doc fixes (openvinotoolkit#3626)

Co-authored-by: Nikolay Tyukaev <[email protected]>

docs/IE_DG/Extensibility_DG/Custom_ONNX_Ops.md

@@ -28,7 +28,7 @@ The example below demonstrates an exemplary model that requires previously creat
 @snippet onnx_custom_op/onnx_custom_op.cpp onnx_custom_op:model
 
 
-For a reference on how to create a graph with nGraph operations, visit [nGraph tutorial](../nGraphTutorial.md).
+For a reference on how to create a graph with nGraph operations, visit [Custom nGraph Operation](AddingNGraphOps.md).
 For a complete list of predefined nGraph operators, visit [available operations sets](../../ops/opset.md).
 
 If operator is no longer needed, it can be unregistered by calling `unregister_operator`. The function takes three arguments `op_type`, `version`, and `domain`.

docs/IE_DG/network_state_intro.md

@@ -216,35 +216,32 @@ LowLatency transformation changes the structure of the network containing [Tenso
 	* [from nGraph Function](../nGraph_DG/build_function.md)
 
 2. [Reshape](ShapeInference) CNNNetwork network if necessary 
+**Necessary case:** the sequence_lengths dimention of input > 1, it means TensorIterator layer will have number_iterations > 1. We should reshape the inputs of the network to set sequence_dimension exactly to 1.
+```cpp
 
-	**Necessary case:** the sequence_lengths dimention of input > 1, it means TensorIterator layer will have number_iterations > 1. We should reshape the inputs of the network to set sequence_dimension exactly to 1.
- 
-	```cpp
-
-	// Network before reshape: Parameter (name: X, shape: [2 (sequence_lengths), 1, 16]) -> TensorIterator (num_iteration = 2, axis = 0) -> ...
+// Network before reshape: Parameter (name: X, shape: [2 (sequence_lengths), 1, 16]) -> TensorIterator (num_iteration = 2, axis = 0) -> ...
 
-	cnnNetwork.reshape({"X" : {1, 1, 16});
+cnnNetwork.reshape({"X" : {1, 1, 16});
 
-	// Network after reshape: Parameter (name: X, shape: [1 (sequence_lengths), 1, 16]) -> TensorIterator (num_iteration = 1, axis = 0) -> ...
-		
-	```
-3. Apply LowLatency transformation
-
-	```cpp
-	#include "ie_transformations.hpp"
+// Network after reshape: Parameter (name: X, shape: [1 (sequence_lengths), 1, 16]) -> TensorIterator (num_iteration = 1, axis = 0) -> ...
 	
-	...
-
-	InferenceEngine::LowLatency(cnnNetwork);
-	```
+```
 
-	**State naming rule:**  a name of state is a concatenation of names: original TensorIterator operation, Parameter of the body, and additional suffix "variable_" + id (0-base indexing, new indexing for each TensorIterator), for example:
+3. Apply LowLatency transformation
+```cpp
+#include "ie_transformations.hpp"
 
-		tensor_iterator_name = "TI_name"
-		body_parameter_name = "param_name"
+...
 
-		state_name = "TI_name/param_name/variable_0"
+InferenceEngine::LowLatency(cnnNetwork);
+```
+**State naming rule:**  a name of state is a concatenation of names: original TensorIterator operation, Parameter of the body, and additional suffix "variable_" + id (0-base indexing, new indexing for each TensorIterator), for example:
+```
+tensor_iterator_name = "TI_name"
+body_parameter_name = "param_name"
 
+state_name = "TI_name/param_name/variable_0"
+```
 4. [Use state API](#openvino-state-api)
 
  
@@ -265,14 +262,14 @@ LowLatency transformation changes the structure of the network containing [Tenso
 
