* [ VariadicSplit ] Dynamic shape inference

* Small code fixes

* Add tests for partial shape inference

* Style-apply

* Style-apply
Co-authored-by: Michal Karzynski <michal.karzynski@intel.com>
Co-authored-by: raramer01 <rebecca.ramer@intel.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* remove dynreshape

* remove header

* use v1::Reshape for shape relevance

* remove return of bool due to function refactor

* remove gpu emit v0 DynReshape

* Merge cleanups

* throw exception for reshape node with dyn shape

* fix style
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Wenzhe Xue <wenzhe.xue@intel.com>
Co-authored-by: Scott Cyphers <scott.cyphers@intel.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* Stricter checks on padding attributes for v1::Convolution

* Move pad argument checks to op constructor
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Michał Karzyński <postrational@users.noreply.github.com>
Co-authored-by: Robert Kimball <robert.kimball@intel.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* GetOutputElement removal preparation

Not all outputs are used so don't force them to be connected in replace
Add pattern that matches on any output
Remove GOEs by default, allow to disable
Fix failing core passes/tests with GOE dependency

* Fix MLIR call

* Fix value handle assignment

* Cleanup

* style

* review comments

* Fix onnx tests

* Allow simplifcations to work on multi-values nodes

* Disable goe removal for MLIR test

* null init of Output
Co-authored-by: nmostafa <nagy.h.mostafa@intel.com>

* Cleanup get_output_shape

* More cleanup

* Update more

* output tensor

* fix input

* get input source ptr

* cleanup

* more changes

* wip

* wip

* more input helpers

* style
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* remove operator size_t in dimension

* use get_length()

* transform uint64_t to size_t for func to_shape()

* more replacement of get_length

* more replacement of get_length in test

* make style-apply

* change in onnx

* more change onnx test

* fix build

* add size_t back to dldt test
will do another PR after dldt update
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

[SPEC][ONNX] Handle negative axis for TopK:v1, add dynamic shape support for ONNX Arg Min/Max ops (#4291)

* First version

* Added support to no_keep_dims

* Excluded tests for PlaidML

* Code review remarks introduced

* Reduced TopK axis restrictions

* Added assert to TopK get_axis

* Added missing EOF

* Style applied

* Code review suggestions introduced

* Disable tests for GPU

* Code review remarks introduced
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Constify the onnx importer conv

* Extract and fix the groups attribute validation for Conv

* Check if the convolution's data input rank is static

* Validate the groups attribute against channels and filters

* Validate the conv operation in a separate function

* Dynamically broadcast the conv bias if needed

* Import a test model with dynamic batch conv op

* Run a conv test with dynamic batch

* Cleanup of conv bias handling code

* Use a proper Broadcast constructor for bias in onnx conv

* Handle dynamic ReduceMean with statically defined rank

* Use the target shape rank to construct the default output shape for Broadcast

* Handle ONNX Squeeze with dynamic input and static rank

* Handle ONNX Shape with dynamic input and static rank

* Handle the dynamic target shape in ONNX Reshape

* Fix for the ONNX Shape input validation

* Handle ONNX Softmax with dynamic input and static rank

* Fix the failing Broadcast type prop test

* Code formatting

* Dont broadcast bias before adding it to the conv node

* Drop the conv node validation and rely on the core op implementation checks

* Code review feedback

* Revert the Broadcast op changes

* More code review feedback

* Dynamic conv test using ng test case

* Obsolete headers removal

* Code formatting

* Variable names refactor

* Disable model_conv_with_dynamic_batch test on GPU

* Code formatting
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* Extend normalization. Part.1

* Normalize axis. Part.2

* Code review remarks introduced

* Fixed normalizes ranges type

* Trigger CI
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

* Squeeze/Unsqueeze dynamic input type/rank infer

* Unit-tests

* style

* Removed squeeze Rank propagation

* Fixed comment

* Revert comment back

* Comment resolved

* Style fixes

* Moved unsqueeze axis check

* Style

* Discussion resolved

* Style

* Assert in decompose_op, if output shape is not static

* Style
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

* Use ConvolutionBackpropData in ONNX ConvTranspose operator.

