Merge remote-tracking branch 'upstream/master' into debian-packages

2022-04-02 11:13:14 +03:00
commit 9446326040
@@ -262,7 +262,6 @@ jobs:
      . $(SETUPVARS) -pyver 3.8 && python3 -m pytest -s $(INSTALL_DIR)/tests/mo/unit_tests --junitxml=TEST-ModelOptimizer.xml
    displayName: 'Model Optimizer UT'
    continueOnError: false
-    enabled: false

  - script: . $(SETUPVARS) && $(INSTALL_TEST_DIR)/ov_core_unit_tests --gtest_print_time=1 --gtest_filter=-*IE_GPU* --gtest_output=xml:TEST-NGraphUT.xml
    workingDirectory: $(INSTALL_TEST_DIR)
@@ -149,8 +149,6 @@ if(THREADING STREQUAL "TBB" OR THREADING STREQUAL "TBB_AUTO" AND NOT ENABLE_SYST
        message(WARNING "Failed to find TBBConfig.cmake in ${TBBROOT} tree. Custom TBBConfig.cmake will be used")
    endif()

-    update_deps_cache(TBBBIND_2_5_DIR "${TBBBIND_2_5}/cmake" "Path to TBBBIND_2_5 cmake folder")
-
    debug_message(STATUS "tbb=" ${TBB})
    debug_message(STATUS "tbb_dir=" ${TBB_DIR})
    debug_message(STATUS "tbbroot=" ${TBBROOT})
@@ -174,6 +172,8 @@ if(ENABLE_TBBBIND_2_5)
                TARGET_PATH "${TEMP}/tbbbind_2_5"
                ENVIRONMENT "TBBBIND_2_5_ROOT"
                SHA256 "a67afeea8cf194f97968c800dab5b5459972908295242e282045d6b8953573c1")
+    elseif(ANDROID)
+        # don't have TBBBIND_2_5
    elseif(LINUX AND X86_64)
        RESOLVE_DEPENDENCY(TBBBIND_2_5
                ARCHIVE_LIN "tbbbind_2_5_static_lin_v2.tgz"
@@ -2,7 +2,8 @@

 Paragraphs below provide details about specifying input shapes for model conversion.

-## When to Specify --input_shape Command-line Parameter <a name="when_to_specify_input_shapes"></a>
+@anchor when_to_specify_input_shapes
+## When to Specify --input_shape Command-line Parameter
 Model Optimizer supports conversion of models with dynamic input shapes that contain undefined dimensions.
 However, if the shape of inference data is not going to change from one inference request to another,
 it is recommended to set up static shapes (when all dimensions are fully defined) for the inputs.
@@ -60,7 +61,7 @@ mo --input_model ocr.onnx --input data,seq_len --input_shape [1..3,150,200,1],[1

 Practically, some models are not ready for input shapes change.
 In this case, a new input shape cannot be set via Model Optimizer.
-Learn more about shape inference <a href="_docs_OV_Runtime_UG_ShapeInference.html#troubleshooting">troubleshooting</a> and ways to <a href="_docs_OV_Runtime_UG_ShapeInference.html#how-to-fix-non-reshape-able-model">relax shape inference flow</a>.
+Learn more about shape [inference troubleshooting](@ref troubleshooting_reshape_errors) and [ways to relax shape inference flow](@ref how-to-fix-non-reshape-able-model). 

 ## When to Specify --static_shape Command-line Parameter
 Model Optimizer provides the `--static_shape` parameter that allows evaluating shapes of all operations in the model for fixed input shapes
@@ -1,7 +1,7 @@
 # Convert TensorFlow Object Detection API Models {#openvino_docs_MO_DG_prepare_model_convert_model_tf_specific_Convert_Object_Detection_API_Models}

 > **NOTES**:
-> * Starting with the 2022.1 release, the Model Optimizer can convert the TensorFlow\* Object Detection API Faster and Mask RCNNs topologies differently. By default, the Model Optimizer 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 pre-processing applied to the input image (refer to the [Proposal](../../../../ops/detection/Proposal_4.md) operation specification for more information). However, this input is redundant for the models trained and inferred with equal size images. Model Optimizer can generate IR for such models and insert operation [DetectionOutput](../../../../ops/detection/DetectionOutput_1.md) instead of `Proposal`. The `DetectionOutput` operation does not require additional model input "image_info" and moreover, for some models the produced inference results are closer to the original TensorFlow\* model. In order to trigger new behaviour 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 2022.1 release, the Model Optimizer can convert the TensorFlow\* Object Detection API Faster and Mask RCNNs topologies differently. By default, the Model Optimizer 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 pre-processing applied to the input image (refer to the [Proposal](../../../../ops/detection/Proposal_4.md) operation specification for more information). However, this input is redundant for the models trained and inferred with equal size images. Model Optimizer can generate IR for such models and insert operation [DetectionOutput](../../../../ops/detection/DetectionOutput_1.md) instead of `Proposal`. The `DetectionOutput` operation does not require additional model input "image_info" and 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, the Model Optimizer 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 [Using Shape Inference](../../../../OV_Runtime_UG/ShapeInference.md) 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, the Model Optimizer 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.

@@ -9,9 +9,9 @@

 You can download TensorFlow\* Object Detection API models from the <a href="https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md">TensorFlow 1 Detection Model Zoo</a> or <a href="https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md">TensorFlow 2 Detection Model Zoo</a>.

-<strong>NOTE</strong>: Before converting, make sure you have configured the Model Optimizer. For configuration steps, refer to [Configuring the Model Optimizer](../../../Deep_Learning_Model_Optimizer_DevGuide.md).
+> **NOTE**: Before converting, make sure you have configured the Model Optimizer. For configuration steps, refer to [Configuring the Model Optimizer](../../../Deep_Learning_Model_Optimizer_DevGuide.md).

-To convert a TensorFlow\* Object Detection API model, go to the `<INSTALL_DIR>/tools/model_optimizer` directory and run the `mo` script with the following required parameters:
+To convert a TensorFlow\* Object Detection API model, run the `mo` command with the following required parameters:

 * `--input_model <path_to_frozen.pb>` --- File with a pre-trained model (binary or text .pb file after freezing) OR `--saved_model_dir <path_to_saved_model>` for the TensorFlow\* 2 models
 * `--transformations_config <path_to_subgraph_replacement_configuration_file.json>` --- A subgraph replacement configuration file with transformations description. For the models downloaded from the TensorFlow\* Object Detection API zoo, you can find the configuration files in the `<PYTHON_SITE_PACKAGES>/openvino/tools/mo/front/tf` directory. Use:
@@ -43,7 +43,7 @@ To convert a TensorFlow\* Object Detection API model, go to the `<INSTALL_DIR>/t
    * `rfcn_support_api_v1.13.json` --- for RFCN topology from the models zoo frozen with TensorFlow\* version 1.13.X
    * `rfcn_support_api_v1.14.json` --- for RFCN topology from the models zoo frozen with TensorFlow\* version 1.14.0 or higher
 * `--tensorflow_object_detection_api_pipeline_config <path_to_pipeline.config>` --- A special configuration file that describes the topology hyper-parameters and structure of the TensorFlow Object Detection API model. For the models downloaded from the TensorFlow\* Object Detection API zoo, the configuration file is named `pipeline.config`. If you plan to train a model yourself, you can find templates for these files in the [models repository](https://github.com/tensorflow/models/tree/master/research/object_detection/samples/configs).
-* `--input_shape` (optional) --- A custom input image shape. Refer to [Custom Input Shape](#tf_od_custom_input_shape) for more information how the `--input_shape` parameter is handled for the TensorFlow* Object Detection API models.
+* `--input_shape` (optional) --- A custom input image shape. Refer to [Custom Input Shape](#custom-input-shape) for more information how the `--input_shape` parameter is handled for the TensorFlow* Object Detection API models.

 > **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. If you convert a TensorFlow\* Object Detection API model to use with the OpenVINO sample applications, you must specify the `--reverse_input_channels` parameter. For more information about the parameter, refer to **When to Reverse Input Channels** section of [Converting a Model to Intermediate Representation (IR)](../Converting_Model.md).

@@ -55,11 +55,11 @@ For example, if you downloaded the [pre-trained SSD InceptionV2 topology](http:/
 mo --input_model=/tmp/ssd_inception_v2_coco_2018_01_28/frozen_inference_graph.pb --transformations_config front/tf/ssd_v2_support.json --tensorflow_object_detection_api_pipeline_config /tmp/ssd_inception_v2_coco_2018_01_28/pipeline.config --reverse_input_channels
 ```

-## OpenVINO&; Toolkit Samples and Open Model Zoo Demos
+## OpenVINO™ Toolkit Samples and Open Model Zoo Demos

 OpenVINO comes with a number of samples to demonstrate use of OpenVINO Runtime API, additionally,
 Open Model Zoo provides set of demo applications to show implementation of close to real life applications
-based on deep learning in various tasks, including Image Classifiacton, Visual Object Detection, Text Recognition,
+based on deep learning in various tasks, including Image Classification, Visual Object Detection, Text Recognition,
 Speech Recognition, Natural Language Processing and others. Refer to the links below for more details.


@@ -78,7 +78,8 @@ There are several important notes about feeding input images to the samples:

 4. Read carefully messaged printed by the Model Optimizer during a model conversion. They contain important instructions on how to prepare input data before running the inference and how to interpret the output.

-## Custom Input Shape <a name="tf_od_custom_input_shape"></a>
+@anchor custom-input-shape
+## Custom Input Shape
 Model Optimizer handles the command line parameter `--input_shape` for TensorFlow\* Object Detection API models in a special way depending on the image resizer type defined in the `pipeline.config` file. TensorFlow\* Object Detection API generates different `Preprocessor` sub-graph based on the image resizer type. Model Optimizer supports two types of image resizer:
 * `fixed_shape_resizer` --- *Stretches* input image to the specific height and width. The `pipeline.config` snippet below shows a `fixed_shape_resizer` sample definition:
 ```
@@ -134,4 +135,5 @@ It is also important to open the model in the [TensorBoard](https://www.tensorfl
 * `--input_model <path_to_frozen.pb>` --- Path to the frozen model
 * `--tensorboard_logdir` --- Path to the directory where TensorBoard looks for the event files.

-Implementation of the transformations for Object Detection API models is located in the file `<INSTALL_DIR>/tools/model_optimizer/extensions/front/tf/ObjectDetectionAPI.py`. Refer to the code in this file to understand the details of the conversion process.
+Implementation of the transformations for Object Detection API models is located in the file [https://github.com/openvinotoolkit/openvino/blob/releases/2022/1/tools/mo/openvino/tools/mo/front/tf/ObjectDetectionAPI.py](https://github.com/openvinotoolkit/openvino/blob/releases/2022/1/tools/mo/openvino/tools/mo/front/tf/ObjectDetectionAPI.py). Refer to the code in this file to understand the details of the conversion process.
+
@@ -34,8 +34,7 @@ class attribute value should be set to the `module + "." + layer` value so the e
 operation.

 Here is a simplified example of the extractor for the custom operation Proposal from Faster-R-CNN model mentioned above.
-The full code with additional checks is provided in the
-`<INSTALL_DIR>/tools/model_optimizer/extensions/front/caffe/proposal_python_ext.py`. The sample code uses
+The full code with additional checks is provided in the [https://github.com/openvinotoolkit/openvino/blob/releases/2022/1/tools/mo/openvino/tools/mo/front/caffe/proposal_python_ext.py](https://github.com/openvinotoolkit/openvino/blob/releases/2022/1/tools/mo/openvino/tools/mo/front/caffe/proposal_python_ext.py) file. The sample code uses
 operation `ProposalOp` which corresponds to `Proposal` operation described in the [Available Operations Sets](../../../ops/opset.md)
 document. Refer to the source code below for a detailed explanation of the extractor.

