Commit Graph

12285 Commits

Author SHA1 Message Date
Maciej Smyk
3daf4cb3b5
[DOCS] Torch.compile() documentation for master (#19447)
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2023-09-04 08:39:50 +02:00
Nesterov Alexander
1b9b9bdc1f
[CPU ARM] Fix subgraph test instances (#19524) 2023-09-04 10:39:20 +04:00
Roman Kazantsev
44657183f3
[TF Hub][TF FE] Fix TF Hub models validation and extend precommit (#19567)
* Add all scope of models for testing

* Fix signature in test

* Fix workaround with output tensor names

* Fix unknown rank input resource case

* [TF Hub][TF FE] Fix TF Hub model validation and extend precommit

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Remove unneeded comments

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-09-04 07:41:42 +02:00
Ilya Lavrenov
00b06adee4
Fixed order of dependent cmake options (#19551)
* Fixed order of dependent cmake options

* Update .ci/azure/linux_cuda.yml

fixed typo in option name
2023-09-04 08:32:01 +04:00
Ilya Lavrenov
7173f530cc
Fixed static build from build tree (#19556) 2023-09-04 08:08:50 +04:00
Tomasz Jankowski
51df17912b
[Ref_Impl] Change namespace from nG to OV (#19363)
* Use quotes for openvino includes

* Drop runtime from openvino::reference

* Drop runtime::reference

* Replace ngraph::reference with ov::reference - defs

* Replace ngraph::reference with ov::reference - uses

* Drop redundant nesting

* Fix non arch64 builds

* Move coordinate*pp files under openvino

* Move Coordinate... helpers under ov:: namespace

* Revert not needed changes

* Fix missing namespace scope

* Fix compilation

* Fix code style

* Use ov suppress deprecated macro instead of ngraph

---------

Co-authored-by: Raasz, Pawel <pawel.raasz@intel.com>
2023-09-04 08:07:06 +04:00
Andrew Kwangwoong Park
92c6316e8e
[GPU] Fix input feature map indexing with pad and batch indices for ROIAlign (#19511)
* [GPU] Fix input feature map indexing with pad and batch indices for ROIAlign

* Fix failed TCs for ov_gpu_func_tests

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Fix to do batch interpretation for inconsistency between ROIALign input and const 1D tensor

Signed-off-by: Andrew Park <andrew.park@intel.com>

---------

Signed-off-by: Andrew Park <andrew.park@intel.com>
2023-09-01 12:43:23 -07:00
Mateusz Tabaka
441adcc122
SplitSqueezeConcatFusion - handle Squeeze nodes without second input (#19512)
Ticket: CVS-119330
2023-09-01 23:35:17 +04:00
Nikita Malinin
a4b0fe51af
[POT] Update for CI (#19067)
* Update references
2023-09-01 18:12:24 +02:00
Ilya Churaev
3c7ea04c69
Enable variable state unit tests (#19529)
* Enable compilation variable state unit tests

* Enable all tests
2023-09-01 16:33:31 +04:00
Nadezhda Ageeva
b81cad6ae5
Update ConvertReduceToReshape transformation to support ReduceProd (#19532) 2023-09-01 10:52:05 +00:00
Ilya Lavrenov
7d718fbff2
Robust detection of Cython version (#19537) 2023-09-01 14:45:51 +04:00
Ilya Lavrenov
936dc051ff
Aligned protobuf version in conanfile.txt with onnx recipe (#19526) (#19533) 2023-09-01 13:37:37 +04:00
Pavel Esir
b8226db465
[OVC] Fix output parsing (#19425)
* fix parsing output

* use always coma backspace to separate outputs ', '

* update docstring

* call parser only for ovc cli tool

* docstring correction

* separate docs for cli tool and convert_model; other minor changes

* drop redundant arg from cli_parser_test.py

* more solid test cases added

* remove redundant argv.framework from cli_parser_test.py

* shape correction in concat

* Apply suggestions from code review

fix: coma -> comma

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>

* apply review suggestions

* remove extra ')'

