Commit Graph

9044 Commits

Author SHA1 Message Date
Ilya Churaev
95cf0ca7ba
Add OV parallel (#14485)
* Expose IE_THREAD definition to end users

* Added new OV parallel

* Fixed naming style

* Rename utils namespace

* Fixed cpu plugin build

* Reuse OV macros

* Remove TBB dependency

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-12-12 11:18:21 +04:00
Pawel Raasz
322768bd30
LogicalNot evaluate uses input tensor count (#14537)
instead of output shape set in operator which can be dynamic
2022-12-12 06:58:07 +04:00
Tomasz Dołbniak
11d9b01adb
Refactor of tests (#14544) 2022-12-12 06:17:14 +04:00
Karol Blaszczak
3c89da1838
Docs menu recreate structure step2 port2master (#14552)
model optimization
deploy locally
run inference
remove OVSA from security (it was duplicated)
2022-12-11 14:30:14 +01:00
Roman Kazantsev
e9e05e508a
[ONNX FE] Support value freezing without specifying type (#14481)
* [ONNX FE] Support value freezing without specifying type

Implement gete_element_type method for ONNX InputModel.
Implement tests with freezing integer input and float models

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Update src/frontends/onnx/frontend/src/input_model.cpp

Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>

* Update src/frontends/onnx/frontend/src/input_model.cpp

Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>

* Update src/frontends/onnx/frontend/src/input_model.cpp

Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>

* Return only element type for model inputs and add ONNX FE tests

* Rename variable in the test

* Add syntax mark

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
2022-12-11 14:58:55 +04:00
Zlobin Vladimir
408bfc50c7
Update OMZ submodule (#14471) (#14547)
* Update OMZ submodule

This update includes models publication for 2022.3
Tickets 95909 and 95910

* Update OMZ submodlue: remove numpy upper bound
2022-12-09 18:34:41 +00:00
Pawel Raasz
45033806fd
Review opset7 einsum for shape inference aspects (#14059)
* Review einsum shape and label propagation
- extend type_prop test by check labels and einsum properties

* Review template implementation of shape inference
- rename StaticShape inference test file
- use common fixture and rename test cases
- add default ctor test
- add equation string setter

* Fix einsum label propagation check
due to improvement of dimensions and labels merge

* Remove BWDCMP_RTTI_DEFINITION from einsum op

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
2022-12-09 17:04:51 +00:00
Ilya Churaev
7a7675a778
Added complex meta tests for C++ and python (#14265)
* Added complex meta tests for C++ and python

* Fixed python test

* Fixed code style

* Fixed python code style

* Added any test
2022-12-09 15:45:12 +00:00
Ilya Lavrenov
330e42a4ad
CI: reduce time for NVIDIA plugin precommit (#14542) 2022-12-09 17:50:21 +04:00
Ilya Lavrenov
1cb4800c03
Added ocl-icd for ubi8 image (#14525) (#14539)
* install_openvino_dependencies: Added ocl-icd for ubi8 image

* install_openvino_dependencies.sh: Added json-devel to pkgs_dev for ubi8

* install_openvino_dependencies: Added pkgconf-pkg-config to pkgs_dev

* install_openvino_dependencies: Moved pkgconf-pkg-config to high-level pkgs_dev

* install_openvino_dependencies: Fixed with case for centos7

* Update scripts/install_dependencies/install_openvino_dependencies.sh

applied comments

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>

Co-authored-by: Artyom Anokhov <artyom.anokhov@intel.com>
2022-12-09 15:42:05 +04:00
Ilya Lavrenov
f7de47e9b5
Added extra dependencies for debian / rpm packages (#14529) 2022-12-09 15:12:18 +04:00
Wilson Seok
c16cee4624
fix PR14422 regression for using arg_max_min opt kernel (#14487) 2022-12-09 00:37:29 -08:00
Karol Blaszczak
fac45d79e4
Docs menu recreate structure step1 (#14526)
* Initial TOC config

TOC depth
prev-next btn
TOC initial links

* extensibility section

header changed to section
section populated

* media processing and CV lib

header changed to section
no content in the node article... needs to be added later

* openvino security

header turned into section
intro article used as the section parent

* ecosystem

header turned to section
section populated

* menu padding adjustment

* benchmarks and release notes

benchmarks moved to resources
release notes moved to top level
case studies link

* OpenVINO IR

IR articles put in a section
the parent article will require more content
2022-12-09 08:23:20 +08:00
Mateusz Bencer
507cbe7045
Added support of custom domain for OpExtension (C++/Python) and ConversionExtension (Python) (#14375)
* Added support for ONNX OpExtension with custom domain

