Vladimir Paramuzov
a5aaa07721
[IE CLDNN] OpenCL headers update ( #4345 )
...
* [IE CLDNN] OpenCL headers update
* Add Win64 Release OpenCL.lib
* Update Windows ICD *.lib
* [IE CLDNN] Linux and Android libraries
* Update ICD for linux
* Update android ICD
* va.h stub
* Add ICD loader revision
* USM fix
* fixed ambiguous calls
* Updated licence files
* try fix centos
* fix x64 debug icd lib
Co-authored-by: Andrey Babushkin <andrey.babushkin@intel.com>
2021-02-19 13:19:45 +03:00
Roman Lyamin
01535161a6
[IE CLDNN] Added MVN-6 operation ( #4190 )
2021-02-19 12:24:52 +03:00
Pavel Esir
7dca134031
[MO] [TF] Added TF broadcast_to extractor ( #4376 )
...
* Added TF broadcast_to extractor
* updated Supported_Frameworks_Layers.md
* corrected name
* corrected op name in Supported_Frameworks_Layers.md
* added a space after BroadcastTo in Supported_Frameworks_Layers.md
2021-02-19 11:44:11 +03:00
Andrew Bakalin
a1f8fe3696
[VPU] Use nGraph value propagation in VPU private ops ( #4291 )
...
* [VPU] Update StaticShapeBroadcast
* [VPU] Update StaticShapeLoop
* [VPU] Update StaticShapeReshape
* [VPU] Update StaticShapeTopK
* [VPU] Get rid of evaluateTargetShape
* [VPU] Invalidate values before DTS
* [VPU] Update TopK tests
* [VPU] Review fixes
* [VPU] Review fixes
2021-02-19 11:23:18 +03:00
Vladimir Gavrilov
2b732ec1d7
Incorrect type of 'scales' input of the operation Interpolate-4 in some cases ( #4375 )
...
* Commit.
* Fixed element type of scales input in the MO transformation UpsampleToResample.
* Fixes in the transformation TFSliceToSliceReplacer.
* Fixes in tests.
* Small fixes.
* Reverted fixes in TFSliceToSliceReplacer.
* Small fix.
* Added tests for fractional scales in the transformation UpsampleToResample.
2021-02-19 10:52:41 +03:00
Maksim Shabunin
9559f6f301
Changed ngraph header to fix client build with VS2015 ( #4386 )
2021-02-19 10:19:52 +03:00
Gorokhov Dmitriy
bd431b2565
[CPU] [WA] Enforce linear_onnx mode in Intepolate node to avoid perf regressions ( #4395 )
...
- Fixed incorrect Interpolate fusing behavior for unsupported configurations
2021-02-19 10:13:35 +03:00
Maxim Andronov
f26c82bde3
[CPU] Supporting constant networks ( #4379 )
2021-02-19 09:38:20 +03:00
Alexey Varyzgin
4e9edd9128
[CPU] [BF16] Switched to Greedy Mode ( #4236 )
2021-02-19 09:36:49 +03:00
Liubov Batanina
ffe99fb66f
Fixed Interpolate headers ( #4403 )
2021-02-19 08:39:19 +03:00
Ilya Churaev
e337fb0661
Fixed backward incompatible change ( #4303 )
...
* Fixed backward incompatible change
* Fixed ngraph unit tests
2021-02-19 08:37:18 +03:00
Bartosz Lesniewski
f90ed75db8
Fix comparison of constant with float NAN values ( #4369 )
...
* check bitwise equality before using the threshold method
* use std functions to check float class instead of reinterpret casting
* add unit test with nan f32 const value
2021-02-19 07:13:10 +03:00
Olesya Martinyuk
0c22a9e111
Add infer tool for cond compilation test( #4384 )
2021-02-18 21:38:52 +03:00
Ilya Churaev
b4221948d2
Fixed undeclared identifier SWITCH_MKLDNNPlugin ( #4391 )
2021-02-18 19:18:19 +03:00
Ilya Churaev
317886a5d5
Revert redundant changes (PR:4262) ( #4399 )
...
* Revert "Add MVN fusion transformation (#4262 )"
This reverts commit 1bfe79cf48
2021-02-18 19:02:56 +03:00
Andrey Dmitriev
f38666ac19
[GNA][SPEECH SAMPLE] Fix problem with calculate bitesize output frame ( #4122 )
2021-02-18 18:31:40 +03:00
Vladimir Paramuzov
c001e54403
[IE CLDNN] Added WA for interpolate mode ( #4382 )
2021-02-18 14:24:00 +03:00
Szymon Irzabek
2051fe2614
Allow enabling cpplint on Windows, fix Windows style after check ( #4380 )
2021-02-18 14:20:10 +03:00
azhogov
312dfbe78e
Revert running MklDnnFunctionalTests via IB
2021-02-18 14:05:29 +03:00
Elizaveta Lobanova
c75c680e1c
[GNA] Documentation update for 1D convolution and concat/split layers ( #4249 )
2021-02-18 12:49:50 +03:00
Alexander Zhogov
eb775a3833
Test IncrediBuild with OpenVINO tests ( #2534 )
...