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-09-01 11:20:22 +02:00
Roman Kazantsev
2cf8f2bc1f
[TF FE][GitHub issue] Support Selu operation and add test (#19528)
* [TF FE] Support Selu operation and add test

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Fix layer test

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-09-01 09:09:58 +00:00
Karol Blaszczak
9715ccd992
[DOCS] adjustment to supported devices
adjustments will continue in following PRs
2023-09-01 10:46:04 +02:00
Ivan Novoselov
b0d917f0cb
Snippets pass manager (#18846) 2023-09-01 12:31:42 +04:00
Vladimir Paramuzov
38cad619af
[GPU] Allow simple attached mem as input memory for network (#19419) 2023-09-01 09:54:30 +04:00
Pawel Raasz
dd258f9607
Improve acos ref accuracy for integral types (#19470) 2023-09-01 07:34:43 +02:00
Ilya Churaev
7c751883fc
Moved functional tests to new API (#19488)
* Moved functional tests to new API

* Renamed legacy tests

* Fixed test

* Fixed test
2023-09-01 06:58:03 +04:00
Steve Yoo
05a24b1776
[GPU] Try to use softmax_ref when types are mismatched (#19209)
* Remove support key for UINT8 and INT8
2023-08-31 16:39:36 -07:00
Ilya Lavrenov
f617cc338e
Aligned protobuf version in conanfile.txt with onnx recipe (#19525) 2023-08-31 23:48:32 +04:00
Wanglei Shen
0651d57c33
Add smoke test for CPU map on MacOS (#18753) 2023-08-31 19:31:21 +04:00
Przemyslaw Wysocki
d3ac00c6d2
Amend cython changes (#19514) 2023-08-31 14:43:28 +00:00
Ilya Lavrenov
ebe1d52e31
Update PePy OpenVINO badge (#19520) 2023-08-31 16:31:53 +02:00
Yury Gaydaychuk
2d3aab33b0
[CPU] Deformable Convolution minor fixes (#19415) 2023-08-31 16:13:39 +02:00
Ilya Churaev
2d2977ff4a
Moved inference unit tests to new API (#19452)
* Moved inference unit tests to new API

* Added infer request and variable state

* Try to fix LTO

* Try to avoid warning from gmock

* Try to fix azure build

* Try to fix Windows build

* Comment all variable_state_test file for future investigation
2023-08-31 16:39:46 +04:00
Sebastian Golebiewski
1cf3fe96af
[DOCS] Improve NNCF workflow images (#19040)
* Update DEVELOPMENT_FLOW_V3_crunch.svg

* Update DEVELOPMENT_FLOW_V3_crunch.svg

* update

* Update DEVELOPMENT_FLOW_V3_crunch.svg

* Update DEVELOPMENT_FLOW_V3_crunch.svg

* Update DEVELOPMENT_FLOW_V3_crunch.svg

* Update docs/optimization_guide/model_optimization_guide.md
2023-08-31 14:00:31 +02:00
Mateusz Tabaka
120a81ff5e
Disallow LeakyReluFusion when alpha is greater than one (#19446)
Tickets: CVS-118898, CVS-82454
2023-08-31 14:41:46 +04:00
Pawel Raasz
463ae19207
Fix padding calculation if interval value is inf (#19383) 2023-08-31 11:57:09 +04:00
Vitaliy Urusovskij
81a02c5586
Fix stoi out_of_range issue (#19455)
* Fix `stoi` out_of_range issue

* Handle incorrect behavior and throw exception

* Remove use of `getVmSizeInKB()` in `TestsCommon()`
2023-08-31 04:19:13 +04:00
Mateusz Tabaka
6ad11108b5
Fix include path in TS ShapeOf tests (#19507) 2023-08-30 17:00:03 +02:00
Pavel Esir
9a1726a419
[ovc] check if input is correct in split_inputs (#19350) 2023-08-30 17:13:43 +04:00
Mateusz Tabaka
02d6c1cb5d
TransposeSinking - add support for ShapeOf (#19471)
* TransposeSinking - add support for ShapeOf

It's often in the model that transposes have two consumers: ShapeOf and
another transpose and with ShapeOf absent - the transpose pair could be eliminated.
This patch's approach is to propagate a transpose through ShapeOf by creating
"ShapeOf->Gather" subgraph and replacing ShapeOf's input with transpose input.

