IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
5,690 Commits 38 Branches 54 Tags
576471cc2759db3c511d50b9bd500cfca410edf4
Commit Graph
5690 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Anton Pankratov 576471cc27 Any used to store standard types (#8946) 2021-12-09 17:19:18 +03:00
Sergey Lyubimtsev 37e23cda8d fix tags for wheel package name (#9098) 2021-12-09 17:05:24 +03:00
Svetlana Dolinina cbae8e0532 Added calculation of lower/upper bound for divide operation (#8325) 2021-12-09 16:40:14 +03:00
Yegor Kruglov 7cb1bd6a1b Extend nGraph for operation Softmax-8 (#8157) 2021-12-09 16:21:55 +03:00
Ilya Lavrenov 12d322807f Compile snippets as a static library (#9095) 2021-12-09 15:40:43 +03:00
Ilya Lavrenov 02e7706776 Merged ngraph & core components (#9101) 2021-12-09 15:38:44 +03:00
Ilya Lavrenov 1e29778aec Added optional for LPT install (#9111) 2021-12-09 15:37:25 +03:00
Vladimir Gavrilov d6ab463ab5 Failure of quantization for some models due to absence ShuffleChannels operation in some set (#8919) 
* Added ShuffleChannels operation into OpVersioning.opset_1_types set.

* Fixed the attribute 'version' of the MO operation ShuffleChannels.

* Reverted opset change for the operation ShuffleChannels.
 2021-12-09 15:20:29 +03:00
Anastasia KuporosovaandMikhail Nosov 8453b6395a [Python API] Bind test_utils (#8549) 
* [Python API] Bind test_utils

* fix building

* fix building

* fix codestyle

* fix codestyle

* try to fix merging

* Update __init__.py

* fix azure jobs

* fixes after master merge

* fix importing

* try to fix import

* Fix array out-of-bounds error (#8966)

* try to fix

* fix building

* fix code style

* undo some changes after rebase

Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>
 2021-12-09 15:07:12 +03:00
Mikhail Ryzhov d2df884274 [CAPI] Fixed memory leak in tests (#9099) 2021-12-09 13:54:45 +03:00
Nikita Demashov 473ca54b0d [LPT] Fix not thread safe function setDefaultPrecisions (#8973) 
* add mutex for protection defaultPrecisions

* add setDefaultPrecisions & getDefaultPrecisions

* move defaultPrecisions to LayerTransformation

* add getDefaultPrecisions() in PrecisionsAttribute

* move getDefaultPrecisions() from PrecisionsAttribute constructor
 2021-12-09 13:23:39 +03:00
Katarzyna Mitrus a787fade68 [Python API] Move openvino.runtime.impl to openvino.runtime (#9096) 2021-12-09 10:40:22 +01:00
Aleksandr Korolev 8b90349529 [VPU] Coverity fixes (#9025) 
VPU and Movidius coverity fixes
 2021-12-09 12:03:24 +03:00
Nikita Demashov 87559aa2b4 disable pullTranspose throught fq (#7894) 
fix 6D tests, add weights to matcher

fix cpu test

add 6D transpose tests

update all tests

lin fix

fix canBeTransformed and update tests

rm concat axis limit

concat axis update

rm concat changing
 2021-12-09 12:00:36 +03:00
Svetlana Dolinina b06ff4ced7 fix iteration count calculation for output record for case of negative start/end and non integer division (#8641) 
* fix iteration count calculation for output record for case of negative start/end and non integer division

* added tests;
process case with both start/end

* test refactoring done
 2021-12-09 11:29:11 +03:00
Tomasz Dołbniak f9949b4140 Alignment of OV and ONNX models outputs naming (#7691) 
* Alignment of OV and ONNX models outputs naming

* Python tests adaptation to new naming rules

* New output naming rules

* Output name retrieval adaptation (tensor iterator node)

