Wilson Seok
2401b0aa3c
[GPU] Skip reorder_node_to_split to avoid change of input data type for ondenn kernel support ( #16827 )
...
* skip reorder_node_to_split when new input data type of onednn kernel is not supported
* update layout_optimizer and add unit test
2023-04-19 15:00:55 +09:00
Marcin Kusmierski
1281074e15
[GNA] Fix for GNA 3_5 fixing tests after review ( #16954 )
...
* [GNA] Fix review comments for Conovolution2DLayer tests
* [GNA] fix review comments for smoke_ConvolutionPoolingStrideNotEqualWindowTest_Above
* [GNA] Fix review comments to GNAPWLExtraSegmentsTestFixture
* [GNA] Fix review comments to smoke_LSTMCellBasicCommon
2023-04-19 07:31:34 +02:00
Kelvin Choi
bd8ca523b9
[GPU] Fix proposal sort condition ( #16981 )
2023-04-18 21:05:32 -07:00
Ilya Lavrenov
3ad3a90e98
Enabled several arm64 tests ( #17032 )
2023-04-19 02:35:32 +04:00
Anastasia Kuporosova
9f250edc7f
[PyOV] use generator is multi config ( #17004 )
...
* [PyOV]- use generator is multi config
* use ov
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-04-18 22:04:22 +00:00
Maksim Kutakov
38d97709d1
[CPU] Remove allocation by the upper bound ( #16666 )
2023-04-19 00:25:58 +04:00
Maksim Kutakov
531b5a3657
[CPU] Optimize TBB usage in the parallel dynamic shapes processing ( #16517 )
2023-04-19 00:25:03 +04:00
Aleksandr Voron
d4ac0b0e79
MultipleLSTMCellTest fix ( #17015 )
2023-04-18 23:27:45 +04:00
Anastasiia Pnevskaia
078f28911b
Fixed parsing of 'layout' param ( #16999 )
...
* Fixed layout parsing.
* Small correction.
* Removed wrong change.
2023-04-18 22:43:38 +04:00
Roman Kazantsev
e93c8e1b1c
[TF FE] Skip one Keras ConvLSTM2D test ( #17028 )
...
* [TF FE] Mark one Keras ConvLSTM2D test with xfail
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Change to skip
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-04-18 22:28:30 +04:00
Ilya Lavrenov
d5cc696e00
Removed contrib repo usage from Linux ARM64 Azure Pipeline ( #17016 )
...
* Removed contrib repo usage from Linux ARM64
* Removed contrib repo usage from Linux ARM64
2023-04-18 21:33:49 +04:00
Ilya Churaev
566ef01a3f
Remove constructors for ov Exceptions ( #16938 )
...
* Remove constructors for ov Exceptions
* Fixed linux build
* Fixed ONNX Frontend
* Fixed paddle
* Fixed exceptions in tests
* Deprecate constructors for ov::Exception
* Suppress some warnings
* Merge several exceptions
* Some small changes
* Suppress more warnings
* More warnings
* mode warnings
* Suppress more warnings
* More warnings
2023-04-18 21:02:26 +04:00
Mateusz Mikolajczyk
441dad2eea
Fix bug with reshape on empty tensor ( #17014 )
...
* Fix empty tensor reshape
* Add test
2023-04-18 20:56:03 +04:00
Vladislav Golubev
e6341917cd
[LPT] PullReshapeThroughDequantization transformation fix ( #16395 )
...
* PullReshapeThroughDequantization fix
* Added a test-case
2023-04-18 15:22:31 +01:00
Katarzyna Mitrus
2a5c69abc6
[ONNX FE] Fix ONNX DequantizeLinear-13 import dynamic shape ( #16966 )
2023-04-18 13:03:55 +02:00
Marcin Kusmierski
d5123056bb
[GNA] Fix issues with GNA 3.5 - Fix pooling for Convolution1D and Convolution2D ( #16734 )
...
* [GNA] Fix 1D Pooling realized as part of 2D Convolution
* [GNA] Fix pooling for GNA_SW_FP32 mode when fused with Convolution2d
* [GNA] Fix ConvolutionPoolingStrideNotEqualWindowTest tests for 3_5
2023-04-18 11:41:04 +02:00
Tatiana Savina
e3fdfc4e09
DOCS shift to rst Plugin updated ( #17000 )
...