* review remarks

* move domain ctor to onnx OpExtension

* code refactor + new test

* styles applied

* [Python API] Support extensions with custom domains

* try to fix windows build error

* removed unnecessary stores
2022-12-08 17:47:45 +00:00
Zlobin Vladimir
156905c381
samples/cpp/build_samples_msvc.bat: don't ignore cmake error (#14499)
Ticket 98429
2022-12-08 21:08:57 +04:00
Przemyslaw Wysocki
c99abd5c24
[PyOV] Make graph tests hardware agnostic - part 1 (#14500)
* Halfway done

* Prepare part 1

* Minor changes

* Minor changes
2022-12-08 21:01:18 +04:00
Roman Kazantsev
32ae862f99
[TF FE] Break the cycle in the different way (#14480)
* [TF FE] Break the cycle in the different way

Earlier solution was incorrect due to inproper handling of forward edges cases
(edges going from parent to grand-child) for which topological sorting
of nodes can be interrupted.

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Break the cycle by NextIteration inputs

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-12-08 17:23:49 +03:00
Alexandra Sidorova
b1700d97f1
[CPU] Fixed segfault in Generic node creation for dynamic models (#14420) 2022-12-08 17:13:26 +04:00
Pavel Durandin
6998321f5b
Improvement of messages for api conformance properties (#14493)
* Improvement of messages for api conformance properties

* Improvement of messages for api conformance properties
2022-12-08 13:08:42 +00:00
Aleksandr Voron
d0f183780c
Update evaluates_map.cpp (#14475) 2022-12-08 12:59:46 +00:00
Ivan Tikhonov
54a774e332
Move transformation tests to the correct directory (#14491)
* Move transformation tests to the correct directory

* Revert "Move transformation tests to the correct directory"

This reverts commit 0c2a932505.

* Move the transformation tests to the correct dir
2022-12-08 11:47:25 +00:00
dependabot[bot]
e40de16e60
Bump certifi from 2020.12.5 to 2022.12.7 in /docs (#14494)
Bumps [certifi](https://github.com/certifi/python-certifi) from 2020.12.5 to 2022.12.7.
- [Release notes](https://github.com/certifi/python-certifi/releases)
- [Commits](https://github.com/certifi/python-certifi/compare/2020.12.05...2022.12.07)

---
updated-dependencies:
- dependency-name: certifi
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2022-12-08 12:15:13 +03:00
Anastasiia Pnevskaia
60bb9e7b7c
Fixed type check in convert_model(). (#14472)
* Fixed passing Path to convert_model().

* Update tools/mo/openvino/tools/mo/convert_impl.py

Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>

Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
2022-12-08 12:51:11 +04:00
Xiping Yan
532000a0ce
[CPU] Fix conditional compilation for oneDNN brgemm Convolution primitive 2022-12-08 12:07:22 +04:00
Felix Dohyun Kim
4e85612cfb
[GPU][DG2] Change tanh to relu in fusion unit tests (#14325)
* fix tanh activation fusecount error
* expected_fused_primitives_onednn
* add onednn fused to mvn test param
* add onednn fused to pooling test param
2022-12-08 16:53:09 +09:00
Sungeun Kim
b799e3eb91
[GPU] set b_fs_yx_fsv32 for first conv and dt is U8. (#14454)
* set b_fs_yx_fsv32 for first conv and dt is U8.

* check input format is bfyx.
2022-12-08 16:52:30 +09:00
mei, yang
0602b852eb
update paddle supported ops (#13923)
* update paddle supported ops

* remove paddle tensor array related ops

* remove version information in paddle supported op name

* Update docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

* Update docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

* Update docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md

* Update docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-12-08 15:07:20 +08:00
Vladimir Paramuzov
6df011c9f6
[GPU] Use transformed gemm shapes for layout optimizer checks (#14407) 2022-12-08 09:12:02 +04:00
Ilya Churaev
f91d3d1d04
Change visit_attributes default behavior, operation by default supports visit attributes (#14470) 2022-12-08 02:35:44 +03:00
Artemy Skrebkov
5651488e06
Fix segfault on windows with MSVC (#14466)
* MSVC compiler cannot handle copying empty AnyMap
2022-12-08 02:32:46 +04:00
Karol Blaszczak
6106ece9dd
DOCS-top-menu-items (#14445)
create top menu navigation
tweak css to display navigation properly
2022-12-07 19:34:55 +01:00
Kelvin Choi
1e75a4b427
[GPU] Update GatherTree Op to use ngraph shape infer (#13626) 2022-12-07 10:18:45 -08:00
Anastasiia Pnevskaia
20bd062d5e
Fix of double printing of errors in MO (#14224)
* Fix of double printing of errors.

