* Introduce Quantize-Dequantize to FakeQuantize transformation
* Revert changes in DequantizeLinear
* apply code format
* Changes after review:
- description for transformation
- remove NGRAPH_CHECK and move some checks from callback to predicates in pattern
- check if out_low/high are broadcastable for FQ's first input
- fix params to copy_runtime_info
* Add type_matches and type_matches_any predicates
* Use get_single_value
* Changes after review:
- add brief description of transformation
- use get_pattern_value_map instead of get_pattern_map
- change opset1 to opset4
- fix params to copy_runtime_info
* Check result of dynamic_pointer_cast
* Fixed NCE hang due to input dimensions exceed HW limitation
* Added convolution test for big input dimensions
Signed-off-by: wenzengc <wenzeng.chen@intel.com>
* partial revert a commit with reference implementations of PriorBox(Clustered), disable references for this ops
* ngraph codestyle
* disable const folding unit tests for PriorBox(Clustered)
* fix arm build
* fix unit test
* Revert "fix unit test"
This reverts commit 1fe59e55d6.
* Added bool to u8 conversion
* Added opset1::ShapeOf handler
* Added ReduceLogicalAnd/Or support in ConvertPrecision pass
* Moved static map inside function; Updated callbacks
* Removed header
* Fixed tyle relaxed for cases when the same output consumes by multiple inputs in the same operation; added tests; fixed input types setting for already created type relaxed operations
* Removed reference implementations from public API
* Remove coordinate_transform from public API
* Introduced static library with reference implementations
* Initial version of ReduceL1, ReduceL2 and ReduceLp enabling in the MO
* Added operations ReduceL1 and ReduceL2 to nGraph
* Removed ReduceLp. Added ReduceL1 and ReduceL2
* Separated specification of ReduceLp into ReduceL1 and ReduceL2
* Updated ReduceL1 and ReduceL2 specification
* Fixed ReduceL1 and ReduceL2 type prop tests
* Implemented nGraph transformation to decompose ReduceL1 and ReduceL2. Disabled them for CPU and GPU plugins
* Updated supported framework layers
* Added unit tests for ReduceL1 and ReduceL2 reference implementation
* Fixed ReduceXXX operations reference implementation by adding support for a new parameter 'keep_dims'
* Fixed constant folding for v0::Any
* Added ReduceL1 and ReduceL2 to Python API
* Implemented ReduceL1 and ReduceL2 decomposition tests and fixed ReduceL2 decomposition
* Added specific creator for ReduceXXX operations instead of NodeBuilders
* Fixed conversion ReduceXXX to CNNLayer
* Fixed parser for ReduceLogicalXXX operations
It was discovered that it is sometimes useful to mark fast stages (e.g. stages that process less than 100 elements) in order to be able to parse them from final performance report and estimate its contribution into performance.
* Added pass for marking fast stages
* Introduced unit tests
* Added new predicates for smart pattern matching
* Added ConvMul and GroupConvMul fusion passes based on opset4; Added CPU functional tests for comparing fusion accuracy
* Improved ConvMultiply fusion to support scalars; Added positive and negative tests
* Added ConvolutionBackprop/GrouConvolutionBackprop Multiply fusion; Added functional tests
* RTTI base for ngraph::Node; cherry-pick from another branch, draft
* Added comments, moved code, switched to custom RTTI-based version of is_type
* Move rtti definitions in ngraph op class to the beginning of each class definition as a preparation for the next replacement
* Migrate part of operations to new RTTI
* Migrate GroupConvolution and Concat to new RTTI
* Apply code style for ngraph part
* Rename RTTI_DECLARATION/DEFINITION to NGRAPH_RTTI_DECLARATION/DEFINITION
* Reverted accidentally updated version of mkldnn
* TMP: rewrite RTTI back to constexprions as an attempt to fix static objects initialization order issue
* Apply ngraph code style
* Finalize move back to constexpr for RTTI
* Applied code-style
* TypeRelaxed template class implementation and necessary changes in ngraph + tests.
* Applied code-style
* Fix in fast algorithm in GraphRewrite, add new tests for this and other cases
* Make parent optional parameter for NGRAPH_RTTI_DECLARATION and remove Node::type_info; remove ability to have Node as a parent for type_info
* Try to resolve compilation error on Windows
* The next attempt to fix Windows build: re-introduce get_type_info_static
* Removed file that was removed in master and kept in this branch by mistake
* Next attempt to fix Windows build: externConstexpr
* Attempt to fix win build: extra public (suspect icc bug), remove get_type_info_static as useless.
* Next attempt to fix Windows: proxy const and constexpr
* Fixed constexpr
* Next attmpts: move get_type_info to cpp file
* Code stype fix
* Re-implemented RTTI without use of constexpr; run-time initialization is used; removed global definitions to avoid issues with order of static objects initialization
* Removed externConstexpr flag and removed TRANSFOMRATIONS_API for TypeRelaxed
* get_type_info_static initializes static local constant with type_info that is used for CLASS::type_info and CLASS::get_type_info
* Removed not needed debug output and useless comments
* Implemented better copy ctor for Node
* Fixed VisualizeTree issue for TypeRelaxed: stopped using < and > in type_info::name
* Better comments and names for methods
* Remove unused include
* Remove commented line
* Workaround for legacy conversion that uses Node::get_type_info().name as a type for the resulting CNNLayer leading to incorrect types for TypeRelaxed-based operations and then to fail in plugins
* Fixed typos, explicit ctor for TypeRelaxedBase, explanation for the need of get_overridden_output_type
* Fix typo
* Fixed issue with non-static name in type definition for TypeRelaxed and fixed WrapType to make it compatible with hierarchical relations between types
* Reverted default ctor for Output and reverted ability to reduce number of outputs for a Node; syntactically better debug message for a Node
* Cover methods of TypeRelaxedBase by tests
* Apply code-style
