* fluid update WW52 2020 OCV 4.5.1 - attempt#2

* fluid update WW52 2020 OCV 4.5.1 - attempt#3 with build fixes

* fluid update WW52 2020 OCV 4.5.1 - attempt#3

Set fixed version of the urllib3 package in the requirements because of the security issue in urllib3==1.25.8 (#3740)

* Set fixed version of the urllib3 package in the requirements because of the security issue in 1.25.8

* Set lower bound version of the urllib3 package in the requirements because of the security issue in 1.25.8

* Added CC macros to validate, clone and visit

* Fixed names

* Fixed code style

* Add exceptions

* Revert "Add exceptions"

This reverts commit 0489ba376f762f1f79b374d79ff63b561662a2c9.

* Update ngraph macros, throw an exception if code is disable for nGraph op

* Fixed code style

* Simplified NGRAPH_OP_SCOPE

* Changed TYPE_CASE macros

* Fixed compilation

* Fixed code style

* Fixed build

* [MO] Implement transformation to avoid RandomUniform in a particular drop-out block
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Remove old RandomUniform transformation and correct const values
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix atol value
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Move DropoutWithRandomUniform transformation to the front
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Change just RandomUniform to Broadcast in the transformation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Correct comment for the transformation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Remove redundant line
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Improve corner-case resistance

* small improvements

* [ONNX] don't hardcode shape in Softmax operator

* use named constant for special zero param in reshape

* Added Get Started Guide for Raspbian

* Updated the TOC xml file

* Minor fixes

* Implemented review comments

* Fixed broken link

* [MO] Add CMake install for Model Optimizer

* [MO] Update test for version.py

* [MO] Add CMake install for Model Optimizer

* [MO] Update test for version.py

* [MO] Add CMake install for Model Optimizer

* [MO] Update test for version.py

* [nGraph] Python API should be compiled and installed via CMake (41857)

* Refactored wheel setup script to build module using CMake

* Update build instructions

* Added USE_SOURCE_PERMISSIONS to cmake install

* Adjust CMake compiler flags conditions

* fix CPack issue for CI build pipeline

* case insensitive option check

* build only python API if ngraph_DIR provided

* fix lib extension for macOS

* -fixed style (flake8)

 -added paralllel build option & description

* fix flake8 B006 check

* add ngraph_DIR & remove unsed env. variables.

* Reworked build & test instructions to make it more straightforward

* remove unused CMake arguments for setup.py

* make source dir condition more general

* Update BUILDING.md

* Update BUILDING.md

* Update BUILDING.md

* beautified instructions wording

* fix wheel build issue after sourcing setupvars

* Extend user options to build, install and develop commands
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>

* Fix for fusing depthwise operations into bf16 convolutions.

* ScaleShift layer was returned to _complementbf16 list.

* Description: currently IRs with NMS version < 5 don't work because conversion of previous NMS versions to NMS-5 happens after DTS (in opset1 to legacy conversion), while for Myriad Plugin it's necessary to do so at the very beginning of ngraph conversion pipeline.

* ovino doc assets

* update cmake doc build

* fixes

* [CPU] Added memory format attribute

* TensorIterator deserialization. Introduce new on_adapter(Function) and add implementation in on_adapter(void) for Input and Output Descriptions. Remove factory adapter.

* Add comments to functions provided. Add missing  on_adapter() after rebase.

* Apply formatting.

* Remove visit_attributes from SubGraphOp, remove declaration for createSubGraphLayer.

* Add port map parsing to address not consecutive order of external_port_id appearance.

* Remove header for factory_adapter.

* Add on_adapter() in V10Parse::parse() function.

* Add m_num_iterations initialization for concat output.

* Remove redundant lines, add doxygen comments.

* Change cpp/ie_cnn_network.h to local include, remove temporary map object from range for loop.

* Restore protected access for SubGraphOp.

