* Fix errors in VariadicSplit layer restored from serialized IR
* Update VariadicSplit specification and error message to allow 1D tensors on 1st input
* Update spec
* Resolve comments
* Apply comments, add unit tests
* Update unit 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>
* 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 test-generator from all MO requirement files except the dev one
* Moved all MO unit tests files to a separate directory
* Added __init__.py files to the tests directory. Fixed importing paths for some unit tests
* Fixed imports in all unit tests. Moved all unit test related files from the MO code to the dedicated directory
* Renamed directory with unit test utils
* Updated imports in unit tests
* Add keep split output ports without consumers
* Fix ir reader for split outputs
* Update unit tests
* Refactoring code according to review
* Fix unit test
* Fix
* 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
* Added attributes save modes
* Added tensor names to IR
* Reformat code
* Add support for tensor names in MO IR Reader
* Unit tests and code refactoring
* Fixed error
* Code refactoring
* Code refactoring
* Code refactoring
* Error fixed
* Error fixed
* Bug fixed
* Bug fixed
* Additional unit tests and comments
* Small update
* Update fake infer function
* Update names restoring
* optimize imports
* Add support for old-style constants and for commas in reader
* Added dest mode in Fuse Mul
* Update default values
* Fix missed debug info in some specific cases
* Fix a lot of issues with missedand wrong names provoding
* Resolve review comments
* Update test IR's
* Refactor and simplify code
* More simplification
* Remove unneccessary changes
* model-optimizer/mo/utils/ir_reader/layer_to_class_test.py
* Add separate tests for names restoring
* Update copyright year
* Apply review comments
Co-authored-by: Anastasia Popova <anastasia.popova@intel.com>
* fix ss
* successfully converted
* successfully run moved infer and normalizer unit-tests
* successfully rewritten StridedSlice infer unittests
* int64 array
* Successfully converter crash-when-loading, xj_feauture and toy nets (cherry-picked maxpoolV4 and tf_broadcast_ext)
* successfully moved PermuteAttrs to general mechanism
* successfully converted xj_feauture and crash when loading with the new rewritten SS infer
* fixed get_shape_from_slice and moved to common utils
* fixed extending masks and some other
* some refactoring
* fixed extending masks in extractor, fixed licence year and some other code clearing
* corrected a couple of unittests
* fox permute for 5 rank slice and 4 rank inputs/
* WIP
* Added comments
* fixed StridedSlice in ProposalMutation.py
* rechecked shape_infer unittests added some new cases
* added shape_infer unit-tests after StridedSliceNormalizer pass and Permute unit-tests
* corrected unittests
* Applied review comments
* general permutations for inputs implemented, corrected ellipsis unrolling when shrink_axis is at the beginning, some other corrections
* removed code duplication in infer and normalizer, moved 'slices' attr normalizing to StridedSliceNormalizer.py
* removed some code duplication and other minor improvements
* Added tests
* minor corrections
* wider range of unittests added (froze the number)
* review comments applied
* enabled skipped unit-test
* comment corrections
* applied review comments: changed op -> type, added some asserts, corrected comments and other minor corrections
* sorted inputs, updated Supported_Frameworks_Layers.md, some minor
* Generate TensorIterator without back edges from TensorFlow models
* Added a check in the MarkSubgraphsWithCorrectLayout to not fail when port is not connected
* Updated the 'protobuf2nx' to consume the graph protobuf message
* Cleanup TI from the IRv7 specific code
* Do not run some front transformations recursively
* Draft support for the ONNX Loop operation when 'cond' = True
* LoopToTI transformation changes
* Added draft of Loop operation and parser for ONNX Loop operation body
* Updated Loop body parser + added shape and type infer for the Loop operation
* Fixes for ONNX Loop operation parser
* Moved Loop parsing to Loop op extractor. Added generation of external edges for the Loop body ops
* Added support for ThresholdedRelu using decomposition
* Added support for Min ONNX operation
* Draft fixes for port_map generation for the Loop
* Rename transformation file and fix BOM
* Fixed shape inference for Loop scan outputs (axis is not None)
* Fixed shape inference for ONNX Loop operation
