* [ci-skip][IE Myriad] ie::ICore pointer passed into FrontEnd from plugin
* [ci-skip][IE Myriad] Added MockICore to fix graph transformer tests
* [ci-skip][IE Myriad] IN renamed to I_N to avoid compile error in Windows build: C2513: 'int': no variable declared before '='
* Add default implementation that throws exception.
* Implement `createROI` for `TBlob` and existing compound blobs.
* Use reference couting for TBlob memory buffer to prolong its life time for ROI blobs.
* Add private extension for ND ROI and use it as implementation detail for now:
* Add `DimSlice` and `TensorSlice` structures for generic ND ROI support.
* Add `make_roi_desc` function to create `TensorDesc` for ROI.
* Removed legacy library includes from plugin api headers
* Removed IInferencePluginAPI interface; merged with IInferencePlugin
* Removed pluginAPIInterface usage in Core implementation
* First variant of tests for keep_constant_inputs
* Redone tests to check number of inputs
* Count inputs of layer via ngraph::Function
* Add additional transformations for CNNNetwork
* Modified work with CNNNetwork via iterators
* Add tests for FullyConnected Network
* Rename function for counting of inputs
* Debug output was deleted
* transformations_callback was removed
* Change ASSERT_GT on ASSERT_EQ
This PR introduces next changes:
1. Transformations *_tbl.hpp files were replaced with direct registration in cpp files.
2. Plugins use pass::Manager to call conversion passes.
3. Transformations callback was moved to PassBase class as there is no more need to keep it in separate class
4. All pattern based transformations must be inherited from MatcherPass class. GraphRewrite class will be used only for matchers registration and execution on function.
MatcherPass class adds new features to pattern-based transformations approach:
* Allows to run matcher pass on a single node.
* Operations that were created inside transformation callback can be added to execution list to be available for pattern matching within single GraphRewrite.
5. GraphRewrite MatchClosure was replaced with MatcherPass. So all matchers will be registered as a MatcherPass.
6. Added pass::Manager::clear_state() method to avoid dependency with nodes that no longer belongs to function after replacement.
7. Some representative transformations were updated to use MatcherPass as an example.
8. Mul->Add sequence fusion transformation was replaced with LinOpSequenceFusion.
9. Pattern and callback registration code was moved to class c-tors (will be finished for remaining passes in other PR) .
10. Updated pass::Manager to get pass names only when NGRAPH_PROFILE_PASS_ENABLE enabled.
11. Moving towards removing PassProperty.
12. Added ngraph::pattern::wrap_type<T>(inputs, pred) to simplify pattern creation.
13. GraphRewrite was updated to execute MatcherPass more efficient.
* Network serializer for v7 is removed
* Fixed compilation
* Fixed Windows build
* WA for GPU
* Create function 2 times
* Fixed compilation
* Added return
* [IE][VPU]: Moves UpgradeNMS4ToNMSDynamic transformation into myriad plugin
* [IE][VPU]: Moves UpgradeNMS4ToNMSDynamic from common to vpu folder
* [IE][VPU]: Moves Dynamic NMS from common folder to vpu
* [VPU]: Makes NMS conversion unconditional
* [VPU][NGraph]: Changes dynamic NMS base class from v3 to v4
* [VPU]: Moves NMS4toDynamic transformation before common optimization
* Try fix parsing error.
* Small exception refinements during importing model.
* More exception refinements.
* Skip segfaulting tests.
* More clear error types and messages. Func rename.
* Fix typo.
* Check on CI whether test_onnx will work.
* Add only those file which pass tests or have failing ones skipped.
* Some pass creates datas duplicate with a different order from time to time (because of unordered_set usage). It leads to a different order in model->datas() list and affects the shape allocation process which relies on this order.
* Make shape allocation be relied on topological order of datas which is stable and doesn't depend on order datas creation during different passes.
Don't increment mapped_idx via prefix increment within the argument of the
potentially unsafe CPU_ISSET_S macro. If the macro is expanded so that the
increment expression is evaluated multiple times, it will return unexpected
results.
While the glibc implementation of CPU_ISSET_S macro seems to be safe, the musl
libc (v1.1.23) version is unsafe and will evaluate the first argument of
CPU_ISSET_S three times.
Co-authored-by: Christian Priebe <cp3213@ic.ac.uk>