Ticket: CVS-118896

* enhance docs
2023-08-30 12:45:48 +00:00
Ivan Tikhonov
38cf4764cb
Transformations: API 2.0 transition part 2 (#19475)
* Transformation component API 2.0:part 2

* Refactoring

* fix build
2023-08-30 14:28:20 +02:00
Katarzyna Mitrus
9c61e0c4dd
[Docs] Remove IR version and nGraph name from the Opset doc (#19503)
* Remove IR version and nGraph name from the Opset12 doc

* Propagate the changes to each opsetX.md file
2023-08-30 11:51:01 +00:00
Sebastian Golebiewski
8aec490128
add-253 (#19500) 2023-08-30 13:46:27 +02:00
Anastasia Kuporosova
23cad1770e
[PyOV] clean up in tests (#19091)
* [PyOV] clean up in tests

* use generated model in tests

* fix ci

* return back fild

* fix ci 1

* fix ci2

* update

* move models

* return back deleted test

* move model creation from conftest

* fix ci

* fix ci
2023-08-30 13:40:14 +02:00
Liubov Talamanova
b790458da6
[POT] Fix bug in classification sample (#19490)
* Fix bug in classification sample

* fix readme
2023-08-30 13:18:44 +02:00
Nadezhda Ageeva
d84fa07841
[HETERO] Save plugin so in tensor (#19489) 2023-08-30 10:23:04 +00:00
Przemyslaw Wysocki
9af0f1eaae
[PyOV] Remove constraints link from torchvision preprocessor converter requirements (#19459) 2023-08-30 11:57:26 +02:00
Sebastian Golebiewski
87f6e34a56
[DOCS] Improving code snippets for quantization (#19479)
* improve-snippets

* Apply suggestions from code review

Co-authored-by: Alexander Suslov <alexander.suslov@intel.com>

* Update docs/optimization_guide/nncf/ptq/code/ptq_tensorflow.py

Co-authored-by: Alexander Suslov <alexander.suslov@intel.com>

* update-path

* Update docs/optimization_guide/nncf/ptq/code/ptq_torch.py

---------

Co-authored-by: Alexander Suslov <alexander.suslov@intel.com>
2023-08-30 11:52:36 +02:00
Mateusz Tabaka
3e8c0fac1b
Remove useless Slices (#19451)
Adjust UselessStridedSliceEraser to work with Slice nodes.

Ticket: CVS-118895
2023-08-30 11:28:33 +02:00
Nesterov Alexander
f2167a9545
[ARM CPU] Remove configure from exec func in eltwise, reduce and pooling (#19071) 2023-08-30 13:12:25 +04:00
Bo Liu
6b57360c55
Fix warnings for Paddle Frontend (#19476)
* Fixed warnings for Paddle Frontend

* fix CI linux-gnu-9 build fail issue
2023-08-30 12:08:08 +04:00
Aleksandr Voron
9b10ef6f6f
[CPU][ARM] Fix inference precision for behaviour tests (#19485) 2023-08-30 09:38:30 +04:00
Taylor Yeonbok Lee
e8f1df495c
[GPU] Fixed reordered memory cache not to contain original weight memory (#19465)
* Fixed reordered memory cache not to contain original weight memory

* Applied review comment

* Applied review comment
2023-08-29 21:54:32 -07:00
Xiuchuan Zhai
36b9de1f25
enable sin/cos && fix top_k_v2 (#17525) 2023-08-30 08:55:57 +08:00
Anton Voronov
49c4c922ff
[CPU][OneDNN] Fix zero pad perf issues (#19417) 2023-08-29 16:55:45 +00:00
Oleg Pipikin
e3e1e8c811
Template plugin tests refactoring (#19397)
* Template plugin tests refactoring

* Apply comments
2023-08-29 13:48:53 +00:00