 	**Current solution:** trim non-reshapable layers via [ModelOptimizer CLI](../MO_DG/prepare_model/convert_model/Converting_Model_General.md) `--input`, `--output` or via nGraph.
 
-	```cpp
-		// nGraph example:
-		auto func = cnnNetwork.getFunction();
-		auto new_const = std::make_shared<ngraph::opset5::Constant>(); // type, shape, value
-		for (const auto& node : func->get_ops()) {
-			if (node->get_friendly_name() == "name_of_non_reshapable_const") {
-				auto bad_const = std::dynamic_pointer_cast<ngraph::opset5::Constant>(node);
-				ngraph::replace_node(bad_const, new_const); // replace constant
-			}
+```cpp
+	// nGraph example:
+	auto func = cnnNetwork.getFunction();
+	auto new_const = std::make_shared<ngraph::opset5::Constant>(); // type, shape, value
+	for (const auto& node : func->get_ops()) {
+		if (node->get_friendly_name() == "name_of_non_reshapable_const") {
+			auto bad_const = std::dynamic_pointer_cast<ngraph::opset5::Constant>(node);
+			ngraph::replace_node(bad_const, new_const); // replace constant
 		}
-	```
+	}
+```

docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_YOLO_From_Tensorflow.md

@@ -110,7 +110,7 @@ where:
 
 > **NOTE:** The color channel order (RGB or BGR) of an input data should match the channel order of the model training dataset. If they are different, perform the `RGB<->BGR` conversion specifying the command-line parameter: `--reverse_input_channels`. Otherwise, inference results may be incorrect. For more information about the parameter, refer to **When to Reverse Input Channels** section of [Converting a Model Using General Conversion Parameters](../Converting_Model_General.md).
 
-OpenVINO&trade; toolkit provides a demo that uses YOLOv3 model. For more information, refer to [Object Detection YOLO* V3 Demo, Async API Performance Showcase](@ref omz_demos_object_detection_demo_yolov3_async_README).
+OpenVINO&trade; toolkit provides a demo that uses YOLOv3 model. For more information, refer to [Object Detection C++ Demo](@ref omz_demos_object_detection_demo_ssd_async_README).
 
 ## Convert YOLOv1 and YOLOv2 Models to the IR
 

docs/doxygen/ie_docs.xml

@@ -79,6 +79,7 @@
                 <tab type="user" title="Atan-1" url="@ref openvino_docs_ops_arithmetic_Atan_1"/>
                 <tab type="user" title="Atanh-3" url="@ref openvino_docs_ops_arithmetic_Atanh_3"/>
                 <tab type="user" title="AvgPool-1" url="@ref openvino_docs_ops_pooling_AvgPool_1"/>
+                <tab type="user" title="BatchNormInference-1" url="@ref openvino_docs_ops_normalization_BatchNormInference_1"/>
                 <tab type="user" title="BatchNormInference-5" url="@ref openvino_docs_ops_normalization_BatchNormInference_5"/>
                 <tab type="user" title="BatchToSpace-2" url="@ref openvino_docs_ops_movement_BatchToSpace_2"/>
                 <tab type="user" title="BinaryConvolution-1" url="@ref openvino_docs_ops_convolution_BinaryConvolution_1"/>

docs/install_guides/installing-openvino-windows.md

@@ -486,7 +486,7 @@ To learn more about converting deep learning models, go to:
 - [Intel Distribution of OpenVINO Toolkit home page](https://software.intel.com/en-us/openvino-toolkit)
 - [Intel Distribution of OpenVINO Toolkit documentation](https://software.intel.com/en-us/openvino-toolkit/documentation/featured)
 - [OpenVINO™ Release Notes](https://software.intel.com/en-us/articles/OpenVINO-RelNotes)
-- [Introduction to Inference Engine](inference_engine_intro.md)
+- [Introduction to Inference Engine](../IE_DG/inference_engine_intro.md)
 - [Inference Engine Developer Guide](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md)
 - [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md)
 - [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md)

inference-engine/ie_bridges/python/sample/ngraph_function_creation_sample/README.md

@@ -13,7 +13,7 @@ When the inference is done, the application outputs inference results to the sta
 
 > **NOTE**: This sample supports models with FP32 weights only.
 
-The `lenet.bin` weights file was generated by the [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) 
+The `lenet.bin` weights file was generated by the [Model Optimizer](../../../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) 
 tool from the public LeNet model with the `--input_shape [64,1,28,28]` parameter specified. 
 The original model is available in the [Caffe* repository](https://github.com/BVLC/caffe/tree/master/examples/mnist) on GitHub\*.
 
@@ -69,4 +69,4 @@ By default, the application outputs top-1 inference result for each inference re
 
 ## See Also
 
-* [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md)
+* [Using Inference Engine Samples](../../../../../docs/IE_DG/Samples_Overview.md)