* Copying of tensor names during output replacement

* Multiout multinode subgraphs handling in the importer

* Proper replacement tensor naming

* Model zoo test runner adaptation

* Backwards compatible python tests runner adaptation

* If node adaptation

* Adaptation to changes in master

* Deprecation warning suppression

* Imports fix in compatibility tests

* If node adaptation to the new naming

* MaxPool python tests re-enabled

* ONNX Identity elimination adaptation

* XFAIL for the Identity op test

* Support for Param->Result models and indentity op

* Fix of the ONNX Indentity handling

* The test that fails only on windows temporarily disabled

* ONNX tensor names test adaptation

* Code cleanup

* Code formatting

* Obsolete helper removal

* One more spot where output name helper should be used

* PyApi fix for tensors with multiple names

* Don't set friendly names for unnamed ONNX nodes

* Revert "Don't set friendly names for unnamed ONNX nodes"

This reverts commit 92c7ac59b5.

* Missing dot...

* And now the mypy nonsense...

* Use get_any_name in Loop

* New way of naming result nodes in ONNX FE
 2021-12-09 11:16:50 +03:00
Victor Kuznetsov 0f1c545a19 [Time tests] Change work with perf_hint (#9090) 
* add performance hint to time infer

* upd_time_tests
 2021-12-09 10:29:55 +03:00
Steve Yoo d3cf7b92d0 Create GatherTree-1 (#8995) 2021-12-09 09:26:43 +03:00
Ilya Lavrenov e0ae61b06d Added optional for exclude_from_all targets (#9100) 2021-12-09 08:51:21 +03:00
Alexander Zhogov e4b8586f72 Azure CI: Enable linux_onnxruntime on master (#9097) 2021-12-09 08:46:00 +03:00
Nikita Demashov ca0cdb896f [LPT] Fix concat transformation tests and add subtract_convert push support (#8904) 
* add test

* supporting pulling subtract convert

* supporting branch without subtract

* add tests with subtract convert and subtract without convert

* Fix allDequantizationShiftConvertAreNotZero & fix precision subtructInput
 2021-12-09 02:13:19 +03:00
Dmitrii Khurtin 3118640569 removed unnecessary code of PWL & added additional tests for increase… (#8994) 
* removed unnecessary code of PWL & added additional tests for increase PWL code coverage

* fixed errors

* removed Configuration from PowerParamsTuple

* fixed a bug related to an incorrect PWL value for functions neglog and neghalflog
 2021-12-09 01:12:33 +03:00
Irina Efode 509797af58 [IE TESTS] Extend filters by results in report (#9089) 2021-12-09 01:05:28 +03:00
Svetlana Dolinina 12ccc66920 move creation of InferRequests back to Infer; fixed tests for QueryState (#8962) 
* move creaton of InferRequests back to Infer; fixed tets for QueryState

* fix indentation

* fix indentation

* fixed MemoryLSTMCell test
 2021-12-09 00:58:33 +03:00
Gleb Kazantaev d18e80b604 Move back temp frolder to the CMAKE_SOURCE_DIR (#9072) 
* Move back temp frolder to the CMAKE_SOURCE_DIR

* Fix windows azure
 2021-12-09 00:00:36 +03:00
Anton Pankratov 32d3dade40 Fixed any kw issues (#9081) 2021-12-08 23:08:39 +03:00
Ilya Lavrenov 7095f2a1f7 Fixed linkage for G-API (#9083) 2021-12-08 20:12:08 +03:00
Wilson Seok 9faf661250 Add slt in template plugin/experimental detectron grid generator (#8923) 
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now

* update repo

* add op reference test of ExperimentalDetectronPriorGridGenerator

* implement actual_comparision_size for compare

* update slt for actual comparison size and add visitor api test

* fixed clang error
 2021-12-08 19:07:40 +03:00
Alexandra Sidorova 92760949bf Added TransposeReshapeEliminationForMatmul Transformation (#7938) 2021-12-08 17:45:40 +03:00
Svetlana Dolinina 672565a8ed deprecate mean_file option in Caffe (#8707) 
* deprecate mean_file option

* add deprecation warning even if error happens

* removed Suppress for now deprecated options

* review fixes

* added dot
 2021-12-08 17:38:46 +03:00
Ilya Lavrenov 64367fbca2 Export frontend_common as dev target (#9003) 2021-12-08 17:18:44 +03:00
Alexey Lebedev ebba28a3e3 [tools] correct options for dynamic models (#9010) 
* process dynamic model with one data_shape as static

