* turned on MarkingSubgraphsWithCorrectLayout for TF NCHW
* restricted MarkSubgraphsWithCorrectLayout.py only to TF
* added comments why need to MarkSubgraphsWithCorrectLayout even for TF NCHW models
* Add support for unregistred operations in MO IR Reader
* Remove commented lines
* Add shapes equality check
* Update comments
* Update groupconv_to_conv function to support case with multiple destinations
* Add ir_data_attrs attribute to restored layers
* Update copy_shape_infer function to new graph api
* Add attribute IE to unsuppurted operations to save their attributes
* Fix wrong attribute name
* Update commentary
* Partially revert updating to new Graph API to fix regression, add appropriate comments
* Update code comments
* Rename copy_shape_infer function and add more comments
* gather-8 upgrade/downgrade transforms
* bump to opset8
* add Gather-8 to MO
* fix permutation for Gather
* added TF layer tests, ONNX layer tests for negative indices, and nG python api unit-tests for negative indices
* typo fix, disable downgrading transformation
* disable downgrade in clDNN, line width style fix
* all Gathers are converted to 7th version, transformations will be enabled/disabled while op will be added into plugins
* disabled Gather8LayerTest on GPU
* added common function for Op replacement
* concretized meaning of negative indices, fixed some typos
* applied review comments: left only meaningful layer tests
* removed op replacing functions from common utils
* returned back transformations without subroutines
* corrected style, added comments to common_optimizations.cpp
* MO: Support of discovering of suitable MOC frontend if --framework is not specified
* Ready for review
* Fix: don't use FrontEndManager if framework is not in list of available frontends
* Apply review comments
* Fixes in the transformation ExpandRangeConstant.
* Fixed test.
* Now we use use ShapeOf for both inputs of Broadcast.
* Now the transformation ExpandRangeConstant uses two Gather layers.
* Deletec commented code.
* Fixed tests for the transformation ExpandRangeConstant.
* Rewritten the transformation ExpandRangeConstant using Select.
* Draft version of new approach for Proposal sub-graph conversion for TF OD API models
* Added clip_after_nms = True for Proposal sub-graph being replaced with DetectionOutput
* Refactored code to insert DetectionOutput instead of Proposal operation
* Code cleanup
* Added separate function to insert DetectionOutput instead of Proposal operation
* Updated transformation configuration files for the TF OD API models with Proposal transformation
* Code refactoring
* Code refactoring
* Fix for the condition
* Fixed transformation
* Fixed transformation. One more time
* Updated document about conversion of the TF OD API models
* Update code comments
* Implement transformation for TensorFlow 2 Map Function primitive
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add a description for get_external_node_by_internal_id function
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct a name for get_external_nodes_by_internal_id function
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix a description for get_external_nodes_by_internal_id function
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add logging and fix indentation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Use skip_nodes_by_condition to by-pass StopGradient nodes for tf.map_fn
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* [MO] Add support to moc_frontend of ":" as delimiter for --input
Additions:
Changed default logic for 'Place::get_in(out)put_port' to return nullptr
Changed default logic for 'InputModel::get_place_by_tensor(operation)_name' to return nullptr
* Corrected comments in code
* Missing empty line
* Clang format fixes
* Fix review comments
* Updated test to verify review comments fixes
* Update unit tests after rebase
* Apply review comments
* Rename "pdpd" frontend to "paddle"
Also renamed mo_pdpd.py+main_pdpd.py to mo_paddle.py+main_paddle.py
Class names were not renamed
* Update package_BOM.txt
* Fix recovery of output subscript in Einsum implicit mode
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix code style
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct layout adjustment for Einsum inputs and output
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct a comment in the unit-test
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Setup correct transformation dependencies for LayoutChangeForEinsum
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add json validate
* Fix json schema
* Fix schema loader
* Add unit test
* Update bom file
* Update all requarments
* Update dev requarments
* Update requrments
* Update path to schema
* Update schema
* Add some unit tests
* Move schema to root dir
* Update schema path in bom file
* Fix unit test
* Fix bom
* Change path to schema
* update setup
* Fix setup
* Fix mo args test
* Refactoring some code
* Refactoring according to review
* Update sort imports
* Remove id attribute from schema
* Refactoring validator
* Fix according to review
* Move schema from json to dict. Update unit tests.
