frontend.md +++ b/docs/resources/supported_operations_framework_frontend.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Check the list of operations supported by OpenVINO Framework Frontend. + + This page lists operations supported by OpenVINO Framework Frontend. diff --git a/docs/resources/telemetry_information.md b/docs/resources/telemetry_information.md index 5126455dc32..4340a409237 100644 --- a/docs/resources/telemetry_information.md +++ b/docs/resources/telemetry_information.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn about OpenVINO™ telemetry, that with your explicit consent + collects only usage data to simplify debugging and further development. + + To facilitate debugging and further development, OpenVINO™ asks its users for a permission to collect telemetry data. It will not be collected without an explicit consent on your part and will cover only OpenVINO™ usage information. diff --git a/docs/resources/tensorflow_frontend.md b/docs/resources/tensorflow_frontend.md index 8342cf82ab4..06697e18692 100644 --- a/docs/resources/tensorflow_frontend.md +++ b/docs/resources/tensorflow_frontend.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: TensorFlow Frontend in OpenVINO Runtime is a C++ based frontend used + by default for converting TensorFlow models to Intermediate Representation (IR). + + TensorFlow Frontend is a C++ based Frontend for converting TensorFlow models. MO now uses the TensorFlow Frontend as the default path for conversion to IR. Also, the frontend allows loading TensorFlow models in SavedModel, MetaGraph, and frozen Protobuf formats directly via the ``read_model()`` method. diff --git a/docs/tuning_utilities.md b/docs/tuning_utilities.md index 57d7e87e16d..c9da800441b 100644 --- a/docs/tuning_utilities.md +++ b/docs/tuning_utilities.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Get to know Accuracy Checker - a deep learning accuracy validation framework and other tuning utilities found in OpenVINO™ toolkit. + .. toctree:: :maxdepth: 1 :caption: Tuning Utilities diff --git a/docs/tutorials.md b/docs/tutorials.md index 64b40fecd60..5784f5c4acf 100644 --- a/docs/tutorials.md +++ b/docs/tutorials.md @@ -5,14 +5,9 @@ .. _notebook tutorials: .. meta:: - :description: A collection of Python tutorials run on Jupyter notebooks. The - tutorials explain how to use OpenVINO™ toolkit for optimized + :description: Run Python tutorials on Jupyter notebooks to learn how to use OpenVINO™ toolkit for optimized deep learning inference. - :keywords: OpenVINO™ toolkit, Jupyter, Jupyter notebooks, tutorials, Python - API, Python, deep learning, inference, model inference, infer a - model, Binder, object detection, quantization, image - classification, speech recognition, OCR, OpenVINO IR, deep - learning model, AI, neural networks + .. toctree:: :maxdepth: 2 diff --git a/samples/c/hello_classification/README.md b/samples/c/hello_classification/README.md index eff1db7de4a..01b2a3512d9 100644 --- a/samples/c/hello_classification/README.md +++ b/samples/c/hello_classification/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of image + classification models, such as alexnet and googlenet-v1, using + Synchronous Inference Request (C) API. + + This sample demonstrates how to execute an inference of image classification networks like AlexNet and GoogLeNet using Synchronous Inference Request API and input auto-resize feature. Hello Classification C sample application demonstrates how to use the C API from OpenVINO in applications. diff --git a/samples/c/hello_nv12_input_classification/README.md b/samples/c/hello_nv12_input_classification/README.md index ebe6509e943..c27625115e6 100644 --- a/samples/c/hello_nv12_input_classification/README.md +++ b/samples/c/hello_nv12_input_classification/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of an image + classification model with images in NV12 color format using + Synchronous Inference Request (C) API. + + This sample demonstrates how to execute an inference of image classification networks like AlexNet with images in NV12 color format using Synchronous Inference Request API. Hello NV12 Input Classification C Sample demonstrates how to use the NV12 automatic input pre-processing API in your applications: diff --git a/samples/cpp/benchmark/sync_benchmark/README.md b/samples/cpp/benchmark/sync_benchmark/README.md index 1065fe29a54..e260bf271fe 100644 --- a/samples/cpp/benchmark/sync_benchmark/README.md +++ b/samples/cpp/benchmark/sync_benchmark/README.