@@ -4,198 +4,198 @@

 .. toctree::
   :maxdepth: 1
-
-   openvino_docs_ops_arithmetic_Abs_1
-   openvino_docs_ops_arithmetic_Acos_1
-   openvino_docs_ops_arithmetic_Acosh_3
-   openvino_docs_ops_pooling_AdaptiveAvgPool_8
-   openvino_docs_ops_pooling_AdaptiveMaxPool_8
-   openvino_docs_ops_arithmetic_Add_1
-   openvino_docs_ops_arithmetic_Asin_1
-   openvino_docs_ops_arithmetic_Asinh_3
-   openvino_docs_ops_infrastructure_Assign_3
-   openvino_docs_ops_arithmetic_Atan_1
-   openvino_docs_ops_arithmetic_Atanh_3
-   openvino_docs_ops_pooling_AvgPool_1
-   openvino_docs_ops_normalization_BatchNormInference_1
-   openvino_docs_ops_normalization_BatchNormInference_5
-   openvino_docs_ops_movement_BatchToSpace_2
-   openvino_docs_ops_convolution_BinaryConvolution_1
-   openvino_docs_ops_movement_Broadcast_1
-   openvino_docs_ops_movement_Broadcast_3
-   openvino_docs_ops_condition_Bucketize_3
-   openvino_docs_ops_sequence_CTCGreedyDecoder_1
-   openvino_docs_ops_sequence_CTCGreedyDecoderSeqLen_6
-   openvino_docs_ops_arithmetic_Ceiling_1
-   openvino_docs_ops_activation_Clamp_1
-   openvino_docs_ops_movement_Concat_1
-   openvino_docs_ops_infrastructure_Constant_1
-   openvino_docs_ops_type_ConvertLike_1
-   openvino_docs_ops_type_Convert_1
-   openvino_docs_ops_convolution_ConvolutionBackpropData_1
-   openvino_docs_ops_convolution_Convolution_1
-   openvino_docs_ops_arithmetic_Cos_1
-   openvino_docs_ops_arithmetic_Cosh_1
-   openvino_docs_ops_sequence_CTCLoss_4
-   openvino_docs_ops_arithmetic_CumSum_3
-   openvino_docs_ops_convolution_DeformableConvolution_1
-   openvino_docs_ops_convolution_DeformableConvolution_8
-   openvino_docs_ops_detection_DeformablePSROIPooling_1
-   openvino_docs_ops_movement_DepthToSpace_1
-   openvino_docs_ops_detection_DetectionOutput_1
-   openvino_docs_ops_detection_DetectionOutput_8
-   openvino_docs_ops_signals_DFT_7
-   openvino_docs_ops_arithmetic_Divide_1
-   openvino_docs_ops_matrix_Einsum_7
-   openvino_docs_ops_activation_Elu_1
-   openvino_docs_ops_sparse_EmbeddingBagOffsetsSum_3
-   openvino_docs_ops_sparse_EmbeddingBagPackedSum_3
-   openvino_docs_ops_sparse_EmbeddingSegmentsSum_3
-   openvino_docs_ops_comparison_Equal_1
-   openvino_docs_ops_arithmetic_Erf_1
-   openvino_docs_ops_activation_Exp_1
-   openvino_docs_ops_detection_ExperimentalDetectronDetectionOutput_6
-   openvino_docs_ops_detection_ExperimentalDetectronGenerateProposalsSingleImage_6
-   openvino_docs_ops_detection_ExperimentalDetectronPriorGridGenerator_6
-   openvino_docs_ops_detection_ExperimentalDetectronROIFeatureExtractor_6
-   openvino_docs_ops_sort_ExperimentalDetectronTopKROIs_6
-   openvino_docs_ops_movement_ExtractImagePatches_3
-   openvino_docs_ops_generation_Eye_9
-   openvino_docs_ops_quantization_FakeQuantize_1
-   openvino_docs_ops_arithmetic_FloorMod_1
-   openvino_docs_ops_arithmetic_Floor_1
-   openvino_docs_ops_normalization_GRN_1
-   openvino_docs_ops_sequence_GRUCell_3
-   openvino_docs_ops_sequence_GRUSequence_5
-   openvino_docs_ops_movement_GatherTree_1
-   openvino_docs_ops_movement_Gather_1
-   openvino_docs_ops_movement_Gather_7
-   openvino_docs_ops_movement_Gather_8
-   openvino_docs_ops_movement_GatherElements_6
-   openvino_docs_ops_movement_GatherND_5
-   openvino_docs_ops_movement_GatherND_8
-   openvino_docs_ops_activation_GELU_2
-   openvino_docs_ops_activation_GELU_7
-   openvino_docs_ops_comparison_GreaterEqual_1
-   openvino_docs_ops_comparison_Greater_1
-   openvino_docs_ops_convolution_GroupConvolutionBackpropData_1
-   openvino_docs_ops_convolution_GroupConvolution_1
-   openvino_docs_ops_activation_HardSigmoid_1
-   openvino_docs_ops_activation_HSigmoid_5
-   openvino_docs_ops_activation_HSwish_4
-   openvino_docs_ops_image_I420toBGR_8
-   openvino_docs_ops_image_I420toRGB_8
-   openvino_docs_ops_signals_IDFT_7
-   openvino_docs_ops_signals_IRDFT_9
-   openvino_docs_ops_infrastructure_If_8
-   openvino_docs_ops_image_Interpolate_1
-   openvino_docs_ops_image_Interpolate_4
-   openvino_docs_ops_normalization_LRN_1
-   openvino_docs_ops_sequence_LSTMCell_1
-   openvino_docs_ops_sequence_LSTMSequence_1
-   openvino_docs_ops_comparison_LessEqual_1
-   openvino_docs_ops_comparison_Less_1
-   openvino_docs_ops_arithmetic_Log_1
-   openvino_docs_ops_logical_LogicalAnd_1
-   openvino_docs_ops_logical_LogicalNot_1
-   openvino_docs_ops_logical_LogicalOr_1
-   openvino_docs_ops_logical_LogicalXor_1
-   openvino_docs_ops_activation_LogSoftmax_5
-   openvino_docs_ops_infrastructure_Loop_5
-   openvino_docs_ops_normalization_MVN_1
-   openvino_docs_ops_normalization_MVN_6
-   openvino_docs_ops_matrix_MatMul_1
-   openvino_docs_ops_sort_MatrixNms_8
-   openvino_docs_ops_pooling_MaxPool_1
-   openvino_docs_ops_pooling_MaxPool_8
-   openvino_docs_ops_arithmetic_Maximum_1
-   openvino_docs_ops_arithmetic_Minimum_1
-   openvino_docs_ops_activation_Mish_4
-   openvino_docs_ops_arithmetic_Mod_1
-   openvino_docs_ops_sort_MulticlassNonMaxSuppression_8
-   openvino_docs_ops_arithmetic_Multiply_1
-   openvino_docs_ops_arithmetic_Negative_1
-   openvino_docs_ops_sort_NonMaxSuppression_1
-   openvino_docs_ops_sort_NonMaxSuppression_3
-   openvino_docs_ops_sort_NonMaxSuppression_4
-   openvino_docs_ops_sort_NonMaxSuppression_5
-   openvino_docs_ops_condition_NonZero_3
-   openvino_docs_ops_normalization_NormalizeL2_1
-   openvino_docs_ops_comparison_NotEqual_1
-   openvino_docs_ops_image_NV12toBGR_8
-   openvino_docs_ops_image_NV12toRGB_8
-   openvino_docs_ops_sequence_OneHot_1
-   openvino_docs_ops_activation_PReLU_1
-   openvino_docs_ops_detection_PSROIPooling_1
-   openvino_docs_ops_movement_Pad_1
-   openvino_docs_ops_infrastructure_Parameter_1
-   openvino_docs_ops_arithmetic_Power_1
-   openvino_docs_ops_detection_PriorBoxClustered_1
-   openvino_docs_ops_detection_PriorBox_1
-   openvino_docs_ops_detection_PriorBox_8
-   openvino_docs_ops_detection_Proposal_1
-   openvino_docs_ops_detection_Proposal_4
-   openvino_docs_ops_generation_RandomUniform_8
-   openvino_docs_ops_generation_Range_1
-   openvino_docs_ops_generation_Range_4
-   openvino_docs_ops_signals_RDFT_9
-   openvino_docs_ops_infrastructure_ReadValue_3
-   openvino_docs_ops_activation_ReLU_1
-   openvino_docs_ops_reduction_ReduceL1_4
-   openvino_docs_ops_reduction_ReduceL2_4
-   openvino_docs_ops_reduction_ReduceLogicalAnd_1
-   openvino_docs_ops_reduction_ReduceLogicalOr_1
-   openvino_docs_ops_reduction_ReduceMax_1
-   openvino_docs_ops_reduction_ReduceMean_1
-   openvino_docs_ops_reduction_ReduceMin_1
-   openvino_docs_ops_reduction_ReduceProd_1
-   openvino_docs_ops_reduction_ReduceSum_1
-   openvino_docs_ops_detection_RegionYolo_1
-   openvino_docs_ops_detection_ReorgYolo_1
-   openvino_docs_ops_shape_Reshape_1
-   openvino_docs_ops_infrastructure_Result_1
-   openvino_docs_ops_movement_Reverse_1
-   openvino_docs_ops_movement_ReverseSequence_1
-   openvino_docs_ops_sequence_RNNCell_3
-   openvino_docs_ops_sequence_RNNSequence_5
-   openvino_docs_ops_detection_ROIAlign_3
-   openvino_docs_ops_detection_ROIPooling_1
-   openvino_docs_ops_movement_Roll_7
-   openvino_docs_ops_arithmetic_Round_5
-   openvino_docs_ops_movement_ScatterElementsUpdate_3
-   openvino_docs_ops_movement_ScatterNDUpdate_3
-   openvino_docs_ops_movement_ScatterUpdate_3
-   openvino_docs_ops_condition_Select_1
-   openvino_docs_ops_activation_Selu_1
-   openvino_docs_ops_shape_ShapeOf_1
-   openvino_docs_ops_shape_ShapeOf_3
-   openvino_docs_ops_movement_ShuffleChannels_1
-   openvino_docs_ops_activation_Sigmoid_1
-   openvino_docs_ops_arithmetic_Sign_1
-   openvino_docs_ops_arithmetic_Sin_1
-   openvino_docs_ops_arithmetic_Sinh_1
-   openvino_docs_ops_movement_Slice_8
-   openvino_docs_ops_activation_SoftMax_1
-   openvino_docs_ops_activation_SoftMax_8
-   openvino_docs_ops_activation_SoftPlus_4
-   openvino_docs_ops_activation_SoftSign_9
-   openvino_docs_ops_movement_SpaceToBatch_2
-   openvino_docs_ops_movement_SpaceToDepth_1
-   openvino_docs_ops_movement_Split_1
-   openvino_docs_ops_arithmetic_Sqrt_1
-   openvino_docs_ops_arithmetic_SquaredDifference_1
-   openvino_docs_ops_shape_Squeeze_1
-   openvino_docs_ops_movement_StridedSlice_1
-   openvino_docs_ops_arithmetic_Subtract_1
-   openvino_docs_ops_activation_Swish_4
-   openvino_docs_ops_arithmetic_Tan_1
-   openvino_docs_ops_arithmetic_Tanh_1
-   openvino_docs_ops_infrastructure_TensorIterator_1
-   openvino_docs_ops_movement_Tile_1
-   openvino_docs_ops_sort_TopK_1
-   openvino_docs_ops_sort_TopK_3
-   openvino_docs_ops_movement_Transpose_1
-   openvino_docs_ops_shape_Unsqueeze_1
-   openvino_docs_ops_movement_VariadicSplit_1
+   
+   Abs-1 <openvino_docs_ops_arithmetic_Abs_1>
+   Acos-1 <openvino_docs_ops_arithmetic_Acos_1>
+   Acosh-3 <openvino_docs_ops_arithmetic_Acosh_3>
+   AdaptiveAvgPool-8 <openvino_docs_ops_pooling_AdaptiveAvgPool_8>
+   AdaptiveMaxPool-8 <openvino_docs_ops_pooling_AdaptiveMaxPool_8>
+   Add-1 <openvino_docs_ops_arithmetic_Add_1>
+   Asin-1 <openvino_docs_ops_arithmetic_Asin_1>
+   Asinh-3 <openvino_docs_ops_arithmetic_Asinh_3>
+   Assign-3 <openvino_docs_ops_infrastructure_Assign_3>
+   Atan-1 <openvino_docs_ops_arithmetic_Atan_1>
+   Atanh-3 <openvino_docs_ops_arithmetic_Atanh_3>
+   AvgPool-1 <openvino_docs_ops_pooling_AvgPool_1>
+   BatchNormInference-1 <openvino_docs_ops_normalization_BatchNormInference_1>
+   BatchNormInference-5 <openvino_docs_ops_normalization_BatchNormInference_5>
+   BatchToSpace-2 <openvino_docs_ops_movement_BatchToSpace_2>
+   BinaryConvolution-1 <openvino_docs_ops_convolution_BinaryConvolution_1>
+   Broadcast-1 <openvino_docs_ops_movement_Broadcast_1>
+   Broadcast-3 <openvino_docs_ops_movement_Broadcast_3>
+   Bucketize-3 <openvino_docs_ops_condition_Bucketize_3>
+   CTCGreedyDecoder-1 <openvino_docs_ops_sequence_CTCGreedyDecoder_1>
+   CTCGreedyDecoderSeqLen-6 <openvino_docs_ops_sequence_CTCGreedyDecoderSeqLen_6>
+   Ceiling-1 <openvino_docs_ops_arithmetic_Ceiling_1>
+   Clamp-1 <openvino_docs_ops_activation_Clamp_1>
+   Concat-1 <openvino_docs_ops_movement_Concat_1>
