* Draft version of the Swish nGraph operation and fusing transformations for different approaches to express the operation
* Swish fusing transformation refactoring
* Added Swish operation and extractor for TF. Removed unfolding transformation for the operation.
* Added SwishIE. Implemented transformation to convert Swish to SwishIE.
* Code style fixes
* Updated Swish reference implementation. Added tests for shape and value inference
* Fixed code style for Python API
* Fixed unit test
* Apply review comments
* Use matcher_pass_callback
* Make m_alpha attribute protected in the SwishIE operation
* Fixed Swish op PythonAPI test
* Added Caffe Slice_ext
* Added TFSlice, AttributedSlice (both with extractors and replacers), corrected SliceConverter and added unittests for all cases
* added comments to each type of Slice operation; optimized shape inference; moved mxlice inside of slice.py; renamed slice_replacers
* removed type annotation for get_shape_after_slice routine
* replaced zeros_like with zeros
* Corrected preserving node names, renamed attributes names, added tests fro slice_replacer onnx phase
* Renamed slice_replacers.py
* added more unittest cases
* added type annotations, moved to more relevant place routines for shape calculation, and some other minor corrections
* corrected a typo `normalize_slice_indices` comment
* corrected shape calculation for Nonconstant inputs
* corrected a few typos
* corrected type declarations
* corrected shape inference with rounding
* refactored unit-tests for front transforms of Slice
* added error raising for negative and zero shapes
* removed magic_num
* corrected AttributedSlice, clarified comments
* fixed unit-test for AttributedSliceToSlice
* typo in type hints corrected
* removed supported_attrs
* returned back default None for attrs of Slice
* Updated ConvertPrecision transformation to be executed for TI Body
* Added type fusion for GenericIE operation
* Added test for TensorIterator body precision conversion
This extends resample optimization for 8-bit types that uses feature
packed to mode to process multiple features in one work-item to features
not being multiple of packing factor.
For nearest resampling it is safe to copy extra feature padding for
blocked formats, so this change only removes this condition.
* Minimized ngraph headers inclusion
* Added compilation of plugin api headers with strict flags
* Fixed -WPedantic issue in ngraph headers
* Fixed compilation
* Trying to fix Windows
* Fixed GNA unit tests compilation
* Disabled WX test on Windows
* Enable ngraph python tests
* Refactor and unify ngraph with onnx python tests
* Revert deprecated test cases
* Set ngraph and onnx python tests as a one test suite execution
* Change unstrict Xfails to strict ones
* Update after review:
- add model zoo to onnx tests,
- improvements of tests
* Revert mounting zoo models dir
Co-authored-by: Michał Karzyński <4430709+postrational@users.noreply.github.com>
* [CPU] Add support 4th and 5th input DetectionOutput
* fix any comments
* move reference to ngraph
* some changes for mx nms
* change namespace for ref impl
Number of ops went down by 4.
Also fewer floating point operations improves precision here, so we're able
to unblock some test cases from ngraph's suite.
* Implement unicode conversion using Windows native functions
* NOCPPLINT
* Fixed deprecated c++ api usage in tests
* Moved impl to cpp
* Moved Unicode utils to Plugin API
* Added missed include for Windows
* Fixes for unit tests; CentOS fixes
* Fixed Windows compilation
* Fixed unit tests on Unix
* Fixed unix 2
* Build dlls with INTEGRITYCHECK flag if ENABLE_INTEGRITYCHECK=ON
INTEGRITYCHECK flag enforces digital signature before loading the binary in Windows.
Also, refine /guard:cf flag enabling - MSCV, Intel, clang compilers does support /guard:cf.