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn how to estimate performance of a model using Synchronous Inference Request (C++) API. + This sample demonstrates how to estimate performance of a model using Synchronous Inference Request API. It makes sense to use synchronous inference only in latency oriented scenarios. Models with static input shapes are supported. Unlike :doc:`demos ` this sample doesn't have other configurable command line arguments. Feel free to modify sample's source code to try out different options. The following C++ API is used in the application: diff --git a/samples/cpp/benchmark/throughput_benchmark/README.md b/samples/cpp/benchmark/throughput_benchmark/README.md index a07ead3e23f..444e053790a 100644 --- a/samples/cpp/benchmark/throughput_benchmark/README.md +++ b/samples/cpp/benchmark/throughput_benchmark/README.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to estimate performance of a model using Asynchronous Inference Request (C++) API in throughput mode. + + This sample demonstrates how to estimate performance of a model using Asynchronous Inference Request API in throughput mode. Unlike :doc:`demos ` this sample doesn't have other configurable command line arguments. Feel free to modify sample's source code to try out different options. The reported results may deviate from what :doc:`benchmark_app ` reports. One example is model input precision for computer vision tasks. benchmark_app sets ``uint8``, while the sample uses default model precision which is usually ``float32``. diff --git a/samples/cpp/benchmark_app/README.md b/samples/cpp/benchmark_app/README.md index ea35571774f..4a2a877de45 100644 --- a/samples/cpp/benchmark_app/README.md +++ b/samples/cpp/benchmark_app/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to use the Benchmark C++ Tool to + estimate deep learning inference performance on supported + devices. + + This page demonstrates how to use the Benchmark C++ Tool to estimate deep learning inference performance on supported devices. .. note:: diff --git a/samples/cpp/classification_sample_async/README.md b/samples/cpp/classification_sample_async/README.md index ec904aa9559..b089090fbe1 100644 --- a/samples/cpp/classification_sample_async/README.md +++ b/samples/cpp/classification_sample_async/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of image + classification models using Asynchronous Inference Request + (C++) API. + + This sample demonstrates how to do inference of image classification models using Asynchronous Inference Request API. Models with only one input and output are supported. diff --git a/samples/cpp/hello_classification/README.md b/samples/cpp/hello_classification/README.md index fda6c76319f..8eb7142aee0 100644 --- a/samples/cpp/hello_classification/README.md +++ b/samples/cpp/hello_classification/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of image + classification models using Synchronous Inference Request + (C++) API. + + This sample demonstrates how to do inference of image classification models using Synchronous Inference Request API. Models with only one input and output are supported. diff --git a/samples/cpp/hello_nv12_input_classification/README.md b/samples/cpp/hello_nv12_input_classification/README.md index c91baf04c08..31fb2820650 100644 --- a/samples/cpp/hello_nv12_input_classification/README.md +++ b/samples/cpp/hello_nv12_input_classification/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of image + classification models with images in NV12 color format using + Synchronous Inference Request (C++) API. + + This sample demonstrates how to execute an inference of image classification models with images in NV12 color format using Synchronous Inference Request API. The following C++ API is used in the application: diff --git a/samples/cpp/hello_query_device/README.md b/samples/cpp/hello_query_device/README.md index fee753ac1e4..8a83a272332 100644 --- a/samples/cpp/hello_query_device/README.md +++ b/samples/cpp/hello_query_device/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to show metrics and default + configuration values of inference devices using Query + Device (C++) API feature. + + This sample demonstrates how to execute an query OpenVINO™ Runtime devices, prints their metrics and default configuration values, using :doc:`Properties API `. The following C++ API is used in the application: diff --git a/samples/cpp/hello_reshape_ssd/README.md