Mikhail Ryzhov
0f1fc504b4
[GNA] Set input scale factors for imported model ( #7139 )
2021-08-19 12:27:02 +03:00
Vladimir Paramuzov
b73788d08c
[GPU] Fix build for gcc 10 ( #7142 )
2021-08-19 11:39:39 +03:00
Paul Youngsoo Ahn
c32738ae43
[GPU] Fixed 'assigned to self' error in loop_inst.h ( #7126 )
2021-08-19 10:36:52 +03:00
Eugeny Volosenkov
38022c4cd6
Mo implementation for If with tf extractor ( #6662 )
...
* Add tf2.x impl for If
* Fix ir_engine
* Fix opset
* Fix BOM file
* Added new test
* Fix comments
* Add subgraph_utils
* Fix comments
* Fix transform
* code refactoring
* Fix description
* rewrite support for empty tensor in if
* added onnx extractor
* delete onnx_if
* fix bug with fake_outputs
* Fix test
* Fix control_flow and fix commentaries
* create method results_mapping_and_finding_fake_outputs(output_nodes_in_subgraph,
2021-08-19 10:13:21 +03:00
Ilya Churaev
506148cff6
Moved Dimension, PartialShape, Interval, Rank to ov namespace ( #7136 )
2021-08-19 05:59:31 +03:00
Elizaveta Lobanova
7104f64a16
[GNA] Fix order of SwapMatMulInput transformations ( #7137 )
2021-08-19 00:22:26 +03:00
Ilya Churaev
2f7483993b
Move ngraph::element::Type to ov namespace ( #7124 )
...
* Moved ngraph::Type -> ov::Type
* Revert original files
2021-08-18 21:26:05 +03:00
Katarzyna Mitrus
5867eb3a40
Removal of FusedOp inheritance leftovers ( #7113 )
...
* Remove FusedOp from v0::Gelu
* Update v0::Gelu NGRAPH_RTTI_DECLARATION
* Enable gelu type_prop tests
* Remove FusedOp from v0::MVN
* Remove FusedOp from HardSigmoid
* Remove FusedOp from LSTMSequence
* Remove supress deprecated
* Add missed NGRAPH_OP_SCOPE to v0 Gelu and HardSigmoid
2021-08-18 20:35:23 +03:00
Alexandra Sidorova
983bab8271
[CPU] Added improvements for StridedSlice ( #6658 )
2021-08-18 20:26:04 +03:00
Rafal Blaczkowski
1247b228db
OpenVINO ONNX CI Azure - update onnx/models on demand only ( #7125 )
...
* debug
* debug2
* debug3
* save
* save
* save
* fix
* save
* workaround
* fix2
* remove old artifacts
* final version
2021-08-18 13:57:30 +03:00
Vitaliy Urusovskij
42e1a49e3a
[CPU] Bump up MKLDNN version to get fix of c26453 warning ( #7089 )
2021-08-18 13:27:48 +03:00
Yury Gaydaychuk
7372708254
[CPU] Deform. conv. - reference enforced ( #6945 )
2021-08-18 13:15:32 +03:00
Shoujiang Ma
8968a328d6
First stage of the AUTO-MULTI merge: redirecting AUTO to the MULTI device plugin ( #7037 )
...
* Redirect -d AUTO to MULTI device plugin
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Modify AUTO tests with MULTI config
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Fix CI
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Fix bug: CVS-62424
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Add some tests for AUTO
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Add select device logic to MULTI
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Fix extract device name bug
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Address reviewer's comment
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Delete AUTO plugin source code
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
2021-08-18 13:12:27 +03:00
Anton Chetverikov
6369f43c99
Support unregistered operations in MO IR Reader ( #6837 )
...
* Add support for unregistred operations in MO IR Reader
* Remove commented lines
* Add shapes equality check
* Update comments
* Update groupconv_to_conv function to support case with multiple destinations
* Add ir_data_attrs attribute to restored layers
* Update copy_shape_infer function to new graph api
* Add attribute IE to unsuppurted operations to save their attributes
* Fix wrong attribute name
* Update commentary
* Partially revert updating to new Graph API to fix regression, add appropriate comments
* Update code comments
* Rename copy_shape_infer function and add more comments
2021-08-18 12:56:13 +03:00
Sergey Lyubimtsev
96732e3f0e
Build openvino wheel package from setup.py ( #7091 )
...
