* 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
* Implementation of Resize-11
* Added support to sizes input
* Add tests to sizes input
* Added missing comment
* fixed tests
* fixed tests
* Fixed test. part 2.
* review remaks. part 1.
* review remarks. part 2.
Co-authored-by: Tomasz Socha <tomasz.socha@intel.com>
* Added more tests
Co-authored-by: Tomasz Socha <tomasz.socha@intel.com>
* DequantizeLinear 10 as a subgraph
* Enable DequantizeLinear from opset 13
* Exclude the failing tests
* Re-enable dequantize linear UTs
* Validation helper
* Create generic RecurrentSequenceDirection enum.
* Helper class RecurrentSequenceOp.
* Add ONNX GRU & RNN operators.
* Use OutputVector.
* Update doc.
* Add UTs for GRU and skip them on IE_CPU
* Add UT for bidirectional mode and fix it.
* Normalize activation function name case.
* Add unit-tests for RNN operator.
* UT for GRU with linear_before_reset set to true.
* Fix ONNX GRU for linear_before_reset case.
* Remove unnecessary symbol export macro.
* Fix CentOS error.
* Update UTs.
- Update few tests accuracy tolerance
- Update rnn_fwd_activations with new reference values and model.
* Review comment: add check for static shape
* Add UT for RNN with constant inputs W, R.
* Skip UT with const W,R on IE_CPU
