* Fix FakeQuantize weights fusion when multiple operations were using the same const
* [GNA] Fix scale factor calculation for Relu if it has source and doesn't have destination statistics
Co-authored-by: Dmitrii Khurtin <dmitrii.khurtin@intel.com>
* NGraph - FrontEndManager - common API
Added Mock frontend for unit testing
* Comment out installation rules
* Fixed review comment
Introduced environment variable OV_FRONTEND_PATH for frontend paths
* Additional cmake cleanup
* More fixes of cmakelists
* Changing template file name for frontends
* Changed copyrights
* Reuse ngraph-utils for file-related operations
* Correct of frontend file extension for macos
More code coverage
* Renamed all methods to according to ngraph-style
In case of unset or empty OV_FRONTENT_PATH - load plugins from current working directory
* Fix review comments
Add clang format target for frontend_manager and mock frontend plugin
* Update docs for FrontEndCapabilities
* Use constants for flags instead of 'enum'
* clang style fix
* Fix comment: using namespace ngraph...
* Fix comment: use replace "frontend_manager" with ${TARGET_NAME} in CMakeLists.txt
* Comment fix: rename 'generic' folder to 'frontend_manager'
* Update documentation comments
* Set FrontEndManager class as 'final'
* Apply review comments
* renamed get_place_by_name_and... to get_place_by_operation_name_and...
* Separated frontend_manager.hpp into 4 header files
* Upload python speech sample draft
* Add function doc strings
* Add the ability to save results to a file
* Add a plugin configuration for GNA to get better accuracy
* Add errors calculation (comparison with a reference)
* Fix flake8 issues
* Add ability to run in hetero mode
* Add ability to load and save numpy format files (.npz)
* Add an error for wrong file extensions & update help message
* Add import and export GNA model options
* Add -we option to export embedded gna model
* Add readme
* Add -oname command line option (Layer names for output blobs)
* Add -iname command line option (Layer names for input blobs)
* Add info about -iname option to README.md
* doc: update readme, fix style
* Add a state reset between inferences
* add reset API to speech README
* doc: remove extra output from README
* remove onnx and TODO, format output
* Add an else branch to the if statement that checks a utterance data type
* Add dummy data for inference if a number of vectors < batch size
* Split the sample into separte files
Co-authored-by: Kate Generalova <kate.generalova@intel.com>
* Moved CC macros for transformations to public API (to reuse their in plugin transformations)
* Added CC to template plugin
* Moved itt.h from nGraph to openvino/cc
* Fixed build
* Caching: pass global CACHE_DIR setting to plugin
This can be helpful for GPU - it doesn't support Import/Export but can
significantly speed up load time when CACHE_DIR is set for device only
* Ignore exception in 'DeviceSupportsConfigKey' if plugin doesn't support GetMetric at all
