IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
9,693 Commits 38 Branches 54 Tags 1.1 GiB
bfe77d0c65
Commit Graph

9693 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Maxim Vafin
bfe77d0c65
Workaround DivideConversion transformation issue in convit model (#15566) 
* Workaround DivideConversion transformation issue in convit model

* Apply suggestions from code review
 2023-02-10 14:25:05 +01:00
Maxim Vafin
d992c6b9c7
[PT FE] Fix aten::flatten, add more tests (#15576) 
* Fix flatten, add more tests

* Apply review feedback

* Fix code style
 2023-02-10 14:23:27 +01:00
Oleg Pipikin
f48b5278fd
Fix ov_coverage target (#15581) 
* Fix ov_coverage target

* Update cmake/coverage.cmake

---------

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
 2023-02-10 14:08:42 +01:00
Vladislav Golubev
67396661a9
[CPU][DEBUG_CAPS] Transformations dump: added CPU opset serialization for XmlBin format (#15565) 2023-02-10 14:01:09 +01:00
Pawel Raasz
19e60759cd
[PT FE] Cannot get length of dynamic dimension (#15449) 
* Create output tensor for bound evaluate depends
on element type and shape, rank dynamism

* Add test to simulate pytorch bound evaluation
for when output has got dynamic data type or rank

* Correct code style

* Correct shape for dynamic tensor.
 2023-02-10 13:36:07 +01:00
Pawel Raasz
264cb18619
Review pad class for shape inference aspects (#15524) 
* Review for partial shape and label propagation

* Review template shape_infer for Pad

* Add evaluate upper/lower, label
- preserve partial value on inputs pads_begin, pads_end

* Fix compilation errors

* Fix pads_begin, pads_end compare

* Minor shape infer assertion corrections

---------

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
 2023-02-10 13:35:47 +01:00
Roman Lyamin
75735ca597
[GPU] Added ScatterUpdate shape agnostic kernel (#15579) 2023-02-10 07:06:30 +01:00
Ilya Lavrenov
4fa5137af4
DEB: use alternative package names for nlohmann json (#15607) 2023-02-10 02:34:16 +04:00
Vladislav Golubev
1b29914c07
[CPU][DEBUG CAPS] Build fix (#15602) 
* [CPU] TransformationPipeline: returned debug config

* Added a macros for variables which can be unused
 2023-02-09 22:49:30 +04:00
Tomasz Dołbniak
8a36ee9c38
PrePostProcessor - compilation warning fix (#15618) 
* Compilation warning fix

* Another approach
 2023-02-09 22:46:13 +04:00
Irina Efode
8213a8f7ec
[CONFORMANCE][IE TEESTS] Move Summary from ngraph:: to ov:: (#15539) 
* [CONFORMANCE] Fix issue with overflowed crash

* [CONFORMANCE][IE TEESTS] Move Summary from ngraph:: to ov::

* Revert "[CONFORMANCE] Fix issue with overflowed crash"

This reverts commit a1f16777b5.

* Apply comments

* Fix build

* Update run_conformance.py
 2023-02-09 15:20:32 +04:00
Roman Kazantsev
6078c95b6a
Revert "[CI] Add task UsePythonVersion@0 to Azure Pipelines (#15240)" (#15598) 
This reverts commit 8acfb87d16.
 2023-02-09 14:51:25 +04:00
Nadezhda Ageeva
ccebc629e2
[GPU] Update caching properties for GPU (#15463) 2023-02-09 10:57:38 +01:00
Jan Iwaszkiewicz
2769e22767
[PyOV] Adding optimizations and shared memory mode to inference calls (#15290) 
* Proposal of data_dispatcher

* Fix C-style for array-like objects

* Added test cases

* Add InferRequestInternal to hold lifetime of converted data

* Change name and location of InferRequestInternal to _InferRequestWrapper

* Fixes for shared data mode to match previous tests, codestyle refactoring

* Fix annotations and style

* Add initial testing

* Fix dtype capture

* Fix set_request_tensor

* Extend doc strings

* Fix docs

* Docs fix

* Change to ndarray in docs

* Fix async case

* Fix async test 2

* Remove linter issue
 2023-02-09 10:50:39 +01:00
Mateusz Bencer
938f210c89
[ONNX FE] Introduced topological sort as additional step of reading model (#15472) 2023-02-09 10:44:01 +01:00
Roman Kazantsev
9cd23790c7
[TF FE] Refactor Tile and add layer test (#15584) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-02-09 08:43:39 +01:00
Ilya Lavrenov
84ecacda26
Windows ARM64 support via LLVM (#15585) 2023-02-09 11:30:07 +04:00
Leonard Sikorski
92788b1838
[PT FE] Add aten::empty operator with layer test (#15490) 2023-02-09 08:24:08 +01:00
Andrew Kwangwoong Park
e77c2ab6d7
[GPU] Added shape agnostic NonZero ref kernel (#15534) 
* [GPU] Added shape agnostic NonZero kernels

