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
* uncomment upload db func
* upd CMakeLists.txt
* fix template path
* fix CmakeLists
* fix imports
* fix work with cmd and with models our_dir
* add quotation marks
* fix quotation marks
* add base config for test
* upd work with db instance
* revert changes with test config
* Add MO coveragerc to tests install pkg
* Use directory install with FILES_MATCHING
* Coveragerc to tools folder
* Update CMakeLists.txt
* Use tests/model_optimizer folder
* Reduce unused macros, where two strategies are used:
(1) Extract batch_headers and let them be included only once in each batch.
(2) Static reduction in primitive_db_gen.py, which scans each macro's users and exclude the macro if there is no user.
* Removed dependency from runtime to kernel_selector
* Resolve too large string error
* Fix duplicated definition (GET_FILTER_XXXX is defined in both fetch_weight.cl and by runtime.
Removed from runtime because the definition is incorrect
* Resolve GRN & deconv & gpu_select issues
* Fix cldnn unittest issues
* Minor fix
* Applied review comments
* Fix rebase error
* Moved FrameworkNode to nGraph
* Moved graph comparator to ngraph test util
* Fixed build
* Try to fix centos
* Fix export target
* Moved engine utils to separate library
* Removed ONNX util from common library
* Fixed build
* Fixed code style
binary post
binary post ops support for gemm convolution and gemm inner product
plugin fixes
mkldnn: avx512: fixed prelu post op
Co-authored-by: dmitrygo <dmitry.gorokhov@intel.com>
* Fixed precisions conversion in new API
* Added tests
* Fixed old IR cases
* Disable FP16
* Fixed regex for CentoOS
* Refactored tests to use new API
* Temp
* Fixed tests
* Moved smart reshape related sources to ngraph
* Added tests for invalid names
* Moved reshape to tensor_names
* clang-format
* Fixed CC build
* Removed IEConv, IEDeconv from primitives pririty
* Initial version
* Added 'network' layout to preprocessing info
Moved existing resize tests to template plugin
* Fix clang
* More tests for 'resize' reference implementation + CPU tests + error cases
Coverage is 100%
* Align with new base_reference_test implementation
* Fixed comments
* Add assert to check that desired size is not out of bounds
* CPU: skip failed test
* Init rt info deserialization
* Add RT Info attributes deserialization
* Add RT Info attributes serialization
* Add Serialization and Deserialization tests
* Code style
* Fix AttributeAdapter place
* Extended rt_info section; added support for multi-field attrs; use version for attr serialization/deserialization
* Align attributes and their usage
* Fix LPT
* Add missing #pragma one
* Fix build
* Change version delimiter to have valid xml
* Fix PromitivesPriority
* Fix tests
* Fix test
* Fix IR Reader; remove empty rt_info
* More explicit attribute name and version representation
* Reference tests via OpenVINO 2.0
* Migrated to new API acos test
* Fixed other tests compilation
* Fixed tests
* Reference tests use ov::
* Fixed compilation
* Use Gna2DeviceCreateForExport when GNA_EXEC_TARGET is != detected
* Update detected GNA device version field in GNA Device helper
* Use EXEC instead of COMPILE TARGET to append
CNN Legacy enforcement (GNA1)
* Apply review
* improved accuracy on model after Accuracy Aware
* refactoring+test
* removed unnessary FakeQuantI8/I16
* added comments, moved fake_quantized from UpdateInputScaleFromNetwork(), removed _Np template param from QuantDescTmpl
