* [CPU] Do not set BF16 on input port for Eltwise after Input
Since Eltwise supports conversion to BF16
Thus unnecessary Reorder is avoided
* Create a separate function for enforcing BF16 on ports
* Add test to verify that no extra Reorder is inserted
Also:
- update legacy test
- remove extra code which is not applicable anymore
* Correct expected precision in legacy test
* Enhance dynamic shape inference of validate and infer types method
* Review op class of DeformableConvolution
* Add node validation checks into validate and infer types specific to element type and shape of inputs
* Refactor validate and infer types method to use common function to validate conv parameters and infer output shape
* Apply these changes to Convolution and BinaryConvolution for alignment
* Add type_prop unit tests
* Add node validation checks for deformable values spatial dimensions
* Fix type_prop and python api shapes
* Fix deformable values spatial dimensions
* Add validation checks in reference implementation
* Address review comments
* Remove reference to const for basic types in ref impl
* Update comment with ticket to add check for u1
* Change deformable values to offset to align with spec
* Add ngraph visitor tests for reduction operations
* Add check for number of expected attributes
* Add ReduceL1 and ReduceL2 to visitor test typed case of reduce ops
* Instantiate reduce operation type in separate file
* initial solution
* added unit-tests + some corrections
* axis getting improvements
* fixed MO IR reader for old IR's
* a couple of corrections
* applied review comments
* corrected negative batch_dims normalization for shape calculation, for IR original negative values are kept
* added additional checks and negative tests
* Extend MO for operation Einsum-7
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add extractor for einsum and optimize code based on review feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix the code based on the review: correct code, tests and comments; move insert_transpose
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix LayoutChangeForEinsum transformation condition
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Update third-party dependencies
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fixed attributes saving to keep tensor debug info in Parameter node.
* Added comment and unit tests.
* Small correction.
* Small correction of unit test.
* Comment corrected.
* BatchNormInference specification refactoring
* Address review comments
* Remove he term Transform from definition
* Add title of the paper where this operation is introduced
* Add missing backticks
* Remove redundant information in attribute epsilon range of values
* Refinement of spec
Remove more mentions to transformation to avoid confusion
* Corrected typos and added changes to improve readability
* Use third person to express operation steps
* New flags for GNA trget
* Add new flags to configuration
* Update utest
* Update speech_Sample
* Add unit tests
* Guard for wrong values
* Use gna execution target as consistent device
* Apply review
* Exclude xbyak from install
* Added automatically generated InferenceEngineConfig.cmake
* Reverted a version back
* Fixed issues with target aliases
* Make TBB dependency private
* Made ie_parallel.cmake self-sufficient
* Don't expose ie_paralle.cmake to end users
* Fixed compilation with TBB
* Fixes for TBB
* Fixed vpu_graph_transformer compilation
* Fixed tests compilation
* Added install of ie_parallel.cmake
* Switched ENABLE_ALTERNATIVE_TEMP to OFF. Fixed COMPONENTS for TBB
* Fixed file name in install rules
* Added find_dependency for TBB in ie_parallel.cmake
* WA for cmake bug with PACKAGE_PREFIX_DIR
* Fixed no-deprecation to fix speech-library build
* Reverted version from 2.1.0 to 2.1
* Revert "Reverted version from 2.1.0 to 2.1"
This reverts commit 7cb5d1563c.
* Returned custom version file back
* Added InferenceEngineConfig-version.cmake to share as well
* Disabled one more GPU test
* Added one more WA for CI
* WA for CI issue for C API
* WIP
It is a known internal issue in gtest when holding a shared_ptr to mocked object, which sometimes reports about memory leak
It is recommended to use Mock::VerifyAndClearExpectations at the end of each test when mock object is not needed anymore
After adding this, issue with incorrect TestThrowOnImport expectations is observed
* [GNA] Additional PWL segments are added to avoid saturation
After design phase for PWL segments has finished,
additional segments are added to avoid saturation.
This commit also reduces the number of PWL segments created
for some layer types.
* [GNA] Make PWL unit tests take into account saturation errata
* Written MO classes for DFT and IDFT operations.
* Added class to read TF (I)FFT operations.
* Written extractors for TF operations FFT, FFT2D, FFT3D, IFFT, IFFT2D, IFFT3D.
* Written MO Roll operation and TF Roll operation extractor.
* Started to write needed transformations.
* Written transformation StridedSlices + Complex + Roll + (i)FFTxD + Roll + (Imag, Real) + Pack -> Roll + (I)DFT + Roll.
* Written transformation for Complex + ComplexAbs.
* Written correction of axes of Roll.
* Small fix.
* Small fix.
* Some fixes.
* Some changes.
* Now TF Roll is read as TFRoll. Written inserting Transposes before and after (I)DFT.
* Small fix.
* Written tests for the transformation TFRollToRoll.
* Added comments to some transformations.
* Deleted redundant import.
* Written tests for the transformation TransposeDFT.
* Fixes in MO IR Reader to read/write (I)DFT.
* Fixes in the list of supported TF layers.
* Started to write tests for SSliceComplexRolledFFTPackBlockReplacement transformation.
* Written tests for the MO transformation SSliceComplexRolledFFTPackBlockReplacement.
* Written tests for the MO transformation ComplexAbs.
* Tests for transformations were moved into unit_tests directory.