* Test IncrediBuild with OpenVINO tests
* Fix
* Remove --gtest_print_time=1
* Move Stop IncrediBuild
* Add analyze_gtest_log.py
* fix
* Fix
* Fix
* fix
* Fix
* Fix
* CPU FuncTests Analyze IB
* Fix
* Remove unused pipelines
* Revert "Remove unused pipelines"
This reverts commit d99cdcf597
2021-02-18 12:21:33 +03:00
Nikolay Shchegolev
a5fce440e1
[CPU] Double registration of MVN6 decomposition. ( #4388 )
2021-02-18 11:11:02 +03:00
Jozef Daniecki
9d28767b72
BinaryConvolution specification review. ( #4093 )
...
* BinaryConvolution specification refactoring.
* Aligh tensor types to current CPU implementation.
* Remove !D & 3D case becuase CPU plugin supports only 2D case.
* Add pad_value to the example.
* Add computation algorithm for mode 'xnor-popcount'.
* Computation formula refactoring.
* Fix typo in the description.
2021-02-18 10:38:34 +03:00
Anton Chetverikov
2c4afd8cd4
Tensor names support in MO IR Reader ( #4194 )
...
* Added attributes save modes
* Added tensor names to IR
* Reformat code
* Add support for tensor names in MO IR Reader
* Unit tests and code refactoring
* Fixed error
* Code refactoring
* Code refactoring
* Code refactoring
* Error fixed
* Error fixed
* Bug fixed
* Bug fixed
* Additional unit tests and comments
* Small update
* Update fake infer function
* Update names restoring
* optimize imports
* Add support for old-style constants and for commas in reader
* Added dest mode in Fuse Mul
* Update default values
* Fix missed debug info in some specific cases
* Fix a lot of issues with missedand wrong names provoding
* Resolve review comments
* Update test IR's
* Refactor and simplify code
* More simplification
* Remove unneccessary changes
* model-optimizer/mo/utils/ir_reader/layer_to_class_test.py
* Add separate tests for names restoring
* Update copyright year
* Apply review comments
Co-authored-by: Anastasia Popova <anastasia.popova@intel.com>
2021-02-18 10:38:04 +03:00
Maxim Vafin
1bfe79cf48
Add MVN fusion transformation ( #4262 )
...
* Add MVN fusion transformation
* Apply suggestions from code review
Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
* Apply review feedback
* Fix build
* Apply review feedback
Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
2021-02-18 06:36:32 +03:00
Michał Karzyński
ec9b5894fb
[ONNX] Add support for BitShift operator ( #4368 )
2021-02-17 16:39:27 +01:00
Vladimir Paramuzov
45ae389842
[IE CLDNN] Fixed layout optimizer ( #4325 )
2021-02-17 18:25:16 +03:00
Andrew Bakalin
695d2a90ba
[IE][VPU]: Fix injection in dynamic case ( #4343 )
...
* Redirect StageDependencies from injected stage to the parent of the injection.
* Change StageDependencyEdge to be Stage<->Stage connection. In fact, it affects only stages order, so it would be more natural (also more convenient) to represent it so.
* Add injectedStageDependencies to InjectionEdge to be able to distinguish those dependencies that were added to hwStage during the injection process and make the revertion correct.
2021-02-17 17:39:07 +03:00
Katarzyna Mitrus
7df5a98dde
[ONNX] Update warning message for ONNX Constant node ( #4355 )
2021-02-17 14:40:47 +01:00
Evgeny Lazarev
f1d86b1455
Added comment to the TopK describing output order of equal elements ( #4381 )
...
* Added comment to the TopK describing output order of equal elements
* Fixed typo
2021-02-17 15:53:36 +03:00
Daniel
563425ce41
add Linux Mint 20.1 (X86_64) support ( #4308 )
...
* add Linux Mint 20.1 (X86_64) support
* update patch
2021-02-17 15:42:17 +03:00
Ilya Lavrenov
dd79dd755c
CC: fixed issue with rebuild when only CC header is changed ( #4370 )
...
* CC: fixed issue with rebuild when only CC header is changed
* Updated submodule as well
2021-02-17 15:41:54 +03:00
iliya mironov
f670b7cb3a
Add CTCGreedyDecoder mo support ( #4009 )
...
