* Removed input_model from meta data dictionary.
* Added test.
* Changed check for more general case.
* Test fixed.
* Temporarily added debug print.
* Fixed test.
* Code corrections.
* Small correction.
* Added type check.
* Added comments, small corrections.
* Refactored MO convert_model() to have single parse_args().
* Small correction.
* Fixed PyTorch converting.
* Small correction.
* Code refactoring, added tests.
* fix checking if there are data nodes for operations with several outputs
* added unit-test
* added ports explicitly, removed redundant lambda
* typo in port
* removed deprecated cli arguments from MO
* removed deprecated options from docs
* Update tools/legacy/benchmark_app/README.md
* removed ConcatOptimization.py, removed deprecated args from unit-tests, renamed tensorflow_use_custom_operations_config -> transformations_config; replaced using or cmd_params.data_type -> cmd_params.compress_to_fp16
* added comment why we set internal 'data_type' always to 'FP32' after introducing 'compress_to_fp16'
* removed openvino_docs_MO_DG_prepare_model_Model_Optimization_Techniques from MO_DevGuide
* returned back --data_type argument
* leftovers from recovering
* returned back to package_BOM.txt; fixed NHWC by default for TF
* recovered --disable_nhwc_to_nchw to MO args
* reverted removing --tensorflow_use_custom_operations_config
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* [Python] Align pc output in Python benchmark, update sorted output to new headers, print floats with 6-digit precision, fix date format printing to excel-friendly
* [PYTHON/C++] Change precision of raports and pc counters report, simplify code
* [C++] Align C++ benchamrk_app report to Python's by setting the precision value to 3
* [C++] Fix CsvDumper precision
* [C++/PYTHON] Align pcand pcsort outputs, merge C++ printSort methods into one
* Update samples/cpp/common/utils/include/samples/common.hpp
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
* Update samples/cpp/common/utils/include/samples/common.hpp
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
* [Tools][MO] Clean up requirements for default installation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update azure config files with extras
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Cleaned up requirements in POT
* Fixed issue
* Removed pandas usage from POT
* Update setup.py
* Removed the upperbound for numpy in the case of Python < 3.11
* Removed numpy logic
* [C++] Display a warning if Power Mode is not 'Max Performance' - rebase from master
* [C++] Prevent std::max from colliding with windows.h max macro
* [PYTHON/C++] Update README docs to reflect possible inaccuracies from optimization settings
* [C++] Cleanup windows optimizations
* cleanup tmp IR files after unexpected failures
* separated catching during tmp serialize and fe.load
* updated file path specification
* moved base MO arguments into utils
* removed redundant 'except' blocks
* shortened specifying MO args
* calling unit-tests from subprocess; joined 2 try/except block into a single one
* changed postfix so that test is run without duplications only once
* [Tools] Avoid use of NumPy deprecated types
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Revert "[Tools] Avoid use of NumPy deprecated types"
This reverts commit 21ffc167d1.
* Move to 1.24 Numpy
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* replace benchmark_app imean and iscale parameters
Tickets 80777 and 80900
* Warn about difference with imean and iscale, note that in help
* Clang format
* Clang format
* mean->scale
* Keep mean scale empty if not set
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
* Preserve input constant when Squeeze and Unsqueeze shape infer is sone in MO IR Reader
* Fix bom test
* Add tests
* Fix value
* Fix test
* Apply suggestions from code review
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* merge master
* reset original format
* remove AUTO
* Update tools/benchmark_tool/openvino/tools/benchmark/main.py
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
* delete condition
* delete condition in py
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
port https://github.com/openvinotoolkit/openvino/pull/14637
Shift to separating the Workflow section, including moving Run and Optimize inference inside Deploy locally
change several article and menu titles
minor additional restructuring
minor content tweaks
remove optimization introduction (may be brought back in parts later)
* several link fixes
* additional link fixes
* [TF FE] Add info messages in Model Optimizer and the preliminary user documentation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add test model with future operation
* Update docs/MO_DG/prepare_model/TensorFlow_Frontend.md
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Apply code-review feedback: Recover use of dict
* Fix the rest of feedback
* Remove User documentation for TF FE
* Correct tests to provide required arguments
* Handle argv without framework argument in deduce_framework function
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* [ONNX FE] Support value freezing without specifying type
Implement gete_element_type method for ONNX InputModel.
Implement tests with freezing integer input and float models
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update src/frontends/onnx/frontend/src/input_model.cpp
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
* Update src/frontends/onnx/frontend/src/input_model.cpp
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
* Update src/frontends/onnx/frontend/src/input_model.cpp
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
* Return only element type for model inputs and add ONNX FE tests
* Rename variable in the test
* Add syntax mark
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
* [TF FE] Support dynamic shape Placeholder freezing and PlaceholderWithDefault
Also, this PR contains reorganization of python unit tests for TF FE that
covers conversion and inference of different models in pbtxt.
This mini-infrastructure will be used in the future for TF FE support.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Revert debug info
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update gna3.json
* Update GNA-related transformations
* Added all GNA devices into one list
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
Maciej Smyk
Anastasiia Pnevskaia
Sebastian Golebiewski
Ilya Naumov
Ilya LavrenovandYuan Xu
Pavel Esir
Ilya Churaev
Przemyslaw Wysocki
Maxim Vafin
Tomasz Dołbniak
Karol Blaszczak
Artyom AnokhovandIlya Lavrenov
Nikita MalininandAlexander Kozlov