+   Constant-1 <openvino_docs_ops_infrastructure_Constant_1>
+   ConvertLike-1 <openvino_docs_ops_type_ConvertLike_1>
+   Convert-1 <openvino_docs_ops_type_Convert_1>
+   ConvolutionBackpropData-1 <openvino_docs_ops_convolution_ConvolutionBackpropData_1>
+   Convolution-1 <openvino_docs_ops_convolution_Convolution_1>
+   Cos-1 <openvino_docs_ops_arithmetic_Cos_1>
+   Cosh-1 <openvino_docs_ops_arithmetic_Cosh_1>
+   CTCLoss-4 <openvino_docs_ops_sequence_CTCLoss_4>
+   CumSum-3 <openvino_docs_ops_arithmetic_CumSum_3>
+   DeformableConvolution-1 <openvino_docs_ops_convolution_DeformableConvolution_1>
+   DeformableConvolution-8 <openvino_docs_ops_convolution_DeformableConvolution_8>
+   DeformablePSROIPooling-1 <openvino_docs_ops_detection_DeformablePSROIPooling_1>
+   DepthToSpace-1 <openvino_docs_ops_movement_DepthToSpace_1>
+   DetectionOutput-1 <openvino_docs_ops_detection_DetectionOutput_1>
+   DetectionOutput-1 <openvino_docs_ops_detection_DetectionOutput_8>
+   Discrete Fourier Transformation (DFT)-7 <openvino_docs_ops_signals_DFT_7>
+   Divide-1 <openvino_docs_ops_arithmetic_Divide_1>
+   Einsum-7 <openvino_docs_ops_matrix_Einsum_7>
+   Elu-1 <openvino_docs_ops_activation_Elu_1>
+   EmbeddingBagOffsetsSum-3 <openvino_docs_ops_sparse_EmbeddingBagOffsetsSum_3>
+   EmbeddingBagPackedSum-3 <openvino_docs_ops_sparse_EmbeddingBagPackedSum_3>
+   EmbeddingSegmentsSum-3 <openvino_docs_ops_sparse_EmbeddingSegmentsSum_3>
+   Equal-1 <openvino_docs_ops_comparison_Equal_1>
+   Erf-1 <openvino_docs_ops_arithmetic_Erf_1>
+   Exp-1 <openvino_docs_ops_activation_Exp_1>
+   ExperimentalDetectronDetectionOutput-6 <openvino_docs_ops_detection_ExperimentalDetectronDetectionOutput_6>
+   ExperimentalDetectronGenerateProposalsSingleImage-6 <openvino_docs_ops_detection_ExperimentalDetectronGenerateProposalsSingleImage_6>
+   ExperimentalDetectronPriorGridGenerator-6 <openvino_docs_ops_detection_ExperimentalDetectronPriorGridGenerator_6>
+   ExperimentalDetectronROIFeatureExtractor-6 <openvino_docs_ops_detection_ExperimentalDetectronROIFeatureExtractor_6>
+   ExperimentalDetectronTopKROIs-6 <openvino_docs_ops_sort_ExperimentalDetectronTopKROIs_6>
+   ExtractImagePatches-3 <openvino_docs_ops_movement_ExtractImagePatches_3>
+   Eye-9 <openvino_docs_ops_generation_Eye_9>
+   FakeQuantize-1 <openvino_docs_ops_quantization_FakeQuantize_1>
+   FloorMod-1 <openvino_docs_ops_arithmetic_FloorMod_1>
+   Floor-1 <openvino_docs_ops_arithmetic_Floor_1>
+   GRN-1 <openvino_docs_ops_normalization_GRN_1>
+   GRUCell-3 <openvino_docs_ops_sequence_GRUCell_3>
+   GRUSequence-5 <openvino_docs_ops_sequence_GRUSequence_5>
+   GatherTree-1 <openvino_docs_ops_movement_GatherTree_1>
+   Gather-1 <openvino_docs_ops_movement_Gather_1>
+   Gather-7 <openvino_docs_ops_movement_Gather_7>
+   Gather-8 <openvino_docs_ops_movement_Gather_8>
+   GatherElements-6 <openvino_docs_ops_movement_GatherElements_6>
+   GatherND-5 <openvino_docs_ops_movement_GatherND_5>
+   GatherND-8 <openvino_docs_ops_movement_GatherND_8>
+   Gaussian Error Linear Unit (GELU)-2 <openvino_docs_ops_activation_GELU_2>
+   Gaussian Error Linear Unit (GELU)-7 <openvino_docs_ops_activation_GELU_7>
+   GreaterEqual-1 <openvino_docs_ops_comparison_GreaterEqual_1>
+   Greater-1 <openvino_docs_ops_comparison_Greater_1>
+   GroupConvolutionBackpropData-1 <openvino_docs_ops_convolution_GroupConvolutionBackpropData_1>
+   GroupConvolution-1 <openvino_docs_ops_convolution_GroupConvolution_1>
+   HardSigmoid-1 <openvino_docs_ops_activation_HardSigmoid_1>
+   HSigmoid-5 <openvino_docs_ops_activation_HSigmoid_5>
+   HSwish-4 <openvino_docs_ops_activation_HSwish_4>
+   I420toBGR-8 <openvino_docs_ops_image_I420toBGR_8>
+   I420toRGB-8 <openvino_docs_ops_image_I420toRGB_8>
+   IDFT-7 <openvino_docs_ops_signals_IDFT_7>
+   IRDFT-9 <openvino_docs_ops_signals_IRDFT_9>
+   If-8 <openvino_docs_ops_infrastructure_If_8>
+   Interpolate-1 <openvino_docs_ops_image_Interpolate_1>
+   Interpolate-4 <openvino_docs_ops_image_Interpolate_4>
+   LRN-1 <openvino_docs_ops_normalization_LRN_1>
+   LSTMCell-1 <openvino_docs_ops_sequence_LSTMCell_1>
+   LSTMSequence-1 <openvino_docs_ops_sequence_LSTMSequence_1>
+   LessEqual-1 <openvino_docs_ops_comparison_LessEqual_1>
+   Less-1 <openvino_docs_ops_comparison_Less_1>
+   Log-1 <openvino_docs_ops_arithmetic_Log_1>
+   LogicalAnd-1 <openvino_docs_ops_logical_LogicalAnd_1>
+   LogicalNot-1 <openvino_docs_ops_logical_LogicalNot_1>
+   LogicalOr-1 <openvino_docs_ops_logical_LogicalOr_1>
+   LogicalXor-1 <openvino_docs_ops_logical_LogicalXor_1>
+   LogSoftmax-5 <openvino_docs_ops_activation_LogSoftmax_5>
+   Loop-5 <openvino_docs_ops_infrastructure_Loop_5>
+   MVN-1 <openvino_docs_ops_normalization_MVN_1>
+   MVN-6 <openvino_docs_ops_normalization_MVN_6>
+   MatMul-1 <openvino_docs_ops_matrix_MatMul_1>
+   MatrixNms-8 <openvino_docs_ops_sort_MatrixNms_8>
+   MaxPool-1 <openvino_docs_ops_pooling_MaxPool_1>
+   MaxPool-8 <openvino_docs_ops_pooling_MaxPool_8>
+   Maximum-1 <openvino_docs_ops_arithmetic_Maximum_1>
+   Minimum-1 <openvino_docs_ops_arithmetic_Minimum_1>
+   Mish-4 <openvino_docs_ops_activation_Mish_4>
+   Mod-1 <openvino_docs_ops_arithmetic_Mod_1>
+   MulticlassNonMaxSuppression-8 <openvino_docs_ops_sort_MulticlassNonMaxSuppression_8>
+   Multiply-1 <openvino_docs_ops_arithmetic_Multiply_1>
+   Negative-1 <openvino_docs_ops_arithmetic_Negative_1>
+   NonMaxSuppression-1 <openvino_docs_ops_sort_NonMaxSuppression_1>
+   NonMaxSuppression-3 <openvino_docs_ops_sort_NonMaxSuppression_3>
+   NonMaxSuppression-4 <openvino_docs_ops_sort_NonMaxSuppression_4>
+   NonMaxSuppression-5 <openvino_docs_ops_sort_NonMaxSuppression_5>
+   NonZero-3 <openvino_docs_ops_condition_NonZero_3>
+   NormalizeL2-1 <openvino_docs_ops_normalization_NormalizeL2_1>
+   NotEqual-1 <openvino_docs_ops_comparison_NotEqual_1>
+   NV12toBGR-8 <openvino_docs_ops_image_NV12toBGR_8>
+   NV12toRGB-8 <openvino_docs_ops_image_NV12toRGB_8>
+   OneHot-1 <openvino_docs_ops_sequence_OneHot_1>
+   PReLU-1 <openvino_docs_ops_activation_PReLU_1>
+   PSROIPooling-1 <openvino_docs_ops_detection_PSROIPooling_1>
+   Pad-1 <openvino_docs_ops_movement_Pad_1>
+   Parameter-1 <openvino_docs_ops_infrastructure_Parameter_1>
+   Power-1 <openvino_docs_ops_arithmetic_Power_1>
+   PriorBoxClustered-1 <openvino_docs_ops_detection_PriorBoxClustered_1>
+   PriorBox-1 <openvino_docs_ops_detection_PriorBox_1>
+   PriorBox-8 <openvino_docs_ops_detection_PriorBox_8>
+   Proposal-1 <openvino_docs_ops_detection_Proposal_1>
+   Proposal-4 <openvino_docs_ops_detection_Proposal_4>
+   RandomUniform-8 <openvino_docs_ops_generation_RandomUniform_8>
+   Range-1 <openvino_docs_ops_generation_Range_1>
+   Range-4 <openvino_docs_ops_generation_Range_4>
+   RDFT-9<openvino_docs_ops_signals_RDFT_9>
+   ReadValue-3 <openvino_docs_ops_infrastructure_ReadValue_3>
+   ReLU-1 <openvino_docs_ops_activation_ReLU_1>
+   ReduceL1-4 <openvino_docs_ops_reduction_ReduceL1_4>
+   ReduceL2-4 <openvino_docs_ops_reduction_ReduceL2_4>
+   ReduceLogicalAnd-1 <openvino_docs_ops_reduction_ReduceLogicalAnd_1>
+   ReduceLogicalOr-1 <openvino_docs_ops_reduction_ReduceLogicalOr_1>
+   ReduceMax-1 <openvino_docs_ops_reduction_ReduceMax_1>
+   ReduceMean-1 <openvino_docs_ops_reduction_ReduceMean_1>
+   ReduceMin-1 <openvino_docs_ops_reduction_ReduceMin_1>
+   ReduceProd-1 <openvino_docs_ops_reduction_ReduceProd_1>
+   ReduceSum-1 <openvino_docs_ops_reduction_ReduceSum_1>
+   RegionYolo-1 <openvino_docs_ops_detection_RegionYolo_1>
+   ReorgYolo-1 <openvino_docs_ops_detection_ReorgYolo_1>
+   Reshape-1 <openvino_docs_ops_shape_Reshape_1>
+   Result-1 <openvino_docs_ops_infrastructure_Result_1>
+   Reverse-1 <openvino_docs_ops_movement_Reverse_1>
+   ReverseSequence-1 <openvino_docs_ops_movement_ReverseSequence_1>
+   RNNCell-3 <openvino_docs_ops_sequence_RNNCell_3>
+   RNNSequence-5 <openvino_docs_ops_sequence_RNNSequence_5>
+   ROIAlign-3 <openvino_docs_ops_detection_ROIAlign_3>
+   ROIPooling-1 <openvino_docs_ops_detection_ROIPooling_1>
+   Roll-7 <openvino_docs_ops_movement_Roll_7>
+   Round-5 <openvino_docs_ops_arithmetic_Round_5>
+   ScatterElementsUpdate-3 <openvino_docs_ops_movement_ScatterElementsUpdate_3>
+   ScatterNDUpdate-3 <openvino_docs_ops_movement_ScatterNDUpdate_3>
+   ScatterUpdate-3 <openvino_docs_ops_movement_ScatterUpdate_3>
+   Select-1 <openvino_docs_ops_condition_Select_1>
+   Selu-1 <openvino_docs_ops_activation_Selu_1>
+   ShapeOf-1 <openvino_docs_ops_shape_ShapeOf_1>
+   ShapeOf-3 <openvino_docs_ops_shape_ShapeOf_3>
+   ShuffleChannels-1 <openvino_docs_ops_movement_ShuffleChannels_1>
+   Sigmoid-1 <openvino_docs_ops_activation_Sigmoid_1>
+   Sign-1 <openvino_docs_ops_arithmetic_Sign_1>
+   Sin-1 <openvino_docs_ops_arithmetic_Sin_1>
+   Sinh-1 <openvino_docs_ops_arithmetic_Sinh_1>
+   Slice-8 <openvino_docs_ops_movement_Slice_8>
+   SoftMax-1 <openvino_docs_ops_activation_SoftMax_1>
+   SoftMax-8 <openvino_docs_ops_activation_SoftMax_8>
+   SoftPlus-4 <openvino_docs_ops_activation_SoftPlus_4>
+   SoftSign-9 <openvino_docs_ops_activation_SoftSign_9>
+   SpaceToBatch-2 <openvino_docs_ops_movement_SpaceToBatch_2>
+   SpaceToDepth-1 <openvino_docs_ops_movement_SpaceToDepth_1>
+   Split-1 <openvino_docs_ops_movement_Split_1>
+   Sqrt-1 <openvino_docs_ops_arithmetic_Sqrt_1>
+   SquaredDifference-1 <openvino_docs_ops_arithmetic_SquaredDifference_1>
+   Squeeze-1 <openvino_docs_ops_shape_Squeeze_1>
+   StridedSlice-1 <openvino_docs_ops_movement_StridedSlice_1>
+   Subtract-1 <openvino_docs_ops_arithmetic_Subtract_1>
+   Swish-4 <openvino_docs_ops_activation_Swish_4>
+   Tan-1 <openvino_docs_ops_arithmetic_Tan_1>
+   Tanh-1 <openvino_docs_ops_arithmetic_Tanh_1>
+   TensorIterator-1 <openvino_docs_ops_infrastructure_TensorIterator_1>
+   Tile-1 <openvino_docs_ops_movement_Tile_1>
+   TopK-1 <openvino_docs_ops_sort_TopK_1>
+   TopK-3 <openvino_docs_ops_sort_TopK_3>
+   Transpose-1 <openvino_docs_ops_movement_Transpose_1>
+   Unsqueeze-1 <openvino_docs_ops_shape_Unsqueeze_1>
+   VariadicSplit-1 <openvino_docs_ops_movement_VariadicSplit_1>