* shift to rst
* test snippets
* test build fixes
* change code block
* test new path
* change path
* add cancel
* change note format
* add docs
* change path to snippet
* change path to snippet
* change list format
* fix list
* fix snippets path
* fix format
* fix lists
* fix snippet
* compiled model doc fix
* change indentation
* small fixes to format
2023-04-18 10:59:15 +02:00
Mikhail Ryzhov
f97eeb59d5
[GNA] Fixed cases when FQ is not the 1st layer ( #16602 )
...
* Fixed cases when FQ is not the 1st layer
* clang formatted
* Added support of Gather
2023-04-18 10:43:31 +02:00
Pavel Esir
d70d8509c3
[FP16][IE] exclude MVN and NormalizeL2 from precision sensitive marking ( #16953 )
...
* exclude MVN from mixed infer
* fix align_mixed_fp32_fp16_types_test.cpp
* fix unit-tests for convert_precision.cpp
* code style fix
2023-04-18 16:20:49 +09:00
Pawel Raasz
3494edeed2
Fix Cast util functor when cast from floating point to integer ( #16959 )
...
* Fix cast to helper from floating point to integer
when floating value is out-of-range of integer
* Fix negative float cast if outside integer range
2023-04-18 07:29:31 +04:00
Min, Byungil
bf2870a63b
[GPU] Resolved failed unit-tests ( #16618 )
...
+ Resolved issues related to deconv
+ Modified test-cases for conv, fc.
+ In fc unit-tests, tiny tensors showed unexpected behavior. Modified tensor size a little
+ Bugfix in get_test_stream
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2023-04-18 11:22:43 +09:00
Ilya Lavrenov
d15cdc81cd
Fixed multi-config generators ( #17003 )
2023-04-18 02:44:38 +04:00
Shen, Wanglei
3f9cc0112a
Hot Fix: using all small core as Ecore ( #16978 )
...
* using all small core as Ecore
* add test case
2023-04-18 00:06:36 +04:00
Ilya Lavrenov
adc733f1e9
Enabled several ARM CPU tests ( #16995 )
...
* Enabled several ARM CPU tests
* Removed not-valid tests
* Fixed several template plugin tests
* Removed non-working suppressions
* Disabled 2 tests on ARM CPU
2023-04-17 22:44:43 +04:00
Egor Duplenskii
e52445dda4
[CPU] Clean up temporary debug toggles ( #16972 )
2023-04-17 22:00:37 +04:00
Sofya Balandina
c14d0d7389
[conformance] Fix itaration of ops_list when recalculating tests counters ( #16993 )
2023-04-17 21:57:56 +04:00
Roman Kazantsev
ae06322cb7
[TF FE] Correct layer test for ConvLSTM2D and add to the pre-commit ( #16996 )
2023-04-17 17:54:19 +00:00
Mikhail Ryzhov
14f38bfde8
[GNA] Reverted internal overload correction ( #16962 )
...
* reverted overload correction
* added comment
* Enabled tests
* Revert merge error
This reverts commit daed290452
2023-04-17 17:39:58 +00:00
Ivan Tikhonov
930441b223
TransposeSinking: Gather and ReverseSequence ( #16532 )
...
* Resolve the performance issues in TransposeSinking transformation
* codestyle
* fix warning as error, fix tests failures
* fix ts for Concat and Reduce
* Fix TransposeReduceBackward
* fix the issue in TransposeFuse transformation
* fix TransposeReduce transformations
* Fix TransposeReduction, fix TransposeSinkingSplit, add unsqueeze support
* delete debug print
* Add additional validations
* fix node validation
* Fix validate for split, revert changes for concat, add BatchToSpace/SpaceToBatch
* Add SpaceToBatch/BatchToSpace
* fix TS for Interpolate + codestyle
* fix gna build
* Support TS for Interpolate, VariadicSplit, IsInf, IsNan, IsFinite + refactoring
* add the missed line
* add include
* TransposeSinking tests refactoring: part1
* TransposeSinking tests refactoring: part2
* Add limited support for StridedSlice op
* codestye
* TransposeReduction: skip the case when 2nd input for Squeeze is not provided
* Transpose sinking tests refactoring: part 3. + Revert changes in MOC.
