Michał Karzyński
db27dcce94
Remove NGRAPH_USE_PROTOBUF_LITE option, always use Lite ( #8286 )
2021-11-03 18:22:20 +03:00
Vladimir Zinoviev
aa00ae8b43
[LPT] AddTransformation: inconsistent element types when subtract on fullPath is empty ( #8277 )
2021-11-03 18:00:06 +03:00
Evgeny Kotov
9999b786ac
add comment ( #7867 )
2021-11-03 17:06:37 +03:00
song, bell
5617d48d72
enable itt trace for AUTO ( #8139 )
...
* enable itt trace for AUTO
Signed-off-by: fishbell <bell.song@intel.com>
* set itt to real loadnetwork path
Signed-off-by: fishbell <bell.song@intel.com>
* refine itt tracing
Signed-off-by: fishbell <bell.song@intel.com>
* formatting
Signed-off-by: fishbell <bell.song@intel.com>
2021-11-03 16:43:01 +03:00
Maxim Andronov
9871747bc6
[CPU] NonMaxSuppression dynamic done ( #8303 )
2021-11-03 16:07:03 +03:00
Mateusz Tabaka
0be6ed752d
[LPT] optimize Subtract with zero_point == 0 when it's not a direct C… ( #8159 )
...
* [LPT] optimize Subtract with zero_point == 0 when it's not a direct Constant
zero_point may be a Constant, but also it may come in form of
Constant->Convert(from low to high precision) subgraph.
If we handle both cases, we can reduce redundant Subtract node
e.g. between weights and Convolution which makes Convolution
to work fully on low precision inputs which significantly improves
performance.
* don't round shift if it's already in low precision
2021-11-03 15:58:48 +03:00
Michał Karzyński
165ce3eeea
Add support for ONNX RandomNormal and RandomNormalLike operators ( #8024 )
...
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
2021-11-03 15:50:35 +03:00
Tatiana Troilova
fb5c9caa4d
Update third party files ( #8382 )
2021-11-03 15:29:42 +03:00
Mikhail Letavin
28706c34a1
[GPU] Fix sporadic fails in canRun3SyncRequestsConsistentlyFromThreads test ( #8377 )
2021-11-03 14:59:38 +03:00
Milana Shhanukova
5d9a76d2f8
Update node name to make ports visible ( #8218 )
2021-11-03 14:46:33 +03:00
Mateusz Tabaka
3fc210af21
Reimplement Extension.OnnxModelWith* cases w/o model in source code ( #8112 )
...
Ticket: 62567
2021-11-03 14:43:44 +03:00
Aleksei Kruglov
4e4e179d67
[VPUX] Updated config's parser ( #7974 )
...
Updated config's parser for compile_tool
The parser can read value containing spaces
2021-11-03 12:14:13 +03:00
Paul Youngsoo Ahn
ece45630f0
[GPU] Set affinity TBB using CPUStreamsExecutor ( #7738 ) ( #7738 )
2021-11-03 11:50:55 +03:00
Mateusz Tabaka
65c3b4c357
Fix 'cannot estimate element if precision is UNSPECIFIED' error cause… ( #7748 )
...
* Fix 'cannot estimate element if precision is UNSPECIFIED' error caused by LPT
In some models after ConvMulFusion and FakeQuantizeMulFusion, output_low contains
denorms. That is problematic since LayerTransformation::getPrecisionDetails function checks
if output_low is close to zero and if it is - the function sets 'signedPrecision' flag to false.
In that case, both 'signedPrecision' and 'unsignedPrecision' are set to false and that makes
getPrecisionDetails return element::undefined.
This patch changes zeroThreshold to handle denorms.
Ticket: 65375
* fix FakeQuantizeTransformation tests
2021-11-03 11:39:52 +03:00
Vladimir Paramuzov
da33abca3a
[GPU] Fixed allocatin type for optimized out outputs ( #8349 )
2021-11-03 11:09:11 +03:00
Vladislav Golubev
6e3c2dd3ec
[LPT] LP Transformations: security fixes ( #8357 )
2021-11-03 10:56:23 +03:00
Andrey Somsikov
24aec7928c
Fix fuzz test failure ( #8380 )
...
Fuzz test execution fails with:
import_pdpd-fuzzer: symbol lookup error: runtime/lib/intel64/libngraph.so: undefined symbol:
__sancov_lowest_stack
2021-11-03 10:35:19 +03:00
Ilya Znamenskiy
0ed285ceb6
[GPU] Removed unneeded bias into quantize shift optimization ( #8369 )
2021-11-03 10:23:21 +03:00
Anastasia Popova
8d44a37f40
Added TID to Telemetry initialization. ( #8194 )
...