* static reshaped to dynamic with one data shape can't be mesuared as static
 2021-12-08 16:53:52 +03:00
Evgenya Stepyreva 86383d07e3 Revert "OpShapeInfer (#8310)" (#9086) 
This reverts commit ee4643d97e.
 2021-12-08 16:31:29 +03:00
Victor Kuznetsov 55f64a505a Expand time tests to cover CPU caching feature (#8938) 
* add performance hint to time infer

* add options for vpu, cpu cache, perf hint

* change VPUX condition

* add perf hint verify

* upd perf hint usage. set as non required
 2021-12-08 15:22:44 +03:00
Krzysztof Bruniecki 893dd4531e [GNA] Move to GNA Lib 3.0.0.1455 with extended CNN2D capabilities for GNA HW 3.0 (#8901) 
* Switch to GNA Lib 3.0.0.1455, Adapt to new GNA 3.0 (ADL) limitations

   Apply limitations for GNA 3.0 CNN2D as in 22013786746
   Add new CNN2D tests for GNA 3.0 and update negative tests
   Switch download of 1455 to 01.org
   Fix weight reducer

* Apply review

	Increase max kernel number to 1024
	Update negative test
 2021-12-08 14:55:20 +03:00
Anton Romanov 18d6fd3296 Fix tests after update archive with models (#9063) 2021-12-08 14:53:18 +03:00
Orest Chura f734e7679b Update fluid (#9007) 2021-12-08 14:43:31 +03:00
Alexander Zhogov 97f6dbf1f2 Update CODEOWNERS 2021-12-08 14:24:15 +03:00
Daria Mityagina af5fba787f [VPU] Add new operation "GatherND-8" (#8745) 
In the MyriadX plugin, GatherND-5 will be called instead of GatherND-8, since the non-default batch_dims parameter values ​​are not plugin use cases.
 2021-12-08 13:44:06 +03:00
Dmitry Pigasin 7fa6c42a8c [IE Python Speech Sample] Enable -we option (#8750) 
* Enable `-we` option

* Update readme
 2021-12-08 13:05:22 +03:00
Sergey Lyubimtsev 01236619b5 Update TPP files for wheels (#8935) 
* Update TPP files for wheels

* Remove myriad plugin and update `openvino` package description

* Update for product names
 2021-12-08 12:50:30 +03:00
Szymon Irzabek 36b4dfedae Gna matmul fix (#9026) 
* [GNA] Handle additional case of matmul transpose with POT

* [GNA] Fix MVN decomposition initialization issue
 2021-12-08 12:47:41 +03:00
Vladislav Golubev 55955f7ae9 [CPU] ROIAlign tests enabled (#8910) 2021-12-08 12:07:58 +03:00
Vladislav Golubev 07b6489524 [LPT] Security fixes (#9006) 2021-12-08 12:07:05 +03:00
Milana Shhanukova 38600949fa [POT] Remove tpe algo (#8929) 
* remove tpe

* delete unused object_dump.py

* delete tpe reference

* tpe removal in optimization

* deleted benchmark

* docs changes

* tunable quantization changes

* mistype in sentence
 2021-12-08 11:43:39 +03:00
Artur Kulikowski bc08878e91 Extend ONNX FE for operation DetectionOutput-8 (#9055) 2021-12-08 09:34:57 +01:00
Artur Kulikowski 64c6ca05ed [Python API] Binding ov::Any (#8996) 2021-12-08 09:34:31 +01:00
Artur Kulikowski 6bbb2c86e5 Extend ONNX FE for operation PriorBox-8 (#9028) 2021-12-08 09:34:10 +01:00
Alexander Zhogov d89d88ecf4 Azure CI: Disable MO based tests due to regressions 2021-12-08 11:27:17 +03:00
Egor Shulman 69b81be14e [CPU] Fixed NormalizeL2 on SSE4.2 for blocked layout (#9071) 2021-12-08 11:20:33 +03:00