Alexandra Sidorova
a032d67cc7
[CPU] Fixed enforcebf16 condition for transformation pipeline ( #17157 )
...
* [CPU] Fixed enforcebf16 condition for transformation pipeline
* [Snippets][CPU][Tests] Added test with bf16
2023-04-26 16:13:01 +04:00
Irina Efode
ca92eb96ad
[CONFORMANCE] Fix Runner on Win ( #17221 )
2023-04-26 13:03:20 +01:00
Zlobin Vladimir
de30d8523d
State single value is uese ( #15458 )
...
Ticket EISW-60868
2023-04-26 14:50:03 +04:00
Ilya Lavrenov
da91b33763
ARM32 ACL kernels in oneDNN ( #17142 )
...
* ARM32 ACL kernels in oneDNN
* Fixed review comments
* Fixed ERF
* Disabled several eltwise tests on arm32
2023-04-26 13:50:10 +04:00
Vitaliy Urusovskij
02bfa7804b
Add copyright ( #17218 )
2023-04-26 13:44:31 +04:00
Luwei Zhou
6cb6c5958a
Fix the SDL issues. ( #17107 )
...
* Fix the SDL issues.
* Applied review comments.
* Update Slice test case to test none-const axis input.
2023-04-26 13:35:36 +04:00
Chenhu Wang
737864bdc7
[CPU] layout alignment to improve perf for interpolate pillow modes ( #17079 )
...
* infer planar layout with [1,2] axis as nhwc layout pass and kernel
* leftover comments apply
* comment apply
2023-04-26 11:33:17 +02:00
Ivan Tikhonov
95ca54d0ab
Update ConstantFolding transformation to support Gather with dynamic input ( #16973 )
...
* ConstFold Gather op in case of dynamic dims in data input
* Update ConstantFolding transformation to support Gather with dynamic input; add test
* always mark ShapeOf nodes as can_be_folded
* add additional checks for fused_names in the gather test
---------
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
2023-04-26 13:22:47 +04:00
Vladimir Paramuzov
ce5f65af14
[GPU] Use hash of test name for random generator initialization ( #17213 )
2023-04-26 12:52:38 +04:00
Ekaterina Aidova
6389f423bf
[PT FE]: implement scaled dot product attention ( #17178 )
...
* [PT FE]: implement scaled dot product attention
* Apply suggestions from code review
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Update src/frontends/pytorch/src/op/scaled_dot_product_attention.cpp
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
---------
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2023-04-26 12:51:02 +04:00
Ekaterina Aidova
5857c4438b
[PT FE]: switch on tracing as main path if example inputs provided ( #17194 )
2023-04-26 12:50:43 +04:00
Eddy Kim
09265083ed
[GPU] fixed a missing data type ( #17200 )
...
* fixed missing data type
* updated the resolution for better accuracy check
2023-04-26 08:28:18 +00:00
Roman Kazantsev
7cf9d109e8
[TF FE] Implement optimal conversion of body graphs ( #17211 )
...
* [TF FE] Implement optimal conversion of body graphs
Preliminary setting input shapes and types for body graph InputModel
provides more optimal conversion of body-graphs.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix build issue
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-04-26 12:12:54 +04:00
Maciej Smyk
5682e178dd
DOCS shift to rst - Opsets D ( #17205 )
...
* Update Operations_specifications.md
* Update Divide_1.md
* Update DFT_7.md
* Update DetectionOutput_8.md
* Update DetectionOutput_1.md
* Update DetectionOutput_1.md
* Update DepthToSpace_1.md
* Update DeformablePSROIPooling_1.md
* Update DeformableConvolution_8.md
* Update DeformableConvolution_1.md
* Update DeformableConvolution_8.md
* fix
* fix
* Update DFT_7.md
* Update DFT_7.md
---------
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2023-04-26 10:11:13 +02:00
Mateusz Tabaka
dfaa4e7bd6
Add ConvertSubtractWithConstant to MOCTransformations ( #17058 )
...
* Add ConvertSubtractWithConstant to MOCTransformations
Ticket: CVS-62419
* fix test_mo_import_from_memory tests
* move test file
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2023-04-26 11:37:42 +04:00
Mateusz Tabaka
da4316845f
ConvMulFusion - handle ConvolutionBackpropData with 3 inputs ( #17145 )
...
* ConvMulFusion - handle ConvolutionBackpropData with 3 inputs
Ticket: 98769
* add using
* use compare functions
2023-04-26 11:37:31 +04:00
Sungeun Kim
3c485feea8
removed case to choose onednn impl for deconv ( #17108 )
...
- in_dt(f16) wei_dt(f16) out_dt(f32)
2023-04-26 13:20:11 +09:00
Egor Duplenskii
dabd5ee412
[CPU][TESTS] Fix cmake test dependencies ( #17202 )
...