* fix build
* codestyle
* Add tests for TS backward transformations, update TransposeSinkingFuse transformation, delete StridedSlice transformation prototype + tests refactoring
* fix unary tests
* Fix warning as error on Windows
* Add new tests for Unsqueeze/Squeeze; refactoring; remove debug code
* TransposeSinking: add support for Slice op
* Add descriptions to the transformations, add additional checks
* fix a warning
* TransposeSinking Rafactoring part2: move the transformations to a separate folder, align namespaces
* TransposeSinking refactoring: class names, namespaces
* codestyle
* resolve merge conflicts
* codestyle
* TSReduction refactoring, move Unsqueeze/Squeeze transformations to separate files, added limited support for Reshape op + tests
* fix minor mistakes
* fix warnings
* Added TSSlice transformation to TSGeneral, created TransposeSinkingGeneral alias in ov::pass namespace
* refactoring
* codestyle
* fix TSSqueeze/TSUnsqueeze transformations
* delete debug serialize
* remove TransposeSinking from MOC
* fix TSSqueeze/TSUnsqueeze transformations in case of Reshape op
* delete debug code
* fix unit tests, revert changes for TSSlice transformation
* TransposeSinking: Add gather support
* TransposeSinking: add support for Gather, ReverseSequence ops; Fix TSReduction, TSSqueeze, TSUnsqueeze transformations
* fix new constants shape
* fix TSReduction, TSSqueeze, TSUnsqueeze transformations; codestyle
* fix TSGather
* Fix TSGather transformation, add tests
* Updated TSGather transformation, updated the tests
* fix TSGather, codestyle
* Add missing files for TS testing
* fix TS for ReverseSequence op; codestyle
* revert local changes
* fix warnings
* delete const folding passes
* disable constant folding for shapeOf subgraph only
* correct thirdparty versions
* codestyle
2023-04-17 16:38:48 +00:00
Ilya Lavrenov
f4fe8400a7
Generic ARM fixes ( #16994 )
2023-04-17 20:37:10 +04:00
Anastasia Kuporosova
f9098cd67c
[PyOV] Mark add_openvnio_libs as internal ( #16971 )
...
* [PyOV] Mark add_openvnio_libs as internal
* fix flake8
2023-04-17 17:34:13 +01:00
Vitaliy Urusovskij
47f0d72f02
Fix broadcasting issue in FQ ref implementation ( #16812 )
2023-04-17 20:33:07 +04:00
Aleksandr Voron
496a608a28
[CPU] ReduceMean fix for ACL Executor ( #16987 )
...
* reduce fix
* enable gru, rnn and lstm tests
2023-04-17 19:17:50 +04:00
Karol Blaszczak
1471a6e8de
[DOCS] benchmarks new page ( #16620 )
2023-04-17 16:43:57 +02:00
Ilya Churaev
25826bfe7d
Added deprecation of nv12 legacy API ( #16982 )
...
* Added deprecation of nv12 legacy API
* Added new files
* Change macros
* Suppress warnings for preprocessing
* Suppress warnings in tests
* Suppress warnings for Windows
2023-04-17 14:13:43 +00:00
Anastasiia Pnevskaia
dc2fa65224
Support of unnamed saved_model_dir in MO Python API ( #16542 )
...
* Added support of unnamed saved_model_dir.
* Switch TF2 layer tests for unnamed saved_model_dir.
* Added test.
* Correction of comment.
* Removed unnecessary pytest mark.
* Code correction, added comment.
2023-04-17 17:20:27 +04:00
Ilya Lavrenov
4a997de4a3
Disabled failed ARM CPU tests ( #16989 )
2023-04-17 15:34:56 +04:00
Shen, Wanglei
98393c0da1
update number of threads per stream on Ecore to 2 for aggressive model on hybrid platform ( #16857 )
...
