* Written nGraph version of the MO transformation SplitConcatPairToInterpolate.
* Small fix.
* Started to write tests for the transformation.
* Small fixes.
* Written more tests.
* Deleted commented code.
* Deleted debug prints.
* Added the transformation SplitConcatPairToInterpolateFusion into common_fusions.
* Small fix.
* Relaced std::set by std::unordered_set.
* Now the function grouped_vector is not template function.
* Small simplification.
* Deleted commented code.
* Now std::pair is used instead of SplitAndScale.
* Enabled the transformation SplitConcatPairToInterpolateFusion and added it into MOCTransformations pipeline.
* Removed the transformation from common_optimization.cpp.
* Small fixes.
* Added comment to the function grouped_vector.
* Deleted the local variable result from the function get_split_before_concat().
* Small change.
* Added comments for the conditions on input rank.
* Used std::tie instead of .first and .second.
* Skipped the ngraph namespace specification in the transformation callback.
* Got rid of std::unordered_set of std::shared_ptr<ngraph::opset8::Split>.
* size_t was replaced with uint64_t.
* Added descrption of the transformation.
* Small fix.
* Added condition that scale_factor != 1.
* Added more tests. Also the transformation has boolean parameter use_shape_for_elimination.
* Small fix.
* Written CPU layer tests for the nGraph transformation SplitConcatPairToInterpolateFusion.
* Some fixes.
* Added tests for the case of dynamic input shapes.
* add "" for windows in cmd line
* requirements test
* requirements test
* add requests in requirements
* add scipy in requirements
* add executable python for prepare models
* remove extra requirements
* add window for supported in memcheck tests
* add scipy in requirements
* change check of product_type
* add return for windows
* change form of return arg in run_memcheck
* change form of return arg in run_memcheck
* remove windows check
* change return format
* remove empty line
* change downloader_path
* ngraph functio sample
* Fixes
* OV2.0: NV12 hello classification with new preprocessing API
* Fix clang-format
* Rewrote several samples
* Some updates
* clang-format
* Fixed TODO
* Fixed comments and improved samples
* Preprocessing comments
* clang-format
* Fixed comment
* Fixed Windows
* Added back Blob support to ClassificationResult
Co-authored-by: Michael Nosov <mikhail.nosov@intel.com>
* Move extra TF Frontend headers to src
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Load a model by GraphIterator
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code style
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Avoid use of InputModelTF in FrontEndTF API and correct a comment
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code style
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply code style
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Enable unit tests in azure
* fix build
* check w/o installing to the package
* return to the package
* remove from the package again and set path to bin for tf unit tests
* Azure CI: set lib path for tf tests
* Azure CI: set correct path for tf tests on Win
* Azure CI: fix test start directory
* fix cmake file
* resolve review comments
* fix destination paths, fix comments
* Add specifiation for GatherND_8 operation
* Update formula
* Add links to op spec
* Fix existed and add new example
* Correct output shape formula
* Add restriction for batch_dims values
* Add reference for gatherND-8 operation
* Update batch_dims=3 example
* Fix output shape in example
* fix lines length
* Fix typo
* Fix wrong shape
* Update note about calculation of out shape
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Optimize blob constructor and remove user blobs
* restore user_blobs
* Rename helper function
* add test
* Remove empty line
* Fix code style
* add const
* Add test for SCALAR layout
* 1. Removed explicit SHARED from libraries
2. Fixed double definition for ie_layer_validators
* Fixed SEG in unit-test: order of initialization for global vars
* Added an ability to find plugins.xml from static IE
* Fixes in unit-test
* Migrated to new macro for import / export
* Minimized number of custom dllexport
* Don't use IR v7 for static libraries
* Revert for merge
* Don't enable tests with dlopen for static libraries
* Code style
* Added condition for export
* Revert format_reader
* Removed forward decalaration with external linkage
* Fixed IE linkage on Windows
* Reverted back 2 flags
* Implement ExperimentalDetectronDetectionOutput shape infer.
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Update on the review comments.
* Update based on review