Co-authored-by: Maksim Doronin <maksim.doronin@intel.com>
2023-04-26 01:17:12 +04:00
Gorokhov Dmitriy
edec7bb897
[CORE] Disable fp32->fp16 optimized constant conversion impl ( #17189 )
2023-04-25 15:50:24 +00:00
Maciej Smyk
72533a7da1
DOCS shift to rst - Quantizing Models with Accuracy Control, Documentation, Get Started & Learn OpenVINO ( #16997 )
...
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* Update AccuracyAwareQuantizationUsage.md
* rst
* fixes
2023-04-25 16:06:34 +02:00
Maciej Smyk
49b5d039db
DOCS shift to rst - Opsets B ( #17169 )
...
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_1.md
* Update BatchNormInference_5.md
* Update BatchToSpace_2.md
* Update BinaryConvolution_1.md
* Update Broadcast_1.md
* Update Broadcast_3.md
* Update Bucketize_3.md
* fix
* fix-2
2023-04-25 16:06:17 +02:00
Anastasiia Pnevskaia
acd424bb5e
Show message with suggestion to try legacy FE in case of conversion error ( #17088 )
...
* Moved exception checks to _convert(), added suggestion to try legacy TF in case of conversion fail.
* Added test.
* Added send_conversion_result() method.
* Small correction.
* Update tools/mo/openvino/tools/mo/convert_impl.py
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Moved test_suggest_legacy_fe() test to check_info_messages_test.py.
* Removed not needed import.
* Small correction.
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-04-25 13:57:01 +00:00
Ilya Lavrenov
57d4ca27e6
Revert "Proper ACL version detection ( #17152 )" ( #17206 )
...
This reverts commit 1aec450fc6
2023-04-25 17:36:18 +04:00
Przemyslaw Wysocki
923b6f297c
[PyOV] Move environment markers to requirements.txt files ( #17113 )
...
* WIP
* WIP
* Debug
* WIP
* Expand function to other setup.pies
* Revert mxnet
* Update docstring'
* restore defusedxml
* Update tools/mo/requirements.txt
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Code review
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-04-25 13:25:21 +00:00
Vladislav Golubev
a8278ba4a6
[LPT] FQ reference implementation reused in foldFakeQuantize function ( #17096 )
...
* [LPT] reused reference FQ implementation in fold_fake_quantize
* [LPT] Removed legacy parameters
* Added plugin tests with per-channel FQ for GrConv wo reshape
* Apply folding only in the case when FQ data input is constant
* EliminateFQ fix
2023-04-25 14:08:01 +01:00
Aleksandr Voron
43a42fa9cd
fix ( #17179 )
2023-04-25 16:50:37 +04:00
Evgenya Stepyreva
cd4c012f08
LogicalNot: convert precision ( #17061 )
...
* CVS-108362 LogicalNot: convert precision
* Test
2023-04-25 12:43:44 +00:00
Ilya Lavrenov
2e3deb8d8f
Windows arm64 support for CPU plugin ( #17075 )
...
* ARM32 support
* ARM32 support
* Fixed packaging
* Windows arm64 support
* Updated submodule
* 32 bits support in Intel CPU plugin
* Fixed FIndAcl.cmake
* Enable proper conditional compilation for Windows ARM64
* Enable proper conditional compilation for Windows ARM64
* Updated submodule
* Updated submodule
* Updated submodule
* Updated submodule
* Updated submodule
* Added template_extension to CPU func tests dependencies
* Updated submodule
* Enabled runtime model tests
* Updated submodule
* Submodule update
2023-04-25 16:41:28 +04:00
Maxim Vafin
d423491bcb
Fix Scatter value infer for fully dynamic value ( #17165 )
...
* Fix issue with dynamic Scatter in MO IR Reader
* Only normalize for 1D tensors
* Add test
2023-04-25 16:38:49 +04:00
Vitaliy Urusovskij
11a2b75161
Fix TSAN issue No2 in GNA plugin ( #17185 )
...
* Fix TSAN issue No2 in GNA plugin
* Misprint
2023-04-25 16:32:06 +04:00
Jan Iwaszkiewicz
512b186231
[PyOV] Enable group_convolution_backprop test ( #17186 )
2023-04-25 12:19:56 +00:00
Evgenya Stepyreva
ee4ccec190
TensorFlow Lite FrontEnd: documentation changes ( #17187 )
...
* First glance doc changes
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Update docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow_Lite.md
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
---------
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2023-04-25 16:18:24 +04:00
Oleg Pipikin
27210b6505
Fix Coverity issue #1505788 ( #17173 )
2023-04-25 16:13:42 +04:00
Oleg Pipikin
ab879f143c
Add check to avoid out of bounds segfault in scatterNDupdate ( #17066 )
...
