* [GNA] Move definition of GNAInferRequest class to source file
* [GNA] Fix handling exception for infer() and wait() gna_infer_request
* fixed handling of exceptions for wait and infer gna_infer_request
* fixed closing ongoing subrequest of divided model in case of exception on
on enqueueing request or waiting for end of request.
* [GNA] Apply review comments, Removed exceptions from enqueue and wait for Worker
* changed API of request worker to return:
* erorr in case wait failed instead of
throw,
* return true/false for enqueue instead of exception for failure case
* [GNA] Fix review commentd related to gna_infer_request and worker_impl
* [GNA] Add tests for GANInferRequest
* added tests for exception handling of Infer, Wait, StartAsync methods of
GNAInferRequest class.
* [GNA] Added final fixes for review comments.
* [GNA] Small Improvement in PWLApproximation and update of unit test for it.
* added template method for floating pointcomparision
* added new tests for PWLApproximation
* [GNA] Refactor numerical_utils and usage of its method in plugin
* refactor numerical utils use template methods for conversion and comparision
* Review tile for shape inference:
- propagate labels and dimension
- template implementation of shape inference
- if repeats is not-positive output dim is always 0
* Refactor Tile shape inference
* Review preserve partial values and labels
* Add support to evaluate bounds from repeats input
* Remove not used code
* [Tools] Avoid use of NumPy deprecated types
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Revert "[Tools] Avoid use of NumPy deprecated types"
This reverts commit 21ffc167d1.
* Move to 1.24 Numpy
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* replace benchmark_app imean and iscale parameters
Tickets 80777 and 80900
* Warn about difference with imean and iscale, note that in help
* Clang format
* Clang format
* mean->scale
* Keep mean scale empty if not set
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
* Fixed shape infer dep for blocked format
* Set preferred format for shape_of to be made from input rank
- ShapeOf should get the original output layout of the previous node, which is not reorderd.
* Preserve input constant when Squeeze and Unsqueeze shape infer is sone in MO IR Reader
* Fix bom test
* Add tests
* Fix value
* Fix test
* Apply suggestions from code review
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Review dims and labels propagation for logical not
* Review dims and labels propagation
for logical and, or, xor
* Remove duplicated tests
* Expand logical ops tests by numpy broadcast
and inputs order
* Review template shape infer of logical ops
- add static shape inference test
- add default ctor test
* Default ctor test for LogicalNot op
* Add ScatterUpdate type_prop tests
* Add evaluate_label for ScatterUpdate
* style update
* Reuse has_no_labels
* Adjust the logic to the single output
* Remove redundant size_check
* Migrate from HostTensor to ov Tensor
* Remove deprecation macro
* Use auto instead of HostTensorPtr
* Adjust tensor element type
* Update to reuse labels vector
* Use sizeof size_t to set element type
* Ensure static shapes on inputs
* [TF FE] Support models with topologically unsorted nodes
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix conversion for models with cycle
* Fix code-style
* Fix code-style
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* updated to get ockable memory for device inputs
* gpuFuncTest to set f64 scalar tensor
* aligned type names
* updated to get lockable memory for some specific precisions
* add a function to get a supported precision
* [TF FE] Support Assert with string tensors
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update src/frontends/tensorflow/src/op/const.cpp
* Update src/frontends/tensorflow/src/op/const.cpp
* Apply code-review feedback: better to use UnsupportedConstant
* Correct unit-test
* Replace Op with Node
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add reverse infer
* Add more convolutions and include transformation in normalize of tf fe
* Fix code style
* Add activations and eltwise support
* Fix code style
* Add deprecation supression
* Fix pad type
* Remove eltwise
* Remove ngraph namespace usage
* Fix code style
* Apply review feedback
* Add tests for activations and eltwise
* Make transformation friend of tensor to avoid deprecated API
* clang fix all
* Update src/common/transformations/include/transformations/common_optimizations/reverse_shape_and_type_infer.hpp
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
