* Fix caching issues with auto-generated friendly names
Introduce "HashPass" to calculate hash like a serialize but without auto-generated friendly names
IE Compilation context: use HashPass to calculate hash of ov::Function
IE Compilation context tests: removed "friendly names" from tests
Layout: serialization support + tests
Parameter/Result: update set/get_layout according to layout changes
* Fix clang
* Tiny correction of CmakeLists
* Renamed VariantWrapper<Layout> to LayoutAttribute
Removed test for conversion from/to fully dynamic layout (allowed now and does nothing)
'set_layout' - remove layout runtime info if empty layout is passed. This allows hashes to be the same if set_layout(param->get_layout()) is called
* Fix build
* change size_t to uint64_t for hash value
Using size_t leads to high probability of conflict for 32-bit platforms
* Removed debug print
* Fix hash calculation for 32-bit platforms
* Fix review comment
* Interpolate reference implementation:
- Support u8 and other numeric types
- For integral types - round result to nearest integer (don't cast)
Preprocessing: enable OpenCV tests and add resize conformance tests with OpenCV
* Revert changes in interpolate.cpp, making them minimal needed (added u8 resize)
* Put JOB_POOL after comments
* Revert "Put JOB_POOL after comments"
This reverts commit a8fc4c64e5.
* Revert "Use jobs pool for PDPD model conversion as well (#7602)"
This reverts commit 1390440256.
Co-authored-by: Alexander Zhogov <alexander.zhogov@intel.com>
* Fix VA OD sample pipeline test failure with batch=64
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
* Update cpu/gpu switching rule for maximum LWS of device capabilities
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
* Add Validate function to compare batch size with device capabilities
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
* Preprocessing: convert_layout<std::vector<uint64_t>> implementation
User is able to use this version without specifying layout explicitly
Same version of convert_layout is added for post-processing
Added usage of new convert_layout to ie_network_reader
* Fix review comment
* New version of PriorBox operation to add new 'min_max_aspect_ratios_order' attribute
* Apply suggestions from code review
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Added transposes insertion for Parameter and Result.
* Separated into several transformations.
* Corrected runtime_info format.
* Fixed runtime info serialization.
* Code refactoring.
* Corrected checks.
* Added debug output.
* Added check.
* Fixed unit tests.
* Changed old api map format, removed debug output.
* Moved serialize to rt_info property, code corrections.
* Refactored RTInfo class.
* Small corrections.
* Small corrections.
* Removed redurant import.
* Added tests, added undefined default type.
* Code reformat.
* Fixed serialization unit tests.
* Added comment.
* Added comment.
* Small test correction.
* Changed default values of old_api_map to values from old API IR.
* np.array -> int64_array
* Update MO to use FE to read IR; Swith MO IR version to 11
* Preserve output node name when inserting Transpose
* Codestyle
* Fix layer tests
* Pylint fix
* Disable ref_graphs comparision in layer tests
* codestyle
* Updated MO IR reader.
* Moved version initialization to constructor of OldApiMap.
* Added shape infer after transpose insertion.
* Fixed Pylint
* Removed wrong attribute removal.
* Added transposes insertion for Parameter and Result.
* Separated into several transformations.
* Corrected runtime_info format.
* Fixed runtime info serialization.
* Code refactoring.
* Corrected checks.
* Added debug output.
* Added check.
* Fixed unit tests.
* Changed old api map format, removed debug output.
* Moved serialize to rt_info property, code corrections.
* Refactored RTInfo class.
* Small corrections.
* Small corrections.
* Removed redurant import.
* Added tests, added undefined default type.
* Code reformat.
* Fixed serialization unit tests.
* Added comment.
* Added comment.
* Small test correction.
* Changed default values of old_api_map to values from old API IR.
* np.array -> int64_array
* Update MO to use FE to read IR; Swith MO IR version to 11
* Preserve output node name when inserting Transpose
* Codestyle
* Fix layer tests
* Pylint fix
* Disable ref_graphs comparision in layer tests
* codestyle
* Updated MO IR reader.
* Moved version initialization to constructor of OldApiMap.
* Added shape infer after transpose insertion.
* Fixed Pylint
* Removed wrong attribute removal.
* Serialize fix.
Co-authored-by: Gleb Kazantaev <gleb.kazantaev@intel.com>
* doc of paddle 2nd batch operations support
* Modified based on UX/DX Team feedback
* update the example command in Convert_Model_From_Paddle.m
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: meiyang-intel <yang.mei@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* 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