* All extractors for (I)FFTxD are in one file now.
* Deleted redundant transformations.
* Fixed extractor for TF Roll: now this operation is read as MO Roll.
* Added comments to TFFFT operation.
* The method insert_transpose of classes TransposeDFT and LayoutChangeForGatherND was moved into the separate function in the file model-optimizer/extensions/middle/InsertLayoutPropagationTransposes.py.
* Fixed comment for the transformation TransposeDFT.
* Small fix.
* Some fixes.
* Deleted shape infer function for the operation TFFFT. Sorted imports in complex_abs.py.
* Small fixes.
* Deleted redundant import.
* Fixes in some asserts.
* Small fix.
* Added names for created nodes in the transformation ComplexAbs.
* Added comments to the method canonicalize_axes.
* The transformation SSliceComplexRolledFFTPackBlockReplacement was split into the sequence of transformations SSliceComplexRollReplacement -> RollRealImagPackReplacement -> TFFFTToDFT.
* Written tests for the transformation SSliceComplexRollReplacement.
* Written tests for the transformation RollRealImagPackReplacement.
* Written tests for the transformation TFFFTToDFT.
* Deleted commented code.
* Fixed types of constants in the transformation ComplexAbs.
* Written tests for canonicalization of signal_size value.
* Deleted 'Replacement' from names of files and classes.
* Used comarison of ids, not names.
* replace_sub_graph was replaced with find_and_replace_pattern.
* Now the transformation RollRealImagPack is executed before running transformation model-optimizer/extensions/front/Pack.py.
* The body of the function create_dft_from_tffft is a part of the transformation TFFFTToDFT body now.
* Now method correct_roll_axes of classes RollRealImagPack and SSliceComplexRoll is moved to the function in mo/front/tf/graph_utils.py.
* Small changes.
* Added comment before mark_input_as_in_correct_layout(roll, 2).
* Now the functions correct_roll_axes generates sub-graph in the input port 2 of Roll.
* Corrected tests for the transformation SSliceComplexRoll.
* Corrected tests for the transformation RollRealImagPack.
* Deleted commented code.
* Some renaming.
* Added decomposition of the separate operation ComplexAbs (without Complex before it).
* Added comment to the transformation ComplexAbsAfterComplex.
* Optimized imports for the transformation TFFFTToDFT.
* The transformation SSliceComplexRoll was split into the sequence SSliceComplex -> CorrectRollAxes and disabled.
* Written tests for the transformation ComplexAbs.
* Written tests for the transformation SSliceComplex.
* Written tests for the transformation CorrectRollAxes.
* Deleted the transformation SSliceComplexRoll.
* Deleted renaming nodes.
* Fixed comment.
* Small fixes.
* Small fix.
* The attribute need_correction was renamed as input_rank_changed.
* Small fixes.
* Deleted commented code.
* Now we iterate over all complex_node.out_port(0).get_connection().get_destinations() input ports and mark the corresponding nodes with the marker attribute.
* Added the attribute 'in_ports_count' into the class FFTBase.
* Tests for the transformation TransposeDFT were rewritten using helper functions.
* Now the transformation RollRealImagPack uses existing Roll node instead of creating new one.
* Small fixes.
* Fix in the documentation.
* Written class to read MxNet (I)FFT operations. Written corresponding extractors.
* Corrected shape infer function for MXFFT operation. Written transformation to convert MXFFT to (I)DFT.
* Fixed shape infer function.
* Fixed the conversion MXFFT to (I)DFT.
* Written tests for the transformation MXFFTToDFT.
* The function correct_roll_axes was replaced with more generic function add_constant_to_negative_values.
* Fixes in classes TFFFT, FFTBase, DFT, IDFT, MXFFT.
* Added asserts in constructors of operations TFFFT and MXFFT.
* Refactored transformation MXFFTToDFT: conversion of DFT and IDFT were moved into separated functions.
* Moved some commented code.
* Fixed BOM file.
* Written function convert_ifft_to_dft.
* Started to rewrite tests for MXFFTToDFT transformations, in the case is_inverse=False.
* Small fixes.
* Fixes in the transformation RollRealImagPack.
* Renaming tests class for the transformation SSliceComplex.
* Fixes in the function compare_graphs. Now we get all output nodes of op node, and these output nodes are sorted by names.
* Fixed tests for the transformation MXFFTToDFT.
* Fix in the transformation ThresholdedReluDecomposition: added disconnect for trelu input port.
* Fixes in test for the transformation TFSliceToSlice.
* Small fix in the transformation ObjectDetectionAPIPreprocessor2Replacement.
* Small fix in comment.
* Optimized imports.
* Used remove_node in the transformation ThresholdedReluDecomposition and remove_nodes_from in the transformation RollRealImagPack, instead of ports disconnection.
* Deleted commented code.
* Deleted test case test_slice_replacer_begin_with_2_inputs.
* Removed constant DDR_MAX_SIZE = 512.
Removed the DDR_MAX_SIZE constant as it could potentially lead to incorrect behavior of devices with a different DDR size (Prism Creek can be up to 2 GB in size). Removed the use of this constant in methods.
* Allow nagative values for batch_dims
* Update formula
* Update spec according to comments
* clarified cases when batch_dims and axis less than zero and enhanced restriction for index types
Co-authored-by: Pavel Esir <pavel.esir@intel.com>