* Added TID to telemetry initialization.
* Moved TID to separate file.
2021-11-03 10:01:49 +03:00
Maxim Andronov
553403496c
[CPU] General fixes for dynamic shapes ( #8205 )
2021-11-03 09:11:28 +03:00
Vladislav Golubev
983d55fba5
[CPU] MatMulToFullyConnected transformation temporary disabled ( #8364 )
2021-11-03 09:10:35 +03:00
Steve Yoo
e3f1813e5c
Migrate Movement 2 (GatherElements-6, GatherND-5) ( #8282 )
2021-11-03 08:02:19 +03:00
Steve Yoo
bd756df2f5
Migrate ngraph backend test of constant operation ( #7996 )
...
* Add test cases for PReLU in cpu plugin
* For case when slope is vector
* Add Constant template plugin reference tests
* Update CMakeLists.txt and delete constant.in.cpp
* Add tests of tensor_2constant and constant_multi_use
* Add test of constant_equality_bool
* Remove wrong comments
* Remove some of strange if
* Merge to one CreateFunction
* Remove test names and update test for types
* Add bf16 and f64 tests
* Add missing type tests
* Clear actualOutData to allow multiple use of Validate()
* Update SetUp and CreateFunction to support CentOS CI
* Remove inputData = {}
2021-11-03 07:52:59 +03:00
Julia Kamelina
7c56155dae
[Python Tools] Align namespace for cross_check_tool ( #7786 )
...
* align openvino namespace
* update README
2021-11-03 01:55:27 +03:00
Artyom Anokhov
f20f4d024c
Deployment Manager CFGs: Added paddlepaddle_ngraph_frontend lib as core part ( #8322 )
2021-11-02 18:23:48 +03:00
Evgeny Talanin
0b0202b90c
Revert "[GPU] Fix some performance degradations from breaking GPU pipeline into explicit stages ( #8084 )" ( #8372 )
...
This reverts commit 03106e0cd9
.
2021-11-02 17:35:37 +03:00
Ilya Lavrenov
384eea4eda
Static version: plugin registration as extension ( #8365 )
...
* Load CPU plugin as extension as well
* Fixed linkage issues
* Added static linux build
* Disabled GPU
2021-11-02 16:07:45 +03:00
Anna Khakimova
0071abffdf
Workaround for fluid's color conversion tests failures.Part 2. ( #8293 )
2021-11-02 15:03:20 +03:00
Vladislav Volkov
680e53a005
[Doc] Optimization guide update ( #8359 )
...
* [Doc] Optimization guide update
* brushing the freq locking section a bit
Co-authored-by: Maxim Shevtsov <maxim.y.shevtsov@intel.com>
2021-11-02 14:35:21 +03:00
Alexander Zhogov
c02d96d17e
CODEOWNERS: Add /tools/pot/ @openvinotoolkit/openvino-pot-maintainers
2021-11-02 13:55:02 +03:00
Victor Kuznetsov
8a46ead91b
add pytest-timeout ( #8352 )
2021-11-02 13:44:02 +03:00
Liubov Batanina
6686f3c052
Remove excess content from POT distribution ( #8300 )
2021-11-02 13:34:27 +03:00
Nikita Malinin
2dadf50a68
[POT] Update AccuracyAware doc ( #8261 )
...
* Update AA doc with GNA
* Apply comments
* Update doc with note
2021-11-02 13:31:51 +03:00
Maksim Proshin
b69a371b8f
[POT] Updated FAQ ( #8320 )
...
* Update FrequentlyAskedQuestions.md
* Update FrequentlyAskedQuestions.md
* Update FrequentlyAskedQuestions.md
2021-11-02 13:13:32 +03:00
Tomasz Jankowski
de4ceba375
[ONNX FE] Add implementation of Frontend API methods for naming and annotation ( #8026 )
2021-11-02 09:35:04 +01:00
Wilson Seok
75c6af7af5
Migrate ngraph backend test/experimental detectron detection & experimental detectron generate proposals ( #8264 )
...