* Refactor checks in the TensorIteratorMerge transformation
* Code refactoring. Enabled commented transformations
* Documentation update for ONNX Loop, ThresholdedRelu and Min
* Fixed typo in the Loop front transformation where execution condition input is connected. Other refactorings
* Fixed in the Loop extractor
* Added printing 'internal_layer_id' attribute in the graph dumper
* Updated calculation of iterations number for the Loop
* Added missing code
* Fixed output port shapes and types generation for Loop operation
* Update function names and variable names in the Loop operation
* Fixed type inference for iteration count input
* Added removal of input/output ports of the Loop if they are not used
* Fixed renumbering Loop operations input/output ports to keep mandatory
* Fixed ThresholdedReluDecomposition transformation
* Updated MO IR Reader to know about Loop operation. But it is still not supported by the MO IR Reader
* Added unit test for Slice op shape infer (reverse the sequence of elements)
* Reverted changes in the ONNX loader function call to protobuf2nx
* Enable Reshape0DToSqueeze transformation recursively
* Refactored Loop operation support implementation
* Changed ThresholdedReluDecomposition to generate Const with shape [1] instead of scalar
* Code style and wording fixes
* Restored accidentally removed 'return' statement in the TI shape infer function
* Fixed comments
* Fixed comment
Co-authored-by: Evgeny Lazarev <elazarev.nnov@gmail.com>
* Add Round-5 operation
* Add ONNX Round to supported operation list
* Add ngraph implementation for Round operation
* Update MO part
* Create UnaryElementwise class, update Round Operation
* Fix mode attr in mxnet extractor
* Add tests for Round shape infer
* Update 'enable' attr
* Update MO IR Reader to support UnaryElementwise operations
* Minor test refactor
* Update ngraph Round operation
* Add reference implementation
* Add test for reference implementation
* Add test for shape infer
* Add test for IE IR Reader
* AddRound operation to python api
* Fix missed mode attr
* Update Round operation version
* Fix codestyle
* Add MxNet Round to supported layers list
* Fix error in reference
* Fix comments style
* Update CMake file
* Update Ngraph reference test
* Update IE IR Reader tests
* Return v0::Round operation
* Update shape infer tests
* Fix v0::Round reference
* Fix codestyle
* Enum instead of string
* Fix codestyle
* Add Mode attribute adapter
* Update Mode attr
* Fix reference for v0::Round
* Fix codestyle
* Fix mode attr
* Fix get() method
* Fix codestyle in python api
* Update test info
* Fix ngraph api part
* Ad round v5 to interpreter tests
* Fix codestyle is ie reader test
* Update ngraph python api __init__.py file
* Adde opser5 to dafault opsets in ie_ir reader
* Add parser for Round layer
* Remove redundant spaces
* Add round creator to appropriate list
* Remove redundant import
* Commit to bump infrastructure version
I'm sorry for this, but this commit will be squashed on merge to master anyway and it is needed for your PR to correctly pass the pipeline
* Fix import
* fix codestyle
* Fix ngraph api part
* Add shape infer tests in python api
* Add .upper() for mode attr
* Refactor MO shape infer test for Round op
* Update tests and add comments
* Revert "Commit to bump infrastructure version"
This reverts commit 56e6ae1e4c.
* remove parser for Round layer
* Update Ronund-5 evaluate test
* Resolve review comments
Co-authored-by: User <user@nnlvdp-achetver.inn.intel.com>
Co-authored-by: Andrey Babushkin <andrey.babushkin@intel.com>
Co-authored-by: Anton Chetverikov <anton.chetverikov@.intel.com>
SparseToDense used in Wide and Deep model is expressed through ScatterND operation.
ScatterND is more functional than SparseToDense. Hence, it was decided to replace SparseToDense
with ScatterND. ScatterND is more useful for other models.
Remove SparseToDense from the previous opset
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Removed back phase transformations related to IRv7
* Fixed setting value for the input port using the 'set_value' method
* Removed front and middle phase transformations related to IRv7
* Cleanup the rest of the Model Optimizer transformations from IRv7 specific transformations
* Final cleanup of the deprecated IR v7 related code
* Removed 'blobs_as_input' usage in the Model Optimizer.
* Removed function '_fuse_add' from the Model Optimizer since it is not used anymore.
* Removed 'keep_in_IR' node attribute for FakeQuantize ops in the MO
* Disabled failing gpu_engine.user_context test
Yegor Kruglov