Commit Graph

7508 Commits

Author SHA1 Message Date
Ilya Churaev
60f9f3dc92
Enabled LTO for static CPU (#11426)
* Enabled LTO for static CPU

* Update CMakeLists.txt

* Update CMakeLists.txt
2022-04-04 20:22:22 +03:00
Maxim Shevtsov
500d36e1c0
cherry-picking opt guide changes from the release branch (#11430) 2022-04-04 19:41:17 +03:00
Mikhail Letavin
417d75d80b
[GPU] Fix allocation for cached USM remote blobs (#11304) 2022-04-04 18:16:53 +03:00
Fedor Zharinov
787610b0db
-l option is replaced with -extensions (#10878) 2022-04-04 16:08:38 +03:00
Elizaveta Lobanova
9b4e8f5b59
[GNA] Fixed cascade concats binding (#11326) 2022-04-04 15:56:13 +03:00
Karol Blaszczak
da8388e263
[DOCS] polish autodevice article (#11171) (#11427)
the article has been changed much and its language has been impacted in the process. Here are some corrections.
2022-04-04 13:12:18 +02:00
Gleb Kazantaev
a52092deb0
Enable FQ fusions in MOC (#11269)
* Enable FQ fusions in MOC

* Fix codestyle
2022-04-04 13:34:01 +03:00
Edward Shogulin
542a374c40
[LPT] Introduce new quantization mode attribute (#11380) 2022-04-04 13:27:03 +03:00
Ilya Churaev
b9ba0bb40c
Removed OV_NEW_API (#11082)
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-04-04 13:07:12 +03:00
Dmitry Pigasin
80e7857eca
[Python Speech Sample] Change argument format (#11012)
* Change `-i` argument format

* Change `-sf` argument format

* Change `-o` and `-r` argument format

* Fix saving file with multiple utterances

* Fix flake8 D415

* fix scale factor for imported models
2022-04-04 13:03:39 +03:00
Roman Kazantsev
9dee25fa79
[MO] Support TensorFlow Grouped Conv2DBackpropInput (#11420)
* [MO] Support TensorFlow Grouped Conv2DBackpropInput

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

* Correct computation of group number for ConvBackpropInput operation

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

* Fix get_conv_backprop_groups function

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

* Add unit-tests for Deconvolution shape inference

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2022-04-04 12:30:31 +03:00
Chenhu Wang
60521a92c9
[CPU] Fixed NMS implementation on APL targets (#10649) 2022-04-04 10:52:22 +03:00
Maxim Andronov
65a182aaea
[CPU] Extract weight cache to executable network (#11118) 2022-04-04 10:47:58 +03:00
Vladimir Paramuzov
afdaa7cf89
[GPU] Align permute axis format with IE (#11379) 2022-04-04 10:28:51 +03:00
Ilya Lavrenov
d879e34363
Tbb: download only if system libraries are not found (#11415)
* Download custom TBB on demand

* Download TBBBind on demand

* Fixed install steps

* FIxes
2022-04-03 19:55:54 +03:00
Edward Shogulin
5d821453ae
[LPT] Introduce new granularity attribute instead of OperationPerTensorQuantizationRestriction (#11330) 2022-04-03 19:35:04 +03:00
Ilya Lavrenov
29fb8c79b1
Don't use template plugin unconditionally (#11409) 2022-04-02 11:40:45 +03:00
Ilya Lavrenov
4fcc18c00e
Tbb 2018 and older usage (#11411)
* fixed TBB

* Fixed compilation with old TBBs

* Fixed installation for custom provided TBB
2022-04-02 11:11:13 +03:00
Ilya Znamenskiy
1e4a1b2b4a
[GPU] Klockwork issue 57997 fix (#10956) 2022-04-02 11:06:56 +03:00
Roman Kazantsev
1a288c2e99
Enable MO unit-tests but bom tests (#11399)
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2022-04-02 10:58:23 +03:00
Ivan Mikhalev
6105ea3902
[CPU] [DEBUG CAPS] Revert DNNL_VERBOSE (#11410)
Compilation with ENABLE_CPU_DEBUG_CAPS was fixed.
Previous to this change it failed due to undefined dnnl::impl::md2dim_str
(since DNNL_VERBOSE was disabled in the scope of PR #11244).
2022-04-02 10:57:29 +03:00
Andrey Zaytsev
415daecc26
Cherry-pick Feature/azaytsev/doc fixes 2022 1 1 (#11388) (#11407)
* Removed a redundant image