@endsphinxdirective
@@ -10,7 +10,7 @@

 OpenVINO™ provides capabilities to change model input shape during the runtime.
 It may be useful in case you would like to feed model an input that has different size than model input shape. 
-In case you need to do this only once <a href="_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#when-to-specify-input-shapes">prepare a model with updated shapes via Model Optimizer</a> for all the other cases follow instructions further.
+In case you need to do this only once [prepare a model with updated shapes via Model Optimizer](@ref when_to_specify_input_shapes) for all the other cases follow instructions further.

 ### Set a new input shape with reshape method

@@ -26,7 +26,7 @@ Please see the code to achieve that:
 ### Set a new batch size with set_batch method

 Meaning of the model batch may vary depending on the model design.
-In order to change the batch dimension of the model, please <a href="_docs_OV_Runtime_UG_preprocessing_overview.html#declare-model-s-layout">set the ov::Layout</a> and call the `ov::set_batch` method.
+In order to change the batch dimension of the model, [set the ov::Layout](@ref declare_model_s_layout) and call the `ov::set_batch` method.

@snippet snippets/ShapeInference.cpp set_batch

@@ -34,7 +34,7 @@ In order to change the batch dimension of the model, please <a href="_docs_OV_Ru

 Once the input shape of `ov::Model` is set, call the `ov::Core::compile_model` method to get an `ov::CompiledModel` object for inference with updated shapes.

-There are other approaches to change model input shapes during the stage of <a href="_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#when-to-specify-input-shapes">IR generation</a> or [ov::Model creation](../OV_Runtime_UG/model_representation.md).
+There are other approaches to change model input shapes during the stage of [IR generation](@ref when_to_specify_input_shapes) or [ov::Model creation](../OV_Runtime_UG/model_representation.md).

 ### Dynamic Shape Notice

@@ -80,10 +80,11 @@ To do the opposite - resize input image to the input shapes of the model, use th

@endsphinxdirective

-Please find usage scenarios of `reshape` feature in our [samples](Samples_Overview.md) starting with [Hello Reshape Sample](../../samples/cpp/hello_reshape_ssd/README.html)
+Please find usage scenarios of `reshape` feature in our [samples](Samples_Overview.md) starting with [Hello Reshape Sample](../../samples/cpp/hello_reshape_ssd/README.md).

 Practically, some models are not ready to be reshaped. In this case, a new input shape cannot be set with the Model Optimizer or the `ov::Model::reshape` method.

+@anchor troubleshooting_reshape_errors
 ### Troubleshooting Reshape Errors

 Operation semantics may impose restrictions on input shapes of the operation. 
@@ -105,9 +106,10 @@ For example, [publicly available Inception family models from TensorFlow*](https
 - Changing the model input shape may significantly affect its accuracy.
 For example, Object Detection models from TensorFlow have resizing restrictions by design. 
 To keep the model valid after the reshape, choose a new input shape that satisfies conditions listed in the `pipeline.config` file. 
-For details, refer to the <a href="_docs_MO_DG_prepare_model_convert_model_tf_specific_Convert_Object_Detection_API_Models.html#custom-input-shape">Tensorflow Object Detection API models resizing techniques</a>.
+For details, refer to the [Tensorflow Object Detection API models resizing techniques](@ref custom-input-shape).

-### How To Fix Non-Reshape-able Model<a name="how-to-fix-non-reshape-able-model"></a>
+@anchor how-to-fix-non-reshape-able-model
+### How To Fix Non-Reshape-able Model

 Some operators which prevent normal shape propagation can be fixed. To do so you can:
 * see if the issue can be fixed via changing the values of some operators input. 
@@ -140,7 +142,7 @@ OpenVINO provides a special mechanism that allows adding support of shape infere

 OpenVINO™ provides capabilities to change model input shape during the runtime.
 It may be useful in case you would like to feed model an input that has different size than model input shape. 
-In case you need to do this only once <a href="_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#when-to-specify-input-shapes">prepare a model with updated shapes via Model Optimizer</a> for all the other cases follow instructions further.
+In case you need to do this only once [prepare a model with updated shapes via Model Optimizer](@ref when_to_specify_input_shapes) for all the other cases follow instructions further.

 ### Set a new input shape with reshape method

@@ -162,7 +164,7 @@ Please see the code to achieve that:
 ### Set a new batch size with set_batch method

 Meaning of the model batch may vary depending on the model design.
-In order to change the batch dimension of the model, please <a href="_docs_OV_Runtime_UG_preprocessing_overview.html#declare-model-s-layout">set the Layout</a> for inputs and call the [set_batch](api/ie_python_api/_autosummary/openvino.runtime.set_batch.html) method.
+In order to change the batch dimension of the model, [set the layout](@ref declare_model_s_layout) for inputs and call the [set_batch](api/ie_python_api/_autosummary/openvino.runtime.set_batch.html) method.

@sphinxdirective

@@ -176,7 +178,7 @@ In order to change the batch dimension of the model, please <a href="_docs_OV_Ru

 Once the input shape of [Model](api/ie_python_api/_autosummary/openvino.runtime.Model.html) is set, call the [compile_model](api/ie_python_api/_autosummary/openvino.runtime.compile_model.html) method to get a [CompiledModel](api/ie_python_api/_autosummary/openvino.runtime.CompiledModel.html) object for inference with updated shapes.

-There are other approaches to change model input shapes during the stage of <a href="_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#when-to-specify-input-shapes">IR generation</a> or [Model creation](../OV_Runtime_UG/model_representation.md).
+There are other approaches to change model input shapes during the stage of [IR generation](@ref when_to_specify_input_shapes) or [Model creation](../OV_Runtime_UG/model_representation.md).

 ### Dynamic Shape Notice

@@ -234,19 +236,19 @@ Dictionary values (representing new shapes) could be

@endsphinxdirective

-Please find usage scenarios of `reshape` feature in our [samples](Samples_Overview.md), starting with [Hello Reshape Sample](../../samples/python/hello_reshape_ssd/README.html)
+Please find usage scenarios of `reshape` feature in our [samples](Samples_Overview.md), starting with [Hello Reshape Sample](../../samples/python/hello_reshape_ssd/README.md).

 Practically, some models are not ready to be reshaped. In this case, a new input shape cannot be set with the Model Optimizer or the `Model.reshape` method.

-### Troubleshooting Reshape Errors <a name="troubleshooting"></a>
+### Troubleshooting Reshape Errors

 Operation semantics may impose restrictions on input shapes of the operation. 
 Shape collision during shape propagation may be a sign that a new shape does not satisfy the restrictions. 
 Changing the model input shape may result in intermediate operations shape collision.

 Examples of such operations:
-* <a href="_docs_ops_shape_Reshape_1.html">Reshape</a> operation with a hard-coded output shape value
-* <a href="_docs_ops_matrix_MatMul_1.html">MatMul</a> operation with the `Const` second input cannot be resized by spatial dimensions due to operation semantics
+* [Reshape](../ops/shape/Reshape_1.md) operation with a hard-coded output shape value
+* [MatMul](../ops/matrix/MatMul_1.md) operation with the `Const` second input cannot be resized by spatial dimensions due to operation semantics

 Model structure and logic should not change significantly after model reshaping.
 - The Global Pooling operation is commonly used to reduce output feature map of classification models output.
@@ -259,9 +261,9 @@ For example, [publicly available Inception family models from TensorFlow*](https
 - Changing the model input shape may significantly affect its accuracy.
 For example, Object Detection models from TensorFlow have resizing restrictions by design. 
 To keep the model valid after the reshape, choose a new input shape that satisfies conditions listed in the `pipeline.config` file. 
-For details, refer to the <a href="_docs_MO_DG_prepare_model_convert_model_tf_specific_Convert_Object_Detection_API_Models.html#custom-input-shape">Tensorflow Object Detection API models resizing techniques</a>.
+For details, refer to the [Tensorflow Object Detection API models resizing techniques](@ref custom-input-shape).

-### How To Fix Non-Reshape-able Model<a name="how-to-fix-non-reshape-able-model"></a>
+### How To Fix Non-Reshape-able Model