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

* Add dynamic TC for ov_gpu_unit_tests

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

* Apply code review

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

---------

Signed-off-by: Andrew Park <andrew.park@intel.com>
 2023-02-08 17:53:18 -08:00
Wilson Seok
0d06e525db
[GPU] add different type support in range kernel (#15422) 
* add different type support in range kernel

* add functional test case for mixed input data type
 2023-02-08 16:36:25 -08:00
Roman Kazantsev
4301ede385
[MO][TF FE] Add additional fallback for Iterator operations (#15582) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-02-09 00:54:33 +04:00
Taylor Yeonbok Lee
b9107ac7ca
Optimized permute kernel cannot be fused with both eltwise + reorder. (#15542) 2023-02-08 10:32:13 -08:00
Ekaterina Aidova
ac1e885324
[PT FE]: add tests for rsub and handle mixed precision (#15555) 
* [PT FE]: add tests for rsub and handle mixed precision

* update tests
 2023-02-08 19:55:43 +04:00
Roman Lyamin
23b863ffe8
[GPU] Added ScatterNDUpdate shape agnostic kernel (#15567) 2023-02-08 16:27:34 +01:00
Artyom Anokhov
8d2eae95a7
Port changes for installing GPU driver from 2022.3 branch (#15408) 
* Port changes for installing GPU driver from 2022.3 branch.

* install_openvino_dependencies: Fixed syntax after ShellCheck

---------

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
 2023-02-08 18:37:51 +04:00
Shen, Wanglei
d72deb955d
move CPU mapping parser API from dev_api header file to specific header file (#15558) 
* move CPU mapping parser API to specific header file

* keep all enum defination in ie_system_conf.h

* move hpp file to inference/src

* fix code style issue
 2023-02-08 18:27:14 +04:00
Ilya Lavrenov
66abecfd3d
Fixed compilation error after conflicting PRs merge (#15577) 2023-02-08 17:52:51 +04:00
Maxim Vafin
6a9608b075
[PT FE] Fix GroupConvolution weights reshape (#15560) 
* Fix GroupConvolution weigts

* Update src/frontends/pytorch/src/utils.hpp

* Update convnd.cpp
 2023-02-08 14:11:35 +01:00
Vladislav Golubev
6630ae82d2
[LPT] Avoid AddTransformation for the cases which introduce Infinite constants after math calculations (#15496) 2023-02-08 13:06:24 +00:00
Maxim Vafin
de4f9c8131
[MO] Add support for dynamic cases in legacy Broadcast shape infer (#15546) 
* [MO] Add support for dynamic cases in legacy Broadcast shape infer

* Update broadcast_test.py

* Update broadcast.py

* Update broadcast_test.py

* Update broadcast_test.py
 2023-02-08 13:53:43 +01:00
Irina Efode
70177dbfb3
[CONFORMANCE] Add support of models and lists of models to the conformance rrunner (#15559) 
* [CONFORMANCE] Add support of models and lists of models to the conformance rrunner

* Update models.lst
 2023-02-08 13:53:02 +01:00
Katarzyna Mitrus
76817f56c2
[ShapeInference] CTCGreedyDecoderSeqLen shape infer improvements (#15501) 
* Shape infer improvements

* Add setter for merge repeated attribute

* Use new shape_infer in validate and infer types

* Add more type prop tests

* Add shape infer tests

* Align variable names in tests

* shape_infer call refactor

---------

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
 2023-02-08 12:24:48 +00:00
Pawel Raasz
c3083589bd
Review reverse class for shape inference aspects (#15426) 
* Check partial shape and label propagation

* Add template shape_infer implementation
 2023-02-08 16:10:51 +04:00
Ilya Lavrenov
1f3e469c5e
Added -Wall for Clang and GCC (#15513) 
* Added -Wall for Clang and GCC

