+ Creation of onednn_engine in ocl_engine is changed to on-demand.
+ benchmark cache_dir option takes longer than cl_cache_dir env in loading network.
+ For clDNN execution, benchmark cache_dir created onednn_engine if just ONEDNN_ENABLE config is ON.
Signed-off-by: Min, Byungil <byungil.min@intel.com>
* [TF FE] Implement conversion for Attention OCR model
The following scope of work is done to make Attention OCR convertable:
1. Refactored translators for BiasAdd, Slice, and ArgMax operations. Add translation for StopGradient operation.
2. The previous traversing algorithm to compute topological sorted nodes list was incorrect. Now it is implemented based on topologically_sorted function from core/graph_util.hpp.
3. The unsupported data types are now preliminary converted to undefined type for the purpose of to have them cut off.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Revert workaround for support of non-frozen models
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Correct third-party dependencies
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply feedback from code-review
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply code-review feedback from PR12444
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply the rest of comments from the code-review
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Previously INPUT/OUTPUT_SIZES was declared as an unnamed array macro.
However current ocl compiler deals with the value obtained from such an array non-constant, so that it results in a side effect in compiler optimization.
Here, a workaround for this issue is applied, i.e., declare the INPUT_OUTPUT_SIZES as a __const array instead of jit constants.
* Fixes for cases when TBB_DIR env var is set
* Don't use make in build_samples.sh script
* First version of Windows installer
* WIndows NSIS installer
* Improved version of debian packages
* Improvements
* Improvements
* Debian packages now look good
* Library versioning
* Fixed tests to run against debian packages
* Fixed frontend tests
* Fixed code style
* FIxed Windows
* Fixed python tests
* Fixed paths in tests
* fdvfdv
* Fixes
* USe versioning only for debian packages
* Relocatable tests
* Fixed
* Fixed all tests
* Fixed clang-format
* Fixed more tests
* Fixed some tests
* Absolute paths in .ci
* Fixes
* Added support of OpenCV 3.4
* Trying to fix gnaUnitTests
* Method Node::constant_fold uses new evaluate method with TensorVector
* Simplify conditions for creating tensor
* Add test for evaluate with TensorVector
* Add line at EOF
* the first approach to fixing the Result edge naming issue
* more robust approach, not depending on the split
* out_nodes_ids type change
* missing if clause
* [TF FE] Fix StridedSlice translator for new_axis vector longer input rank
Currently, new_axis vector is cut by input rank that is correct and leads to the loss of new axes.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Use int64 type in mask_to_vector function
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* WIP graph tests fixing
* Fix collectiors graph tests
* remove debug code
* Fix rebase
* eps update for scales tests
* Outputs for some reference models was changed
* Sanity reference metrics update for VNNI CI hosts
* Unused hyperopt dependency which broke python3.6 support is commented
* Minor comments fixes
* Update doc for AUTO and AUTO_BATCH
Signed-off-by: Chen Peter <peter.chen@intel.com>
* Update docs/OV_Runtime_UG/automatic_batching.md
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
* [MO] Relax MO upper-bound requirements for TensorFlow and NumPy
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Just debug numpy version
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Pin upper-bounds for NumPy and TensorFlow modules in all reqs files
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update submodule dependency for open_model_zoo
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Install numpy module first
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update NumPy version in POT setup.py
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Extend telemetry tests with a set of possible solutions for events
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix build issue
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update NumPy module version for layer tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* get data type of convolution weights from node.weights() when network is internal
* use only instance.node.weights().get_output_layout().data_type
* fix typo
* add unit test for the case
* Add exception handling for calc_output_layout
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Apply comment to error handler
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add static shared_objects map in FEM
- add unit tests for frontend lib close
- not use static FEM in ie network reader
- add main for gtest which can use manifest file to filter tests
* Move library pointers map to manger impl
- add to manger impl method to make frontend from loaded plugin
* Add shutdown function to ov namespace
it cleans the static resources
* Revert changes related to linking mian for tests
* Add python binding to ov::openvino_shutdown
* Renamed shutdown method and added to legacy C++ API
(cherry picked from commit a8395bd207)
* Added C bindings
(cherry picked from commit d2c9ddc263)
* Move frontend lib close test to ieFunctTest
- moved to not introduced new test binary and modification on CI
the frontend tests use dynamic linked frontend lib which is load
on test application start and mask lib close tests
- remove gtest_main_manifest as not required now
- add ov::shutdown test to expect application crash
* Fix lib_close test
- remove not get_disabled_tests from utils
- revert CMake file formating
* Fix get model path in lib close tests
* Skip frontend lib close tests if static lib build
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