 Some operators which prevent normal shape propagation can be fixed. To do so you can:
 * see if the issue can be fixed via changing the values of some operators input. 
@@ -1,60 +0,0 @@
-<svg width="678" height="259" viewBox="0 0 678 259" fill="none" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<rect x="394" y="59" width="64" height="56" fill="url(#pattern0)"/>
-<rect x="19" y="69" width="52" height="40.8571" fill="url(#pattern1)"/>
-<path d="M266.53 146.484C266.823 146.191 266.823 145.716 266.53 145.423L261.756 140.651C261.463 140.358 260.989 140.359 260.696 140.652C260.403 140.944 260.403 141.419 260.696 141.712L264.939 145.954L260.697 150.197C260.405 150.49 260.405 150.965 260.698 151.258C260.99 151.551 261.465 151.551 261.758 151.258L266.53 146.484ZM0.000130016 146.75L266 146.704L266 145.204L-0.000130016 145.25L0.000130016 146.75Z" fill="#8B8E97"/>
-<path d="M645.53 147.484C645.823 147.191 645.823 146.716 645.53 146.423L640.756 141.651C640.463 141.358 639.989 141.359 639.696 141.652C639.403 141.944 639.403 142.419 639.696 142.712L643.939 146.954L639.697 151.197C639.405 151.49 639.405 151.965 639.698 152.258C639.99 152.551 640.465 152.551 640.758 152.258L645.53 147.484ZM379 147.75L645 147.704L645 146.204L379 146.25L379 147.75Z" fill="#8B8E97"/>
-<path d="M98.5451 89.0303C98.838 88.7374 98.838 88.2626 98.5451 87.9697L93.7721 83.1967C93.4792 82.9038 93.0043 82.9038 92.7114 83.1967C92.4185 83.4896 92.4185 83.9645 92.7114 84.2574L96.9541 88.5L92.7114 92.7426C92.4185 93.0355 92.4185 93.5104 92.7114 93.8033C93.0043 94.0962 93.4792 94.0962 93.7721 93.8033L98.5451 89.0303ZM80.9854 89.25H98.0147V87.75H80.9854V89.25Z" fill="#8B8E97"/>
-<path d="M480.545 93.0303C480.838 92.7374 480.838 92.2626 480.545 91.9697L475.772 87.1967C475.479 86.9038 475.004 86.9038 474.711 87.1967C474.419 87.4896 474.419 87.9645 474.711 88.2574L478.954 92.5L474.711 96.7426C474.419 97.0355 474.419 97.5104 474.711 97.8033C475.004 98.0962 475.479 98.0962 475.772 97.8033L480.545 93.0303ZM462.985 93.25H480.015V91.75H462.985V93.25Z" fill="#8B8E97"/>
-<path d="M202.5 55.5L227.5 86M227.5 86L202.5 77.5M227.5 86L202.5 99.5M227.5 86L202.5 122.5" stroke="#8B8E97"/>
-<path d="M189 55H162.509L189 78M189 55L162.509 123M189 55L162.509 101M189 55L162.509 78M189 78H162.509M189 78L162.509 123M189 78L162.509 101M162.509 78L189 100M162.509 78L189 123M189 100C189 100.8 171.34 101 162.509 101M189 100L162.509 123M189 100L162 55L189 123M162.509 101L189 123M189 123H162.509" stroke="#8B8E97"/>
-<path d="M149.5 56.5L123.5 65.5M149.5 56.5L123.5 87.5M149.5 56.5L123.5 109.5M123.5 65.5L149.5 78.5M123.5 65.5L149.5 100M123.5 65.5L149.5 122.5M149.5 78.5L123.5 87.5M149.5 78.5L123.5 109.5M123.5 87.5L149.5 100M123.5 87.5L149.5 122.5M149.5 100L123.5 109.5M123.5 109.5L149.5 122.5" stroke="#8B8E97"/>
-<circle cx="117" cy="65" r="6.5" fill="#76CEFF" stroke="#8B8E97"/>
-<circle cx="117" cy="88" r="6.5" fill="#76CEFF" stroke="#8B8E97"/>
-<circle cx="117" cy="111" r="6.5" fill="#76CEFF" stroke="#8B8E97"/>
-<circle cx="156" cy="124" r="6.5" fill="#00A3F6" stroke="#8B8E97"/>
-<circle cx="156" cy="101" r="6.5" fill="#00A3F6" stroke="#8B8E97"/>
-<circle cx="156" cy="78" r="6.5" fill="#00A3F6" stroke="#8B8E97"/>
-<circle cx="156" cy="56" r="6.5" fill="#00A3F6" stroke="#8B8E97"/>
-<circle cx="196" cy="55" r="6.5" fill="#0068B5" stroke="#8B8E97"/>
-<circle cx="196" cy="78" r="6.5" fill="#0068B5" stroke="#8B8E97"/>
-<circle cx="196" cy="101" r="6.5" fill="#0068B5" stroke="#8B8E97"/>
-<circle cx="196" cy="124" r="6.5" fill="#0068B5" stroke="#8B8E97"/>
-<circle cx="233" cy="86" r="6.5" fill="#00285A" stroke="#8B8E97"/>
-<path d="M584.5 59.5L609.5 90M609.5 90L584.5 81.5M609.5 90L584.5 103.5M609.5 90L584.5 126.5" stroke="#8B8E97"/>
-<path d="M571 59H544.509L571 82M571 59L544.509 127M571 59L544.509 105M571 59L544.509 82M571 82H544.509M571 82L544.509 127M571 82L544.509 105M544.509 82L571 104M544.509 82L571 127M571 104C571 104.8 553.34 105 544.509 105M571 104L544.509 127M571 104L544 59L571 127M544.509 105L571 127M571 127H544.509" stroke="#8B8E97"/>
-<path d="M531.5 60.5L505.5 69.5M531.5 60.5L505.5 91.5M531.5 60.5L505.5 113.5M505.5 69.5L531.5 82.5M505.5 69.5L531.5 104M505.5 69.5L531.5 126.5M531.5 82.5L505.5 91.5M531.5 82.5L505.5 113.5M505.5 91.5L531.5 104M505.5 91.5L531.5 126.5M531.5 104L505.5 113.5M505.5 113.5L531.5 126.5" stroke="#8B8E97"/>
-<circle cx="499" cy="69" r="6.5" fill="#76CEFF" stroke="#8B8E97"/>
-<circle cx="499" cy="92" r="6.5" fill="#76CEFF" stroke="#8B8E97"/>
-<circle cx="499" cy="115" r="6.5" fill="#76CEFF" stroke="#8B8E97"/>
-<circle cx="538" cy="128" r="6.5" fill="#00A3F6" stroke="#8B8E97"/>
-<circle cx="538" cy="105" r="6.5" fill="#00A3F6" stroke="#8B8E97"/>
-<circle cx="538" cy="82" r="6.5" fill="#00A3F6" stroke="#8B8E97"/>
-<circle cx="538" cy="60" r="6.5" fill="#00A3F6" stroke="#8B8E97"/>
-<circle cx="578" cy="59" r="6.5" fill="#0068B5" stroke="#8B8E97"/>
-<circle cx="578" cy="82" r="6.5" fill="#0068B5" stroke="#8B8E97"/>
-<circle cx="578" cy="105" r="6.5" fill="#0068B5" stroke="#8B8E97"/>
-<circle cx="578" cy="128" r="6.5" fill="#0068B5" stroke="#8B8E97"/>
-<circle cx="615" cy="90" r="6.5" fill="#00285A" stroke="#8B8E97"/>
-<line x1="14" y1="36" x2="14" y2="173" stroke="#A1A3AB" stroke-width="2" stroke-dasharray="5 4"/>
-<line x1="390" y1="37" x2="390" y2="174" stroke="#A1A3AB" stroke-width="2" stroke-dasharray="5 4"/>
-<line y1="-1" x2="137.013" y2="-1" transform="matrix(0.0134586 0.999909 -0.999875 0.0158316 243 36)" stroke="#A1A3AB" stroke-width="2" stroke-dasharray="5 4"/>
-<line y1="-1" x2="137.013" y2="-1" transform="matrix(0.0134586 0.999909 -0.999875 0.0158316 625 37)" stroke="#A1A3AB" stroke-width="2" stroke-dasharray="5 4"/>
-<path d="M126.941 164H124.385V158.294C124.385 157.238 123.959 156.71 123.107 156.71C122.567 156.71 122.141 156.902 121.829 157.286C121.529 157.658 121.379 158.204 121.379 158.924V164H118.823V154.91H120.281C120.893 154.91 121.199 155.174 121.199 155.702V156.332C121.439 155.792 121.805 155.384 122.297 155.108C122.801 154.82 123.377 154.676 124.025 154.676C124.673 154.676 125.213 154.82 125.645 155.108C126.089 155.384 126.413 155.792 126.617 156.332C126.881 155.804 127.265 155.396 127.769 155.108C128.273 154.82 128.867 154.676 129.551 154.676C130.499 154.676 131.225 154.97 131.729 155.558C132.245 156.134 132.503 156.968 132.503 158.06V164H129.947V158.294C129.947 157.238 129.521 156.71 128.669 156.71C128.129 156.71 127.703 156.902 127.391 157.286C127.091 157.658 126.941 158.204 126.941 158.924V164ZM138.469 156.62C138.049 156.62 137.719 156.692 137.479 156.836C137.239 156.968 137.119 157.172 137.119 157.448C137.119 157.676 137.191 157.856 137.335 157.988C137.479 158.108 137.671 158.204 137.911 158.276L139.279 158.69C140.119 158.942 140.737 159.272 141.133 159.68C141.541 160.076 141.745 160.616 141.745 161.3C141.745 162.212 141.403 162.932 140.719 163.46C140.047 163.976 139.123 164.234 137.947 164.234C137.203 164.234 136.519 164.132 135.895 163.928C135.271 163.712 134.719 163.412 134.239 163.028L135.193 161.408C135.589 161.684 136.015 161.9 136.471 162.056C136.939 162.212 137.395 162.29 137.839 162.29C138.259 162.29 138.589 162.212 138.829 162.056C139.069 161.9 139.189 161.66 139.189 161.336C139.189 161.12 139.123 160.946 138.991 160.814C138.871 160.67 138.655 160.55 138.343 160.454L136.849 160.022C136.105 159.806 135.535 159.494 135.139 159.086C134.755 158.666 134.563 158.12 134.563 157.448C134.563 156.992 134.653 156.596 134.833 156.26C135.013 155.912 135.259 155.624 135.571 155.396C135.895 155.156 136.279 154.976 136.723 154.856C137.167 154.736 137.653 154.676 138.181 154.676C138.829 154.676 139.459 154.766 140.071 154.946C140.683 155.114 141.199 155.354 141.619 155.666L140.809 157.286C140.065 156.842 139.285 156.62 138.469 156.62Z" fill="#0068B5"/>
-<path d="M492.887 163.032V168H490.259V155.58H498.359V157.632H492.887V160.98H497.549V163.032H492.887ZM502.87 163.734V168H500.296V155.58H504.94C506.368 155.58 507.472 155.934 508.252 156.642C509.032 157.338 509.422 158.346 509.422 159.666C509.422 160.938 509.032 161.934 508.252 162.654C507.484 163.374 506.374 163.734 504.922 163.734H502.87ZM502.87 157.506V161.808H504.508C505.276 161.808 505.852 161.64 506.236 161.304C506.62 160.968 506.812 160.422 506.812 159.666C506.812 158.91 506.62 158.364 506.236 158.028C505.864 157.68 505.294 157.506 504.526 157.506H502.87ZM516.117 157.434C515.397 157.434 514.839 157.56 514.443 157.812C514.059 158.052 513.867 158.436 513.867 158.964C513.867 159.384 514.005 159.714 514.281 159.954C514.569 160.194 514.965 160.386 515.469 160.53L517.341 161.088C518.349 161.388 519.105 161.796 519.609 162.312C520.125 162.816 520.383 163.506 520.383 164.382C520.383 164.982 520.263 165.522 520.023 166.002C519.783 166.482 519.441 166.89 518.997 167.226C518.565 167.562 518.043 167.82 517.431 168C516.831 168.18 516.165 168.27 515.433 168.27C514.569 168.27 513.729 168.138 512.913 167.874C512.097 167.61 511.365 167.208 510.717 166.668L511.851 164.904C512.379 165.288 512.931 165.594 513.507 165.822C514.083 166.038 514.701 166.146 515.361 166.146C516.069 166.146 516.627 166.014 517.035 165.75C517.443 165.486 517.647 165.084 517.647 164.544C517.647 164.124 517.509 163.806 517.233 163.59C516.969 163.374 516.573 163.188 516.045 163.032L514.047 162.492C513.135 162.24 512.421 161.832 511.905 161.268C511.389 160.704 511.131 159.972 511.131 159.072C511.131 158.484 511.245 157.956 511.473 157.488C511.713 157.02 512.037 156.624 512.445 156.3C512.865 155.976 513.363 155.73 513.939 155.562C514.527 155.394 515.175 155.31 515.883 155.31C516.699 155.31 517.485 155.424 518.241 155.652C519.009 155.88 519.663 156.21 520.203 156.642L519.195 158.316C518.307 157.728 517.281 157.434 516.117 157.434Z" fill="#0068B5"/>