* Fix BOM file
* Update bom file
* Static library for ngraph::frontend_manager
* Static + Shared versions
* Fix CI
* USE_STATIC_FRONTEND_MANAGER macro
* Set USE_STATIC_FRONTEND_MANAGER compile definition as public
* Revert back incorrectly removed line
* Apply more review comments
* Remove split-concat subgraph before pad op
* Fix unit tests
* Add unit tests for PadNormalizer
* Fix according to review
* add propagation up for Pad
* Fix value propogation
* Remove PadMormolizer
* Refactoring according to review
* Enable common optimizations on MO
* Added tensor name tracking; updated tests
* Disable DilatedConvolution transform
* Fix TopK3 transformation
* Codestyle fix
* Update tensor name logic
* Fix scatter nd shape inference for dynamic shape
* Update FrameworkNode to propagate dynamic output shape
* Enable HSwish in MO that is missing in nGrpah
* Cleanup MO and IE code
* Fix review comments
* Fix unit test
* Remove sudo from mo install_prerequisites.sh
* Move venv folder to $HOME dir
* Wrap $venv_python_binary with double quotes
* Add variable to store `$HOME/venv_mo`
* Use one venv for all OpenVINO tools
* Add ROOT_DIR variable
* Add python venv creation
* Add message about venv to the .bat script
* Fix a typo
* Implement way to provide keep_output_port attribute to add_opoutput function
* Update tests
* Update comment
* Fake commit to pictures merge problem
* Change default value
* Add type
* Revert "Fake commit to pictures merge problem"
This reverts commit 41850765e0.
* Updated conversion of TF OD API 2.4 SSD models
* Fixed issue when more Conv2D nodes were selected for weights permutation when converting TF OD API models
* Code style fixes
* Fixed code comments
* add priors to loader and counts transformation
* fixes in select insertion for case with context gathering - LSTM - context gathering
fix for edge parallel to ReadValue
extend counts option to case of priors inside mdl model file
* fixed tests
* fixed typo
* fixed issue with input names
* fix priors loading + comments
* fix e2e test: error with not found transformation
* print debug info for dependency graph - should be reverted
* should be reverted: debug commit
* Revert "fix e2e test: error with not found transformation"
This reverts commit 8320fa99bf.
* revert debug commits
* fixes after review
* review fixes
* review change
* review changes
* [MO] Fix showing graceful error message when no ngraph case
Move frontend-related imports inside appropriate functions
And use try/except if import fails to show graceful error message
* Revert "[MO] Fix showing graceful error message when no ngraph case"
This reverts commit 72d52bd946.
* Print error before running of subprocess if IE or nGraph Python API is not found
* Added pytest to requirements_dev.txt
* Fixed review comment
* [NG Frontend] Introduce classes and macros for Frontend-specific exceptions
* [nGraph Frontend] Python bindings
Exposing Python API for nGraph FrontEndManager introduced in PR #5470
* Exposing 'Dimension' class to Python nGraph API
* Model optimizer code from pdpd_frontend
Removed 'use_legacy_frontend' option as not needed for PDPD integration
* Added XML/BIN prints for 'ngraph-FE' serialization path
* Update python bindings to latest code from PR #5995
* Add OV_FRONTEND_PATH to LD_LIBRARY_PATH by default for Model Optimizer
* Test with 'mock' frontend
* Added meta info to generated IR
Added more tests to cover currently supported scenarios
Clang config for MO mock frontend
* some flake8 and pylint fixes
* Try to 'import' ngraph-related packages on top of python files
This will help to specify type of function arguments, but can break unit tests if they're using functions directly without ngraph
* CI fixes
* Run tests from 'main_test.py' inside ngraph environment
* Fixed review comments
* Fixed comments
Added more tests for checking if inputs and outputs are same
* Renamed front_ng to moc_frontend
* Update package_BOM.txt
* Turn on IE and NG python APIs by default inside Model Optimizer
* Remove fallback
* Fix mo_ut
* Remove MO wheel tests
* Add model_optimizer custom target to gather all MO deps inside single traget
* Fix PR comments
* Add ShapeOfConstFolding transform
* Add unit tests
* Update bom file
* Update transform file
* Hot fix
* Fix midle replaser
* Update unit tests
* Fix get value
* Refactoring Const Folding transformation. Move to back
* Update bom file
* Remove unuse code
* Add some unit tests
* Refactoring unit test
* Hot fix