* Replace deprecated functions and update documentation.

* Remove GroupConvolutionTranspose fused op.

* Add more UT for GroupConvolutionBackpropData.

- They're transformed from GroupConvolutionTranspose

* Fix validate_and_infed types for ConvolutionBackpropData v1.

* Add new constructor for GroupConvolutionBackpropData

- Additionally do some code formatting.

* Improve validation in GroupConvBackprop v0.

* Update/fix upgrade & downgrade passes for
(Group)ConvolutionBackpropData.

* Add decomposition and validation for GroupConvolutionBackpropData:v1

* Type properties UT for GroupConvolutionBackprop v1

* Remove include of deleted header.

* Add squeeze to opset1::builder.

* Use opset1 squeeze.

* Helper functions for padding and output spatial shape inference.

These helper functions are specialized only for *ConvolutionBackpropData operators.

* Update documentation.

* Add more checks and remove deprecated assert.

* Refactor GroupConvolutionBackpropData validation.

- Use helper functions to infer padding and output shape.
- Change get_output_shape to return only spatial features dimensions

* Remove unnecessary code from donwgrade pass.

The GroupConvolutionBackpropData node has already computed all those required
information.

* Call Node API. Small review suggestions.

* Work only on spatial dimensions inside helper functions.

* Enhance documentation for ConvolutionBackpropData

* Refactoring.

* Reuse values computed in downgraded operator.

* Check for correct filters input shape.

* Add additional check on auto pad value.

* Remove unused variables.

* Rename helper function.

* Add more checks.

* Override is dynamic and add more restrictive check.

* Fix merge artifact and force unsigned type for argument.

* Review comments: renaming.

* Change Convolution + bias pattern.

Change from bias broadcasting to appropriate convolution output shape
into reshape into (1, C, 1, 1) shape, which sould work better.

* Add few more test cases for ONNX ConvTranspose op.

* Skip one UT failing on PlaidML backend due to accuracy.

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

* Printing cleanup

Add Input/Output
Simplify element type
Simplfy Node printing  implementation, try to de-noise it a bit
Enable printing of Node*

* Adjust printing

* Add doc note

* Update src/ngraph/node.cpp
Co-Authored-By: Robert Kimball <robert.kimball@intel.com>

* Update src/ngraph/node.hpp
Co-Authored-By: Robert Kimball <robert.kimball@intel.com>

* Cleanup

* typo
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

* Resolved problems with too restrictive data type

* Apply suggestions from code review

Code review remarks introduced
Co-Authored-By: Tomasz Socha <tomasz.socha@intel.com>

* Code review remarks. Part.2
Co-authored-by: Tomasz Socha <tomasz.socha@intel.com>
Co-authored-by: Adam Rogowiec <adam.osewski@intel.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* Removed LogSoftmax FusedOp, changed onnx to produce v1

* Code review remakrs introduced

* fix after merge from master
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Removed Recoprocal FusedOp and moved definition to ONNX importer.

* Removed unnecessary changes.

* Added test.

* Undo unnecessary changes.
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* Update license to new year

* Pick up some strays

* Added scatterND op to ONNX importer.

* Added ScatterND FusedOp.

* Removed unnecessary files.

* Added op to config files.

* Changed input order.

* Fixed validation checking.

* Added suport for int64 in ScatterNDAdd op.

* Changed test.

* Disabled test for plaidML.

* Code refactoring

* Added tests.

* First debug version of support ND input

* Added type_prop tests

* Implemented ND support for SpaceToDepth

* Added type_prop tests for SpaceToDepth

* Added fused op tests

* code refactor

* Fixed DepthToSpaceMode::BLOCKS_FIRST

* Code review remarks introduced

* Code review ramarks. Part.2

* Using NODE_VALIDATION_CHECK introduced

* Change generate_adjoints to take an OutputVector instead of a NodeVector for deltas.