* Fixes

* Don't use /J

* Fixed warnings

* Fixed warnings

* More fixes

* Fixed for MSVC

* Fixed more warnings on Windows

* Suppressed some warnings in template plugin

* Update src/tests/functional/plugin/shared/include/behavior/plugin/caching_tests.hpp

* Added suppression for PT FE

* Suppressed warnings in TF FE

* Suppressed warnings on Core unit tests

* Suppress warnings in python

* Suppressed Windows warning for 3rd party modules

* Suppresed one more warning
 2023-02-08 15:01:00 +04:00
Irina Efode
6b503099db
[CONFORMANCE] Fix issue with overflowed crash (#15538) 2023-02-08 10:54:42 +00:00
Roman Kazantsev
a350bd7e85
[TF FE] Support SaveV2 operation (#15572) 
* [TF FE] Support SaveV2 operation

Also, implement transformation to remove UnsupportedConstant to Result
isolated sub-graphs

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

* Revert change for Constant

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-02-08 10:35:39 +00:00
Haiqi Pan
82286cc2af
fix dump/load_config using opencv (#15540) 
* fix dump/load_config using opencv

* fix format

* remove empty line

* fix format
 2023-02-08 10:33:51 +00:00
Tomasz Dołbniak
44f5238e3a
ONNX TopK missing tests (#15556) 2023-02-08 10:59:20 +01:00
Roman Kazantsev
6582ad7e4d
[TF FE] Fix sporadic failure in LinSpace (#15570) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-02-08 08:54:58 +00:00
Katarzyna Mitrus
d94dae79d8
[ShapeInference] CTCGreedyDecoder shape infer improvements (#15474) 
* Add setter for ctc_merge_repeated

* shape infer improvements

* Add type prop tests

* Add cpu shape infer tests

* Tests refactor
 2023-02-08 11:41:14 +04:00
Wilson Seok
18905ada20
add default infer_probs (#14653) 
* add default infer_probs

* fix clang format

---------

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
 2023-02-08 09:27:13 +04:00
Sergey Shlyapnikov
7b649c4150
[GPU] Fix reset_execution() method with wait option enabled for in_order queue type (#15562) 2023-02-08 09:18:46 +04:00
Nadezhda Ageeva
421d791f58
[HETERO] Return only own properties for compiled model (#15547) 2023-02-07 23:54:08 +04:00
Ilya Churaev
26108b1b67
Deprecate clone_model API, use model->clone() instead of (#15482) 
* Deprecate clone_model API, use model->clone() instead of

* Renamed clone_nodes function

* Fixed exception
 2023-02-07 23:53:17 +04:00
Ivan Tikhonov
a0a73d443e
Enable TransposeSinking transformation in Tensorflow FrontEnd (#15410) 
* Enable TransposeSinking in MOC

* replace TransposeSinking in TF Frontend

* fix TS for concat op

* Fix TS for Binary/Concat ops: broadcast transposed input

* Fix transpose sinking for Pad op

* fix pad tests

* fix dynamic case for Concat/Binary ops

* codestyle

* fix TransposeSinking for Split/Concat ops

* fix split

* Resolve review comments
 2023-02-07 19:21:34 +00:00
Maxim Vafin
9bac41b466
Replace ListConstruct on inputs to Roll and Broadcast (#15442) 
* Replace ListConstruct on inputs to Roll and Broadcast

* Apply suggestions from code review

* Fix codestyle

* Add AdaptiveAvgPool

* Remove unused inputs to MultiSubGraphOp

* Update listconstruct_replacer.cpp

* Apply code style

* Fix build
 2023-02-07 20:11:14 +01:00
Ilya Churaev
68ccd078dc
Export TBlob specialization for Windows (#15516) 
* Export TBlob specialization for Windows

* Changed macro in define

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
 2023-02-07 22:11:49 +04:00
Roman Kazantsev
180e77f047
[TF FE] Refactor Softmax and add layer test (#15553) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-02-07 16:22:36 +01:00
Roman Kazantsev
2be9cdc5c5
[TF FE] Refactor Reshape and add layer test (#15549) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-02-07 16:19:37 +01:00
Anastasiia Pnevskaia
1f5faf6cee
Added preserving logger state to mo.convert_model(). (#15529) 2023-02-07 18:38:33 +04:00