* Add check to avoid out of bounds segfault in scatterNDupdate
* Fix code style
2023-04-25 16:13:14 +04:00
Aleksandr Voron
6e11645018
[CPU] Add axis check to ACL Reduce isSupported method ( #17188 )
...
* fix
* fix2
2023-04-25 16:11:50 +04:00
Sergey Shlyapnikov
0a5975bdfa
[GPU] Add real kernels' execution timings collection for DumpProfilingData debug option ( #15797 )
2023-04-25 14:33:08 +04:00
Ilya Lavrenov
1aec450fc6
Proper ACL version detection ( #17152 )
2023-04-25 14:05:52 +04:00
Sungeun Kim
8c09a128ac
[GPU] update weights_layout for GroupConv 1d spatial ( #17109 )
...
* update weights_layout for GroupConv 1d spatial
2023-04-25 18:54:54 +09:00
Georgy Krivoruchko
3f07c8b48b
[TF FE] Added MetaGraph file format ( #16524 )
...
* Separeted SavedModelVariablesIndex class from Saved Model
* Renamed SavedModelVariablesIndex class
* Enabled Tensorflow MetaGraph
* Enabled Tensorflow MetaGraph
* Covered VariableV2 and Assign nodes
* Applied review comments
* Added tests
* Added names to input/output ports too
* Fixed naming for using with MO
* Applied part of review comments
* Renamed meta.cpp and saved_model.cpp
* Applied shared_ptr for memory management of PtrNode
* Fixing CI
* Prevent cycles while passing thru graph
* Released requirement for Checkpointable Object Graph
* Changed naming approach to align port order
* Changed renaming order (before reordering)
* Added a Placeholder translator which checks updated shape
* WA missing Identity name
* Fix CI and restored lost translators after rebase
* WA for output names
* Removing unused params after cutting a model
* Prevents crash in case VariableV2 appears in freezed model
* Fixed saved model in case no variables.index found, but
variables exists
* Changed approach for handling native formats support
* Aligned behavior with freezing .meta files
* Fixed behavior for cutting a model by input tensor
* Applied review comments
2023-04-25 13:46:06 +04:00
Maciej Kwapulinski
9c01de4b6e
[GNA] fix: embedded export is available for embedded targets only ( #17105 )
...
* fix: embedded export is available for embedded targets only
* [GNA] functional tests fix - embedded export should NOT be possible on non-embedded target
* [GNA] tests added/justified to process both negative and positive path
2023-04-25 10:45:47 +01:00
Andrew Kwangwoong Park
72906ca242
[GPU] Fix i8/u8 representation error for clamp due to overflow ( #17183 )
...
* [GPU] Fix i8 representation error for clamp due to overflow
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix to not include in ocl code
Signed-off-by: Andrew Park <andrew.park@intel.com>
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
2023-04-25 09:41:01 +00:00
Ekaterina Aidova
39ed9a624f
[PT FE]: extend batch norm to support training mode ( #17040 )
2023-04-25 11:27:00 +02:00
Vladimir Paramuzov
f736c71feb
[GPU] Fix reshape split for dynamic models + accuracy fix for SAM ( #16911 )
2023-04-25 09:21:31 +00:00
Alexandra Sidorova
9247906879
[Snippets][CPU] Fixed coverity ( #17094 )
2023-04-25 09:12:58 +00:00
hyunback kim
19f8f5a3a7
[GPU] Disable oneDNN post-op Prelu in FC,gemm ( #17084 )
...
* [GPU] Disable oneDNN post-op relu
Only disable Prelu fusion in Fc, gemm
- check additional data input
Signed-off-by: hyunback <hyunback.kim@intel.com>
2023-04-25 18:06:22 +09:00
Yuan Hu
2255bb25fd
fix input issuse of ScatterNDUpdate conformance test ( #16406 )
...
* fix input issuse of ScatterNDUpdate conformance test
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
* fix typo and optimize temporary variable
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
---------
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
2023-04-25 13:00:22 +04:00
Vladimir Paramuzov
ca1102b855
[GPU] Support MVN cases with axis=-1 w/o decomposition ( #17020 )
2023-04-25 12:59:03 +04:00
Katarzyna Mitrus
0617ce9089
Set ONNX opset in Reduce ops layer tests ( #17170 )
2023-04-25 10:38:56 +02:00
Ilya Lavrenov
22aee08958
Revert "[CPU] Fix data race in concurrent compile_model calls ( #17164 )" ( #17184 )
...
This reverts commit 8879ef53a7
2023-04-25 12:01:02 +04:00
Nikita Malinin
e37288fbcc
[POT] Added inference shape for in-place statistics ( #17114 )
...
* Added inference shape for inplace statistics
* Update graph_builder
2023-04-25 11:14:34 +04:00