* Add CTCGreedyDecoder mo support
* Update copiright
* Update bom file
* Add transformation
* Fix code style
* Fix according to review
* Add CTCGreedyDecoder v6 to ConvertPrecision
* Hot fix
* Add replasment for ctc_greedy_decoder
* Fix test
* Fix
* Update ie transform
* Draft ctc lost replaser
* Add ctcloss replaser
* Update
* Refactoring code
* Update transformation
* Update decoder
* Remove comments
* Convert seq mask from int to float
* Fix unit test
* Add dynamic tests
* Refactoring code
* Fix py code style
* update style
* Disable ctcgreedydecoder transform for mkldnn plugin
* Add some comments
* Add transfor code comments
* Enable transform from differend plagins
* Fix mo
* fix tests
* Fix comment
* Fix convert precition
* Update comment
* Fix prcition
* Refactoring according to reviw
* Add ir reder extender
* Rename transformation
* Update bom file
* Fix mo replacer
* Fix tests
* Move transform to decomp
* Add check blank_index
* Rafactoring ctcloss
* Change dinemic rank check
* Fix ctclos extractor
* Remove comment
* Fix code style
* Refactoring pattern matcher for transformation CTCGreedyDecoder
* Disavle transform for vpu
* Refactoring according to review
* Refactoring code
* Disable transformation for cldnn
* Remove unused code
* Reverse transfomation
* Fix code style
* Hot fix transform
* Fix unit tests
* Update transform
* Enable transform in common pipline
* Fix names replasments for mo transformations
* Hot fix
* Fix
2021-02-17 14:38:51 +03:00
Ilya Lavrenov
edbb802e55
Removed some legacy code ( #4371 )
2021-02-17 13:57:14 +03:00
Evgeny Lazarev
2f9e215f7d
Changed check for dimension size to be non-negative ( #4328 )
...
* Changed check for dimension size to be non-negative
* Added unit test for reading model with ShapeOf from scalar and fixed IE IR parser
* Added comment to the test
* Fixed ShapeOfFromScalar test
* Fixed incorrect merge
* Added test for a negative value of "dim" in IR
2021-02-17 12:19:44 +03:00
Vladimir Gavrilov
3b2506989e
Fixed performance drop for Interpolate-4 ( #4354 )
...
* Commit.
* Reverted fix in the nGraph conversion of Intepolate-1 into Interpolate-4.
* Small fix.
* Added comment.
* Added TODO.
2021-02-17 10:58:08 +03:00
Maksim Kutakov
24aeb16fd1
[CPU BF16] OneHot layer extended with bf16 support. ( #4171 )
2021-02-17 10:52:23 +03:00
Michał Karzyński
66634a9939
Update ONNX compliance test list ( #4360 )
...
* Update ONNX compliance test list
* Update test_backend.py
2021-02-17 07:40:47 +03:00
Evgeny Lazarev
f8f60b2d83
Stick requirement version of astroid to be 2.4.2. Also fixed pylint issue with astroid==2.5 ( #4365 )
2021-02-16 21:34:51 +03:00
Polina Mishanina
d383bc0d83
Add try-except ( #4357 )
2021-02-16 19:47:38 +03:00
Yanglei Zou
d9140a0f83
Fix some bugs for ROI Align ( #4212 )
2021-02-16 18:25:13 +03:00
Irina Efode
36799dce86
[IE TESTS] Add Opset6 to the report ( #4348 )
2021-02-16 18:17:13 +03:00
Vladislav Golubev
8a4aa1bafa
[LPT] StridedSliceTransformation accuracy degradation fix ( #4300 )
...
* [LPT] StridedSliceTransformation fix
* added comments
2021-02-16 16:41:37 +03:00
Tomasz Jankowski
5e17926604
[ONNX Editor] Add initializers for model inputs ( #4025 )
2021-02-16 14:12:27 +01:00
Andrew Bakalin
0a36e4e810
[VPU] Change data structure in processTrivialCases method ( #4250 )
...
* [VPU] Fix PR #4060
* [VPU] Review fixes
2021-02-16 14:39:56 +03:00
Tomasz Socha
185aaacc07
[ONNX] Add support for Softmax v11 in opset 7 models ( #4340 )
2021-02-16 11:58:39 +01:00
Mateusz Bencer
cc645d50e4
Resolve Klocwork issues ( #4341 )
2021-02-16 11:55:28 +01:00
Jan Iwaszkiewicz
a3af43c8e4
[ONNX] Minimum op xfail updated ( #4332 )
2021-02-16 11:43:07 +01:00
Katarzyna Mitrus
a980bc9bd9
Spec update ( #4353 )
2021-02-16 13:18:40 +03:00
Patryk Elszkowski
e1d983a12e
XmlDeserializer - move to src file ( #4347 )
...
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
2021-02-16 13:15:41 +03:00
