* [TF FE] Support NonMaxSuppression with named outputs
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Simplify the test for NMS named outputs
* Share a script for test model generation
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Applied w/a to resolve softmax accuracy issue
The original impl resulted in accuracy issue if leftover is not aligned with subgroup size.
(e.g., for shape [1024, 306] where the lws = 32, itemsNum = 9, leftover = 18, subgroup size = 16)
In such a case, the result got wrong if subgroup block read/write is used.
As a w/a, not to use subgroup block read/write if leftover is not aligned with nsubgroup size.
However we can come up with better itenNum size / lefover handling in the follot bwing up work.
* Fix build error & minor revise
* Fix condition
* [LPT][TESTS] GrConv: added test cases with per channel dq on weights and without reshape
* FoldFQ: don't transform FQ with quantization by several dimensions
* ConvolutionTransformation: supported GrConv with per channel dq on weights and without reshape
* fold_reshape: refactoring
* [TF FE] Test ResourceGather operation and fix debug caps
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix test generation script
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove cache_dir property from AUTO plugin
* Pass the secondary property to hardware plugin
* Update test case
* Update test case, meta plugin will pass the properties to device without checking
* Fix unit test failure with broadcast primitive
* After introduce shape canonicalization, static broadcast unit test failed.
* Guilty commit is https://github.com/openvinotoolkit/openvino/pull/16166
Signed-off-by: hyunback <hyunback.kim@intel.com>
* [AUTO] Initialize variable / reduce variable copy
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Be compatible with C++11
https://stackoverflow.com/questions/18184096
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Fix C7555
C7555 “use of designated initializers requires at least ‘/std:c++latest’” in extern “C” code.
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Init in constructor and use auto const &
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Fix cpplint issue
common.hpp:72: You don't need a ; after a }
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Support all possible parameter numbers (0-6)
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Fix cpplint issues
Signed-off-by: Peter Chen <peter.chen@intel.com>
---------
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Fix in create_same_type_const_scalar; accurate updating type for parameter when inlining function call body
* Added Unique to the list of operations with named output ports (another MUSE fix)
* Draft: working version of extension with named ports in TF
* Merge fixes
* Refactor and productize POC
* Clean up
* Fix build
* Fix code style
* Fix lib so extension test
* Fix namespaces
* Remove usage of Any from CreatorFunction
* Fix build
* Fix arm build
* Apply review feedback
* Fix build after merge
* Apply suggestions from code review
---------
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
* [GPU] Fix sub kernel ordering issue in kernels_cache (#16746)
* [GPU] Add unit test for sub kernel idx (#16746)
* [GPU]Follow up code review (#16746)
* [GPU] Skip kernel compilation when current node is optimized out in update_impl (#16746)
* [GPU]Code refactoring (#16746)