* Added ability to build wheel package by executing `setup.py bdist_wheel`
* fix linter issues
* fix formating
* remove blank line
2021-08-18 12:38:54 +03:00
Daria Mityagina
ed9b4ada23
Remove deprecated option and enable compilation without device ( #6022 )
2021-08-18 12:31:19 +03:00
Tomasz Dołbniak
f23f924989
MaxPool-8: pads_value attribute removal from the operator definition ( #7119 )
2021-08-18 10:42:15 +02:00
Michał Karzyński
220b3ed1a1
Propose new MaxPool-8 operation ( #5359 )
2021-08-18 10:41:59 +02:00
Ilya Sharikov
1dfc2369b7
Renamed component name ( #7110 )
2021-08-18 09:48:38 +03:00
Vladimir Paramuzov
2210f12e03
[GPU] Get rid of memory alloc for input_layout in internal networks ( #6897 )
2021-08-18 09:31:04 +03:00
Ilya Churaev
cbe33f5997
Deprecate ngraph file utils. Need to have common functions ( #7105 )
2021-08-18 07:35:32 +03:00
Sergey Shlyapnikov
2ffcb2f035
[GPU] Fix ScatterNDUpdate unit tests ( #7103 )
2021-08-17 18:33:25 +03:00
Vladislav Golubev
a41a8896b3
[LPT] LP Transformations refactoring after dynamic shapes support ( #6950 )
...
* [LPT] Transformations refactoring after dynamic shapes support
* [LPT] ReshapeTransformation: 2D->2D fix
* [LPT] fixes after review
2021-08-17 16:51:15 +03:00
Ilya Churaev
aaf590bd65
Change ngraph public api ( #6920 )
...
* Moved nGraph function
* Added legacy nGraph function
* Moved export API
* Moved variant
* Added old header for backward compatibility
* Fixed build
* Introduce define
* Fixed code style
* Fixed comments
2021-08-17 15:27:06 +03:00
Mateusz Bencer
9be53225f0
Add support for is_equal_data, get_source_tensor, get_target_tensor methods in ONNX FE API ( #6991 )
2021-08-17 13:14:11 +02:00
mei, yang
74dd61b3b3
add document Convert_Model_From_Paddle.md ( #6976 )
...
* add document Convert_Model_From_Paddle.md
* To fix syntax error in Convert_Model_From_Paddle.md
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2021-08-17 09:29:27 +03:00
Edward Shogulin
4a3626997d
[LPT] optimizeMultiplierAfter refactorinig & Reshape fix ( #7036 )
...
* [LPT] ReshapeTransformation: 2D->2D fix
* [LPT] optimizeMultiplierAfter refactorinig & Reshape fix
Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
2021-08-17 09:04:51 +03:00
Bartek Szmelczynski
563fd8fa9b
Revise greater ( #6955 )
...
* add template test, remove backend tests, update spec
* minor spec update
* fix spelling errors in spec
* add not converted types
2021-08-17 07:16:56 +03:00
Ilya Sharikov
85b85cf259
Added install for sea_itt_lib ( #7039 )
...
* Added install for sea_itt_lib
* Updated install
2021-08-17 06:42:01 +03:00
Kate Generalova
56bb84f0b2
fix mo module version check ( #7041 )
...
* fix mo module version check
* add one more version check
2021-08-16 21:22:40 +03:00
Elizaveta Lobanova
a9f7c8effa
[GNA] Fixed Eltwise split and batch size selection during 2d reshape ( #7042 )
...
* [GNA] Fixed Eltwise split and batch size selection during 2d reshape
* [GNA] Added exception if memory isn't allocated for concat filter
* Added assert for minZeroDimSize
* [GNA] Added unit test for GetAlignedSplitSizes()
2021-08-16 19:27:48 +03:00
Ilya Churaev
05c632e072
Deprecated graph utils ( #7077 )
2021-08-16 18:36:48 +03:00
Alexander Zhogov
e0ba6e0e6d
Azure CI: Remove IB on Windows CC ( #7094 )
2021-08-16 17:32:59 +03:00
Alexander Zhogov
1aca3019ec
Azure CI: Remove IncrediBuild on Windows ( #7085 )
...
* Azure CI: Remove IncrediBuild on Windows
* Fix ninja path
2021-08-16 16:40:55 +03:00
Dawid Kożykowski
751f6c304a
Update spec for LogicalXor operation ( #6913 )
...
* update markdown file for logical xor operator
* update information on broadcasting
* update xor spec to match other logical ops specs
2021-08-16 14:59:49 +03:00
Anton Pankratv
e01dc67b6e
[CPU] Added tbb executor ( #557 )
2021-08-16 12:04:33 +03:00
Ilya Lavrenov
b7f29a467c
Removed Protobuf_lite CI ( #7066 )
2021-08-16 07:45:03 +03:00
Dawid Kożykowski
8543daf95d
Revise LogicalXor operation reference implementation ( #6929 )
...
* add tests for logical xor op
* update tests to use introduced libraries
* add empty line at the end of file
* adapt files to new clang-format rules
* fix braces typo
2021-08-16 07:29:31 +03:00
Szymon Durawa
f2bb49d2ed
Remove class FakeQuantizeLayerTestRevise. ( #7057 )
...
* Remove class FakeQuantizeLayerTestRevise.
* Remove fqLayerTestParamsSetRevise.
