* Pre-process:
- Implicit conversions for element type and layout
- 'convert_element_type' with default argument to network
- Convert_element_type - don't add ops if dst and src types are same
- Convert_layout - don't add ops if dst and src layouts are same
- Custom step - use Output<Node> instead of shared_ptr<Node>
- Support of addressing input by tensor name
Post-process:
- Avoid duplication of tensor names after post-processing
* Fixed IE tests
* Enabled support of IR v11 in IR frontend
* Enabled serialization to v11
* Added indexes for Inputs/Outputs
* Fixed typo
* Fixed code style
* Fixed deserialization tests
* FIxed typo
* Avoid changes in the original serialized function
* Split IRv7 and IRv10 code
* Added preprocessing steps to read network
* Added preprocessing for new API for IR v10
* clang-format
* Updates for compiler flags
* Reverted some changes
* Fixed TI tests
* Removed version from the function and indexes from parameters/results
* Restore function version
* Clone function rt info
* Removed v11 version
* Added serialization of old API map in ngraph.
* Changed order type to int64_t.
* Fixed uint64_t error, added comments.
* Apply suggestions from code review
Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
* Read old_api_map
* Added tests with undefined type and empty order.
* Fixed reprocessing
* Updated gitignore
* Updated serialize / deserialize tests
* Added set, get and has methods.
* Fix in tests.
* Applied old_api_map tests
* Fixed empty convert_layout
* Allow Layout from empty string
* Fixed clang-format
* Export FEM::load_by_model
* Apply suggestions from code review
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* Made inline methods, changed to shared_ptr.
* Small fix.
* Moved methods to header file.
* Small fix.
* Applied post-processing
* Fixed review comments
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
Co-authored-by: Anastasia Popova <anastasia.popova@intel.com>
Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* Added ConcatAlignFilter support for Accuracy Aware mode
* fails after reviewing and added tests
* moved the test to gna/scale_factors_tests; added comments to test
* Added serialization of old API map in ngraph.
* Changed order type to int64_t.
* Fixed uint64_t error, added comments.
* Apply suggestions from code review
Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
* Added tests with undefined type and empty order.
* Added set, get and has methods.
* Fix in tests.
* Apply suggestions from code review
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* Made inline methods, changed to shared_ptr.
* Small fix.
* Moved methods to header file.
* Small fix.
Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* PrePostProcessor.output() - first implementation of post-processing
Supported convert_layout, convert_element_type and custom operations
* Fix review comments
* Added test for pre and post processing together
Fix clang-format
* Move 'validate_and_infer_types' before post-processing
* # Conflicts:
# docs/template_plugin/tests/functional/op_reference/convert_color_nv12.cpp
# inference-engine/tests/functional/plugin/cpu/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp
# inference-engine/tests/functional/shared_test_classes/include/shared_test_classes/single_layer/convert_color_nv12.hpp
# inference-engine/tests/functional/shared_test_classes/src/single_layer/convert_color_nv12.cpp
# ngraph/core/include/openvino/core/preprocess/input_tensor_info.hpp
# ngraph/core/include/openvino/core/preprocess/preprocess_steps.hpp
# ngraph/core/include/openvino/op/nv12_to_bgr.hpp
# ngraph/core/include/openvino/op/nv12_to_rgb.hpp
# ngraph/core/src/op/nv12_to_bgr.cpp
# ngraph/core/src/op/nv12_to_rgb.cpp
# ngraph/core/src/preprocess/pre_post_process.cpp
# ngraph/core/src/preprocess/preprocess_steps_impl.hpp
# ngraph/test/CMakeLists.txt
* Added more test to cover 100% of code
Allow convert element type for 'multi-plane' color format
* Inherit tensor names for 'convert_color'
* Clang
* Fix tests
* Disable 'int8' preprocessing resize test
* Fix review comments
* Add more restrictions and tests for planes sub-names
* 1) Added check for uniqueness of tensor names generated for nodes
Raise error if user's plane sub-name conflicts with some node in a function
2) Added exception safety to preprocess build. Before, when input #2 fail, only one preprocess will be applied to function and it will be corrupted
Exception guard will restore function to original state if exception occurs
* Fix clang-format
* Initial change to allow saving graphto IR without meta_info
* Update saving and restoring functions, add more comments
* Add unit tests for define_data_type() function
* Fix wrong name
* Update condition
* Update meta_data checks
* Update data_type restoretion and missed outpurt ports handling
* Update and add new test
* Update comments
* Remove commented code
* Rename function
* Update temporary Result operations processing
* Remove define_data_type function
* Move node_normalize_output function to Op class methods
* Update comments
* Update comments
* Mk/ov pybind poc (#48)
* Move _pyngraph module to ngraph.pyngraph
* Stub for IECore and IENetwork classes
* Additional API classes
* passing test, extended functions and added blob
* worksave
* [POC Python API] Add IECore methods
* [POC Python API] Add iecore tests
* ienetwork
* ienet, input_info, dataptr
* irequest and exeecnet
* adapted benchmark
* Move _pyngraph module to ngraph.pyngraph
* Stub for IECore and IENetwork classes
* Additional API classes
* passing test, extended functions and added blob
* worksave
* [POC Python API] Add IECore methods
* [POC Python API] Add iecore tests
* ienetwork
* ienet, input_info, dataptr
* irequest and exeecnet
* adapted benchmark
* Added suport for InputInfo bindings
* Add Blob support for different types
* fix typo
* Fixed InputInfo maps
* Add keys() to inputs maps
* add uint8 blob
* return read_network as it should be
* return read_network as it should be
* fix blob buffer
* remove const input_info files and fix codestyle
* add mode parameter in benchmark app
* return _pyngraph
* delete benchmark copy
* return pyngraph as in master
* fix benchmark working
* add comment with api which need to implement
* remove unnecessary code from benchmark
* remove hardcoded path from setup.py
* Rename vars in setup.py
* working wheel
* fix wheel building
* Revert "working wheel"
This reverts commit 11d03a1833.