-<path d="M13.4948 15.948H19.0748V18H10.8668V5.58H13.4948V15.948ZM20.1278 15.444C20.1278 14.496 20.4698 13.776 21.1538 13.284C21.8378 12.78 22.7798 12.528 23.9798 12.528H25.4558V12.168C25.4558 11.64 25.3118 11.256 25.0238 11.016C24.7478 10.764 24.3038 10.638 23.6918 10.638C23.2358 10.638 22.7978 10.704 22.3778 10.836C21.9578 10.968 21.5738 11.154 21.2258 11.394L20.3438 9.9C20.8478 9.516 21.4178 9.216 22.0538 9C22.6898 8.784 23.3738 8.676 24.1058 8.676C25.3538 8.676 26.2898 8.976 26.9138 9.576C27.5498 10.176 27.8678 11.04 27.8678 12.168V15.66C27.8678 15.936 27.9158 16.122 28.0118 16.218C28.1078 16.302 28.2818 16.344 28.5338 16.344H28.7318V17.91C28.5998 17.958 28.4438 18 28.2638 18.036C28.0838 18.072 27.8678 18.09 27.6158 18.09C27.0878 18.09 26.6918 17.982 26.4278 17.766C26.1638 17.55 26.0078 17.232 25.9598 16.812C25.7438 17.244 25.3838 17.586 24.8798 17.838C24.3758 18.09 23.7998 18.216 23.1518 18.216C22.2398 18.216 21.5078 17.97 20.9558 17.478C20.4038 16.986 20.1278 16.308 20.1278 15.444ZM23.7998 16.38C24.3158 16.38 24.7178 16.212 25.0058 15.876C25.3058 15.54 25.4558 15.066 25.4558 14.454V13.986H24.2138C23.6858 13.986 23.2778 14.094 22.9898 14.31C22.7138 14.514 22.5758 14.826 22.5758 15.246C22.5758 15.63 22.6838 15.918 22.8998 16.11C23.1278 16.29 23.4278 16.38 23.7998 16.38ZM35.3058 16.038V17.946C35.1138 17.994 34.9038 18.03 34.6758 18.054C34.4478 18.078 34.1778 18.09 33.8658 18.09C32.7858 18.09 31.9938 17.844 31.4898 17.352C30.9858 16.848 30.7338 16.032 30.7338 14.904V10.854H29.3838V8.91H30.7338V6.732H33.2898V8.91H35.3058V10.854H33.2898V14.67C33.2898 15.21 33.4098 15.576 33.6498 15.768C33.8898 15.948 34.3218 16.038 34.9458 16.038H35.3058ZM38.9461 14.004C39.0421 14.796 39.3061 15.372 39.7381 15.732C40.1821 16.08 40.7941 16.254 41.5741 16.254C41.9941 16.254 42.3961 16.2 42.7801 16.092C43.1641 15.984 43.5061 15.828 43.8061 15.624L44.6701 17.136C43.8181 17.868 42.6961 18.234 41.3041 18.234C40.4761 18.234 39.7561 18.114 39.1441 17.874C38.5441 17.622 38.0401 17.28 37.6321 16.848C37.2361 16.416 36.9421 15.906 36.7501 15.318C36.5581 14.73 36.4621 14.1 36.4621 13.428C36.4621 12.648 36.5821 11.964 36.8221 11.376C37.0621 10.776 37.3861 10.278 37.7941 9.882C38.2141 9.486 38.7001 9.186 39.2521 8.982C39.8161 8.778 40.4101 8.676 41.0341 8.676C41.6701 8.676 42.2341 8.778 42.7261 8.982C43.2181 9.174 43.6261 9.45 43.9501 9.81C44.2861 10.17 44.5381 10.602 44.7061 11.106C44.8861 11.598 44.9761 12.15 44.9761 12.762C44.9761 12.966 44.9641 13.182 44.9401 13.41C44.9281 13.626 44.8981 13.824 44.8501 14.004H38.9461ZM41.0341 10.548C40.4581 10.548 39.9901 10.722 39.6301 11.07C39.2701 11.418 39.0601 11.898 39.0001 12.51H42.6721V12.276C42.6721 11.724 42.5221 11.298 42.2221 10.998C41.9341 10.698 41.5381 10.548 41.0341 10.548ZM46.9504 8.91H48.4084C49.0204 8.91 49.3264 9.174 49.3264 9.702V10.368C49.5664 9.852 49.9444 9.444 50.4604 9.144C50.9764 8.832 51.5944 8.676 52.3144 8.676C53.2864 8.676 54.0364 8.958 54.5644 9.522C55.1044 10.086 55.3744 10.932 55.3744 12.06V18H52.8184V12.24C52.8184 11.184 52.3504 10.656 51.4144 10.656C50.8264 10.656 50.3584 10.866 50.0104 11.286C49.6744 11.706 49.5064 12.288 49.5064 13.032V18H46.9504V8.91ZM59.9724 13.446C59.9724 14.334 60.1764 15.012 60.5844 15.48C61.0044 15.936 61.6344 16.164 62.4744 16.164C62.8224 16.164 63.1584 16.122 63.4824 16.038C63.8184 15.942 64.1064 15.81 64.3464 15.642L65.1024 17.388C64.7544 17.64 64.3344 17.844 63.8424 18C63.3504 18.156 62.7804 18.234 62.1324 18.234C61.3884 18.234 60.7224 18.126 60.1344 17.91C59.5464 17.682 59.0484 17.364 58.6404 16.956C58.2324 16.548 57.9144 16.05 57.6864 15.462C57.4704 14.874 57.3624 14.208 57.3624 13.464C57.3624 12.72 57.4764 12.054 57.7044 11.466C57.9324 10.878 58.2504 10.38 58.6584 9.972C59.0784 9.552 59.5824 9.234 60.1704 9.018C60.7704 8.79 61.4424 8.676 62.1864 8.676C62.7864 8.676 63.3204 8.748 63.7884 8.892C64.2564 9.036 64.6644 9.228 65.0124 9.468L64.2384 11.214C64.0104 11.058 63.7464 10.944 63.4464 10.872C63.1464 10.788 62.8284 10.746 62.4924 10.746C61.7244 10.746 61.1124 10.968 60.6564 11.412C60.2004 11.844 59.9724 12.522 59.9724 13.446ZM68.7827 8.91L70.8347 15.858L72.8507 8.91H75.5327L71.5367 19.404C71.3687 19.836 71.1887 20.208 70.9967 20.52C70.8047 20.844 70.5767 21.108 70.3127 21.312C70.0607 21.528 69.7667 21.684 69.4307 21.78C69.0947 21.876 68.6987 21.924 68.2427 21.924C68.0027 21.924 67.7927 21.912 67.6127 21.888C67.4447 21.864 67.2947 21.84 67.1627 21.816V19.89H67.6487C67.9727 19.89 68.2367 19.866 68.4407 19.818C68.6567 19.77 68.8367 19.686 68.9807 19.566C69.1247 19.446 69.2507 19.284 69.3587 19.08C69.4667 18.876 69.5807 18.618 69.7007 18.306L66.0467 8.91H68.7827Z" fill="#0068B5"/>
-<path d="M389.546 8.632V19H386.918V8.632H382.85V6.58H393.614V8.632H389.546ZM393.738 9.91H395.196C395.808 9.91 396.114 10.174 396.114 10.702V11.818C396.306 11.206 396.624 10.72 397.068 10.36C397.524 9.988 398.088 9.802 398.76 9.802C399.036 9.802 399.276 9.832 399.48 9.892V11.98H398.958C398.046 11.98 397.374 12.214 396.942 12.682C396.51 13.15 396.294 13.93 396.294 15.022V19H393.738V9.91ZM409.361 14.446C409.361 15.202 409.247 15.88 409.019 16.48C408.803 17.068 408.491 17.566 408.083 17.974C407.675 18.382 407.183 18.694 406.607 18.91C406.031 19.126 405.389 19.234 404.681 19.234C403.973 19.234 403.331 19.126 402.755 18.91C402.179 18.694 401.687 18.382 401.279 17.974C400.871 17.566 400.553 17.068 400.325 16.48C400.109 15.88 400.001 15.202 400.001 14.446C400.001 13.69 400.109 13.018 400.325 12.43C400.553 11.842 400.871 11.344 401.279 10.936C401.687 10.528 402.179 10.216 402.755 10C403.331 9.784 403.973 9.676 404.681 9.676C405.389 9.676 406.031 9.784 406.607 10C407.183 10.216 407.675 10.528 408.083 10.936C408.491 11.344 408.803 11.842 409.019 12.43C409.247 13.018 409.361 13.69 409.361 14.446ZM406.751 14.446C406.751 13.522 406.571 12.826 406.211 12.358C405.863 11.89 405.353 11.656 404.681 11.656C404.009 11.656 403.493 11.89 403.133 12.358C402.785 12.826 402.611 13.522 402.611 14.446C402.611 15.382 402.785 16.084 403.133 16.552C403.493 17.02 404.009 17.254 404.681 17.254C405.353 17.254 405.863 17.02 406.211 16.552C406.571 16.084 406.751 15.382 406.751 14.446ZM419.54 19H418.082C417.746 19 417.506 18.928 417.362 18.784C417.218 18.64 417.146 18.418 417.146 18.118V17.614C416.906 18.154 416.534 18.562 416.03 18.838C415.538 19.102 414.968 19.234 414.32 19.234C413.324 19.234 412.568 18.94 412.052 18.352C411.548 17.764 411.296 16.906 411.296 15.778V9.91H413.852V15.616C413.852 16.204 413.966 16.624 414.194 16.876C414.422 17.128 414.758 17.254 415.202 17.254C415.79 17.254 416.234 17.044 416.534 16.624C416.834 16.204 416.984 15.634 416.984 14.914V9.91H419.54V19ZM421.264 20.296C421.264 19.756 421.408 19.312 421.696 18.964C421.996 18.616 422.404 18.376 422.92 18.244C422.5 18.136 422.188 17.95 421.984 17.686C421.78 17.41 421.678 17.092 421.678 16.732C421.678 16.276 421.816 15.922 422.092 15.67C422.368 15.406 422.698 15.238 423.082 15.166C422.698 14.89 422.398 14.548 422.182 14.14C421.978 13.732 421.876 13.294 421.876 12.826C421.876 12.358 421.972 11.932 422.164 11.548C422.368 11.152 422.644 10.816 422.992 10.54C423.34 10.264 423.754 10.054 424.234 9.91C424.726 9.754 425.26 9.676 425.836 9.676C426.604 9.676 427.288 9.802 427.888 10.054H430.714V11.584H429.4C429.724 11.908 429.886 12.388 429.886 13.024C429.886 13.948 429.526 14.674 428.806 15.202C428.086 15.718 427.126 15.976 425.926 15.976C425.362 15.976 424.894 15.922 424.522 15.814C424.15 15.922 423.964 16.174 423.964 16.57C423.964 16.822 424.06 17.014 424.252 17.146C424.444 17.266 424.714 17.326 425.062 17.326H426.97C428.098 17.326 428.968 17.536 429.58 17.956C430.192 18.376 430.498 19 430.498 19.828C430.498 20.32 430.378 20.764 430.138 21.16C429.91 21.556 429.58 21.892 429.148 22.168C428.716 22.444 428.194 22.654 427.582 22.798C426.982 22.942 426.304 23.014 425.548 23.014C424.204 23.014 423.154 22.774 422.398 22.294C421.642 21.814 421.264 21.148 421.264 20.296ZM425.224 18.964C424.732 18.964 424.354 19.054 424.09 19.234C423.826 19.414 423.694 19.696 423.694 20.08C423.694 20.5 423.874 20.818 424.234 21.034C424.606 21.262 425.14 21.376 425.836 21.376C426.544 21.376 427.084 21.256 427.456 21.016C427.84 20.788 428.032 20.446 428.032 19.99C428.032 19.642 427.906 19.384 427.654 19.216C427.402 19.048 426.994 18.964 426.43 18.964H425.224ZM427.474 12.826C427.474 12.358 427.33 11.986 427.042 11.71C426.766 11.434 426.376 11.296 425.872 11.296C425.368 11.296 424.978 11.434 424.702 11.71C424.426 11.986 424.288 12.358 424.288 12.826C424.288 13.294 424.426 13.666 424.702 13.942C424.978 14.218 425.368 14.356 425.872 14.356C426.376 14.356 426.766 14.218 427.042 13.942C427.33 13.666 427.474 13.294 427.474 12.826ZM432.269 6.094H434.825V11.062C435.101 10.63 435.473 10.294 435.941 10.054C436.421 9.802 436.973 9.676 437.597 9.676C438.629 9.676 439.403 9.97 439.919 10.558C440.435 11.134 440.693 11.968 440.693 13.06V19H438.137V13.24C438.137 12.184 437.669 11.656 436.733 11.656C436.157 11.656 435.695 11.866 435.347 12.286C434.999 12.694 434.825 13.27 434.825 14.014V19H432.269V6.094ZM445.579 11.458C445.855 10.846 446.281 10.396 446.857 10.108C447.433 9.82 448.045 9.676 448.693 9.676C449.785 9.676 450.667 10.066 451.339 10.846C452.011 11.614 452.347 12.748 452.347 14.248C452.347 14.98 452.257 15.652 452.077 16.264C451.909 16.876 451.657 17.404 451.321 17.848C450.997 18.28 450.595 18.622 450.115 18.874C449.635 19.114 449.095 19.234 448.495 19.234C447.991 19.234 447.481 19.138 446.965 18.946C446.461 18.742 446.053 18.394 445.741 17.902V22.78H443.185V9.91H444.661C445.273 9.91 445.579 10.18 445.579 10.72V11.458ZM445.669 14.572C445.669 15.412 445.837 16.072 446.173 16.552C446.521 17.02 447.031 17.254 447.703 1Line truncated
-<path d="M359.163 232.48V238H356.243V224.2H365.243V226.48H359.163V230.2H364.343V232.48H359.163ZM370.255 233.26V238H367.395V224.2H372.555C374.142 224.2 375.368 224.593 376.235 225.38C377.102 226.153 377.535 227.273 377.535 228.74C377.535 230.153 377.102 231.26 376.235 232.06C375.382 232.86 374.148 233.26 372.535 233.26H370.255ZM370.255 226.34V231.12H372.075C372.928 231.12 373.568 230.933 373.995 230.56C374.422 230.187 374.635 229.58 374.635 228.74C374.635 227.9 374.422 227.293 373.995 226.92C373.582 226.533 372.948 226.34 372.095 226.34H370.255ZM384.973 226.26C384.173 226.26 383.553 226.4 383.113 226.68C382.686 226.947 382.473 227.373 382.473 227.96C382.473 228.427 382.626 228.793 382.933 229.06C383.253 229.327 383.693 229.54 384.253 229.7L386.333 230.32C387.453 230.653 388.293 231.107 388.853 231.68C389.426 232.24 389.713 233.007 389.713 233.98C389.713 234.647 389.58 235.247 389.313 235.78C389.046 236.313 388.666 236.767 388.173 237.14C387.693 237.513 387.113 237.8 386.433 238C385.766 238.2 385.026 238.3 384.213 238.3C383.253 238.3 382.32 238.153 381.413 237.86C380.506 237.567 379.693 237.12 378.973 236.52L380.233 234.56C380.82 234.987 381.433 235.327 382.073 235.58C382.713 235.82 383.4 235.94 384.133 235.94C384.92 235.94 385.54 235.793 385.993 235.5C386.446 235.207 386.673 234.76 386.673 234.16C386.673 233.693 386.52 233.34 386.213 233.1C385.92 232.86 385.48 232.653 384.893 232.48L382.673 231.88C381.66 231.6 380.866 231.147 380.293 230.52C379.72 229.893 379.433 229.08 379.433 228.08C379.433 227.427 379.56 226.84 379.813 226.32C380.08 225.8 380.44 225.36 380.893 225C381.36 224.64 381.913 224.367 382.553 224.18C383.206 223.993 383.926 223.9 384.713 223.9C385.62 223.9 386.493 224.027 387.333 224.28C388.186 224.533 388.913 224.9 389.513 225.38L388.393 227.24C387.406 226.587 386.266 226.26 384.973 226.26ZM405.902 228V230.2H396.942V228H405.902ZM405.902 232.42V234.62H396.942V232.42H405.902Z" fill="#0068B5"/>
