* Add GatherND_8 operation
* Update shape infer function and tests
* Initial commit for nGraph GatherND_8 operation
* Add GatherNDBase class implementation
* Fix base class errors
* Add missrd header
* Update base class
* Update GatherND_8 implementation
* Fix codestyle
* Fix wrong rank
* Implement tests for gatherND_8 shape inference function
* fix codestyle
* Add limitation to doc
* Siplyfy check in shape inference
* Add more test cases
* Update shape inference function
* Add more test cases to cover all case with dynamic input shapes
* Update shape inference function
* Refactor tests
* Initial commit for gatherND_8 reference implementation
* Add visitor tests for gatherND_8 operation
* Add visitor tests for gatherND_8 operation
* Correct comment
* Add additional check is shape inference function
* Update shape inference implementation for gathernd operartion
* Fix codestyle
* Remove restriction for data is fully defined
* Update shape inference functon
* Add gatherND_8 reference to evaluate map
* Add tests for gathernd_8 reference in batch_dims > 1
* Fix codestyle
* Fix codestyle
* Fix missed check for nonetype
* Remove redundant checks for batch_dims
* Use get_shape method instead of get_input_shape in GatherND reference implementation call
* update reference implementation call
* Properly add GatherND_8 to test opset table
* Update GatherND reference implementation for support opset8 version
* Add unit tests for gatherND_8 reference implementation
* Update gatherND reference implementation call in evaluate map
* Mark failed tests for missed plugin gatherND_8 implementations
* Fix codestyle
* Fix codestyle
* Fix codestyle
* Update tests
* Move common methods to base class
* Fix codestyle
* Revert clone_with_new_input function moving
* Add more test for reference
* partially revert API changes
* Proper cmake install for static libraries case
* Added an ability to skip template plugin
* Added install rules for VPU / GPU
* Install more libraries
* Fixed absolute TBB include paths
* Disable GNA
* Fixed issue with linker
* Some fixes
* Fixed linkage issues in tests
* Disabled some tests
* Updated CI pipelines
* Fixed Windows linkage
* Fixed custom_opset test for static casr
* Fixed CVS-70313
* Continue on error
* Fixed clanf-format
* Try to fix Windows linker
* Fixed compilation
* Disable samples
* Fixed samples build with THREADING=SEQ
* Fixed link error on Windows
* Fixed ieFuncTests
* Added static Azure CI
* Revert "Fixed link error on Windows"
This reverts commit 78cca36fd2.
* Merge static and dynamic linux pipelines
* Fixed Azure
* 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)
* NV12 Ref impl: Align with Legacy NV12 conversion
Little-endian tricks are completely not needed finally
Basic tests of OV20 preprocessing vs Legacy preprocessing:
- Mean/Scale
- Resize (Linear vs Bilinear)
- NV12 color conversion
* Register Template plugin in legacy core before CNNNetwork compliance test
NV12: round to nearest integer for 'u8' mode
Fix preprocess-reference NV12 tests (swap U & V)
* Decreased default threshold and use random distribution for inputs generation
* Added tests RefImpl vs OpenCV - NV12 color conversion
Added CPU accuracy tests + nightly (including all RGB color combinations)
* Fix build issue after rebase
* Remove test code
* Fix comments
Disable OpenCV tests on CI (some machines can't load opencv_imgproc during test)
* tmp
* Fix atanh correctness test issue and veriyf pass.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Only keep available input value for correctness test.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Deprecated old evaluate methods
* Suppress node
* Fixed some warnings
* Fixed documentation and warnings
* Fixed some warnings
* Disable some warnings
Introduced 'absolute threshold' for LayerTests and BaseReferenceTests to consistently catch absolute differences
Previously, when set 'threshold=1.f' it was treated as 'allowed difference is 100%", so there was no way to allow absolute difference as 1.f
* Written reference implementation of the operation ExperimentalDetectronROIFeatureExtractor.
* Small fixes.
* Started to write tests for evaluation of the operation ExperimentalDetectronROIfeatureExtractor.
* Written test for evaluation of the nGraph operation ExperimentalDetectronROIFeatureExtractor.
* Some changes.
* Added debug prints to evaluates.map.
* Added more debug prints.
* Added another debug prints.
* Added more debug prints.
* Added more debug prints.
* Added more debug prints.
* Inserted additional static_casts.
* Added more static_casts.
* Commented some debug prints.
* Some reversion.
* Deleted some debug prints.
* Deleted some debug prints.
* Deleted more debug prints.
* Added some casts and debug prints.
* Some changes.
* Small changes.
* Some changes.
* Added png files.
* Small changes.
* Code style fixes.
* Code style fixes.
* Rewritten some auxiliary functions.
* Corrected the body of the function experimental_detectron_roi_feature_extractor().
* Some code style fixes.
* Code style fixes.
* Small code style fixes.
* Commented one debug print.
* Small changes.
* Added some debug print.
* Small changes.
* Added more debug prints.
* Small fixes.
* Added more debug prints.
* Commented some code.
* Indexing operation [] was replaced by .at() method in the function pre_calc_for_bilinear_interpolate().
* Deleted unneeded variables w1, w2, w3, w4.
* Deleted variable xx.
* Added GCC pragma before the function pre_calc_for_bilinear_interpolate().
* Fixes in macros.
* Fixed pragma before the function pre_calc_for_bilinear_interpolate().
* Deleted some debug prints.
* Deleted more debug prints and fixed some code style issues.
* Deleted redundant assert.
* Deleted redundant assert in the function split_points().
* Started to move tests for nGraph reference implementation of ExperimentalDetectronROIFeatureExtractor to template plugin.
