* refactor: add clang style check for samples
* fix: add .clang-format for ie
* fix: style check for missing headers
* refactor: remove cpplint for IE samples
* fix: setw is not a member of std for classification_results.hpp
* feat: add indent after ifdefine
* feat: set up google style for IE samples
* fix indents for w_dirent headers
* fix: include issues for utils.cpp due to clang-format
* Fix deepcopy
* Add test
* Revert dtype for BF16 precision
* Fix test
* Add exception for BF16
* Update BlobBuffer dtype for FP16 precision
* Revert exception for BF16
* Update test
* Separate workdir for parallel runs
* Use random
* Get back old working configuration
* Change label
* Debug parameters
* Change models dir to SHA approach
* Fix WORKDIR names
* Change mountig models dirs
* Update model preproces script
* Improvements
* Isolate all private variables
* Fix model dir path
* Update model preproces
* Update node label
* Remove debug printlns
* Enabled Wall for nGraph
* Fixed Linux build
* Fixed ONNX Editor and class-memaccess
* Fixed topK
* Fixed some builds
* Fixed nGraph Python API
* Use std::fill instead of cycle
* Wno-unded and deprecation for app python versions
* [IE CLDNN] Enabled fusing all types of reorders to permute
- Fusing reorder to differnt dims (e.g., 4D=>5D, 6D=>4D, etc)
- Fusing reorder to permute_opt kernel for blocked formats
- Fixed bug for activation_opt kernel for blocked formats
* [IE CLDNN] Enabled fusing all types of reorders to permute
Refactoring for permute fsv opt kernel
* [IE CLDNN] Permute reorder fusing
Support reordering to different dims from optimized permute kernel for blocked format
- gen9_common_conv_bwd_data_kernel (used for fsv16 format) has additional overhead w.r.t stride. Current intention of the kernel implementation is to reuse kernel b/w multiple input values but if the stride gets bigger the reusable rate descreses.
- Thus, added additional panelty for deciding deconv kernel (format)
* Removed suppressions for IInferRequest deprecation
* Fixed Windows
* More fixes for Windows
* Fixed compilation on Windows
* Fixed comment in documentatipn
* Fixes for Andorid
* Fixes for old gcc 4.8
* WA for cross-compilations
* Fixed compilation
* Fixed HETERO plugin compilation for old compilers
* Flags
Co-authored-by: lab_ddpqa <lab_ddpqa@intel.com>
* add floor_mod type prop test to CMakeList
* create floor_mod type prop tests
* create op_eval tests for floor mod
* Update copyright
* add op to summarize.py
* update copyright
* remove unused variable
* add tests for int64 and int32
* clear unit test file
* Change second input generation of single layer test of cpu plugin to also generate negative numbers for floorMod
* Update test results and remove one test
* fix bug with secondaryInput shape
* add backend tests
* add new line
* create additional backend tests
* Update backend tests
* [GNA] Update GNA library to 1191 version
* append symlink to libgna.so
* append selective unpacking of the archive
* changed the criterion for checking the unpacking process (exit code)
* remove tabs
* add equalToReferenceWithDelta_1191
* removed equalToReferenceWithDelta_1191
* master -> update_gna_library
* Added out of bounds check for output ports
* Corrected if condition
* Updated exception message
* Added functional test
* Verified particular type of exception
* refactor exp class
* add backend and type_prop tests
* add SLT for exp operator
* add SLT for serialzation for activation type ops
* remove redundant files
* GeLU fusion
* Fix matcher and sqrt(2) value
* Replace with math constant
* Correct comments in header file
* Add tests for transformations
* Add define of math constants in tests
* refactor code and add checks for nullptr
* Extend tests with failing examples
* change tests
* Removed test-generator from all MO requirement files except the dev one
* Moved all MO unit tests files to a separate directory
* Added __init__.py files to the tests directory. Fixed importing paths for some unit tests
* Fixed imports in all unit tests. Moved all unit test related files from the MO code to the dedicated directory
* Renamed directory with unit test utils
* Updated imports in unit tests
* Specify Einsum-7 operation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Finalize specification for Einsum-7 operation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Remove duplicate example
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Update doc headers with Einsum operation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply comments after the first review: grammar corrections and sentence rephrase
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply feedback from tech-writers and online review
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Make additional grammar corrections
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct documentation: optimize some sentences, links and examples
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Support capital letters in equation and implicit mode
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* [GNA] Add basic low precision support for more layer types, add simple test
* [GNA] Fix test
* [GNA] Make divisor const, add more clarity to some conditions
* v7->v1 works fine
* gather v1->v7 works fine
* changed op::v7 -> opset7, op:v1 -> opset1
* bumped to gather7 in all transformations
* applied review comments
* fixed pre-commit failures
* disabled incorrect unit-test, fixed f32->i32
* added comments why AddConvertToReorderTest was disabled
* Revert "bumped to gather7 in all transformations"
This reverts commit 965dc295
* fixed typos in v1->v7, v7->v1
* added GatherBase, redefined pattern in eliminate_unsqueeze gather, turned on Gather downgrading transformation
* resolved conflicts and build errors
* 🚀 finally EliminateUnsqueezeGather works: added inheritance of RTTI info from GatherBase
* fixed pre-commit failurer
* removed redundant debug code
* reverted f32 for Gather-1 indices in unit-tests and transformations
* relaxed restrictions for indices and axis type for v1::Gather
* corrected op scope
* moved type_check to validation_util.cpp
* removed type checks from Gather, removed upgrading transformation
* applied review coments
* fixed minor typos
* Revise Squeeze op class
* code style fix
* Move backend tests from fused_op.in.cpp to a separate file
* Add missing newline
* added axes input range and type validation
* add validation checks for the second input rank and type
* style fix
* remove axes input type checks
* add support for a single input squeeze op
* remove output static rank assignment in validate_and_infer_types
* Improve shape propagation for partial shape inputs with static ranks
* %~dp0 can't handle path which include Space
The default OpenVINO install directory is C:\\Program file(86)\\Intel\\..., which contains space. So when users run this script, the path is wrong.