* Fixed ops specifications and other issues

* converted html links to anchor links

* converted html links to anchor links

* Fixed a link

* Fixed a link

* Changed anchor links according to dev review
# Conflicts:
#	docs/OV_Runtime_UG/Operations_specifications.md
2022-04-01 19:53:58 +03:00
Ilya Lavrenov
8ae7c9f2cc
Disabled TBBBind usage for oneTBB (#11386) 2022-04-01 19:09:06 +03:00
Maxim Gordeev
2388f3b976
Updated docs for python's version of hello_reshape_ssd (#11401) 2022-04-01 18:21:40 +03:00
Vladislav Golubev
a02b3f4995
[Transformation] MarkPrecisionSensitiveDivides extending to mark fp32 divides (#11391)
* MarkPrecisionSensitiveDivides: fp32 divides marking enabled

* ConvertDivide: added a negative test-case with fp32 divide on precision sensitive subgraph
2022-04-01 17:31:23 +03:00
Maksim Derbasov
56df3962e3
Fix for warnings spotted by clang compiler (#11384) 2022-04-01 16:10:51 +03:00
Maxim Andronov
3d92c8c4c7
[CPU] Avoid inserting reorder after RNN in native order case (#10799) 2022-04-01 16:02:50 +03:00
Nikita Semaev
fca159293d
Fix Bucketize Conformance tests for Template plugin (#11029)
* Right fill in the values of the inputs

* Using create_and_fill_tensor_unique_sequence() instead of create_and_fill_tensor()

* Fixing a problem with a missing parameter when calling the create_and_fill_tensor method

* Fix Bucketize Conformance tests inputs generation for Template plugin

* Correct filling of the first port (data)
2022-04-01 15:22:45 +03:00
Andrey Zaytsev
cad355a03e
Docs labels adjustment (#11227) (#11294)
* Adjusted documentation labels

* Renamed images

* fix doc tests

Co-authored-by: CCR\ntyukaev <nikolay.tyukaev@intel.com>
# Conflicts:
#	docs/IE_PLUGIN_DG/ExecutableNetwork.md
2022-04-01 15:06:55 +03:00
Anton Grishin
7efc85063b
[GNA] Add GRUCell/GRUSequence/LSTMSequence support (#11333)
* Add grucell/gruseq/lstmseq unrolling

Add tests

* remove bidirectional decomposition

* completly remove bidirectional_sequences_decomposition
2022-04-01 14:16:11 +03:00
Nikita Semaev
dc55f8bb5a
Correct the order of passing arguments to the InputGenerateData constructor (Fix Round, Ceiling Conformance tests for Template plugin) (#11099)
* Correct the order of passing arguments to the InputGenerateData constructor

* Full range correction for random numbers

* Refactoring the argument sequence of the InputGenerateData class constructor

* A small imperfection

* Rollback changes that are related to range
2022-04-01 13:42:10 +03:00
Alexey Lebedev
6eaa15745a
[PYTHON API] Tensor.data property for low precisions + packing (#11131)
* rebase old branch with master

* Fix doc style

* fix test

* update tests

* Add missed param

* Rewrite docstring for tensor and refactor set_input_tensors test

* update python exclusives

* keep compatibility

* remove notes about slices

* fix code style

* Fix code style
2022-04-01 12:04:04 +03:00
Karol Blaszczak
701d75eafa
[DOCS]continue_language_review-transitionguide (#11177)
PR for 22.1 made, now porting to release...
some discrepancy between this version and the 22.1 branch seems to exist, so I adjusted the conflicting link to avoid build check errors...

the overview has been merged, the remaining articles are reviewed here
2022-04-01 17:03:40 +08:00
Ilya Churaev
80739700ff
Added clone method for ov::Model (#11390)
* Added clone method for ov::Model

* Changed python API
2022-04-01 10:52:31 +03:00
Ilya Churaev
8ab5dbade0
Revert "Add constant folding to hetero to avoid dynamism on GPU (#10572)" (#11370)
This reverts commit 5b18677f1b.
2022-04-01 10:16:14 +03:00
Bo Liu
070f27a089
Paddle FasterRCNN Ops Conversion: roi_align, strided_slice, where (#10893)
* Paddle FasterRCNN Ops Conversion: roi_align, strided_slice, where

* add check for 'aligned' feature of 'roi_align' op; use common function for idx_node in 'striede_slice' op

* Apply suggestions from code review

* use common funciton for stride_slice and slice, OP_CHECK for 'where' op conversion

* Apply suggestions from code review
2022-04-01 14:37:28 +08:00
yanlan song
4057e408d8
Bell/shape auto (#11284)
* Fix batchability check of MAX_BATCH_SIZE

* Applied review comment

* clonenetwork in auto

Signed-off-by: fishbell <bell.song@intel.com>

* clone in correct way

Signed-off-by: fishbell <bell.song@intel.com>

Co-authored-by: Taylor Yeonbok Lee <taylor.lee@intel.com>
2022-04-01 11:09:22 +08:00
Mikhail Nosov
e52bd441e2
Frontend exception safety (#11368)
* Frontend exception safety

Every call to frontend's API (except Places) can throw exception. If during exception handling, FrontEndManager is destroyed and calls 'dlclose' for plugin - call stack will be corrupted and crash will occur.

