* Propose new Slice-8 operation
(cherry picked from commit a44ed32a6f)
* Align category
* Update detailed descripiton
* Update Inputs/Outputs description
* Add no attributes info
* Precise range of axis values
* Update descriptions
* More details about negative steps and slicing backwards
* Add more details
* Add examples
* Change step input to Required
* Apply spell check comments
* Add missing commas
* Add separate T_AXIS type for axis input
* Make example data 2D
* Remove duplicated example
* Apply review suggestions
Co-authored-by: Michal Karzynski <michal.karzynski@intel.com>
* update spec
* remove backend tests and create op_reference test
* add logicalNot to constants
* add NGRAPH CHECK for number of inputs and outputs
* create type_prop tests
* create visitor test
* add type_op and visitor tests to CMakeLists
* remove backend test from CMakeList
* update T to T_BOOL
* update outputs part in spec
* fix type in the spec
* fixed conflicts in CMakeList
* update ReferenceLogicalLayerTest to also work with unary logical operator
* update logical_not op_reference test to use ReferenceLogicalLayerTest
* fix style
* fix style
* resolve conflict
* resolve conflict
* remove typo
* fix style
* Update ReferenceLogicalLayerTest class tto take input as a vector
* Create makeLogical function that takes ParameterVector as parameter
* update op_reference logical tests to take input as a vector
* Replace elem_type with input.type
* update getTestCaseName method
* update spec
* create op_reference test
* add greateEqual to constants.py
* add ngraph_check for number of inputs and outputs
* add include
* fix style
* add information about broadcast in examples in spec
* Remove redundant reegistration of a new test class
* Remove visit_attributes method
* update outputs part in Greater and GreaterEqual spec
* fix typos in spec
* Add transformation for single CTCGreedyDecoder operation
* Fix style in op specification
* Update transformation logic
* refactor old tests and add tests for new transformation
* Move tf specific front transformations to tf folder
* Update transformation logic and comments
* Add run_after function and update comments
* Add output_sparse_format attribute to extractor
* Update transformation conditions and tests
* Fix incorrect comment
* Move sparse_to_dense_replacer to front/tf folder to fix problems with class registration
* Update import
* Update output ports handling in transformation
* Update test
* Fix BOM file
* Update pattern for ctcloss transformation
* Fix and refactor tests for ctcloss transform
* Update transformation conditions
* inserted Convert to unsigned
* moved declarations from hpp into cpp, specification corrected
* added static const modifier
* updated convert specification
* minor corrections
* split into 3 passes(Init, Propogate, Update), renamed final pass to ConvertNmsGatherPathToUnsigned
* added description why transformation is needed
* added matcher for several NMS versions, removed TRANSFORMATIONS_API macros from cpp
* applied comments:
- used GraphRewrite instead of FunctionPass
- simplified some expressions
- corrected case when Converts output goes to multiple nodes
- added to MOC transformations
- other minor corrections
* removed redundant namespace prefixes
* fixed #include <ngraph/pass/graph_rewrite.hpp>
* removed matcher_scope, debug code, and redundant dynamic_cast
* ReverseSequence specification refactored
* Change attribute description to avoid confusion
* Allow seq_lenghts input to be of floating-point precision
* Hiding the problem, Validate() changes 'function'
* Review/update spec for NotEqual operation
* Remove unnecessary edits not related to the ticket
* Removing the extra word binary for the short description
* Re-writing detailed description
* Correcting punctuation docs/ops/comparison/NotEqual_1.md
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Specifying auto_broadcast in the short description is similar to Equal spec
* The range of values for auto_brodcast is similar to Equal spec and includes the missing pdpd
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* 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>
* update spec, init backend file for equal op
* add backend, visitors, serialize SLT tests
* add backend test to manifest cause of mismatch of output type with cpu plugin
* add equal to list of trusted ops and to cmakelist file
* refactor backend tests to the new template
* refactor spec
* remove external link in numpy broadcast and update example
* remove comparison.in.cpp file and related tests from manifest
* fix example
* remove redundant arguments
* refactor backend tests
* add pdpd broadcast to the spec, and different precison to SLT test
* add precisions to SLT cpu
* remove unsupported type from SLT
* revert the deletion of comparison.in.cpp file
* remove visitors test, since it will be added in the other PR
* remove equal from CMakeLists.txt
* refactor links in the spec
* revert unwanted changes
* remove equal from unit test manifest
* revert links modification in spec
* add namespace
* split SSLTs for comaprison ops into seperate files
* fix SSLTs names
* add missing new lines
* udpate output type in spec
* rafactor numeric backend test to template
* merge numeric template tests into equal
* update markdown file for logical or operator
* update information on broadcasting in logical operators spec
* change *T* to *T_BOOL*
* add information about input shape
* remove divergence between logical_or and logical_and specs
* 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>
* update spec, add visitors, backend test
* remove visitors test as it is implemented in another PR
* remove visitors test from CMakeLists
* remove old backend tests, refactor minor parts of the code
* add namespace
* refaactor template test for less_equal op
* update docs
* add host tensors validation
* create type_prop tests
* create serialization single layer test
* create visitor test
* create op_reference test
* add logicalAnd to constants.py
* create additional op_reference tests
* add check for number of visited attributes in visitor test
* update auto_broadcast description
* remoove backend test
* update LogicalNot params name
* remove backend test from CMakeList
* create util function for type_prop tests
* update op_reference tests
* remove typo in docs
* remove unsupported types from evaluate
* fix bug in op_reference test
* refactor visitor test
* update math formula in the spec
* update has_evaluate types
* Revise spec
* Comparison backend test POC
* Split Comparison ops tests into separate files
* remove comparison.cpp, remove unused imports, replace for_each with range based for
* remove unnecessary ngraph:: prefixes
* Fix links in spec
* Add Less to trusted ops list
* Add missing ','
* Use builder in backend tests
* Remove old backend tests for less, equal
* Revise Erf OP sepc
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Revise the NGraph Erf OP implment to switch to RTTI.