-<path d="M439.625 224H437.069V214.91H439.625V224ZM437.051 211.184H439.643V213.506H437.051V211.184ZM442.149 214.91H443.607C444.219 214.91 444.525 215.174 444.525 215.702V216.368C444.765 215.852 445.143 215.444 445.659 215.144C446.175 214.832 446.793 214.676 447.513 214.676C448.485 214.676 449.235 214.958 449.763 215.522C450.303 216.086 450.573 216.932 450.573 218.06V224H448.017V218.24C448.017 217.184 447.549 216.656 446.613 216.656C446.025 216.656 445.557 216.866 445.209 217.286C444.873 217.706 444.705 218.288 444.705 219.032V224H442.149V214.91ZM458.231 213.092H457.817C457.145 213.092 456.659 213.194 456.359 213.398C456.071 213.59 455.927 213.992 455.927 214.604V214.91H458.141V216.854H455.927V224H453.371V216.854H452.021V214.91H453.371V214.244C453.371 213.188 453.677 212.39 454.289 211.85C454.901 211.31 455.789 211.04 456.953 211.04C457.157 211.04 457.379 211.052 457.619 211.076C457.859 211.088 458.063 211.118 458.231 211.166V213.092ZM461.39 220.004C461.486 220.796 461.75 221.372 462.182 221.732C462.626 222.08 463.238 222.254 464.018 222.254C464.438 222.254 464.84 222.2 465.224 222.092C465.608 221.984 465.95 221.828 466.25 221.624L467.114 223.136C466.262 223.868 465.14 224.234 463.748 224.234C462.92 224.234 462.2 224.114 461.588 223.874C460.988 223.622 460.484 223.28 460.076 222.848C459.68 222.416 459.386 221.906 459.194 221.318C459.002 220.73 458.906 220.1 458.906 219.428C458.906 218.648 459.026 217.964 459.266 217.376C459.506 216.776 459.83 216.278 460.238 215.882C460.658 215.486 461.144 215.186 461.696 214.982C462.26 214.778 462.854 214.676 463.478 214.676C464.114 214.676 464.678 214.778 465.17 214.982C465.662 215.174 466.07 215.45 466.394 215.81C466.73 216.17 466.982 216.602 467.15 217.106C467.33 217.598 467.42 218.15 467.42 218.762C467.42 218.966 467.408 219.182 467.384 219.41C467.372 219.626 467.342 219.824 467.294 220.004H461.39ZM463.478 216.548C462.902 216.548 462.434 216.722 462.074 217.07C461.714 217.418 461.504 217.898 461.444 218.51H465.116V218.276C465.116 217.724 464.966 217.298 464.666 216.998C464.378 216.698 463.982 216.548 463.478 216.548ZM469.395 214.91H470.853C471.465 214.91 471.771 215.174 471.771 215.702V216.818C471.963 216.206 472.281 215.72 472.725 215.36C473.181 214.988 473.745 214.802 474.417 214.802C474.693 214.802 474.933 214.832 475.137 214.892V216.98H474.615C473.703 216.98 473.031 217.214 472.599 217.682C472.167 218.15 471.951 218.93 471.951 220.022V224H469.395V214.91ZM476.426 214.91H477.884C478.496 214.91 478.802 215.174 478.802 215.702V216.818C478.994 216.206 479.312 215.72 479.756 215.36C480.212 214.988 480.776 214.802 481.448 214.802C481.724 214.802 481.964 214.832 482.168 214.892V216.98H481.646C480.734 216.98 480.062 217.214 479.63 217.682C479.198 218.15 478.982 218.93 478.982 220.022V224H476.426V214.91ZM485.174 220.004C485.27 220.796 485.534 221.372 485.966 221.732C486.41 222.08 487.022 222.254 487.802 222.254C488.222 222.254 488.624 222.2 489.008 222.092C489.392 221.984 489.734 221.828 490.034 221.624L490.898 223.136C490.046 223.868 488.924 224.234 487.532 224.234C486.704 224.234 485.984 224.114 485.372 223.874C484.772 223.622 484.268 223.28 483.86 222.848C483.464 222.416 483.17 221.906 482.978 221.318C482.786 220.73 482.69 220.1 482.69 219.428C482.69 218.648 482.81 217.964 483.05 217.376C483.29 216.776 483.614 216.278 484.022 215.882C484.442 215.486 484.928 215.186 485.48 214.982C486.044 214.778 486.638 214.676 487.262 214.676C487.898 214.676 488.462 214.778 488.954 214.982C489.446 215.174 489.854 215.45 490.178 215.81C490.514 216.17 490.766 216.602 490.934 217.106C491.114 217.598 491.204 218.15 491.204 218.762C491.204 218.966 491.192 219.182 491.168 219.41C491.156 219.626 491.126 219.824 491.078 220.004H485.174ZM487.262 216.548C486.686 216.548 486.218 216.722 485.858 217.07C485.498 217.418 485.288 217.898 485.228 218.51H488.9V218.276C488.9 217.724 488.75 217.298 488.45 216.998C488.162 216.698 487.766 216.548 487.262 216.548ZM501.836 224H500.36C499.748 224 499.442 223.73 499.442 223.19V222.596C499.202 223.1 498.83 223.502 498.326 223.802C497.834 224.09 497.24 224.234 496.544 224.234C495.944 224.234 495.404 224.12 494.924 223.892C494.444 223.664 494.036 223.346 493.7 222.938C493.376 222.518 493.124 222.014 492.944 221.426C492.764 220.838 492.674 220.178 492.674 219.446C492.674 218.69 492.77 218.018 492.962 217.43C493.154 216.83 493.424 216.332 493.772 215.936C494.12 215.528 494.534 215.216 495.014 215C495.506 214.784 496.052 214.676 496.652 214.676C497.228 214.676 497.744 214.79 498.2 215.018C498.656 215.246 499.016 215.57 499.28 215.99V211.094H501.836V224ZM499.352 219.464C499.352 218.588 499.178 217.904 498.83 217.412C498.494 216.908 497.996 216.656 497.336 216.656C496.688 216.656 496.184 216.902 495.824 217.394C495.464 217.886 495.284 218.576 495.284 219.464C495.284 220.364 495.452 221.054 495.788 221.534C496.124 222.014 496.622 222.254 497.282 222.254C497.93 222.254 498.434 222.008 498.794 221.516C499.166 221.012 499.352 220.328 499.352 219.464ZM508.752 214.91H510.21C510Line truncated
-<path d="M439.099 241.458C439.375 240.846 439.801 240.396 440.377 240.108C440.953 239.82 441.565 239.676 442.213 239.676C443.305 239.676 444.187 240.066 444.859 240.846C445.531 241.614 445.867 242.748 445.867 244.248C445.867 244.98 445.777 245.652 445.597 246.264C445.429 246.876 445.177 247.404 444.841 247.848C444.517 248.28 444.115 248.622 443.635 248.874C443.155 249.114 442.615 249.234 442.015 249.234C441.511 249.234 441.001 249.138 440.485 248.946C439.981 248.742 439.573 248.394 439.261 247.902V252.78H436.705V239.91H438.181C438.793 239.91 439.099 240.18 439.099 240.72V241.458ZM439.189 244.572C439.189 245.412 439.357 246.072 439.693 246.552C440.041 247.02 440.551 247.254 441.223 247.254C441.583 247.254 441.889 247.182 442.141 247.038C442.405 246.894 442.615 246.696 442.771 246.444C442.939 246.18 443.059 245.874 443.131 245.526C443.215 245.178 443.257 244.806 443.257 244.41C443.257 243.522 443.095 242.844 442.771 242.376C442.447 241.896 441.961 241.656 441.313 241.656C440.629 241.656 440.101 241.92 439.729 242.448C439.369 242.964 439.189 243.672 439.189 244.572ZM447.885 239.91H449.343C449.955 239.91 450.261 240.174 450.261 240.702V241.818C450.453 241.206 450.771 240.72 451.215 240.36C451.671 239.988 452.235 239.802 452.907 239.802C453.183 239.802 453.423 239.832 453.627 239.892V241.98H453.105C452.193 241.98 451.521 242.214 451.089 242.682C450.657 243.15 450.441 243.93 450.441 245.022V249H447.885V239.91ZM463.509 244.446C463.509 245.202 463.395 245.88 463.167 246.48C462.951 247.068 462.639 247.566 462.231 247.974C461.823 248.382 461.331 248.694 460.755 248.91C460.179 249.126 459.537 249.234 458.829 249.234C458.121 249.234 457.479 249.126 456.903 248.91C456.327 248.694 455.835 248.382 455.427 247.974C455.019 247.566 454.701 247.068 454.473 246.48C454.257 245.88 454.149 245.202 454.149 244.446C454.149 243.69 454.257 243.018 454.473 242.43C454.701 241.842 455.019 241.344 455.427 240.936C455.835 240.528 456.327 240.216 456.903 240C457.479 239.784 458.121 239.676 458.829 239.676C459.537 239.676 460.179 239.784 460.755 240C461.331 240.216 461.823 240.528 462.231 240.936C462.639 241.344 462.951 241.842 463.167 242.43C463.395 243.018 463.509 243.69 463.509 244.446ZM460.899 244.446C460.899 243.522 460.719 242.826 460.359 242.358C460.011 241.89 459.501 241.656 458.829 241.656C458.157 241.656 457.641 241.89 457.281 242.358C456.933 242.826 456.759 243.522 456.759 244.446C456.759 245.382 456.933 246.084 457.281 246.552C457.641 247.02 458.157 247.254 458.829 247.254C459.501 247.254 460.011 247.02 460.359 246.552C460.719 246.084 460.899 245.382 460.899 244.446ZM467.622 244.446C467.622 245.334 467.826 246.012 468.234 246.48C468.654 246.936 469.284 247.164 470.124 247.164C470.472 247.164 470.808 247.122 471.132 247.038C471.468 246.942 471.756 246.81 471.996 246.642L472.752 248.388C472.404 248.64 471.984 248.844 471.492 249C471 249.156 470.43 249.234 469.782 249.234C469.038 249.234 468.372 249.126 467.784 248.91C467.196 248.682 466.698 248.364 466.29 247.956C465.882 247.548 465.564 247.05 465.336 246.462C465.12 245.874 465.012 245.208 465.012 244.464C465.012 243.72 465.126 243.054 465.354 242.466C465.582 241.878 465.9 241.38 466.308 240.972C466.728 240.552 467.232 240.234 467.82 240.018C468.42 239.79 469.092 239.676 469.836 239.676C470.436 239.676 470.97 239.748 471.438 239.892C471.906 240.036 472.314 240.228 472.662 240.468L471.888 242.214C471.66 242.058 471.396 241.944 471.096 241.872C470.796 241.788 470.478 241.746 470.142 241.746C469.374 241.746 468.762 241.968 468.306 242.412C467.85 242.844 467.622 243.522 467.622 244.446ZM476.179 245.004C476.275 245.796 476.539 246.372 476.971 246.732C477.415 247.08 478.027 247.254 478.807 247.254C479.227 247.254 479.629 247.2 480.013 247.092C480.397 246.984 480.739 246.828 481.039 246.624L481.903 248.136C481.051 248.868 479.929 249.234 478.537 249.234C477.709 249.234 476.989 249.114 476.377 248.874C475.777 248.622 475.273 248.28 474.865 247.848C474.469 247.416 474.175 246.906 473.983 246.318C473.791 245.73 473.695 245.1 473.695 244.428C473.695 243.648 473.815 242.964 474.055 242.376C474.295 241.776 474.619 241.278 475.027 240.882C475.447 240.486 475.933 240.186 476.485 239.982C477.049 239.778 477.643 239.676 478.267 239.676C478.903 239.676 479.467 239.778 479.959 239.982C480.451 240.174 480.859 240.45 481.183 240.81C481.519 241.17 481.771 241.602 481.939 242.106C482.119 242.598 482.209 243.15 482.209 243.762C482.209 243.966 482.197 244.182 482.173 244.41C482.161 244.626 482.131 244.824 482.083 245.004H476.179ZM478.267 241.548C477.691 241.548 477.223 241.722 476.863 242.07C476.503 242.418 476.293 242.898 476.233 243.51H479.905V243.276C479.905 242.724 479.755 242.298 479.455 241.998C479.167 241.698 478.771 241.548 478.267 241.548ZM487.658 241.62C487.238 241.62 486.908 241.692 486.668 241.836C486.428 241.968 486.308 242.172 486.308 242.448C486.308 242.676 486.38 242.856 486.524 242.988C486.668 243.108 486.86 243.204 487.1 243.276L488.468 243.69C489.308 243.942 489.926 244.272 490.322 244Line truncated
-<line x1="678" y1="231" x2="416" y2="231" stroke="#0068B5" stroke-width="2"/>
-<defs>
-<pattern id="pattern0" patternContentUnits="objectBoundingBox" width="1" height="1">
-<use xlink:href="#image0" transform="translate(-0.00717841) scale(0.00133997 0.00153139)"/>
-</pattern>
-<pattern id="pattern1" patternContentUnits="objectBoundingBox" width="1" height="1">
-<use xlink:href="#image1" transform="translate(-0.00324676) scale(0.00162338 0.00206612)"/>
-</pattern>
-<image id="image0" width="757" height="653" xlink:href="data:image/png;base64,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 truncated
-<image id="image1" width="620" height="484" xlink:href="data:image/png;base64,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 truncated
-</defs>
-</svg>
@@ -87,7 +87,8 @@ Here we've specified all information about user's input:
 - [Layout](./layout_overview.md) is "NHWC". It means that 'height=480, width=640, channels=3'
 - Color format is `BGR`