* fix tests
* Added async infer
* pass by ref
* add ccompiler to requirements
* fix blob creation and view
* replace abscent method with working code in benchmark
* fix building
* worksave
* worksave queue
* no-deadlock async infer
* add lock handle in waitAll
* fix building issues with includes
* update of setup and cmakelist
* fix setup.py way of building
* add new methods for ie_core
* add ienetwork methods: serizlize and getfunction
* add methods for exec net and infer request class
* remove ccompiler from requirements
* remove set from cmake
* Update Blob class with precisions
* Rewrite test_write_numpy_scalar_int64
* Generic Blob casting in infer queue
* implementation of preprocess_info
* update license
* add set_blob method
* worksave
* added template for setblob
* Added blob convert in infer request
* move blob casting to common namespace
* add_outputs method
* work with func from pyopenvino
* add user_id to callbacks
* remove hardcoded root dir
* refactor code and comments
* [Python API] use parametrize in blob tests
* move common functions to conftest file
* Add tests for blob
* Update test_blob and test_network
* add parametrize in blob tests
* blob refactoring
* Fix sync in InferQueue and add default callbacks
* patch for protobuf cmake
* blob refactoring
* rename convert_to_blob to cast_to_blob
* rename to cast_to_blob in infer queue
* add missing cast_to_blob
* remove boost
* change license
* undo in cmake
* fix building
* [IE PYTHON API POC] Add fixed InferQueue and modification in async part of benchmark
* Add read_network(model,blob)
* Add blob_from_file helper
* Add read from Path
* Add tests
* Add read_network from bytes
* Error throwing in Common IE functions
* Cleaning samples
* Changes in ConstInputInfoWrapper class
* Add StatusCode to callback function for InferRequest
* Add random image generation and model path getting
* Move example model to examples path
* Adapt sync and async examples to new helpers
* Return request info containing StatusCode and ID from InferQueue for top idle request.
* Update benchmark app to use new API with request info
* Update examples to use two different approaches to InferQueue
* reset new line
* Add is_ready() to InferQueue
* fix building
* remove benchmark
* temporary add separate flag for building poc
* refactoring
* Remove GIL acquire in default callback and latencies
* Adapt benchmark to Core()
* Codestyle
* fix building
* [Python API] Move ngraph python api to the new destination
* fix building tests
* fix code-style checks
* building in azure
* fix building wheels
* apply fixes
* new structure
* fix building
* Add support for InferRequest::Cancel in pyopenvino
* fixes
remove gil release
add async infer after cancel
* remove extra files
* remove examples and benchmark
* fix code style
* fix building
* fix tests
* merge inits from old and new api
* fix azure ci
* fix setup.py
* fix setup.py building
* try to fix mac
Co-authored-by: Michal Karzynski <michal.karzynski@intel.com>
Co-authored-by: jiwaszki <jan.iwaszkiewicz@intel.com>
Co-authored-by: anastasia.kuporosova <akuporos@akuporos.inn.intel.com>
Co-authored-by: Alexey Lebedev <alexey.lebedev@intel.com>
Co-authored-by: Mateusz Tabaka <mateusz.tabaka@intel.com>
* Fix comments
* fix comments: cmakelist
* fix building on arm
* permission for merge script
* permission for merge script
Co-authored-by: Michal Karzynski <michal.karzynski@intel.com>
Co-authored-by: jiwaszki <jan.iwaszkiewicz@intel.com>
Co-authored-by: anastasia.kuporosova <akuporos@akuporos.inn.intel.com>
Co-authored-by: Alexey Lebedev <alexey.lebedev@intel.com>
Co-authored-by: Mateusz Tabaka <mateusz.tabaka@intel.com>
* Enabled support of IR v11 in IR frontend
* Enabled serialization to v11
* Added indexes for Inputs/Outputs
* Fixed typo
* Fixed code style
* Fixed deserialization tests
* FIxed typo
* Avoid changes in the original serialized function
* Fixed TI tests
* Removed version from the function and indexes from parameters/results
* Restore function version
* Clone function rt info
* Removed v11 version
* [GPU] Merge mvn kernel updates
+ Support bs_fs_yx_bsv32_fsv32 format for i8 and u8 dtype.
+ Support bs_fs_yx_bfv32_fsv16 format for fp16 dtype.
* [GPU] Fix a bug of resample kernel selector.
* [GPU] fix a build error of mvn unit tests
* Fixed precisions conversion in new API
* Added tests
* Fixed old IR cases
* Disable FP16
* Fixed regex for CentoOS
* Refactored tests to use new API
* Temp
* Fixed tests
* Moved smart reshape related sources to ngraph
* Added tests for invalid names
* Moved reshape to tensor_names
* clang-format
* Fixed CC build
* Removed IEConv, IEDeconv from primitives pririty
* Added tests for Inference chaining
* Fixed dynamic chaining for template plugin
* Added test for 2 conflicting names for the single parameter
* Removed invalid test
* Added more tests for dynamism
* Fixed clang-format
* Fixed macosx compilation
* Some simplifications