* Cleanup

* Adjoints class convert to use Output<Node>

* More cleanup

* More cleanup

* Post-merge build issues

* Don't push initial bprops multiple times

* Eliminate GOE correctly

* back-compatibility, unit test

* Added v1::Select op with support for implicit broadcasting

* Addressed PR feedback

* Constant folding support for v1::Select op

* Remove commented-out code

* More shape inference tests

* NonMaxSuppression op skeleton

* Validation of the NonMaxSuppresion op

* Correct last 'boxes' dimention check

* onnx_importer support for NonMaxSuppression

* Code formatting

* Type and shape inference for NonMaxSuppression

* Different initialization of NMS inputs in onnx_importer

* Code formatting

* Basic type_prop tests for NonMaxSuppression

* More type_prop validation for NMS

* GatherTree introduced

* Added GatherTree type_prop tests

* Initial commit

* Moved DeformablePSROIPooling to v1

* Moved DeformablePSROIPooling to v1. Part.2

* Added missing fields

* Added inferance shape

* Added type prop UT

* Added serialization

* Doc + styles applied

* Revert incorrect changes

* Revert incorrect changes. Part.2

* Moved to NGRAPH_API

* integration with master

* Code review remarks introduced

* DeformablePSROIPooling updated to new spec

* Changed axis to Node

* Added using normalize from validation util

* refactored split

* Added typrop tests to Split

* Added set_input_is_relevant_to_shape for Split

* clang style applied

* Fixed var name

* Code refactor

* mergre from master. part.2

* Constructor to provide CI compatibility

* CI compatibility

* CI compatibility

* Updated get_outputs

* CI compitability

* Fixed get_outputs function

*  relax check for LRN for requirement rank should be >=3

* rename unit test names

* - Disable lrn unit test with axes for CPU backend

* remove outdated unit test on rank requirement from type_prop

* - disable newly added lrn unit test in plaidMl

* [SPEC] Adjust ConvolutionBackpropData op.

```
inputs:
  1. filters-------+
  2. output_delta  |  -> 1. data
                   +---> 2. filters
  3. data_batch_shape -> 3. output_shape(+optional)

attributes:
  1. strides          -> 1. strides
  2. dilations-----+
  3. pads_begin    |  -> 2. pads_begin
  4. pads_end      |  -> 3. pads_end
                   +---> 4. dilations
		      -> 5. +auto_pad(optional)[PadType::EXPLICIT]
		      -> 6. +output_padding(optional)[zeros]
```

* Review fix I

* Added negative axes support for ReverseRequence

* code review remarks introduced

* Disable reverse sequence for PlaidMl tests

* Fixed styles

* Fixed axes assignment

* Fixed normalized axes assignment

* Moved OneHot to v0

* Introduced OneHot:v1

* Added shape calculation for OneHot:v1

* Added element types checking

* Added output shape tests

* Added tests to checking if inputs are scalars

* Updated OneHot:v1 doc

* Implemented OneHot:v1 downgrade pass

* Using OneHot:v1 in onnx_importer

* Implemented OneHot:v0 upgrade

* Fixed OneHot onnx_importer

* Refactored normalize_axis

* Added OneHot:v1 serialized

* Code review remarks introduced

* Added doc to normalize_axis

* Stub for CropAndResize

* Cut and pasteo

* Need a cast

* Construct HardSigmoid with alpha and beta as inputs

* Switch to the new HardSigmoid constructor entirely

* Broadcast with numpy style in hard sigmoid

* Python bindings adjustment to the new constructor

* Different way of creating constants

* Accept scalars instead of 1D vectors for alpha and beta

* Adjust the python tests to the new HardSigmoid constructor

* Use v1 ops in fused HardSigmoid

* Relax the static shape requirement for alpha and beta

* Fix merge

* Initial commit

* Add decompose_op and unit-test

* Style fix

* Fix CI error

* Address review comments

* Remove CPUBatchFusion

* Address review feedback

* Address review feedback

* Added type_prop tests

* Moved 1 test from cpu to core to keep together

* Address PR comments

* Fix style