* Added log test.

* Small correction.

* Test fix.
2022-12-07 18:27:16 +04:00
Karol Blaszczak
3dceb7c3bb
DOCS- add telemetry info page (#14206) 2022-12-07 11:15:34 +01:00
Liubov Talamanova
7ceb8bfce0
[POT] Update test references (#14318)
* Update references

* Update GNA references

* Rebase branch
2022-12-07 14:05:03 +04:00
Evgeny Kotov
f8b347ecd3
[GNA] Fixed extended debug build (#14355)
* fix build

* move debug define to cmake build options

* using namespace

* add debug build check

* remove build type check
2022-12-07 10:46:13 +01:00
Vladimir Paramuzov
7b7e1d19b0
[GPU] allow softmax_bf for axis=Y && X==1 case (#14443) 2022-12-07 13:04:47 +04:00
Ilya Churaev
ed36ddac55
Removed legacy get_name() from descriptor::Tensor (#13934)
* Removed legacy get_name() from descriptor::Tensor

* Fixed GPU plugin

* One more fix for GPU

* Fixed typo

* Revert constructor changes

* Revert get_name for internal plugins
2022-12-07 12:57:11 +04:00
Ilya Churaev
d5d67b2be8
Removed using of BWDCMP macro (#14292)
* Removed using of BWDCMP macro

* Fixed code style

* Removed type info

* Fixed ONNX tests

* Fixed CPU tests

* Fixed ExecutionNode
2022-12-07 12:47:16 +04:00
Roman Kazantsev
d3fa858fcc
[TF FE] Support dynamic shape Placeholder freezing and PlaceholderWithDefault (#14450)
* [TF FE] Support dynamic shape Placeholder freezing and PlaceholderWithDefault

Also, this PR contains reorganization of python unit tests for TF FE that
covers conversion and inference of different models in pbtxt.
This mini-infrastructure will be used in the future for TF FE support.

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Revert debug info

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-12-07 12:13:10 +04:00
Taylor Yeonbok Lee
a47688e593
[GPU] Fix for a corner case for broadcast with dynamic input and static output (#14451) 2022-12-07 09:13:15 +04:00
Nadezhda Ageeva
a21da85eb9
Fix some tests (#14434) 2022-12-06 22:03:09 +04:00
Karol Blaszczak
88b116af66
Update benchmarks articles (#14438)
Update performance_benchmarks_faq.md
Update performance_int8_vs_fp32.md
2022-12-06 17:37:40 +01:00
Nikita Malinin
4171f258b2
[POT] Update GNA3-3.5 configs & passes (#14429)
* Update gna3.json

* Update GNA-related transformations

* Added all GNA devices into one list

Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
2022-12-06 16:25:29 +00:00
Sun Xiaoxia
f5e6816633
fix compilation of test fails on Android x86 (#14442) 2022-12-06 20:24:18 +04:00
Irina Efode
eb19a7f7ad
[CONFORMANCE] Fix condition for WIN in Conformance runner (#14441) 2022-12-06 20:14:05 +04:00
Tomasz Dołbniak
6da95784c7
Unique-10 tests and improvements (#14315) 2022-12-06 19:09:30 +03:00
Luwei Zhou
79f04a704c
[CPU] Extend AMX deconv int8 to support oscale+eltwise+eltwise post ops pattern (#14026)
* Extend AMX deconv int8 to support oscale+eltwise+eltwise post ops pattern.

* Add deconv AMX test cases.

* Add multi-eltwise test on deconv AMX int8.

* Applied review comments.

* Update onednn submodule.
2022-12-06 18:32:02 +04:00
Maxim Vafin
3b86f12c37
Revert "Fix squeeze shape infer to not change axis value (#13975)" (#14430)
This reverts commit 580c0c6b90.
2022-12-06 17:32:56 +04:00
Irina Efode
a27d69db75
[CONFORMANCE] FIX ISSUES FOR WIN IN CONF RUNNER (#14439) 2022-12-06 16:06:04 +03:00