G-API: oneVPL DX11 inference

* Draft GPU infer

* Fix incorrect subresource_id for array of textures

* Fix for TheOneSurface in different Frames

* Turn on VPP param configuration

* Add cropIn params

* Remove infer sync sample

* Remove comments

* Remove DX11AllocResource extra init

* Add condition for NV12 processing in giebackend

* Add VPP frames pool param configurable

* -M Remove extra WARN & INFOs, Fix custom MAC

* Remove global vars from example, Fix some comments, Disable blobParam due to OV issue

* Conflict resolving

* Revert back pointer cast for cv::any

Adapt remote inference to operate with NV12 blobs

* Media Frame Adapter support

* address comments

[G-API] Enable 2D inputs for GIEBackend

* Enable 2D inputs

* Fix typo

[G-API] Fix bugs in GIEBackend

* Remove inputs/outputs map from IEUnit

* Add test

* Add NV12 test

* Reorganize setBlob function

* Check that backend don't overwrite blob precision

* Stop setting config to global IE::Core

* Replace mutable to const_cast

* Update modules/gapi/test/infer/gapi_infer_ie_test.cpp

* Update modules/gapi/test/infer/gapi_infer_ie_test.cpp

* Make blob parameter as const ref

* Cosmetic fixes

* Fix failed test on inferROI

* Removed double ref for ii

* Disable tests

* Skip tests if device not available

* Use Sync prim under shared_ptr to avoid issue on MAC

* Apply WA for IE::Core

* Apply WA for MAC build

* Try to apply another WA

* Not release IE::Core for apple

* Put comment

* Support PreprocInfo for

* InferROI
* InferList
* InferList2

* Remove empty line

* Fix alignment
Co-authored-by: NMaxim Pashchenkov <maxim.pashchenkov@intel.com>

G-API: Extend ie::Params to specify batch size

* Add cfgBatchSize to ie::Params

* Fix comments to review

[G-API] Prohibit setPrecision & preprocessing for importedNetworks

* Prohibit preprocessing for imported networks

* Fix typo

input_names -> output_names

* Move setBlob logic to separate function

* Change comment

[G-API] Expand PyParams to support constInput

* Wrap constInputs to python

* Wrap cfgNumRequests

* Fix alignment

* Move macro to the line above

[G-API] Support FP16 input precision for IE backend

* Support fp16 input precision IE backend

* Add support to wrapIE

G-API: Support remote inference

* Extend MediaFrame to be able to extract additional info besides access

* Add API for remote inference

* Add default implementation for blobParams()

* Add default implementation for blobParams()

* Address review comments

* Fix any_cast usage

* Add comment on the default blobParams()

* Address review comments

* Add missing rctx

* Minor fix

* Fix indentation and comment

* Address review comments

* Add documentation

[G-API] IE backend convert fp32 to fp16

* Support FP16 in IE backend

G-API: ONNX. Adding INT64-32 conversion for output.

* Added int64 to 32 conversion

* Added warning

* Added type checks for all toCV

* Added type checks for tests

* Small fixes

* Const for fixture in test

* std::tuple if retutn value for toCV

* Mistake

* Changed toCV for tests

* Added Assert

* Fix for comments

* One conversion for ONNX and IE

* Clean up

* One more fix

* Added copyFromONNX

* Removed warning

* Apply review comments

G-API: IE. Adding support for INT32 type.

* Added support for int32

* Added sample for semantic-segmentation-adas-0001

* Alignment

* Alignment 2

* Rstrt build

* Removed test for sem seg

[G-API] Support generic infer overloads

* Overloads for generic infer

* Fix build

* Refactoring

* Fix docs

* Put extra stuff to detail namespace

* Add doc for usings

* Remove uneccessary template in Priv

G-API: Implement async version for InferList & Infer2

* Implement async version for InferList & Infer2

* Fix warning

* Fix bug with roi ordering

* Post input meta instead of empty

* Fix comments to review

[G-API]: Adding reshape for CNN input.

