Added more information about tensor names (#11070)

* Added more information about tensor names

* Fixed comment and added documentation for extensions

* Fixed code style

* Fixed typo

docs/OV_Runtime_UG/integrate_with_your_application.md

@@ -63,7 +63,7 @@ Use the following code to create OpenVINO™ Core to manage available devices an
 
 ### Step 2. Compile the Model
 
-`ov::CompiledModel` class represents a device specific compiled model. `ov::CompiledModel` allows you to get information inputs or output ports by a tensor name or index.
+`ov::CompiledModel` class represents a device specific compiled model. `ov::CompiledModel` allows you to get information inputs or output ports by a tensor name or index, this approach is aligned with the majority of frameworks.
 
 Compile the model for a specific device using `ov::Core::compile_model()`:
 

docs/OV_Runtime_UG/migration_ov_2_0/common_inference_pipeline.md

@@ -2,6 +2,7 @@
 
 Usually to inference model with the OpenVINO™ Runtime an user needs to do the following steps in the application pipeline:
 - 1. Create Core object
+ - 1.1. (Optional) Load extensions
 - 2. Read model from the disk
  - 2.1. (Optional) Model preprocessing
 - 3. Load the model to the device
@@ -22,6 +23,18 @@ OpenVINO™ Runtime API 2.0:
 
 @snippet docs/snippets/ov_common.cpp ov_api_2_0:create_core
 
+### 1.1 (Optional) Load extensions
+
+To load model with custom operation, you need to add extensions for these operations. We highly recommend to use [OpenVINO Extensibility API](../../Extensibility_UG/Intro.md) to write extensions, but if you already have old extensions you can load it to new OpenVINO™ Runtime:
+
+Inference Engine API:
+
+@snippet docs/snippets/ie_common.cpp ie:load_old_extension
+
+OpenVINO™ Runtime API 2.0:
+
+@snippet docs/snippets/ov_common.cpp ov_api_2_0:load_old_extension
+
 ## 2. Read model from the disk
 
 Inference Engine API:
@@ -225,4 +238,4 @@ OpenVINO™ Runtime API 2.0 processes outputs:
        :language: cpp
        :fragment: [ov_api_2_0:get_output_tensor_aligned]
 
-@endsphinxdirective
+@endsphinxdirective

docs/OV_Runtime_UG/model_representation.md

@@ -10,7 +10,11 @@ Each operation in `ov::Model` has the `std::shared_ptr<ov::Node>` type.
 
 For details on how to build a model in OpenVINO™ Runtime, see the [Build a Model in OpenVINO™ Runtime](@ref build_model) section.
 
-OpenVINO™ Runtime allows using tensor names or indexes to work wit model inputs/outputs. To get model input/output ports, use the `ov::Model::inputs()` or `ov::Model::outputs()` methods respectively.
+OpenVINO™ Runtime allows to use different approaches to work with model inputs/outputs:
+ - `ov::Model::inputs()`/`ov::Model::outputs()` methods allow to get vector of all input/output ports.
+ - For a model which has only one input or output you can use methods `ov::Model::input()` or `ov::Model::output()` without arguments to get input or output port respectively.
+ - Methods `ov::Model::input()` and `ov::Model::output()` can be used with index of input or output from the framework model to get specific port by index.
+ - You can use tensor name of input or output from the original framework model together with methods `ov::Model::input()` or `ov::Model::output()` to get specific port. It means that you don't need to have any additional mapping of names from framework to OpenVINO, as it was before, OpenVINO™ Runtime allows using of native framework tensor names.
 
 @sphinxdirective
 

docs/snippets/ie_common.cpp

@@ -96,5 +96,8 @@ int main() {
         // process output data
     }
     //! [ie:get_output_tensor]
+    //! [ie:load_old_extension]
+    core.AddExtension(std::make_shared<InferenceEngine::Extension>("path_to_extension_library.so"));
+    //! [ie:load_old_extension]
     return 0;
-}
+}

docs/snippets/ov_common.cpp

@@ -1,6 +1,8 @@
 // Copyright (C) 2018-2021 Intel Corporation
 // SPDX-License-Identifier: Apache-2.0
 //
+#include <ie_extension.h>
+
 #include <openvino/core/core.hpp>
 #include <openvino/runtime/runtime.hpp>
 
@@ -84,7 +86,7 @@ int main() {
     // which restarts inference inside one more time, so two inferences happen here
 
     auto restart_once = true;
-    infer_request.set_callback([&, restart_once] (std::exception_ptr exception_ptr) mutable {
+    infer_request.set_callback([&, restart_once](std::exception_ptr exception_ptr) mutable {
         if (exception_ptr) {
             // procces exception or rethrow it.
             std::rethrow_exception(exception_ptr);
@@ -110,5 +112,11 @@ int main() {
 
     outputs_aligned(infer_request);
 
+    OPENVINO_SUPPRESS_DEPRECATED_START
+    //! [ov_api_2_0:load_old_extension]
+    core.add_extension(std::make_shared<InferenceEngine::Extension>("path_to_extension_library.so"));
+    //! [ov_api_2_0:load_old_extension]
+    OPENVINO_SUPPRESS_DEPRECATED_END
+
     return 0;
-}
+}