* Enabled test INTERPRETER.onnx_model_experimental_detectron_roi_feature_extractor.
* Deleted backend tests for the reference nGraph implementation of the operation ExperimentalDetectronROIFeatureExtractor.
* Deleted commented code.
* Fixed typo.
* Some fixes.
* Some fixes.
* Some fixes.
* Some fixes.
* Some fixes.
* Renamed the function that calculates ROIAlign.
* Deleted redundant usings.
* Now input shapes are parameters of test.
* Small fix.
* Now element type is also test parameter.
* Deleted some commented code.
* Added test for float16 case.
* Small fix.
* Added test for bfloat16 case.
* Deleted redundant parameters of tests.
* Deleted commented code.
* Deleted redundant structure.
* Small fix.
* Some reverting.
* Add visitor api test
* Review ngraph op shell with type_prop tests
* Add op to list of trusted operations
* Change name of struct with information of inputs
* Add include of array data structure to fix windowds compilation error
* Add template plugin test class
* Remove usage of CoordinateTransform index function call from reference implementation
* Rename SLT test suite
* Add template plugin unit test
* Add serialization SLTs
* Add indentation on GatherTreeParams class data members
* Hiding the problem, Validate() changes 'function'
* Template plugin tests
* Undo the changes that are not necessary
* Align code style
* Added \n at end of file
* Removing an unused implementation
* New version with Code Style checking
* Cleaning backend tests
* Reworked the tests the right way
* Removed visit_attributes()
* Removed visit_attributes() in source file
* Added NGRAPH_CHECK macros to evaluate()
* Removed zero_sized_not_equal mention from unit_test.manifest
* Added function name to the constants.py
* Revert "Added function name to the constants.py"
This reverts commit 5b7478056f.
* Return visit_attributes() for op::v1::NotEqual due to NotEqual being moved to another location
* Deprecate stopwatch
* Deprecate some utils
* Deprecate versions
* Moved slice_plan from the top level
* Fixed build
* Deprecate more old structures
* Fixed linux build
* ReverseSequence ngraph op shell revision with type_prop tests
* Add attribute count check in visitor test
* Refactor backend tests to template plugin test with reference values
* Rename cpu SLT instances
* Add op to list of trusted operations
* Rewrite validation check for input type due to backward compatibility
* Reference implementation speed up by replacing index function call of CoordinateTransform by precalculated strides
* New CumSum implementation init
* Unified ndim approach
* Move transpose to separate function
* Move transpose to original to separate function
* Move slice_count calculation to function
* Negative axes support
* Refactor redundant copy
* Changed copy to move
* Temp more backend tests
* Add const to shape arg
* Use span for slices calculation
* Remove unused headers
* CumSum new ref tests
* Add more ref tests
* Add all cumsum modes ref tests
* new optimized cum_sum reference
* Add reverse mode
* Optimized cumsum ref
* Remove deprecated cumsum backend tests
* Add more CumSum reference tests
* Simplify CumSum shared layer tests SetUp
* Replace auto to size_t in loop
* Change static_cast to T{}
* Enabled NCC for enums
* Fixed enum values
* Marked lower case enum as deprecated
* Fixed deprecated enums
* Disable deprecation for Windows and GCC < 6
* Try to fix build
* revise ../docs/ops/arithmetic/Atanh_3.md
* revise atanh
* recall atanh input data type description
* Revert "recall atanh input data type description"
This reverts commit 08e38f8c76.
* Migrate atanh to template plugin reference tests
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* fix build fail.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Remove atanh.in.cpp
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Atanh only accept [-1,1].
If input value outside of this range, it will return nan.
But nan is not value, can't compare.
So I update the reference implement.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* clang format
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Revert submodule mkl-dnn
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* op::Atanh->op::v3::Atanh
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Keep algin with "Tensorflow", revert range input to [-1.0, 1.0];
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* fix template test issue: if expect and actual both are nan, return true.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* 1: revert add new code to process condition: res and ref both are nan.
2: change || to ^, it looks like better.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* revise tan op
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* update doc
add examples in desciption
add the unit of measure
clear input type
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add template plugin test case for int type
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add template plugin test case for uint and float
remove the float test in backend
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* modify document
change type to any supported numeric type
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix compile error in openvino-lin
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* minor changes in Op class and add ref impl for acosh
* acosh in new test framework
* add Acosh type test
* add SLT for Acosh
* run more test
* new acosh plugin test
* add visitor test
* fix test utils
* add template test for all supported types in Acosh
* add builder to template tests
* update grn template_plugin test
* update maste to feature branch
* new implementation of FakeQuantize
* move FakeQuantize backend test to fake_quantize.in.cpp
* enable some test for FakeQuantize
* Add support for PDPD broadcasting and some backend tests
* arm plugin expect less attributes in function call
* try to fix arm plugin build
* try to build arm plugin
* start changing backend test
* add check for attributes number in visitor test
* fix backend test after refactoring
* add default parameter value to runtime::reference::fake_quantize
* Revert "add default parameter value to runtime::reference::fake_quantize"
This reverts commit 9d2c00d967.
* add SLT for FakeQuantize
* remove fesetround
* change `v1` namesapce to `v0` in ref impl
* add FakeQuantize-1 to VERIFIED_OP_REFERENCES
* pass immutable reference to test functions
* Move type prop tests to separate file, add cases with exceptions thrown
* Add visitor test, add step to pbc attributes
* SLT for CPU, adjust GPU and SSLT to serve the step attr
* Add backend test
* Fix variance issue, verify by SLT
* Formatting fix
* Add another backend testcase
* Add PriorBoxClustered to trusted ops list
* Add step attr description, remove obsolete comments from ref impl
* Test multiple step values in SLT
