IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,447 Commits 38 Branches 54 Tags
5a564197a70e5077b2a96e045e82c887b3615bc1
Commit Graph
4447 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Andrew Kwangwoong Park 5a564197a7 [GPU] Fix clBuildProgram failure with ssd_mobilnet_v1_coco and batch=256 (#7121) 2021-08-23 10:08:03 +03:00
Maksim Shabunin 5da224abc4 Fixed ngraph_onnx_importer compatibility target creation for older cmake (3.10) (#7176) 2021-08-23 09:46:11 +03:00
Vladislav Golubev 55bf88473a [CPU][TESTS][LPT] MatMulTransformations test-cases removed from skip config (#7181) 2021-08-23 08:59:54 +03:00
Pavel Esir f77d838e6c [MO] turn on MarkSubGraphsWithCorrectLayout for TF NCHW (#7150) 
* turned on MarkingSubgraphsWithCorrectLayout for TF NCHW

* restricted MarkSubgraphsWithCorrectLayout.py only to TF

* added comments why need to MarkSubgraphsWithCorrectLayout even for TF NCHW models
 2021-08-20 18:47:45 +03:00
Anastasia PopovaandAnastasiya Ageeva ef84c90367 Updated list of supported operations. (#6981) 
* Updated list of supported layers.

* Removed Crop, softsign from Kaldi list.

* Updated limitations.

* Corrected limitations.

* Updated limitations.

* Added Einsum, corrected Where.

* Apply suggestions from code review

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>
 2021-08-20 17:03:36 +03:00
Rafal Blaczkowski 600eef24bc parametrize proxy (#7174) 2021-08-20 12:27:02 +03:00
Olesya Martinyuk a052b07fe6 MemCheck add INT8 models to pre-commit (#7166) 
* updated desktop configs with int8 models

* updated desktop reference configs with actual values

* added commit comments
 2021-08-20 12:25:59 +03:00
Gabriele Galiero Casay 211ea3c63c ReverseSequence specification refactored (#7112) 
* ReverseSequence specification refactored

* Change attribute description to avoid confusion

* Allow seq_lenghts input to be of floating-point precision
 2021-08-20 11:58:16 +03:00
Alexander Shchepetov afd49e662a Install layer tests with CMake (#6892) 
* add CMakeLists.txt

* add copyright docstring

* add newline after copyright

* set target name

* change TARGET to DIRECTORY

* Rename layer tests dir to avoid name conflict

* cmakelists.txt final version

* Change destination to tests\layer_tests_openvino

* Add cmake_minimum_required to CMakeLists.txt

* Update CMakeLists.txt
 2021-08-20 11:09:42 +03:00
Anastasiia Urlapova e1201e8bfe CVS-56144 Enable all OMZ scope (#7084) 2021-08-20 11:00:03 +03:00
Vladislav Golubev 78dea9a7d6 [LPT] MarkupCanBeQuantized: handled unsupported concat (#7045) 
* [LPT] MarkupCanBeQuantized: added check on unsupported concat

* [LPT] ConcatTransformation: added test-case with unsupported concat and convolution

* [LPT] added test on rtInfo check for unsupported concat

* [LPT] ConcatTransformation: added test-case with unsupported axis to plugin tests
 2021-08-20 09:58:56 +03:00
Katarzyna Mitrus 551b17db81 CumSum reference implementation revision (#6915) 
* New CumSum implementation init

* Unified ndim approach

* Move transpose to separate function

* Move transpose to original to separate function

* Move slice_count calculation to function

* Negative axes support

* Refactor redundant copy

* Changed copy to move

* Temp more backend tests

* Add const to shape arg

* Use span for slices calculation

* Remove unused headers

* CumSum new ref tests

* Add more ref tests

* Add all cumsum modes ref tests

* new optimized cum_sum reference

* Add reverse mode

* Optimized cumsum ref

* Remove deprecated cumsum backend tests

* Add more CumSum reference tests

* Simplify CumSum shared layer tests SetUp

* Replace auto to size_t in loop

* Change static_cast to T{}
 2021-08-20 09:50:09 +03:00
Anton Pankratv 2fefe1164d Added common.hpp file with aliases (#7158) 2021-08-20 07:17:56 +03:00
Katarzyna Mitrus 7aeec6ffe4 CumSum spec revision (#6966) 
* Update detailed description

* Update exclusive attribute description

* Update Inputs/Outpu description

* Update types

* Update descriptions

* Update data input rank info
 2021-08-20 06:55:13 +03:00
Bartosz Lesniewski df17cba68f Enable PriorBoxClustered tests (#7078) 2021-08-20 06:54:12 +03:00
Bartosz Lesniewski 9c5e7654d9 Revise CTCLoss OP (#6953) 
* Add visitor test to CTCLoss

* Add CTC Loss SSLT

* Add CTC Loss template tests

* Use ngraph rtti macros

* Code style fix
 2021-08-20 06:53:37 +03:00
Ilya Churaev 334bf9d227 Moved DiscreteTypeInfo to ov namespace (#7127) 
* Moved DiscreteTypeInfo to new opset

* Revert old header

* Fixed code style
 2021-08-20 06:42:15 +03:00
Nikita SemaevandTatiana Savina 184b3cbe42 Review/update spec for NotEqual operation (#6797) 
* Hiding the problem, Validate() changes 'function'

* Review/update spec for NotEqual operation

* Remove unnecessary edits not related to the ticket

* Removing the extra word binary for the short description

* Re-writing detailed description

* Correcting punctuation docs/ops/comparison/NotEqual_1.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Specifying auto_broadcast in the short description is similar to Equal spec

* The range of values for auto_brodcast is similar to Equal spec and includes the missing pdpd

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
 2021-08-19 21:54:18 +03:00
Michał Karzyński b8445401bc Add support for ONNX Crop operator (#6956) 2021-08-19 15:51:03 +00:00
Gleb Kazantaev 06d212ad83 Enable NormalizeL2Fusion and LeakyReluFusion inside MOC (#7096) 
* Enable NormalizeL2Fusion inside MOC

* Fix NormalizewL2 decomposition (KeepDims=True)
 2021-08-19 17:24:41 +03:00
Ilya Churaev e46f6ce573 Moved DEPRECATION macro and ITT domains to ov namespace (#7153) 
* Moved DEPRECATION macro and ITT domains to ov namespace

* Fixed code style
 2021-08-19 13:28:45 +03:00
Olesya Martinyuk 133b3b6468 Remove local configs and it's copying to bin/ for stress tests (#7131) 2021-08-19 12:57:47 +03:00
Liu BoandTatiana Savina 26c96a44cc add doc:'Paddle_Support.md' (#7122) 
* add doc:'Paddle_Support.md'

* Apply suggestions from code review

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Apply suggestions from code review

* Update docs/IE_DG/Paddle_Support.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
 2021-08-19 12:55:27 +03:00
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, yangandTatiana Savina 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 ShogulinandVladislav Golubev 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