2021-08-16 07:17:50 +03:00
Vladislav Golubev
a4d2e1a9c5
[LPT] PadTransformation ( #5316 )
...
* [nGraph] op::Pad: added RTTI macros
* [LPT][TESTS] operator<< for std::vector moved to layer_transformation.hpp
* [LPT] PadTransformation
* [LPT][TESTS] PadTransformation functional tests
* [LPT][TESTS] PadTransformation plugin tests
* [TESTS] Added the ability to add test-cases with dynamic shapes
* merge fixes
* [LPT] PadTransfomation: dynamic shapes support
* [LPT] PadTransformation added to the main LPT pass
* [LPT] MarkupTransformations: added Pad to SupportOps list
* [LPT] PadTransformation: added nonzero padValue support
* [LPT] PadTransformation: plugin tests extending
* compilation error fix
* naming fix
2021-08-14 16:20:46 +03:00
Eugeny Volosenkov
e13ac4d9ac
If. nGraph implementation + reference ( #6777 )
...
* Add If implementation with reference
* fix test
* fix comments
* Fix validate_and_INFER_TYPES
* rewrite tests for dynamic cases
* Fix ci failed
* add comentaries for validate_and_infer_types
* fix api
* Added ngraph checks and delete copied op from opset8
* code style fix
* fix code style
* add checkers to reference
* add has_evaluate
* fix eval
* Fix code style
* fix code style
2021-08-13 20:28:04 +03:00
Polina Brzezinskaya
c32ecd957b
[TEST] Add cache tests ( #7024 )
...
* [TEST] Add cache tests
* Fix based on review
2021-08-13 20:07:30 +03:00
Ilya Churaev
33b4c69215
Try to enable deprecation warnings for Windows ( #7051 )
...
* Try to enable deprecation warnings for Windows
* Changed macro
* Fixed build
2021-08-13 16:42:03 +03:00
Mikhail Ryzhov
e03abc343c
[GNA] Disabled TransposeReduction ( #7011 )
...
* Rebase master
* [gna] Fixed export/import precision
* Revert "[gna] Fixed export/import precision"
This reverts commit d381a2e216d381a2e216
2021-08-13 15:57:37 +03:00
Mikhail Ryzhov
12903bf3c3
[GNA] FQ accuracy fixes ( #6924 )
2021-08-13 15:54:21 +03:00
Katarzyna Mitrus
30914f76ca
CumSum ng op shell revision ( #6990 )
...
* Validate and infer types cleanup
* Fix clone with new inputs for default
* Add initial values for bool attrs
* Remove old style spec from the cum_sum.hpp
* Add expected attr count to cum_sum visitor tests
* Add visitor test with no axis input
* Remove redundant headers form visitor tests
* Add CumSum type prop tests
* Add input size check to type prop tests
* Update code style
2021-08-13 15:50:07 +03:00
Xie Zhengtian
79290a7dc0
[Doc] Add doc for Auto-Device Plugin 2021.4 ( #5982 )
...
* [Doc] Add doc for Auto-Device Plugin 2021.4 (#6190 )
* Add doc for Auto-Device Plugin
Signed-off-by: Zhengtian Xie <zhengtian.xie@intel.com>
* Update doc for auto-device plugin
Signed-off-by: Zhengtian Xie <zhengtian.xie@intel.com>
* Update auto-device plugin doc
* Add openvino_docs_IE_DG_supported_plugins_AUTO into web page
Signed-off-by: Zhengtian Xie <zhengtian.xie@intel.com>
* Update AUTO.md
Co-authored-by: Maxim Shevtsov <maxim.y.shevtsov@intel.com>
2021-08-13 14:23:44 +03:00
Mikhail Ryzhov
d1e5e848b4
[GNA] Fixed issue for concat connection to memory layer ( #6985 )
...
* Fix for concat connection to memory layer
2021-08-13 13:31:42 +03:00
Pavel Esir
4738bbd757
[MO][nG] add Gather-8 to MO, layer tests, nG python api unit-tests and up/down-grading transformations ( #6560 )
...
* gather-8 upgrade/downgrade transforms
* bump to opset8
* add Gather-8 to MO
* fix permutation for Gather
* added TF layer tests, ONNX layer tests for negative indices, and nG python api unit-tests for negative indices
* typo fix, disable downgrading transformation
* disable downgrade in clDNN, line width style fix
* all Gathers are converted to 7th version, transformations will be enabled/disabled while op will be added into plugins
* disabled Gather8LayerTest on GPU
* added common function for Op replacement
* concretized meaning of negative indices, fixed some typos
* applied review comments: left only meaningful layer tests
* removed op replacing functions from common utils
* returned back transformations without subroutines
* corrected style, added comments to common_optimizations.cpp
2021-08-13 11:56:49 +03:00
Kate Generalova
f324ca7fcd
update configuration mgmt owner files ( #7052 )
2021-08-13 11:48:28 +03:00
