* Refactoring FunctionsComparator - extract node comparison part

* try to fix logic and CentOS bulids

* Add negative test for precision

* Use fixed ngraph::descriptor::Tensor type instead template type

* reorganize ngraph_test_utils.cpp

* Cleanup after merge master into branch

Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>

* Winograd conv seems to cause slight error
* Enable fsv16 path in case where RegionYolo exists
* Prefer bfyx from RegionYolo primitive

* [Docs] Add opset6 content and add opset reference

Delta to opset5:
 * CTCGreedyDecoderSeqLen
 * GatherElements
 * MVN-1 -> MVN-6

* Update opset6.md

* adding ie_docs.xml based on @lazarevevgeny comment

* fix ss

* successfully converted

* successfully run moved infer and normalizer unit-tests

* successfully rewritten StridedSlice infer unittests

* int64 array

* Successfully converter crash-when-loading, xj_feauture and toy nets (cherry-picked maxpoolV4 and tf_broadcast_ext)

* successfully moved PermuteAttrs to general mechanism

* successfully converted xj_feauture and crash when loading with the new rewritten SS infer

* fixed get_shape_from_slice and moved to common utils

* fixed extending masks and some other

* some refactoring

* fixed extending masks in extractor, fixed licence year and some other code clearing

* corrected a couple of unittests

* fox permute for 5 rank slice and 4 rank inputs/

* WIP

* Added comments

* fixed StridedSlice in ProposalMutation.py

* rechecked shape_infer unittests added some new cases

* added shape_infer unit-tests after StridedSliceNormalizer pass and Permute unit-tests

* corrected unittests

* Applied review comments

* general permutations for inputs implemented, corrected ellipsis unrolling when shrink_axis is at the beginning, some other corrections

* removed code duplication in infer and normalizer, moved 'slices' attr normalizing to StridedSliceNormalizer.py

* removed some code duplication and other minor improvements

* Added tests

* minor corrections

* wider range of unittests added (froze the number)

* review comments applied

* enabled skipped unit-test

* comment corrections

* applied review comments: changed op -> type, added some asserts, corrected comments and other minor corrections

* sorted inputs, updated Supported_Frameworks_Layers.md, some minor

Support (Gather+GatherElements) optimization for GatherElements layer.
Includes PR: #4140

Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>

* [VPU] Fix PR #4060

* [VPU] Review fixes

* [LPT] StridedSliceTransformation fix

* added comments

…ssue with astroid==2.5 (#4365)

* Update ONNX compliance test list

* Update test_backend.py

* Commit.

* Reverted fix in the nGraph conversion of Intepolate-1 into Interpolate-4.

* Small fix.

* Added comment.

* Added TODO.

* Changed check for dimension size to be non-negative

* Added unit test for reading model with ShapeOf from scalar and fixed IE IR parser

* Added comment to the test

* Fixed ShapeOfFromScalar test

* Fixed incorrect merge

* Added test for a negative value of "dim" in IR

* Add CTCGreedyDecoder mo support

* Update copiright

* Update bom file

* Add transformation

* Fix code style

* Fix according to review

* Add CTCGreedyDecoder v6 to ConvertPrecision

* Hot fix

* Add replasment for ctc_greedy_decoder

* Fix test

* Fix

* Update ie transform

* Draft ctc lost replaser

* Add ctcloss replaser

* Update

* Refactoring code

* Update transformation

* Update decoder

* Remove comments

* Convert seq mask from int to float

* Fix unit test

* Add dynamic tests

* Refactoring code

* Fix py code style

* update style

* Disable ctcgreedydecoder transform for mkldnn plugin

* Add some comments

* Add transfor code comments

* Enable transform from differend plagins

* Fix mo

* fix tests

* Fix comment

* Fix convert precition

* Update comment

* Fix prcition

* Refactoring according to reviw

* Add ir reder extender

* Rename transformation

* Update bom file

* Fix mo replacer

* Fix tests

* Move transform to decomp

* Add check blank_index

* Rafactoring ctcloss

* Change dinemic rank check

* Fix ctclos extractor

* Remove comment

* Fix code style

* Refactoring pattern matcher for transformation CTCGreedyDecoder

* Disavle transform for vpu

* Refactoring according to review

* Refactoring code

* Disable transformation for cldnn

* Remove unused code

* Reverse transfomation

* Fix code style

* Hot fix transform

* Fix unit tests

* Update transform

* Enable transform in common pipline

* Fix names replasments for mo transformations

* Hot fix

* Fix

* [MO][TF] Fixed TFSliceToSlice conversion error on Win, replaced int32_max with ShapeOf, minor correction in comments

* review apply: added create_op_with_const_inputs

* review apply: renamed variables, updated typehints for int64_array, float_array, float32_array

* renamed to correct_ends

* returned back check_op_attrs=True

One badge for all checks: including GitHub actions, Azure DevOps, Jenkins

* [GNA] Enable Zero Padding

   Fix CNN2D stride order
   Draft pooling

* Implement CNN2D FP32 mode in GNAPlugin

* Move padding flag to Policy

* Remove inactive output rotation code from CNN2D graph compiler routine (review)

* Add ConvReluSequence tests to gnaFuncTest as DISABLED

* [GNA] Added import/export names of memory layer

Added test

Added fix

[GNA] Added import/export names of memory layer

Added fix

test build

centOS fix

* Added fix version

* [GNA] Added export/import scale factor for memory layer

* [GNA] Fix comments

* Replaced ie::NetPass::ConvertPrecision with ngraph::ConvertPrecision
* Fixed case with wrong behavior in merge_subsequent_dsr_operations.cpp
* Remove NGRAPH_RTTI from vpu/ngraph #49823

* Fix puttern matcher condition

* Refactoring pattern matcher

* Update unit tests

…zation (#4378)

* Add tests which reproduces issue

* Fix Output Names in StridedSlice optimization

* Fix codestyle

* Add check if at least one StridedSlice has Result operation as a consumer

…4421)

* [IE][VPU] Add config option to disable asynchronous DMA on device
* Parse option
* Update firmware

* [LPT] denormal handling in AddTransformation

* [LPT] ReshapeTransformation: 4D->3D after Convolution fix

* [LPT] fuse eltwise to fq fix

* [LPT] fuse mul to fq: mul by zero handling

* [LPT] FuseConvertTransformation: convert with unexpected precision

* [LPT] Disable constant folding on weights during reshape

* [LPT] new Q/DQ weigths prerequisites

* [LPT] AddTransformation (swapMultiplyAndAdd) constant precision definition workaround

Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>

* draft - looks good, need merge with other branch

* apply suggestions from PR

* apply suggestions from PR

* add unit test - NotValidInputOrOutput

* rephraze equal for constant

* cleanup all TODOs

* Try to fix TI

* try to satisfy PR comments

* fix spelling

Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>

* Removed hardcoded shapes from LogSoftmax operation

* Added tests

* Fixed comments

…#4492)

This reverts commit a15246e.

)

* [CPU] Fixed MVN with negative axes

* Added tests

* Added tests with unordered axes case

* Added rpath for plugins

* Corrected dll pathes for PIP

* Fixed plugin install names

* Put libs to the sub-package

* Corrected libraries path according to the new location

* Added download and home page urls

* Improve axes input specification for MVN-6

* Apply feedback