Solution is to wrap 'plugins' calls with try/catch and throw new exception in 'openvino' context

TODO: currently "Place" objects don't have 'actual' wrappers, so exception in 'place' objects will potentially cause such crash (if exception handler destroys FrontEndManager). Workaround for user would be to try/catch any calls of Place API on their side.
We're not expecting users to use Place API directly, so this workaround looks acceptable

* Add check for exception message

* Keep type of frontend exception during rethrow

* IR FE tests: don't expect InferenceEngine::exception as it be not propagated as is by FrontEndManager
2022-03-31 22:23:40 +03:00
Anastasia Kuporosova
dd54cb9c17
[Python API] Remove old api class from the new api (#10470)
* [Python API] Remove old api class from the new api

* start working on refactoring of OVAny

* fix tests

* fix code-style

* remove tuple test

* fix test

* fix omz hash

* one more overload

* fix pyfloat

* move from_ov_any to utils

* code-style

* move function from common to utils
2022-03-31 21:57:05 +03:00
Elizaveta Lobanova
d3060d4bcc
[GNA] Fixed handling of unaligned crop layer (#11316) 2022-03-31 20:03:51 +03:00
Vladimir Paramuzov
1cb254307e
[GPU] Gather params update (#11369) 2022-03-31 19:46:38 +03:00
Ilya Lavrenov
3c724a1dee
Build with system TBB (#11244)
* Build with system TBB

* Fixes

* Check whether system TBB is available

* Try to fix ONNX Runtime build with system TBB

* Test

* Fixed compilation of threading.cpp

* Fixed unset of cache dirs

* Limit dearch paths of TBB

* Try to enable pip packages with custom TBB

* Fix for TBB 2021.2

* Install only needed TBB libraries

* Install TBB from system to pip package

* Reverted usage of TBBROOT

* Fixed oneTBB case

* Try to fix Android

* Escape some paths

* Added samples path

* Fixed TBBBind usage for case of system TBB
2022-03-31 18:05:59 +03:00
Ekaterina Aidova
d99104cf55
[OMZ]: update submodule (#11305) 2022-03-31 17:53:41 +03:00
Alina Kladieva
dc83410cd7
Revert "Skip sporadic GPU canInferOnUserQueue test case (#11310)" (#11362)
This reverts commit 458378e9e7.
2022-03-31 17:38:03 +03:00
Vladimir Paramuzov
15b4553eaf
[GPU] Align OneHot primitive parameters with ngraph (#11361) 2022-03-31 17:13:49 +03:00
Alexey Lebedev
1efb0a034f
[PYTHON API] release GIL (#10810)
* AsyncInferQueue nogil update + refactoring

* nogil in compiled model

* nogil in Core

* fix refactoring

* nogil in infer_request

* add tests

* Fix code style

* update test with incrementing reference counting

* try to fix code style

* fix code style

* release gil in reshape and preprocessing

* make args optional in test

* fix code style

* add docs about GIL

* try to link doc string with docs

* Apply suggestions from code review

Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>

* Fix docs

* docs refactoring

* Apply review comments

* Fix code style

Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
2022-03-31 16:12:48 +03:00
Maxim Andronov
1d247815be
Don't execute reference::strided_slice if input/output tensor is empty (#11337) 2022-03-31 15:42:10 +03:00
Alexandra Sidorova
9185f03e77
Added specification for Eye-9 (#11104)
* Added specification for EyeLike-9

* Update docs/ops/generation/EyeLike_9.md

* removed batch from TF

* minor fix

* Applied comment by Anton

* Added new example with dynamic output, added corner case

* Fixed corner case description

* Rename matrix

* applied comments by Yuan

* Added diag_idx as input, minor fixes, renaming

* added support of batch_shape from TF

Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
2022-03-31 14:46:55 +03:00
Smirnov Grigorii
a87e8f7880
moved TransformationsTestsF method's definitions from .hpp to .cpp (#11359)
* moved

* fix style
2022-03-31 14:07:41 +03:00
Pavel Esir
16a5962698
[MO] pad fusing fix (#10453)
* pad fusing fix

* added unit-tests for pad fusing fix

* fixed port reconnecting

* Update tools/mo/openvino/tools/mo/middle/passes/fusing/mark_unfused_nodes.py

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
2022-03-31 14:07:07 +03:00