* [MO] Add CMake install for Model Optimizer

* [MO] Update test for version.py

* [MO] Add CMake install for Model Optimizer

* [MO] Update test for version.py

* [MO] Add CMake install for Model Optimizer

* [MO] Update test for version.py

* - fix install paths for onnx_reader and ir_reader

- remove static lib installation for plugins on plugins
- 97-myriad-usbboot.rules is installed only for Linux

* added new line

* - Return GNAPlugin to default build list

- Remove test artifacts from cmake install distribution
- Remove nGraph static libs from cmake install distribution

* revert install rule for archive(.lib)

* revert install rule for onnx_importer (.lib)

* async network loading in the MULTI. makes the overall load time as MAX of the individual devices loading timings, as opposite to the current SUM

* correct way of getting perf counters flag for the MULTI (adding to the async load PR, as this is minor change)

* accomodating remark from the code review- MULTI enables the perf counters only if all devices support/enable that

* CMAKE: Added MODULE linker flags

* Fixed plugins.xml s

* Use module instead of shared library

* Fixes

* tab 2 spaces

* Renamed get_shared_library_name to ie_plugin_get_file_name

* Try ENABLE_FASTER_BUILD on public CI

* Fixed UNITY compilation for Windows

* Add new path for constant in IR serializer.

* Apply suggestion from review.

* Unique name for temporary test file

* Switch from static to constant member function - GetTestName

* Ensure bin path is not empty.

* Compare Constants op by string values converted to float.

* Add path validation.
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>

* create type_prop tests

* add abs type_prop tests to CMakeList

* add type prop test for dynamic input shape

* fix style

Co-authored-by: Roman Lyamin <roman.lyamin@intel.com>
Co-authored-by: Mikhail Letavin <mikhail.letavin@intel.com>

* New Gather op reference implementation.

* Unify span implementation for gather and gather_nd.

Create span.hpp for common implementation of span.

* Move span to utils directory.

* Address review comments.

* update span

* Address PR comments.
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>

* Errors and warnings highlighting for UNIX platforms

* The option added for errors and warning highlighting enabling

* add 4 tests for operators based on model zoo

* fix wrong names of the models

* add functional tests for equal, lstm_cell and psroi_pooling operators

* add functional tests for ConverLike and Mod operators

* add funtional tests which were disabled, and add a minor change in convert_function_to_cnn_network.cpp file in order to make LogicalNot operator pass a test

* back to the previous .xml model

* made a changes in ir_layer_parsers.cpp in order to make logicalNot pass a test

* minor fixes to LogicalNot operator in ie_layers_parsers.cpp

* rename friendly name to "not"

* add if statement for Activation type

* fix style

* [IE CORE] enable plugins & dependent libs loading using absolute path

urrently this allowed to use plugins.xml file to specify full path to specific plugin with it's all dependency, not to be persisted in CWD or in PATH

* Code review fixes

* Disable tests which read prototxt if protobuf lite is used

* added missing line

* cmake flags refactor

* Refactored developer package

* Added fuzzing for CMAKE_MODULE_LINKER_FLAGS as well

* Added options for developer package

* More improvements

* Further improvements

* Removed global CMAKE_MODULE_PATH population

* Fixes

* Final fixes

* Fixed python build

* Fix for TBB

* Fixed Find TBB

* Fixed install

* Fixes for OV features

* Split developer targets per component

* Fixed IE build tree config

* Fixed ITT

* Fixed review comments

* Clean export dependencies

* Fixed export of pugixml

* Added IEDevScripts_DIR for Android

* Fixed Android #2

* Fixed Android #3

* Fixed python cc

* Disabled Core threading tests on GNA

* Added if DEFINE construction

* Changed OV_SCOPE semantic

* Fixed the code style

* Fixed redundant lines

Constant port numbering was changed in MO serialization, needed to
regenerate models for serialization functional tests to reflect current
MO IR.

Previously Loop shape inference function
produced dynamic shapes for body parameters
and loop outputs if iteration count is
unknown (dynamic) or loop input data is
dynamic. At the same, time some dimensions
of input/outputs of body/loop could be
inferred under this circumstances which could
critical for model enablement (ex. Myriad-X
could support convolutions with dynamic batch,
but could not support convolutions with dynamic
spatial dimensions)
Signed-off-by: Gladilov, Gleb <gleb.gladilov@intel.com>

* Remove broadcusting

* Refactoring some code

* Add unit tests

* Update description

* Refactoring transformation

* Add is_broadcastable_shapes checks

* Update is_eliminate_broadcast func

* Add unit tests

* Update unit tests

* Add unit tests

* Add unit tests

* Remove unused include

* Add dynemic tests

* Update unit tests

* Fix code style

* Fix unit tests code style

* Fix code style

* Add one more case for elumenate broadcast

* Fix according to review

* Refactoring transformation code