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now
* update repo
* add op reference test of experimental_detectron_detection_output and experimental_detecteion_generate_proposals and remove ngraph backend test
* modify visitor api test of experimental_detectron_detection for clang-format
* modify visitor api test of experimental_detectron_detection for clang-format again
* modify visitor api test of experimental_detectron_detection for clang-format again2
2021-11-02 10:48:15 +03:00
Mang Guo
0a850ce73e
[Shape infer] Implement ExperimentalDetectronTopKROIs shape infer ( #7926 )
...
* Implement ExperimentalDetectronROIs shape infer
* Fix review comments
* Update for review comments
Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
2021-11-02 05:32:46 +03:00
Ilya Lavrenov
f3ca0a99a8
Fixed some coverity issues ( #8334 )
2021-11-02 03:04:37 +03:00
SofyaBalandina
973ff46c21
Fix incorrect result in the Conformance report ( #8331 )
...
Issue: CVS-68570
2021-11-01 18:15:53 +03:00
Vladimir Paramuzov
d9847f7303
[GPU] Limit number of threads used for onednn build ( #8328 )
2021-11-01 17:59:30 +03:00
Anton Chetverikov
bfa7d41038
Fix incorrect example in GatherND_8 specification ( #8308 )
...
* Fix incorrect example
* Added varsion=8 to examples
2021-11-01 14:39:01 +03:00
Anton Chetverikov
fb02aec976
[MO]Fix Merge shape infer function ( #7864 )
...
* Update merge shape infer function
* Update merge shape inference tests
2021-11-01 13:52:46 +03:00
Ilya Lavrenov
b82cc125fa
Support of oneTBB via env TBBROOT ( #8327 )
2021-11-01 13:43:48 +03:00
Anastasia Kuporosova
3251e0cbc3
[Samples] Move C samples to the new samples directory ( #8021 )
...
* [Samples] Move C samples to the new samples directory
* fix samples
* [Samples] Move C samples to the new samples directory
* fix samples
* code reivew inspired fixes
* rename folder to lower case
* move ENABLE_SAMPLES cond level up, fix readmes
* fix ref in doc
* fix install path
* fix install of samples to tests
Co-authored-by: Vladimir Dudnik <vladimir.dudnik@intel.com>
2021-11-01 12:59:09 +03:00
Anastasia Kuporosova
58d845f351
[IE Python API] Add set_config for executable_network ( #7796 )
...
* [IE Python API] Add set_config for executable_network
* fix test
* fix test comment
2021-11-01 12:12:31 +03:00
Alexey Lebedev
6c00da6e48
[IE PYTHON] Fix sporadic test ( #8192 )
...
* Fix sporadic test
* set switch interval before starting a thread
* remove assert
2021-11-01 11:52:02 +03:00
Mikhail Letavin
03106e0cd9
[GPU] Fix some performance degradations from breaking GPU pipeline into explicit stages ( #8084 )
2021-11-01 10:57:29 +03:00
Ilya Churaev
4122ef50d6
Introduce OV Extension base api ( #7562 )
...
* Moved so loader to utils
* Fixed extension tests
* Fixed tests and style
* Fixed style and tests
* Fixed ARM build
* Fix windows
* Fix ieFuncTests
* Wrap runtime exception
* Fixed tests
* Added separate new extension
* Fixed unicode extension loading
* Try to fix windows
* Fixed windows
* Fixed macro
* Fixed doc
* Fixed build
* Fixed comments
* Try to fix build
* Fixed build
* Fixed build
* Fixed shared_from_this
* Temp commit
* Changed extension
* Fixed merge conflicts
* Removed ngraph namespace from new extensions
* Fixed code style
* Added core add_extension methods and tests
* Added new tests
* Implement tile operation
* Enabled new extensions support
* Fixed build
* Fixed code style
* Try to fix windows
* Changed base extension class
* Removed redundant Ptr
* Fixed comments
* Fixed friend decl
* Fixed Windows export
* Fixed centos
* Added template add_extension method
* Move destructor to public
* Removed BaseExtension class
* Added variadic add_extension methods
* Fixed doc and typo
* Added BaseOpDestructor
* Allow to create new extension only for new operations
* Revert tests
* Fixed comments
* Fixed comments
* Fixed comment
* Added SO Extension wrapper
2021-11-01 10:36:30 +03:00
Jan Iwaszkiewicz
d8f9445a96
Add new init to Tensor from array, add tests and helper methods for openvino tests ( #8306 )
2021-11-01 10:16:35 +03:00
Min, Byungil
74562e5ae6
Modify reorders for onednn impl of first conv ( #8154 )
...
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2021-11-01 16:04:20 +09:00