To handle this issue, I modify two part:
one is the python_command, use a local var to store this path.
The other is the errorlevel, just add double quotation marks
* fix python_command path issue
* delete unused blank line
* Add deformable_convolution unit tests
* add 2D unit test
* Add unit-tests for 3D deformable_convolution
* create shared test class for deformable_convolution
* create single layer test for cpu plugin
* create single layer test for serialization
* add deformable_convolution to opset1
* create empty evaluate method
* add group and deformable_group to parameters
* Create impl for generateInput method
* add deformable_val to deformable_conv paramset
* create additional unit-tests
* Remove 3D single layer tests
* Update GenerateInput and SetUp method
* Update parameters values for SLT
* Update GenerateInput method and create Validate method
* Create additional parameters set for cpu plugin SLT
* Create unit-test with padding and add it to disabled
* add interpreter unit tests to manifest
* style-apply
* create file for reference impl
* Update year of copyright and make Validate an override method
* Update parameters names for serialization single layer tests
* Update parameters names for functional single layer tests
* add failing unit tests for interpreter to manifest
* make tests parameters more readable
* style-apply
* Include deformable_convolution inside evaluates_map
* add support for groups parameter for reference impl
* style-apply
* remove DeformableConvolutionParams struct
* fix bug with filter
* fix bug with offset type
* Update interpreter manifest
* impl evalute method
* style-apply
* Update year
* Update test names
* add utils func for deformable convolution operation
* fix filter group count
* add calculation of index of offset
* Update offsets in unit test
* add support for multiple input channels
* add padding tests
* add padding support
* style apply
* update copyright year
* create validation check helper
* Update convolve function name
* update copyright year
* style-apply
* remove integer type from serialize layer tests
* add tests for deformable_groups
* fix bug with group > 1
* style-apply
* add group unit test
* create additional group tests
* fix bug with groups attribute
* Enhance dynamic shape inference of validate and infer types method
* Add type_prop unit tests
* Fix broken op create test in python api
* fix bug with shapes in group tests
* update deformable_convolution method
* add unit test with 2 groups and 2 defromable groups
* Fix code style.
* Update UT manifests with current test status.
* Refactored backend test: names, removed duplication, add TOODs
* Add missing test cases in 'integral offsets' group.
* Fixed group attribute.
* Update interprer manifest to disable tests with integer offsets.
* Fix style.
* Remove changes in operator class.
* Revert "Enhance dynamic shape inference of validate and infer types method"
This reverts commit 2f9ce2ccd4.
* Revert "Add type_prop unit tests"
This reverts commit 944af98b8c.
* Revert "Fix broken op create test in python api"
This reverts commit 72fbfc2967.
* Fix op class.
* Convert implementation to 2D.
* Simplify implementation.
* Fix centos build.
* Reimplemented offsets handling.
* Fixed integral offsets test cases.
* Fixed deformable group attribute.
* Add bilinear interpolation.
* Refactoring regarding tolerance_bits.
* Fix groups & def_groups test case.
* Add more unit tests for group & defgroup attribute.
* Remove debug code.
* Minor refactoring.
* Add integer types to SLT.
* Revert "Add integer types to SLT."
This reverts commit 2fefe8926d.
* Add tests with real number offsets.
* Refactored bilinear_interpolation().
* Turned on SLT.
Additionally refactored and offset input set to range <0,2>.
* Update headers with short version.
* Fix SLT offests generation with int offsets.
* Add integer types to SLT.
* Fix grup + def_group test case.
* Add ticket to address IE_CPU backend test failures
* Enable real resolution for deformable values
* Add op to list of trusted operations in python script
* Fix comparison of integer expressions of different signedness compilation error
* Add comment with closing namespace and empty lines
Co-authored-by: pszmel <piotr.szmelczynski@intel.com>
Co-authored-by: ggalieroc <gabriele.galiero.casay@intel.com>
* BatchToSpace, SpaceToBatch layers optimizations
* Fix according to review
* Fix tests for oneDNN (v1.6)
* Fix of support BF16
* Fix in/out config
* Add support of Blocked layout
* Fix of support U8
* Add support for in/out channels of different sizes
* Removed xfail
* Removed xfail_issue_34327
* BatchToSpace, SpaceToBatch layers optimizations
* Fix according to review
* Fix according to review
* 3 different implementations -> 1 implementation
* Fix THROW
* Fix Exception
* Revert Batch_to_Space to parallel_for
* Fix remarks
* parallel_for -> parallel_nt
* Fix remarks
* Fix data separation
* Fix according to review
* Fix memory size calculation in Tensor and HostTensor
* Backend test for Constant operator
* `read_raw_data` in constant.in.cpp
yet another formula to calculate memory size in bytes
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