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Remove the duplicated Erf in the activation type vector.
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Add NGraph visitor API test case.
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Enalbe the Erf visitor API CmakeLists.txt.
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Revise the Erf OP backend test
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Migrate to use the template test.
* Add erf type_prop test.
* Update the license
* Unary Visitor test template fix
-Migrate OP Tanh to use RTTI;
-Remove the using namespace in the header file
-Migrate the Swish and Tanh visitor test to use template code
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Revert "Unary Visitor test template fix"
This reverts commit b686c933d3.
* Update the doc format.
* Update the document format and description.
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Add Erf OP into the layer test summary list
* Migrate the Erf backend test into template_plugin infrastructure
* Update the Erf supported input type.
* Remove the boolean type support in erf reference implement.
validate_and_infer_elementwise_arithmetic() will fail with boolean type.
* Update the erf test with all supported types.
* Update with separate namespace of CommonReferenceTest
* Added RandomUniform specification.
* Extended description of obtaining float numbers.
* Added description of obtainin float16 and double values.
* Added description of xor symbol.
* Small correction.
* Small corrections.
* Added initial type attribute.
* Corrected IR example, removed unnecessary default values.
* Small correction.
* Added information about type cast between initial and output types.
* Removed initial type attribute.
* Corrected output_type description.
* Corrected minval, maxval description. Corrected IR example.
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Removed unnecessary paper link.
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* update docs
* add sign to intActivationTypes
* add RTTI macro
* update backend test
* add type prp test
* add visitor test
* add visitor and type_prop test to CMakeList
* add sign to constants.py
* delete backend tests and create new reference tests
* style fix
* remoove sign backend test from CMakeList
* create reference test for all supported types
* remove boolean type from evaluate method
* Update spec for MVN-1 and MVN-6.
* Add reduction_axes attribute to MVN-1.
* Fix mean value calculation using ReduceMean.
* Correct reduction_axes attrbute name.
* Restore default value for normalize_variance and eps_mode.
* Remove dafult value for required attributes.
* Correct typeo.
* Move detailed description up, add backtics to attr types
* Add backtics for range in clip attr description, remove non-existing attributes
* Adjusting the spec to review comments
* floating-point instead of floating point, remove default value for mandatory attribute
* BatchToSpace specification refactored
* Add minor changes
* Added \ldots to latex formula
* Change output tensor to lower-case y
* Added mention to reverse operation SpaceToBatch
* Corrected dots in formulas
* Enable rank greater or equal than 2 for data input and add more examples
* Minor changes in detailed description
* Improve short and detailed descriptions
* revise atan op
* use parametrized vistor API
* use new gtest macros
* Update docs/ops/arithmetic/Atan_1.md
Co-authored-by: Gabriele Galiero Casay <gabriele.galiero.casay@intel.com>
* Update docs/ops/arithmetic/Atan_1.md
Co-authored-by: Gabriele Galiero Casay <gabriele.galiero.casay@intel.com>
* Update ngraph/core/src/op/atan.cpp
Co-authored-by: Gabriele Galiero Casay <gabriele.galiero.casay@intel.com>
* update doc to follow the rules
* create type_prop for atan
* drop op_eval to be covered in backend
* add the missing type prop case
* add integer type ref impl
* fix clang issue
Co-authored-by: Gabriele Galiero Casay <gabriele.galiero.casay@intel.com>
* update sinh spec
* add rounding for integral type
* refactor ngraph sinh class, add backend, visitors and type_prop tests
* refactor backend test for int32, remove redundant includes, refactor spec, add SLT for ints
* fix style
* add sinh to list of trusted ops
* re-add Sinh to int SLT
* update python modules
* revert update of python modules, and fix the depracated typed_test formula
* fix deprecated typed_test formula
* bulk change `type T` to `type *T*` in spec
* update all `T` which referee to type to use *T* pattern
* get back with `T` where T is dimension
* fix *T*1 -> *T1*
* Make italic types where was no formating
* Update docs
* create type_prop test for cos
* Create visitor test foor cos
* add RTTI macro
* Create separate ref impl for integer input
* add cos to SLT integer activation type
* add backend test for int input
* add cos to constants.py
* style apply
* fix spec
* add ngraph check for outputs and inputs
* fix inputs ngraph check
* remove unnecessary includes
* style dix