-### Declare model's layout <a name="declare_model_s_layout"></a>
+@anchor declare_model_s_layout
+### Declare model's layout

 Model's input already has information about precision and shape. Preprocessing API is not intended to modify this. The only thing that may be specified is input's data [layout](./layout_overview.md)

@@ -1,4 +1,4 @@
-## If <a name="If"></a> {#openvino_docs_ops_infrastructure_If_8}
+## If {#openvino_docs_ops_infrastructure_If_8}

 **Versioned name**: *If-8*

@@ -1,4 +1,4 @@
-## DeformableConvolution<a name="DeformableConvolution"></a> {#openvino_docs_ops_convolution_DeformableConvolution_8}
+## DeformableConvolution {#openvino_docs_ops_convolution_DeformableConvolution_8}

 **Versioned name**: *DeformableConvolution-8*

@@ -1,4 +1,4 @@
-## RandomUniform <a name="RandomUniform"></a> {#openvino_docs_ops_generation_RandomUniform_8}
+## RandomUniform {#openvino_docs_ops_generation_RandomUniform_8}

 **Versioned name**: *RandomUniform-8*

@@ -1,4 +1,4 @@
-## Gather <a name="Gather"></a> {#openvino_docs_ops_movement_Gather_8}
+## Gather {#openvino_docs_ops_movement_Gather_8}

 **Versioned name**: *Gather-8*

@@ -1,4 +1,4 @@
-## Slice <a name="Slice"></a> {#openvino_docs_ops_movement_Slice_8}
+## Slice {#openvino_docs_ops_movement_Slice_8}

 **Versioned name**: *Slice-8*

@@ -1,4 +1,4 @@
-## AdaptiveAvgPool<a name="AdaptiveAvgPool"></a> {#openvino_docs_ops_pooling_AdaptiveAvgPool_8}
+## AdaptiveAvgPool {#openvino_docs_ops_pooling_AdaptiveAvgPool_8}

 **Versioned name**: *AdaptiveAvgPool-8*

@@ -1,4 +1,4 @@
-## AdaptiveMaxPool<a name="AdaptiveMaxPool"></a> {#openvino_docs_ops_pooling_AdaptiveMaxPool_8}
+## AdaptiveMaxPool {#openvino_docs_ops_pooling_AdaptiveMaxPool_8}

 **Versioned name**: *AdaptiveMaxPool-8*

@@ -1,4 +1,4 @@
-## MaxPool <a name="MaxPool"></a> {#openvino_docs_ops_pooling_MaxPool_8}
+## MaxPool {#openvino_docs_ops_pooling_MaxPool_8}

 **Versioned name**: *MaxPool-8*

@@ -1,4 +1,4 @@
-# ReduceLp {#openvino_docs_ops_reduction_ReduceL1_4}
+# ReduceL1 {#openvino_docs_ops_reduction_ReduceL1_4}

 **Versioned name**: *ReduceL1-4*

@@ -1,4 +1,4 @@
-# ReduceLp {#openvino_docs_ops_reduction_ReduceL2_4}
+# ReduceL2 {#openvino_docs_ops_reduction_ReduceL2_4}

 **Versioned name**: *ReduceL2-4*

@@ -1,4 +1,4 @@
-##  MatrixNonMaxSuppression<a name="MatrixNonMaxSuppression"></a> {#openvino_docs_ops_sort_MatrixNms_8}
+##  MatrixNonMaxSuppression {#openvino_docs_ops_sort_MatrixNms_8}

 **Versioned name**: *MatrixNonMaxSuppression-8*

@@ -1,4 +1,4 @@
-##  MulticlassNonMaxSuppression<a name="MulticlassNonMaxSuppression"></a> {#openvino_docs_ops_sort_MulticlassNonMaxSuppression_8}
+##  MulticlassNonMaxSuppression {#openvino_docs_ops_sort_MulticlassNonMaxSuppression_8}

 **Versioned name**: *MulticlassNonMaxSuppression-8*

@@ -7,6 +7,11 @@ include(cmake/ie_parallel.cmake)
 # pre-find TBB: need to provide TBB_IMPORTED_TARGETS used for installation
 ov_find_tbb()

+if(TBB_FOUND AND TBB_VERSION VERSION_GREATER_EQUAL 2021)
+    message(STATUS "Static tbbbind_2_5 package usage is disabled, since oneTBB is used")
+    set(ENABLE_TBBBIND_2_5 OFF)
+endif()
+
 if(ENABLE_TBBBIND_2_5)
    # try to find prebuilt version of tbbbind_2_5
    find_package(TBBBIND_2_5 QUIET)
@@ -46,18 +51,11 @@ if(THREADING MATCHES "^(TBB|TBB_AUTO)$" AND

    if(TBB MATCHES ${TEMP})
        set(tbb_downloaded ON)
-    elseif(DEFINED ENV{TBB})
+    elseif(DEFINED ENV{TBBROOT})
        set(tbb_custom ON)
    endif()

-    if(tbb_custom OR ENABLE_SYSTEM_TBB)
-        # since the setup.py for pip installs tbb component
-        # explicitly, it's OK to put EXCLUDE_FROM_ALL to such component
-        # to ignore from IRC distribution
-        set(exclude_from_all EXCLUDE_FROM_ALL)
-    endif()
-
-    if(ENABLE_SYSTEM_TBB)
+    if(ENABLE_SYSTEM_TBB OR tbb_custom)
        # need to take locations of actual libraries and install them
        foreach(tbb_lib IN LISTS TBB_IMPORTED_TARGETS)
            get_target_property(tbb_loc ${tbb_lib} IMPORTED_LOCATION_RELEASE)
@@ -68,40 +66,40 @@ if(THREADING MATCHES "^(TBB|TBB_AUTO)$" AND
            # We need to install such files
            get_filename_component(name_we "${tbb_loc}" NAME_WE)
            get_filename_component(dir "${tbb_loc}" DIRECTORY)
+            # grab all tbb files matching pattern
            file(GLOB tbb_files "${dir}/${name_we}.*")
            foreach(tbb_file IN LISTS tbb_files)
                if(tbb_file MATCHES "^.*\.${CMAKE_SHARED_LIBRARY_SUFFIX}(\.[0-9]+)*$")
+                    # since the setup.py for pip installs tbb component
+                    # explicitly, it's OK to put EXCLUDE_FROM_ALL to such component
+                    # to ignore from IRC / apt / yum distribution;
+                    # but they will be present in .wheel
                    install(FILES "${tbb_file}"
                            DESTINATION runtime/3rdparty/tbb/lib
-                            COMPONENT tbb ${exclude_from_all})
+                            COMPONENT tbb EXCLUDE_FROM_ALL)
                endif()
            endforeach()
        endforeach()
-    else()
+    elseif(tbb_downloaded)
        if(WIN32)
            install(DIRECTORY "${TBB}/bin"
                    DESTINATION runtime/3rdparty/tbb
-                    COMPONENT tbb ${exclude_from_all})
-        elseif(tbb_custom OR tbb_downloaded)
+                    COMPONENT tbb)
+        else()
            install(DIRECTORY "${TBB}/lib"
                    DESTINATION runtime/3rdparty/tbb
-                    COMPONENT tbb ${exclude_from_all}
-                    FILES_MATCHING
-                        # install only versioned shared libraries
-                        REGEX "^.*\.${CMAKE_SHARED_LIBRARY_SUFFIX}(\.[0-9]+)*$")
+                    COMPONENT tbb)
        endif()
-    endif()
-
-    # development files are needed only for 'tbb_downloaded' case
-    # which we are going to distribute
-    if(tbb_downloaded)
-        ie_cpack_add_component(tbb_dev REQUIRED)
-        list(APPEND core_dev_components tbb_dev)

        install(FILES "${TBB}/LICENSE"
                DESTINATION runtime/3rdparty/tbb
                COMPONENT tbb)

+        # install development files
+
+        ie_cpack_add_component(tbb_dev REQUIRED)
+        list(APPEND core_dev_components tbb_dev)
+
        set(IE_TBB_DIR_INSTALL "3rdparty/tbb/cmake")
        install(FILES "${TBB}/cmake/TBBConfig.cmake"
                    "${TBB}/cmake/TBBConfigVersion.cmake"
@@ -115,13 +113,14 @@ if(THREADING MATCHES "^(TBB|TBB_AUTO)$" AND
            # .lib files are needed only for Windows
            install(DIRECTORY "${TBB}/lib"
                    DESTINATION runtime/3rdparty/tbb
-                    COMPONENT tbb)
+                    COMPONENT tbb_dev)
        endif()
+    else()
+        message(WARNING "TBB of unknown origin. TBB files are not installed")
    endif()

    unset(tbb_downloaded)
    unset(tbb_custom)
-    unset(exclude_from_all)
 endif()

 # install tbbbind for static OpenVINO case
@@ -21,6 +21,9 @@
 #if ((IE_THREAD == IE_THREAD_TBB) || (IE_THREAD == IE_THREAD_TBB_AUTO))
 #    include <tbb/concurrent_queue.h>
 #    include <tbb/enumerable_thread_specific.h>
+#    ifndef TBB_PREVIEW_GLOBAL_CONTROL
+#        define TBB_PREVIEW_GLOBAL_CONTROL 1
+#    endif
 #    include <tbb/global_control.h>
 #    include <tbb/task_group.h>
 #    include <tbb/task_scheduler_observer.h>
@@ -29,7 +29,11 @@ function(ie_add_mkldnn)
    set(DNNL_CPU_RUNTIME "${THREADING}" CACHE STRING "" FORCE)
    set(DNNL_GPU_RUNTIME "NONE" CACHE STRING "" FORCE)
    set(DNNL_BLAS_VENDOR "NONE" CACHE STRING "" FORCE)
-    set(DNNL_VERBOSE "OFF" CACHE STRING "" FORCE)
+    if (ENABLE_CPU_DEBUG_CAPS)
+        set(DNNL_VERBOSE "ON" CACHE STRING "" FORCE)
+    else()
+        set(DNNL_VERBOSE "OFF" CACHE STRING "" FORCE)
+    endif()
    set(SDL_cmake_included ON)  ## to skip internal SDL flags. SDL flags are already set on IE level
    if (ANDROID OR ((CMAKE_CXX_COMPILER_ID STREQUAL "MSVC") AND NOT (THREADING STREQUAL "OMP")))
        set(OpenMP_cmake_included ON) ## to skip "omp simd" inside a code. Lead to some crashes inside NDK LLVM..
@@ -319,7 +319,9 @@ std::vector<size_t> GetOptimalLocalWorkGroupSizes(std::vector<size_t> gws, const
        // Revert basic priority if something is wrong
        if (priority_order[0] == priority_order[1] || priority_order[0] == priority_order[2] || priority_order[1] == priority_order[2] ||
            priority_order[0] > 2 || priority_order[1] > 2 || priority_order[2] > 2) {
-            priority_order = { 0, 1, 2 };
+            priority_order[0] = 0;
+            priority_order[1] = 1;
+            priority_order[2] = 2;
        }
    }

@@ -42,6 +42,7 @@ class TestBOMFile(unittest.TestCase):
            r'^# SPDX-License-Identifier: Apache-2.0$',
        ]]

+    @unittest.skip("83076 - test infra change affects bom tests")
    def test_bom_file(self):
        missing_files = list()
        for src_dir in dirs_to_search:
@@ -67,10 +68,12 @@ class TestBOMFile(unittest.TestCase):
                print(f.replace('\\', '/'))
        self.assertTrue(not len(missing_files), '{} files missed in BOM'.format(len(missing_files)))

+    @unittest.skip("83076 - test infra change affects bom tests")
    def test_bom_does_not_contain_unittest_files(self):
        for file_name in self.existing_files:
            self.assertFalse(file_name.endswith('_test.py'), 'BOM file contains test file {}'.format(file_name))

+    @unittest.skip("83076 - test infra change affects bom tests")
    def test_deleted_files_still_stored_in_bom(self):
        deleted = list()
        for file in self.existing_files:
@@ -82,6 +85,7 @@ class TestBOMFile(unittest.TestCase):
                print(f)
        self.assertTrue(not len(deleted), '{} files deleted but still stored in BOM'.format(len(deleted)))

+    @unittest.skip("83076 - test infra change affects bom tests")
    def test_alphabetical_order_and_duplicates(self):
        sorted_bom = sorted([x for x in self.existing_files if self.existing_files.count(x) == 1], key=str.lower)
        if self.existing_files != sorted_bom:
@@ -89,6 +93,7 @@ class TestBOMFile(unittest.TestCase):
            print(*sorted_bom, sep='\n')
            self.assertTrue(False)

+    @unittest.skip("83076 - test infra change affects bom tests")
    def test_missed_intel_header(self):
        missing_files = list()
        for src_dir in dirs_to_search: