Commit Graph
8637 Commits
Author SHA1 Message Date
Jan Iwaszkiewicz b44eb83551 [PyOV] Fix typo in filename generator (#13948) 2022-11-11 10:11:13 +01:00
Nikita Malinin 8e9a6d3457 [POT] BC update for transformers (#13869)
* Update node_utils

* HBC update

* Updated HBC & added test

* Apply comments
2022-11-11 11:33:11 +04:00
Xiake Sun 7ab81d0950 Add missing opset5 header for LSTMSequence in LPT (#13953) 2022-11-11 09:43:31 +03:00
OlehKravchyshyn 11d020ea06 [GPU] adjusted LWS for batch-blocked format (#13764)
LWS is adjusted to make items are fetched along batch axes in a workgroup if a layout has bsv32 or bsv16
2022-11-11 10:37:34 +04:00
Xuejun Zhai 5f1ce082ea [C API][Unite Test] Add more tests to achieve code coverage target (#13885)
* [C API][Unite Test] Add more unite test case for C API (functional level)

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [C API][Unite Test] remove unused function

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [C API][Unite Test] fix function code coverage issue

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [C API][TEST CASE] fix error

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>
2022-11-11 09:20:05 +04:00
Oleksii Khovan 71c23489c6 [GPU] Blocked layouts support for ExperimentalDetectronGenerateProposalsSingleImage (#12126)
* Blocked layouts support for ExperimentalDetectronGenerateProposalsSingleImage

* fix RHEL 8.2 build

* reduce number of tests

* Added bs_fs_yx_bsv16_fsv32 format
2022-11-10 18:03:39 -08:00
Haiqi PanandIlya Churaev 28549a77bf Fixed warnings for Auto plugin (#13810)
* fix warnings

* remove MSVC

* Update src/plugins/auto/auto_executable_network.cpp

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

* Update src/plugins/auto/auto_schedule.cpp

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
2022-11-11 04:56:54 +03:00
Jade Cho f2d5c0cb5d [GPU] Fix a bug of reorder input (#13840) 2022-11-10 17:30:30 -08:00
054eea3c5a [SAMPLES/PYTHON] Fix ACCESS_VIOLATION error when importing cv2 (#13443)
* [PYTHON] CV2 module required only when loading images

* [PYTHON] Update tools/benchmark_tool/openvino/tools/benchmark/utils/inputs_filling.py

Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>

* [PYTHON] Make CV import not global

* [PYTHON] Update format of inputs_filling.py

* [PYTHON] Fix missing newline

* Update tools/benchmark_tool/openvino/tools/benchmark/utils/inputs_filling.py

Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>

* [BENCHMARK_APP/PYTHON] Introduce exception when module is installed but fails to import

* [SAMPLES/PYTHON] Sporadic access violation fix through checking whether module was cached

Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2022-11-11 04:10:20 +03:00
OlehKravchyshyn 3443079a7b [GPU] gemm batch format support (#12474) 2022-11-10 16:01:38 -08:00
5eef0298d9 Transformation component transition to OV namespace (phase 1) (#13469)
* Move GeluFusion into ov namespace

It required to move utils as well.

* Move AddFakeQuantizeFusion into ov namespace

* Move AlignEltwiseInputRanks into ov namespace

* Move BatchToSpaceFusion into ov namespace

* Move BinarizeWeights into ov namespace

* Move BroadcastElementwiseFusion into ov namespace

* Move ClampFusion into ov namespace

* Move Concats and Eliminations into ov namespace

* Move many passes and such  into ov namespace

* Move many passes and such into ov namespace

ngraph_ops
op_conversions

* Move control_flow into ov namespace

* Apply style

* Move smart_reshape into ov namespace

* Move opset_conversions into ov namespace

* Move low_precision into ov namespace

* Apply style

* Move fused_names into ov namespace

* Add missing aliases

* Move few passes into ov namespace

ConvertPrecision
FixRtInfo
InitNodeInfo

* Move CommonOptimizations into ov namespace

* Fix convert_precision conflicting namespaces

* Apply code style

* ov-nize Type Relaxed definitions

* Remove useless aliases

bulkly added by script

* Revert opsets

* Address review comments

* Remove NGRAPH_RTTI

* Clean up remains of yet another implicit inclusion

Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
2022-11-11 02:52:19 +03:00
Roman Lyamin 4dd75a1b8b [GPU] Added Pad/Interpolate dynamic support and MVN dynamic tests (#13874)
* [GPU] Pad dynamic

* [GPU] Added MVN dynamic tests

* [GPU] Interpolate dynamic
2022-11-10 15:33:45 -08:00
Egor Duplenskii c1733b5542 [CPU][LPT] Support quantized RNN (LSTM and GRU algorithms) (#12981) 2022-11-10 23:48:51 +03:00
Anastasia Kuporosova 96d835244c [PyOV] Fix finding libs on windows (#13902)
* [PyOV] Fix finding libs on windows

* exclude install pkg dirs

* undo changes in setup.cfg

* change the logic
2022-11-10 21:32:47 +01:00
Ilya Churaev 63e24773ee Added documentation for get_layout API (#13937)
* Added documentation for get_layout API

* Fixed typo
2022-11-10 18:10:07 +03:00
Oleksii KhovanandMykhailo Hnap cf34d48e53 [GPU] MulticlassNMS (#13370)
* Single-layer test:
  - support both v8 and v9 in shared test;
  - add test for GPU.

* Transformation:
  - convert both v8 and v9 to internal operation;
  - add transformation to GPU pipeline.

* GPU primitive and CreateOp() for MulticlassNMS operation

* kernel stuff

* add unittests

* Added bs_fs_yx_bsv16_fsv32 format

* add int64 support

Co-authored-by: Mykhailo Hnap <mhnap@lohika.com>
2022-11-10 23:59:13 +09:00
Smirnova MariaandDaria Ilina 8f97ee55fc Modify time tests so that data can be pushed to OVVP (#13636)
* Set db_api_handler for pushing to new database in timetests

* Change function of pushing to db.

Co-authored-by: Daria Ilina <daria.krupnova@intel.com>
2022-11-10 15:17:39 +01:00
Anastasia Kuporosova 0942c6617b [PyOV] Add function which create unique names for test files (#13929) 2022-11-10 17:04:25 +03:00
Jan Iwaszkiewicz d6fe686237 [PyOV] Bump version of pytest for compatibility API (#13932) 2022-11-10 16:55:42 +03:00
Marcin Kusmierski 25ad4a6728 [GNA] Create new tests for PWL approximation validation (#13515)
* added tests using new validation algorithm
* consolidated fp32eq usage by introducing is_fp_eq
* refactored float to int rounding methods
2022-11-10 11:32:19 +00:00
Andrey Churkin dbb91c5e69 Minor changes to integrate AA algorithm into NNCF (#13765) 2022-11-10 13:17:50 +03:00
Roman Kazantsev e2c320a455 [TF FE] Fix translator for Rank operation and test it (#13927)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-11-10 12:33:43 +03:00
Ilya Lavrenov 473bded2b2 Compile_tool is excluded from Debian / RPM (#13911)
* Compile_tool is excluded from Debian / RPM

* Removed warnings related to compile_tool

* Removed noarch for core-dev
2022-11-10 12:30:11 +04:00
Mingyu Kim c478f7b266 Handle DT_UNKNOWN as DT_REG during file list-up (#13811)
* Handle DT_UNKNOWN as DT_REG during file list-up

Some filesystem does not return dt_type properly. (such as sshfs)
Without this fix, openvino fails to search frontend when mounted on
sshfs.

* style fix

* style fix
2022-11-10 12:21:45 +04:00
mdovbnia-lohikaandMykhailo Hnap 1b2aff95a1 [GPU] Added blocked layouts support for roi_pooling operations (#12983)
* [GPU] Added unit tests for roi polling operations.

* [GPU] Added blocked layouts support for roi_pooling operations

* [GPU] Added single layer tests for roi polling operations.

* [GPU] Fix attach roi pooling impl, remov const from formats and types

* [GPU] Fix roi polling kernel, bilinear pooling operation

* Fix, whenever output_width and output_hight are equal to 1, which cause a dividing to 0.
* Fix, for proper calculation y and x.

Co-authored-by: Mykhailo Hnap <mhnap@lohika.com>
2022-11-09 22:37:12 -08:00
Taylor Yeonbok Lee 70cc27de53 [GPU] Fake alignment for fc kernel for improve dynamic shape perf improvement (#13887)
* Fake alignment infra + fake alignment for fc kernel for improve dynamic shape performance optimization

* Applied review

* Added unittest

* Removed unused function
2022-11-09 16:46:48 -08:00
Roman Kazantsev aaefe0a256 [Common] Unique decomposition: fix the single element case (#13918)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-11-10 01:25:43 +03:00
Ilya Churaev c7cd2645f4 Fix caching tests (#13928)
* Disabled set model

* Fixed sporadic fail
2022-11-09 22:55:27 +04:00
Sebastian Golebiewski 7d651a649f DOCS: Fixing a list in Model Optimizer Extensibility - for master (#13380)
A minor fix that creates a list of main transformations responsible for a layout change.
2022-11-09 17:39:06 +01:00
Mateusz Mikolajczyk 1c03be58ff [CORE] IsFinite, IsInf, IsNan reference implementation (#13621)
* Add reference implementation for Is ops

* FIx test

* Fix typo

* Remove deprecated

* Fix issues with API switch

* Force cast to float for float16/bfloat16 in ref

* Fix style

* Remove BWDCMP_RTTI

* Remove TensorVector helper check

* Remove evaluate functions

* Disable faling tests due to missing eval
2022-11-09 19:17:26 +03:00
Sebastian Golebiewski 5a50266dd7 DOCS: Fixing formatting in Multi Device (#13292) 2022-11-09 17:02:33 +01:00
Sebastian Golebiewski 95234490c2 Updating links in Model Optimization Guide (#13303)
Adding a link to Model Optimizer.

Porting:
https://github.com/openvinotoolkit/openvino/pull/13300
2022-11-09 16:59:07 +01:00
Sebastian Golebiewski 5941490d81 Fixing indentation in General Optimizations for master (#13305)
A minor fix that corrects indentation of snippets.

Porting:
https://github.com/openvinotoolkit/openvino/pull/13302
2022-11-09 16:54:04 +01:00
Maciej Smyk 3127c28a35 DOCS: Model Conversion Tutorials fix - Port to master (#13429) 2022-11-09 18:44:36 +03:00
Anastasia Kuporosova e043dcbae7 fix markupsafe version (#13930) 2022-11-09 18:43:19 +04:00
Sebastian Golebiewski f779755d39 DOCS: Language-agnostic version of 'Changing Input Shapes' - for master (#13814)
Removing the 'global' tabs and preparing a language-agnostic version of the article. Replacing png image with a scalable svg file. Proofreading the article.
2022-11-09 15:29:10 +01:00
Liubov Talamanova 848c09336e [POT] Add GPU HW config (#13896)
* [POT] Add GPU HW config

* Add note
2022-11-09 15:13:09 +04:00
Vladimir Paramuzov e615962266 [GPU] Fixed bias fusion logic (#13845) 2022-11-09 13:24:05 +04:00
Ilya ChuraevandVladislav Golubev 9e9430e69a Fix sanitizer check (#12728)
* Fix sanitizer check

* Fixed check

* Disabled sign-compare warning

* Fixed core tests

* Fixed ieFuncTests

* Disable some CPU tests

* Additional fix for CPU plugin

* Update src/tests/functional/inference_engine/lp_transformations/disable_convert_on_const_path_transformation.cpp

Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>

* Update src/tests/functional/inference_engine/lp_transformations/disable_convert_on_const_path_transformation.cpp

Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>

* Fixed comment

* Disable warnings for windows

* Fixed build

* Fixed static build

* Fixed float16

Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
2022-11-09 12:17:22 +04:00
Ilya Churaev 22b69304e8 Disable stderr output in Release builds (#13666)
* Disable stderr output in Release builds

* Reverted TF FE changes

* Try to avoid ONNX issue

* Revert "Try to avoid ONNX issue"

This reverts commit 9c5bd7e7fa.

* Try to fix ONNX tests

* Revert "Try to fix ONNX tests"

This reverts commit b74f21baf6.

* Try to fix build

* Try to fix ONNX debug build
2022-11-09 12:16:58 +04:00
Alexandra Sidorova fedcfa8eac [Snippets] [CPU] Fixed isSuitableChildForFusingMatMul for dynamic case (#13898) 2022-11-09 11:31:17 +04:00
Xuejun Zhai 23882408c4 [C API][DOC]add doc capi reference (#13886)
* [Test] Build doc for C API reperence

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [Test] Build doc for C API reperence add C path

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [Test] Build doc for C API reperence add C path

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [C API][DOC][DOXYGEN] refact the components of C API

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [DOC][API reference] remove useless code

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [C API][DOC] Modify format to generate api reference

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

* [DOC][API reference] fix doc build error

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>
2022-11-09 11:20:32 +04:00
Ilya Churaev 63bfeb7eba Enable linker warnings as error for Windows (#13696)
* Enable linker warnings as error for Windows

* Fisable some linker warnings

* Suppress warnings

* Fixed build

* Change if opset

* Try to fix some warnings

* Revert some changes

* Try to fix warning

* Define OpenVINO static library for static libraries
2022-11-09 11:19:36 +04:00
Ilya Churaev 9eb4878d01 Added doxygen comment for opset10 (#13919) 2022-11-09 10:41:59 +04:00
Kelvin Choi bf8a2b6503 [GPU] Update Select Op to use ngraph shape infer (#13565) 2022-11-08 22:30:41 -08:00
Zhang Yi 46cf87f467 [CPU]Decompose Logsoftmax (#13679) 2022-11-09 09:01:37 +03:00
Mateusz Tabaka 3077b45995 [Pruning] propagate mask through Split and VariadicSplit (#13506)
Ticket: 88441
2022-11-09 06:37:41 +01:00
Sungeun Kim 7cf727cb26 fuse reorder to next conv (#13683)
-in_fmt:bfyx, out_fmt:b_fs_yx_fsv16, bs_fs_yx_bsv16_fsv16
-shallow input conv
2022-11-09 13:52:26 +09:00
Min, Byungil 0e486c1b9b [GPU] Reduce overhead in device_query (#13200)
+ Reduced overhead of is_local_block_io_supported in ocl_device
+ Updated hash_value in kernels_cache

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-11-09 11:59:52 +09:00
cecilia peng 3bdb9cae54 [CPU] add support for internal ops augrucell and augrusequence (#12647)
* [cpu] enable augru.

* initiate opset_private_tbl.hpp for private ops.

* fix ngraph_functions target_linker.

* temporaliy disable a failure test.
2022-11-09 05:58:04 +03:00