* Moved element_type() to MemoryBlob
* Updated indentation in documentation
* Added more fixes for precisions
* Fixed documentation for new serialize methods
* 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
* [GNA] Use built in ngraph padding calculation
* [GNA] Use less channels for tests
* [GNA] Rename tests file
* [GNA] Add ngraph reference tests and some minor fixes in the transformation itself
* [GNA] Add invalid ngraph reference tests
* [GNA] Align brace style
* [GNA] Remove unnecessary condition
* BatchToSpace specification refactored
* Add minor changes
* Added \ldots to latex formula
* Change output tensor to lower-case y
* Added mention to reverse operation SpaceToBatch
* Corrected dots in formulas
* Enable rank greater or equal than 2 for data input and add more examples
* Minor changes in detailed description
* Improve short and detailed descriptions
* Enable lower input rank for BatchToSpace operation by fallback
* Added conditions to check valid data input rank for evaluate and has_evaluate methods
* Add visitor unit test
* BatchToSpace operation class refactored
* Add RTTI definiton/declaration
* Add checks in validate_and_infer_types
* Add input/output checks in evaluate method
* Add type_prop tests covering checks in validate_and_infer_types method
* Fix incorrect variable names to specify crops_begin and crops_end inputs
* Add backend tests
* Use array stl to handle batch to space inputs in type_prop tests
* Add more backend tests
* Clean up manifest
* Address review comments
* Add node validation check for out of bounds crops
* Add validation checks in evaluate method
* Add error message to ngraph checks
* Modify check for input rank to allow rank 4 or greater to align with spec and plugins impl
* revise atan op
* use parametrized vistor API
* use new gtest macros
* Update docs/ops/arithmetic/Atan_1.md
Co-authored-by: Gabriele Galiero Casay <gabriele.galiero.casay@intel.com>
* Update docs/ops/arithmetic/Atan_1.md
Co-authored-by: Gabriele Galiero Casay <gabriele.galiero.casay@intel.com>
* Update ngraph/core/src/op/atan.cpp
Co-authored-by: Gabriele Galiero Casay <gabriele.galiero.casay@intel.com>
* update doc to follow the rules
* create type_prop for atan
* drop op_eval to be covered in backend
* add the missing type prop case
* add integer type ref impl
* fix clang issue
Co-authored-by: Gabriele Galiero Casay <gabriele.galiero.casay@intel.com>
Add a configuration for the UndefinedBehavior sanitizer, disabled by default.
Refactor sanitizer configuration to split options which are common across sanitizers.
Unify sanitizer runtime linkage accross sanitizers to use compiler default.
* Fix InferenceEngine::Core initialization. Previously IE::Core was
default constructed first, then overwritten by another instance.
This causes problems if the library user attempts to opt-out of the
default "plugins.xml" plugin loading mechanism.
* Use ngraph rtti macros
* Check attribute count in visitor test case
* Add priorBox class for SLT
* Add priorBox SSLT
* Add CPU SLT
* moved type_prop tests to type_prop directory
* Add backend tests
* Add PriorBox to trusted ops list
* infer first dimension of size 2
* Change the build dir for cpp samples
* Add info about `-sample-options` to the help message
* Use `python -m pip` instead of `pip3`
* Add the line of code to update pip
* Update help messages
* Add python venv creation
* Use `model-optimizer/requirements.txt` instead of `install_prerequisites.bat`
* [demo_benchmark_app.bat] Update the help message
* [demo_benchmark_app.bat] Add venv creation
* [demo_benchmark_app.bat] Replace model_optimizer prerequisites with the requirements.txt
* Change the venv location
* Remove the mention of FPGA from the help message
* Fix venv folder path
* Change venv folder to `venv_openvino`
* Remove sudo package installation from demo scripts
* Change the build_dir path (benchmark_app.sh, squeezenet_download_convert_run)
* Remove redundant pip_binary
* Revert 'inference_engine_samples_build' as the build folder for .bat
* Add check for python 3.8
* Update help messages
* Use `model-optimizer/requirements.txt` instead of `install_prerequisites.sh`
* Add `--user` for python package installation (demo_security_barrier_camera.sh)
* Add python venv creation
* Create venv in $HOME instead of $ROOT_DIR
* Make the step messages look the same as in the .bat scripts
* Make the same changes to demo_benchmark_app.sh as in other .sh scripts
* Remove a mention of FPGA from a help message
* Set venv folder to `venv_openvino`
* 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.
