* 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>
* Added info on DockerHub CI Framework
* Feature/azaytsev/change layout (#3295)
* Changes according to feedback comments
* Replaced @ref's with html links
* Fixed links, added a title page for installing from repos and images, fixed formatting issues
* Added links
* minor fix
* Added DL Streamer to the list of components installed by default
* Link fixes
* Link fixes
* ovms doc fix (#2988)
* added OpenVINO Model Server
* ovms doc fixes
Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com>
* Updated openvino_docs.xml
* Edits to MO
Per findings spreadsheet
* macOS changes
per issue spreadsheet
* Fixes from review spreadsheet
Mostly IE_DG fixes
* Consistency changes
* Make doc fixes from last round of review
* integrate changes from baychub/master
* Update Intro.md
* Update Cutting_Model.md
* Update Cutting_Model.md
* Fixed link to Customize_Model_Optimizer.md
Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com>
Co-authored-by: baychub <cbay@yahoo.com>
* Added nGraph Python API for operations DFT and IDFT.
* Written tests for the DFT Python API.
* Written tests for IDFT nGraph Python API.
* Small fixes.
* Started to add tests for the signal_size case.
* Written tests for signal_size case of DFT.
* Written tests for signal_size case of IDFT.
* Some code style fixes in IDFT nGraph Python API tests.
* Code style fixes in tests for DFT nGraph Python API.
* Now DFT nGraph Python API tests are used numpy FFT ressults as expected results of tests.
* Now IDFT nGraph Python API tests without signal_size are used numpy FFT result as input data.
* Now IDFT nGraph Python API tests use numpy IFFT as expected results for signal_size cases.
* Deleted redundant function.
* Formatting fix.
* Now test data for DFT and IDFT nGraph Python API are randomly generated.
* Added seed initialization.
* update tanh v1 spec
* Apply review suggestions
* add rounding info
* Move Tanh to activation functions
* reorganize spec and add rounding rule for integers
* back to arithemtic functions
* Update `short description` to adjust with new EW description template
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
* Removed transformation which removes Const->Result sub-graphs
* Removed one more MO transformation which removes Const->Result sub-graph during the front phase
* Use Serialization as a default engine in MO
* Added cmd option to use old serialization
* Added mapping file generation
* Test mapping file generation
* Fix setBatchsize parameters order; fix mapping file generation
* Added FrameworkNode; added method to read models with custom ops but without extensions
* Added python API for read_network_without_extensions function; updated mo not to use IECore
* Added read_model_without_extensions to IReader and IParser
* Fix V7 IR reader
* Fix pword value
* Fix dllexport macro usage
* Add metainfo to IR
* Fix nGraph code style
* Fix license header
* Restore prepare_emit_ir behaviour
* Fix compare_function to resolve situation when Result input port has multiple names
* Update Compare Functions
* Fix FrameworkNode validation
* Self-review
* CodeStyle check
* --use_fallback -> --use_legacy_ir_generation
* Sort imports in main.py
* --path_to_model -> --input_model
* Use logging instead of print
* Code simplifucation&cleanup
* Fix offline_Transformations key
* Fix GeneraeMappingFile comments
* Use Extension approach to work with custom ops
* Fix versions check
* Code clean-up
* Moved FrameworkNode to inference_engine_transformations library
* Fix FrameworkNode includes
* Code clean-up
* Extend blobs dumping with filtering by environment variables
The idea is to dump blogs without rebuilding
We cannot just use environment variables without compile-time flag
because of security flaws.
Instead, it is expected that developers just always set additional
macro (BLOB_DUMP_PATH) which is not set for the production builds:
export CXXFLAGS="-DBLOB_DUMP_PATH=\\\"mkldnn_dump\\\""
This macro activates blob dump filtering using environment variables.
To prevent unnecessary dumping, blobs are not dumped by default even
if macro is defined.
* Extend nGraph Python API and test IE IR reader for Einsum
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Format description for test auxiliary function
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Remove print from the python test
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* [cldnn] Add initial fused conv eltw POC
- Add cldnn unit test
- Add fused dependency list to the fused_primitive_desc
- fuse_nodes update for saving fusing history and depenecies
- Modify Jitter to create jit constants using fused dependencies
- Add cldnn unit-test cases for multiple serial and parallel eltwise fuse pattern
- Modify Jitter and add default values in sum input
Signed-off-by: Ahn, Paul Y <paul.y.ahn@intel.com>
Co-authored-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
* [cldnn] Update fused_conv_eltwise cldnn unit test
- Add execute and compare function
- Add cldnn unit-test case for multiple parallel eltwise and additional eltwise
- Add cldnn unit-test case for combination of multiple parallel eltw
- Add cldnn unit-test cases for serial and diverged quantize and eltwise
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
* [cldnn] Modify checking fusibility of eltwise fusing
- Add new checking fusibility rule in prepare_primitive_fusing
- Move cldnn eltwise fusing test to fusing_gpu_test.cpp
- Modify method to get input var name in jitter
Signed-off-by: Ahn, Paul Y <paul.y.ahn@intel.com>
* [cldnn] Fix fusing item type and activation fusibility checking condition
- Extract input_data_supports_fusings from fuse_activaion_f
- Fix checking supported mode bug
Co-authored-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