b/samples/cpp/hello_reshape_ssd/README.md index 4e2d7d10ad1..f3776717f5a 100644 --- a/samples/cpp/hello_reshape_ssd/README.md +++ b/samples/cpp/hello_reshape_ssd/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of object + detection models using shape inference feature and Synchronous + Inference Request (C++) API. + + This sample demonstrates how to do synchronous inference of object detection models using :doc:`input reshape feature `. Models with only one input and output are supported. diff --git a/samples/cpp/model_creation_sample/README.md b/samples/cpp/model_creation_sample/README.md index 1c5cdba3d4c..7d0acb80e2a 100644 --- a/samples/cpp/model_creation_sample/README.md +++ b/samples/cpp/model_creation_sample/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to create a model on the fly with a + provided weights file and infer it later using Synchronous + Inference Request (C++) API. + + This sample demonstrates how to execute an synchronous inference using :doc:`model ` built on the fly which uses weights from LeNet classification model, which is known to work well on digit classification tasks. You do not need an XML file to create a model. The API of ov::Model allows creating a model on the fly from the source code. diff --git a/samples/cpp/speech_sample/README.md b/samples/cpp/speech_sample/README.md index 16911cee379..4b3b8a55b40 100644 --- a/samples/cpp/speech_sample/README.md +++ b/samples/cpp/speech_sample/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to infer an acoustic model based on Kaldi + neural networks and speech feature vectors using Asynchronous + Inference Request (C++) API. + + This sample demonstrates how to execute an Asynchronous Inference of acoustic model based on Kaldi\* neural networks and speech feature vectors. The sample works with Kaldi ARK or Numpy* uncompressed NPZ files, so it does not cover an end-to-end speech recognition scenario (speech to text), requiring additional preprocessing (feature extraction) to get a feature vector from a speech signal, as well as postprocessing (decoding) to produce text from scores. diff --git a/samples/python/benchmark/bert_benchmark/README.md b/samples/python/benchmark/bert_benchmark/README.md index 7591b0d8b71..e88ec1bd7d1 100644 --- a/samples/python/benchmark/bert_benchmark/README.md +++ b/samples/python/benchmark/bert_benchmark/README.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to estimate performance of a Bert model using Asynchronous Inference Request (Python) API. + + This sample demonstrates how to estimate performance of a Bert model using Asynchronous Inference Request API. Unlike :doc:`demos ` this sample doesn't have configurable command line arguments. Feel free to modify sample's source code to try out different options. The following Python API is used in the application: diff --git a/samples/python/benchmark/sync_benchmark/README.md b/samples/python/benchmark/sync_benchmark/README.md index 3593e529371..aa7d810bf85 100644 --- a/samples/python/benchmark/sync_benchmark/README.md +++ b/samples/python/benchmark/sync_benchmark/README.md @@ -2,6 +2,10 @@ @sphinxdirective +.. meta:: + :description: Learn how to estimate performance of a model using Synchronous Inference Request (Python) API. + + This sample demonstrates how to estimate performance of a model using Synchronous Inference Request API. It makes sense to use synchronous inference only in latency oriented scenarios. Models with static input shapes are supported. Unlike :doc:`demos ` this sample doesn't have other configurable command line arguments. Feel free to modify sample's source code to try out different options. The following Python API is used in the application: diff --git a/samples/python/benchmark/throughput_benchmark/README.md b/samples/python/benchmark/throughput_benchmark/README.md index d43cf6024d9..df129f6ef4c 100644 --- a/samples/python/benchmark/throughput_benchmark/README.md +++ b/samples/python/benchmark/throughput_benchmark/README.md @@ -2,6 +2,9 @@ @sphinxdirective +.. meta:: + :description: Learn how to estimate performance of a model using Asynchronous Inference Request (Python) API in throughput mode. + This sample demonstrates how to estimate performance of a model using Asynchronous Inference Request API in throughput mode. Unlike :doc:`demos ` this sample doesn't have other configurable command line arguments. Feel free to modify sample's source code to try out different options. diff --git a/samples/python/classification_sample_async/README.md b/samples/python/classification_sample_async/README.md index 47b3c728c58..85742e2dfa8 100644 --- a/samples/python/classification_sample_async/README.md +++ b/samples/python/classification_sample_async/README.