* Review spec of Selu operation
* Fix path for Selu op in opset files
* Remove unnecessary line in example
* Address review comments related to wording
* fix batch adding to init value of read value
* fix for batch in Kaldi models
* added broadcast to be able reshape in IE
* test fixes, added batch broadcasting to created constants
* pep fixes
* move all changes to 1 transformation
* added unit test and fix insertSelect transformation
* added comments
* remove unneeded params search
* fix element_size to send correct batch
* fix update batch in element_size
* couple fixes
* update BOM file
* fix review comments
* review fixes
* review fixes
* fix license headers
* Initial working solution
* moved bfs_search_apply_on_shapeof_subgraph_nodes from utils/graph.py to MarkShapeOfSubgraphDataType.py
* Reused bfs from MarkSubgraphsWithCorrectLayout.py
* fixed e2e precomit issues: specified correct const data_types, fixed BFS search staring point to avoid nodeless shapeof subgraphs
* fixed mxnet_rnnt: added converting all Const nodes in ShapeOf subgraph in MarkAndChangeDataTypeInShapeOfSubgraphs.py, revised Const values in transformations that affect ShapeOf subgraph nodes
* reverter ReverseV2ToReverseSequence.py and DecomposeBidirectionalRNNSequence.py
* in MarkSubgraphsWithCorrectLayout BFS search beauty applied
* apply review comments, returned back 'in_shape_subgraph' attribute
* graph condition added
* MO IR reader fix for mixed FP16 models, added replacer order placement comment
* moved to back phase
* new solution with marking nodes from bottom to top (WIP)
* successfully tested on back phase
* corrected unittest
* removed check for start nodes size in bfs
* fix transformations that insert f64 to f32 in shape subgraph
* corrected log.warning -> log.debug
* revised list if shape input operations added unittest for Const shape inputs
* applied @lazarevevgeny's comments
* licence head corrections
* Operation class review
* Remove clamp from FusedOp
* Add node validation checks
* Add type_prop unit tests
* Move backend unit tests into a separate file
* Remove unnecessary includes
* Add support for i8, i16, u8, u16 and bf16 precisions
* Refactor backend unit tests
* Remove instance with f64 precision
* Move dynamic shape tests to op_eval
* Group failing tests into manifest
* Add single layer tests and serialization tests
* Skip tests with conversion due to plugin misbehavior
* Add unit tests fails to manifest with documented issues
* Fix centos7 test to skip slt cpu instances of integer precision
* Enable dynamic test for float element type
* Address review comments
* change docker approach
* Experiment with run onnx runtime tests over MS Azure
* experiment to run bnaries directly
* enable all tests
* Set tests execution as separated scripts
* Configurations update:
- Add new yml file for onnx_runtime check
- Add specific tag to checkout for onnx runtime
* Rename according to conventions
* Change OpenVINO release version
* [Hetero plugin] Model caching support
- Enable IMPORT_EXPORT_SUPPORT metric
- Introduce internal FORCE_DISABLE_CACHE flag to avoid caching of subnetworks
- Added test for hetero with plugins which don't support caching
- Added test for hetero with plugins supported different cache architecture
* Hetero plugin - support DEVICE_ARCHITECTURE
Test setup:
mock.1 - mock.9 returns "one" for DEVICE_ARCHITECTURE
mock.10 - mock.99 returns "two"
Test:
Load "HETERO:mock.1,mock.51".
Load "HETERO:mock.2,mock.52" - cache shall be reused
* Fixed review comments
Covered use case case
ie.SetConfig({{"TARGET_FALLBACK", "CPU"}}, "HETERO");
ie.LoadNetwork(network, "HETERO");
* Fixed more comments and failed tests
Don't propagate FORCE_DISABLE_CACHE to plugins as they can throw exception
Fixed case with set TARGET_FALLBACK from core with different architectures of one plugin
* Fix unit tests
Add 'FORCE_DISABLE_CACHE' config key only for LoadExeNetwork
It is not needed to have in in QueryNetwork and other places
* Attempt to fix failed func test on Windows
