* Use prebuilt cmake in install-dependencies steps
* Removed building of custom python to save Azure CI time
* Adjusted conditions in cmake
* Download VPU custom kernels compiler only for x86
* Removed -pyver argument
* Improvements
* Detect glibc version
* Usage of new glic variable
* Fixed typo
* Increased glibc version for MYRIAD case
* Made OpenVINO cmake Linux flavors agnostic
* Detect glibc version on RedHat
* Use clcompiler only since ubuntu 18.04
* Universal way to detect glibc version
* Revert some changes
* Apply suggestions from code review
fixes issue with GNA
* Apply suggestions from code review
fixed typo
Becuase pooling to use ngraph shape infer, extend 1D to 2D logic moveed ngraph opt to cldnn pooling.
This change has side-effect in onednn pooling, onednn pooling also doesn't support 1D.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* temp resolution to support model path for CPU in auto
Signed-off-by: fishbell <bell.song@intel.com>
* disable batch when load through model path
Signed-off-by: fishbell <bell.song@intel.com>
* add mark for future release
Signed-off-by: fishbell <bell.song@intel.com>
* implement step1: donotparse batch config if user not set explictly
Signed-off-by: fishbell <bell.song@intel.com>
* correct typo in case
Signed-off-by: fishbell <bell.song@intel.com>
Signed-off-by: fishbell <bell.song@intel.com>
* fix AddressSanitizer: stack-use-after-scope in ov::frontend::paddle::NodeContext::get_attribute_as_any
* fix cyclic reference of op place and decoder.
* fix code style
* fix code style.
* Updated install_dependencies.sh
* Added Fedora support
* Improvements for RPM generation
* Refactored work with gflags
* Apply suggestions from code review
* Improvements
* Several improvements for Ubuntu 18.04
* Improvements in gflags
* Update thirdparty/CMakeLists.txt
temporary install samples dependencies
* Fixed several mistakes
* Fixed issues with gflags
* Don't install dependencies on Linux
* Added nlohmann findinds on debian9 case
* Added FATAL_ERROR is gflags is not found in samples
* Fixes for samples on CentOS 7
* Cross-compiled debian packakges with proper libraries location
* Fixed include for old nlohman-json versions
* Fixed compilation with old json
* Applied review comments
* Added support of old nlohmann versions via submodule
* Temporary WA for CentOS 7
* Fixed compilation with old gflags
* Fixed compilation of C samples
* Fixed gflags on RHEL8.2 / Debian 9
* Use openvino pass graph_rewrite
* Use openvino pass pattern matcher
* Remove ngraph opsets
* Remove ngraph.hpp
* Remove ngraph includes
* Remove ngraph includes
* Use transformations API
* Remove ngraph includes
* Remove ngraph rt_info
* Remove unused ngraph includes
* Replace ngraph:: scope with ov:: here and there
* Remove serialize proxy header
* Remove proxy include
* Bring back a file for vpu-plugin
* Fix after upstream merge
* Remove nested namespace conflict
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
Co-authored-by: Mateusz Tabaka <mateusz.tabaka@intel.com>
* [FE] Fix freezing placeholder via freeze_placeholder_with_value option
Currently, freezing placeholder via freeze_placeholder_with_value option does not work for any frontends. It happens due to absence of a node in _input_shapes dictionary.
* Add get_element_type method for InputModel
* Revert not needed changes
* Revert not needed changes
* Update freeze_placeholder_test
* Add tests for TF FE with freezing values of different types
* Fix Python API return value
* Correct returned type for get_numpy_ctype
* Apply code-review feedback
* Update src/frontends/tensorflow/src/input_model.hpp
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Apply code-review feedback: no tf legacy specific routine and parameter names
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Replace primitive's input with input_new and corresponding updates
Signed-off-by: Andrew Park <andrew.park@intel.com>
* unittests updates
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix conflicts and remaining unittests update
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Replace node and primitive's deps with deps_new and corresponding updates
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Replace output_padding and output_data_type with output_paddings and output_data_types
- Fix corresponding updates (primitive creation API, calc_output_layout|s, opt passes)
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix conflicts and updates
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix failing CI issues
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Apply code review
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix conflicts and corresponding updates
Signed-off-by: Andrew Park <andrew.park@intel.com>
Signed-off-by: Andrew Park <andrew.park@intel.com>
* [Common] Implement SelectWithOneValueCondition common transformation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add transformation tests for select_with_one_value_condition
* Move call of SelectWithOneValueCondition transformation to MOC
* Apply code-review feedback
* Remove corner case with dynamic output shape for Select
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* update code deps for rhel
* new neo driver version
* new neo driver version fix
* fix
* fix
* drop not needed gpu packages
* removed not necessry NEO packages, updated ov deps
* add gflag for rhel8 os
* update python on ubuntu18 and add core rhel8 rpm URLs
* add libpython3.8
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* No-break space->space, asssuming->assuming
* benchmark_app: don't print warning each iteration
* Russian с->English c
* Warn no batch only once
* Allow anonymus namespaces
* Keep only one report of model bach size, warn_if_no_batch for static model as well
* [Python API][Tools] Top up upper bound version for dependencies: NumPy, TensorFlow, NetworkX
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove upper-bound for TensorFlow and NumPy
* Revert "Remove upper-bound for TensorFlow and NumPy"
This reverts commit 662085df2e.
* Remove upper-bound for NumPy for default installation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update docstrings after prohibition of not absolute
paths for plugins
* Use only absolute internal paths to load plugins
After introduction of plugins loading via absolute path,
libraries are still tried to load by names if wasn't found.
So safe last place of search (most common) in order to
get useful error message
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