* update number of threads per stream on Ecore to 2 when aggressive model run on hybrid platform
* update for corner case and add test case
2023-04-17 18:42:55 +08:00
Jan Iwaszkiewicz
816c0f76e2
[PyOV] Deprecate PerformanceMode.UNDEFINED and refactor deprecation ( #16965 )
2023-04-17 12:38:28 +02:00
bstankix
7c41d78b5d
Add OVMS benchmarks ( #16984 )
...
* Add ovms support for Graph Builder
* Add new OVMS dataset
2023-04-17 12:27:58 +02:00
Katarzyna Mitrus
834e611bde
[Interpolate-11] Additional tests for Interpolate-11 reference implementation ( #16956 )
...
* bf precision tests
* i32 prec tests
* Default axes test
* Add f16 prec tests
* i8 prec tests
* Update eval types in the new file
2023-04-17 11:39:09 +02:00
Przemyslaw Wysocki
9ca85eb363
[PyOV] Update docs with Python 3.11 ( #16366 )
2023-04-17 11:33:15 +02:00
Przemyslaw Wysocki
d72d833a96
[PyOV] Enable Python 3.11 ( #15144 )
...
* Bump ONNX version
* Bump protobuf
* Add xfails and skips
* Add tickets
* Skip ONNX Serialization tests
* Compile ONNX with C++17
* Force cpp17 - 2
* Use MSVC check
* Relax python reqs, enable 311 in azure
* Fix setupvars error
* Ignore watchdog error
* Update tensorflow
* Minor change
* Bump onnx to 1.13.1
* Bump protobuf to 3.20.3
* Debug test tf
* Xfail tests in comp
* Update comp tests
* Update tf reqs
* Remove deprecated ONNX function
* Align PDPD FE protobuf req with 2.4.1
* Satisfy dependency review
* Attempt to fix dependency review
* Revert pdpd protobuf
* Skip pdpd tests
* Fix MO-TF-PB test
* Skip TF test case
* Enable py311 on rest of jobs
* Try disabling pdpd req
* Exclude pdpd form cmake
* Update .ci/azure/linux.yml
Fixed unmerged merge-conflict
* CR
* Fix reqs
* Skip pdpd tests
* Disable pdpd tests building in cmake
* Skip another pdpd cmake
* Add file
* Add paddle constraint to tests
* Disable paddle reqs
* Debug prints
* Skip TF test if Python ver is 3.11
* Apply Mish cr comments
* Debug
* Debug
* Constrain tensorflow_addons
* Fix pdpd skipping
* Add debug prints
* Update skips
* Remove prints
* Minor change
* Update OMZ commit
* Fix some tests
* Minor change
* Disable pdpd at all
* Disable pdpd at all
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-04-17 13:30:17 +04:00
Wang Wangwang
589bd6d076
Add the implementation to GetExecGraphInfo API in AUTO plugin ( #16979 )
2023-04-17 17:24:07 +08:00
Ilya Churaev
aa1f26a2b7
Enable more tests for Template plugin ( #16874 )
...
* Enable more tests for Template plugin
* Removed deprecated API
* Fixed typo
* Added internal properties
* Removed incorrect tests
* Fixed code style
* Enabled some tests
2023-04-17 07:07:09 +00:00
Andrew Kwangwoong Park
7282728cec
[GPU] Fix incomplete condition for NMS shape inference ( #16960 )
...
Signed-off-by: Andrew Park <andrew.park@intel.com>
2023-04-16 22:41:57 -07:00
Eddy Kim
9b9c31d46b
[GPU] Updated to allocate memory in order of size while deserializing ( #16867 )
...
* updated to allocate memory in order of size while deserializing
* fix windows build error
* updated to check dependencies between not connected nodes
2023-04-16 22:33:57 -07:00
Egor Duplenskii
175db3523a
[CPU] Add few tests to smoke scope ( #16963 )
2023-04-17 09:04:57 +04:00
Taylor Yeonbok Lee
c96a5c4b70
Fix prepare padding which was not handling group size properly ( #16977 )
2023-04-16 21:42:03 -07:00
Ilya Lavrenov
31398bb3eb
Fixed deprecated API warnings ( #16949 )
2023-04-17 07:19:53 +04:00