* Added CNN input IE reshape

* rbs

* Added unordered_set instead vector

* Alignment

[G-API] Introduce cv.gin/cv.descr_of for python

* Implement cv.gin/cv.descr_of

* Fix macos build

* Fix gcomputation tests

* Add test

* Add using to a void exceeded length for windows build

* Add using to a void exceeded length for windows build

* Fix comments to review

* Fix comments to review

* Update from latest master

* Avoid graph compilation to obtain in/out info

* Fix indentation

* Fix comments to review

* Avoid using default in switches

* Post output meta for giebackend

[G-API] Support multiple asynchronous requests

* Support nireq option

* Disable tests to check CI

* Fix bug with hanging

* WA to green CI

* Snapshot

* Simplify RequestPool

* Add default values to id

* Fix win warning

[G-API] Async infer request hotfix

* Fix hanging on empty roi list

* Prevent possible data race

* Clean up

[G-API] Implement async infer

* Implement async infer

* Fix typo

G-API: ONNX. Const input

* Added const input for ONNX backend

* Returned initMatrixRandu, added some comments, rebase

[G-API] Support GFrame for infer

* GInfer(GFrame), currently broken

* Fixed (API only)

* Support GFrame in GIEBackend

* Fix comments to review

* Fix comments to review

* Fix doxygen

* Fix building with different IE versions

* Fix warning on MacOS
Co-authored-by: NDmitry Matveev <dmitry.matveev@intel.com>
Co-authored-by: NSmirnov Alexey <alexey.smirnov@intel.com>

Expand ie::Params to support config

* Add config to IE params

* Add test

* Remove comments from tests

* Rename to pluginConfig

* Add one more overloads for pluginConfig

* Add more tests

- desync() is a new (and for now, the only one) intrinsic
  which splits the graph execution into asynchronous parts
  when running in Streaming mode;
- desync() makes no effect when compiling in Traditional mode;
- Added tests on desync() working in various scenarios;
- Extended GStreamingExecutor to support desync(); also extended
  GStreamingCompiled() with a new version of pull() returning a
  vector of optional values;
- Fixed various issues with storing the type information & proper
  construction callbacks for GArray<> and GOpaque;

- Introduced a new infer(Roi,GMat) overload with a sample;

- Introduced an internal API for Islands to control fusion
  procedure (to fuse or not to fuse);
- Introduced handleStopStream() callback for island executables;
- Added GCompileArgs to metadata of the graph (required for other
  features).

[G-API] Wrap cv::gapi::infer<Generic> into python

* Introduce generic infer

* Move Generic to infer.hpp

* Removew num_outs

* Fix windows warnings

* Fix comments to review

* Fix doxygen

* Add comment

* Fix comments to review

* Wrap inference to python

* Add default ctor to Params

* Add test

* Fix clang build

* Implement GInferInputs/GInferOutputs as Pimpl

* Add checkIEtarget to infer test

* Fix path

* Supress warning

* Use getAvailableDevices insted of checkIETarget

* Move PyParams to bindings_ie

* Add namespace

* Update CMakeLists.txt

[G-API] Support ImportNetwork for cv::gapi::infer

* wip

* Refactoring

* Fix comments to review

* Fix warning
Co-authored-by: NRuslan Garnov <ruslan.garnov@intel.com>

[G-API] Introduce generic version for cv::gapi::infer

* Introduce generic infer

* Move Generic to infer.hpp

* Removew num_outs

* Fix windows warnings

* Fix comments to review

* Fix doxygen

* Add comment

* Fix comments to review

* standoalone ifdef in ginfer.cpp

* Fix test

[GAPI] RMat integration into the framework

* RMat integration

* Added initialization of input mat in GArray initialization tests

* Fixed klocwork warnings in RMat tests, changed argument order in EXPECT_EQ

[G-API]: Add GOpaque and GArray serialization support

* Add GOpaque and GArray serialization support

* Address review comments

* Remove holds() method

* Address review comments

* Remove comments

* Align streaming with kind changes

* Fix kind in kernel

* Address review comments