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of image classification models + using Asynchronous Inference Request (Python) API. + + This sample demonstrates how to do inference of image classification models using Asynchronous Inference Request API. Models with only 1 input and output are supported. diff --git a/samples/python/hello_classification/README.md b/samples/python/hello_classification/README.md index bbcee3dfcf6..02f530ac25b 100644 --- a/samples/python/hello_classification/README.md +++ b/samples/python/hello_classification/README.md @@ -2,6 +2,11 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of image classification + models using Synchronous Inference Request (Python) API. + + This sample demonstrates how to do inference of image classification models using Synchronous Inference Request API. Models with only 1 input and output are supported. diff --git a/samples/python/hello_query_device/README.md b/samples/python/hello_query_device/README.md index 3ad65fd8af0..39ba45bcc16 100644 --- a/samples/python/hello_query_device/README.md +++ b/samples/python/hello_query_device/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to show metrics and default + configuration values of inference devices using Query + Device (Python) API feature. + + This sample demonstrates how to show OpenVINO™ Runtime devices and prints their metrics and default configuration values using :doc:`Query Device API feature `. The following Python API is used in the application: diff --git a/samples/python/hello_reshape_ssd/README.md b/samples/python/hello_reshape_ssd/README.md index 2664e3bce69..5d5cb1ed2c9 100644 --- a/samples/python/hello_reshape_ssd/README.md +++ b/samples/python/hello_reshape_ssd/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to do inference of object detection + models using shape inference feature and Synchronous + Inference Request (Python) API. + + This sample demonstrates how to do synchronous inference of object detection models using :doc:`Shape Inference feature `. Models with only 1 input and output are supported. diff --git a/samples/python/model_creation_sample/README.md b/samples/python/model_creation_sample/README.md index 287fc9ad335..a02d03a87a0 100644 --- a/samples/python/model_creation_sample/README.md +++ b/samples/python/model_creation_sample/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to create a model on the fly with a + provided weights file and infer it later using Synchronous + Inference Request (Python) API. + + This sample demonstrates how to run inference using a :doc:`model ` built on the fly that uses weights from the LeNet classification model, which is known to work well on digit classification tasks. You do not need an XML file, the model is created from the source code on the fly. The following OpenVINO Python API is used in the application: diff --git a/samples/python/speech_sample/README.md b/samples/python/speech_sample/README.md index ac1c9654051..b530e299b8d 100644 --- a/samples/python/speech_sample/README.md +++ b/samples/python/speech_sample/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to infer an acoustic model based on Kaldi + neural networks and speech feature vectors using Asynchronous + Inference Request (Python) API. + + This sample demonstrates how to do a Synchronous Inference of acoustic model based on Kaldi\* neural models and speech feature vectors. The sample works with Kaldi ARK or Numpy* uncompressed NPZ files, so it does not cover an end-to-end speech recognition scenario (speech to text), requiring additional preprocessing (feature extraction) to get a feature vector from a speech signal, as well as postprocessing (decoding) to produce text from scores. diff --git a/tools/benchmark_tool/README.md b/tools/benchmark_tool/README.md index 5d9d07415ee..4b08610d78e 100644 --- a/tools/benchmark_tool/README.md +++ b/tools/benchmark_tool/README.md @@ -2,6 +2,12 @@ @sphinxdirective +.. meta:: + :description: Learn how to use the Benchmark Python Tool to + estimate deep learning inference performance on supported + devices. + + This page demonstrates how to use the Benchmark Python Tool to estimate deep learning inference performance on supported devices. .. note::