* FQ+Mul fusion transform skeleton
* FQ+Mul fusion transform tests prep
* Basic UT for the transform
* Basic implementation of the transform
* Parametrized UTs for FQMul transform
* Parametrization of FQ+Mul UTs
* Make sure that the shapes of constants match
* Check if the mul constant matches FQ data
* CentOs compilation error fix
* PR feedback and adjusted tests
* NHWC layout of the mul constant
* UT: FQ output limits 4D
* Redundant CF pass removed
* Rewrite the graph in a different way
* Shape checking infrastructure skeleton
* Handle some negative cases
* Check the rt info in the fusion test
* Fuse all Mul nodes detected after FQ node
* Dont cast the original FQ node
* Dont throw if CF fails in new output range calculation
* More UTs
* Accept any type of input to FQ in the transformation
* Test the fusion when all FQ inputs are non-const
* Fusion test when only one output limit is const
* setupvars.sh: Added logic for exporting path env in case if it not defined
* setupvars: Removed duplicated colon
* Kept quotes where they were
* setupvars: updated copyrights
* [GNA] fix scale factor calculation for unfused bias after fc
* change check
* add test
* apply requested changes
* cpplint fix
* apply test changes
* modify model for test to match ::op::
* Remove dead code.
* Protect device specific config options with device checks.
* Add missing space to precision parsing error message.
* Allow to switch FP32 input precision to U8.
* Commit.
* Added opset4 version in the class Interpolate.
* Added class ONNXResize11Op to read ONNX Resize with opset version >= 11.
* Added support for Interpolate-4 into transformations TestInterpolateReshapeWA and InterpolateConcat.
* Added support for Interpolate-4 into transformation InterpolateWithConcat.
* Deleted redundant checks from the transformation UpsampleToResample.
* Reverted last changes.
* Changed ONNX Resize extractor to support for Interpolate-4.
* Added conversion of ONNXResize11Op into Interpolate-4.
* Added support for Interpolate-4 into the transformation InterpolateSequenceToInterpolate.
* Small fix for formatting.
* Written tests for MO version of Interpolate-4 with shape_calculation_mode = sizes.
* Written tests for infer function of Interpolate-4.
* Now transformations InterpolateWithConcat, InterpolateConcat, InterpolateReshapeWA skip Interpolate-4.
* Used create_op_with_const_inputs in the transformation InterpolateSequenceToInterpolate.
* The transformation ONNXResize11ToInterpolate4 was rewritten using find_and_replace_pattern.
* Now the dictionary infers (dictionary of infer functions of Interpolate) is a class static attribute.
* Deleted unused variable.
* Restored original logic of find_and_replace_pattern method of the class InterpolateReshapeWA.
* Used create_op_with_const_inputs() in the transformation InterpolateSequenceToInterpolate for opset1 case.
* Replaced resize_name by resize.soft_get('name', resize.id).
* Small fixes.
* Added two tests for Interpolate-4 infer function.
* Fixed the transformation ONNXResize11ToInterpolateV4 for the case when ONNXResize11 operation has 3 inputs.
* Added conversion of ONNXResize11 with tf_crop_and_resize_mode to ROIPooling + ONNXResize11.
* Fixed bugs in the transformation ONNXResize11ToInterpolateV4 and in the infer function of the operation ONNXResize11.
* Small changes.
* Renamed transformation that converts ONNXResize11 into ROIPooling + ONNXResize11 and fixed BOM-file.
* Fixed tests for the transformation InterpolateSequenceToInterpolate.
* Small change.
* Now the transformation InterpolateSequenceToInterpolate preserves output layer name.
* Deleted the transformation ONNXResize11ToTFCropAndResize.
* Fix for concat layer with more than 2 inputs
Signed-off-by: Bartosz Sochacki <bartosz.sochacki@intel.com>
* Fixed check if affine is used for crop layer
Signed-off-by: Bartosz Sochacki <bartosz.sochacki@intel.com>
* code cleanup for fix affine layer check
Signed-off-by: Bartosz Sochacki <bartosz.sochacki@intel.com>
* added test for concat layer with multiple inputs
* simplified test to use less number of layers
* fixed code style
* fixed coding style
* addressed review comments and one more issue that appeared during testing
* fixed code style errors
* scale factor propagation for concat layer with multiple inputs
* fix for a case when all inputs to concat are activation layers
* fix for linux compilation - C++14 is not enabled and fails on lambda with auto parameters
* corrected current year in headers in concat multi input tests
* fixes for code review issues raised by Denis Orlov
* enabled integer mode computation in GNA concat multi input test
* removed 1 space per review comment
* a fix to fail when not all scale factors are equal
* added GNA_DEVICE_MODE config to concat multi input test
* corrected searching for a next input to concat layer
* changed selection of 2nd candidate for source quant value
* code style fix - else and brackets should be in the same line
* small code improvement
* fix for mixing line endings
* addressed with endless requantization loop and fixed failing tests
Special test case with input values which cannot be correctly processed via
decomposition with int AVG pool layer.
Signed-off-by: Alexander Peskov <alexander.peskov@intel.com>
