* Enable aten::multinomial in PT FE
* Add aten::multinomial test
* Fix typo
* Update tests/layer_tests/pytorch_tests/test_multinomial.py
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Update multinomial to changes in specification
* rm ;
* Add temporary convert for multinomial i64 support
* Revert convert
* Fix torch test
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Moved test in onnx_import_com_microsoft to new API
* Updated onnx_import_constant_folding.in.cpp to new API
* Tests in onnx_import_controlflow.in.cpp moved to new API
* Tests in onnx_import_convpool.in.cpp moved to new API
* Test in onnx_import_deprecated.in.cpp moved to API 2.0
* Removed usage of API1.0 in onnx_reader_external_data.cpp
* Removed API1.0 usage in onnx_import.in.cpp
* Replaced old calls by convert_model in onnx_import.in.cpp
* Removed a deprecated API in onnx_import.in.cpp
* Fixed code style
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* faster large data loading by double buffering
* added get_allocating_order() that is cached for faster loading
* added offset usm memory copy tests
* removed negative_same_names_within_different_networks_cache
* replaced get_processing_order() with processing_order
* add onnx models test job
* rm sudo
* add missing update
* add missing git-lfs
* add missing package
* correct var
* correct command
* try with pytest
* provide path to models
* use mounted path
* add msft models
* use symlinks
* correct name for model
* use -h
* create and use directory for models
* use share as source for models
* fix test names, use fresh onnx repo
* return names
* fix test names
* change folder structure for onnx model downloading
* skip tests; clean up logs; adapt azure counterpart
* make skip names lowercase
* increase parallel
* add missing git-lfs
* fix dir
* install git-lfs properly
* use sudo
* use 12 parallels; rm -f
* use skip
* rm unnecessary requirements
* rm pytorch from installing
* disable test
Needed to be able to run coverity on a specific commit from nightly, like we did in Azure (workflow_dispatch doesn't support running workflow from sha by default).
* WIP working Tensor with automatic casting
* Update infer functions and minor fixes
* Impl for multi-dim arrays with fixes for strides
* Fix strides for S kind and refactor tests
* Added str_data and bytes_data to Tensor, cleaning up the solution
* Add test of warning while using data property
* Allow lists as inputs for single Tensors, refactor infer code to return OVDict with decoded strings, some refactoring, tests
* Replace string with another invalid input
* Added bytes_str and string_str properties, clean up common part of bindings, added test cases
* Improve string element type to be created from numpy/python counterparts, refactor of common code, small improvements
* Add tests for types
* Remove print
* Small fix for tensors from pointers
* Small fix for asserts
* Add tests for data dispatcher
* Fix comments
* fix tests
* Fix edge-case for scalar-like values and unlock tests for data dispatcher
* set core_type = MAIN_CORE_PROC with latency mode and enable hyper threading in pecore machine
* add test case
* change pcore_only to ecore_used
---------
Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
Wang Wangwang
Vitaliy UrusovskijandIlya Lavrenov
Irina Efode
Piotr Krzemiński
Jan Iwaszkiewicz
Sebastian Golebiewski
Mateusz MikolajczykandRoman Kazantsev
Georgy Krivoruchko
Ivan Tikhonov
Roman Lyamin
Jade Cho
Chenhu Wang
Sungeun Kim
Eddy Kim
Andrey Kashchikhin
Alina Kladieva
Chen Peter
Zhang Yi
Pavel Esir
Ahmad Chalhoub
Maxim VafinandIvan Tikhonov
Przemyslaw Wysocki
Sun XiaoxiaandWanglei Shen
Nikolay Shchegolev
Areeb Syed
Oleg Pipikin
Vladimir Paramuzov
Alexandra Sidorova
Anastasiia Pnevskaia
Wang, Yang