Commit Graph

8873 Commits

Author SHA1 Message Date
Mykhailo Hnap
4e519eb110
[GPU] Implement GridSample-9 (#13460)
* [GPU] Implement GridSample-9

* [GPU] Implement kernel GridSample-9

Co-authored-by: ozhydkov-lohika <ozhydkov@lohika.com>
2022-10-31 13:16:27 -07:00
Irina Efode
53c9197354
Enable call set_device_name (#13340)
* [IE TESTS] Using Gflags instead of parsing command-line options

* Apply infra for suffix

* remove extra

* Squashed commit of the following:

commit c249f5d581
Author: iefode <irina.efode@intel.com>
Date:   Thu Oct 6 11:56:11 2022 +0400

    Fix default values for command-line argument

commit b2dbb4418c
Author: iefode <irina.efode@intel.com>
Date:   Wed Oct 5 18:09:22 2022 +0400

    rename gflags config

* Fix errors

* Remove gflag using

* Remove gflags

* Remove extra

* fix build
2022-10-31 14:06:56 +03:00
Artur Kulikowski
0aeb3d8151
Add ONNX model metadata to ov::Model (#13712)
* Add ONNX model metadata to ov::Model

* Add correct path to onnx models
2022-10-31 08:15:26 +01:00
Xuejun Zhai
af5e06bb8b
[C API] fix warning as error issue (#13671)
Signed-off-by: Zhai <xuejun.zhai@intel.com>

Signed-off-by: Zhai <xuejun.zhai@intel.com>
2022-10-31 04:57:58 +03:00
Sungeun Kim
eeabb86b80
[GPU] set bfyx to input format for shallow conv (#13614)
* set bfyx to input format for shallow conv
2022-10-31 10:22:39 +09:00
Taylor Yeonbok Lee
454bc61018
Fix error in perpare_buffer_fusing w.r.t accessing invalid output layout (#13723) 2022-10-29 00:00:09 -07:00
Anastasia Kuporosova
bb296fcb11
[PyOV] some fixes and improvements in python tests (#13656)
* [PyOV] mark device dependent test

* fix assert in test

* fix assert error
2022-10-29 08:00:49 +02:00
Eddy Kim
daec2605e4
[GPU] changing references to pointers for GPU graph serialization (#13559)
* cldnn serialization

* read layout from _impl_param instead of node

* changed ref in kernel_impl_param to pointer

* removed serialization utils

* removed serialzation related changes

* restored references in function arguments

* remove trailing spaces

* revert change in bs_x_bsv16

* fix to rebase
2022-10-29 04:39:51 +03:00
Sun Xiaoxia
0e60489df4
fix performance degradation on windows platform (#13705) 2022-10-29 02:57:18 +03:00
Georgy Krivoruchko
1a35726f51
Changed behavior of SubgraphDumper in case of Constans (#13678) 2022-10-29 01:51:13 +04:00
Roman Kazantsev
22de883e6e
[Core] Fix leftovers from PR13581 (#13693)
* [Core] Fix leftovers from PR13581

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

* Revert incorrect change for shrink axis

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-10-28 23:15:27 +03:00
Irina Efode
04f09ba0c0
Fix Warning in ARM Post-Commit build (#13689)
* Fix ARM Post-Commit build

* Update locale.cpp

* test

* revert

* Remove format-truncation skip

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
2022-10-28 19:21:13 +04:00
Sergey Shlyapnikov
6c6b3666a4
[GPU] Add additional condition for VA surface buffers detection (#13691) 2022-10-28 18:19:02 +03:00
Evgenya Stepyreva
cd76557df5
Make Resize Bilinear infer in f32 (#13650) 2022-10-28 18:26:14 +04:00
Artyom Anokhov
769d87b400
debian.cmake: Suppress openvino_latest ubu18 description-starts-with-package-name error (#13714) 2022-10-28 16:38:16 +04:00
Krzysztof Bruniecki
7196a0cfd2
[SAMPLES] Remove unneeded GNA clock multiplier in performance counters (#13657) 2022-10-28 13:43:25 +02:00
Ilya Churaev
578df5486a
Kill old actions in case of new changes (#13700)
* Kill old actions in case of new changes

* Some new changes

* Revert redundant line
2022-10-28 15:16:46 +04:00
Ilya Churaev
d80636c56c
Try to suggest clang format changes (#13685)
* Enable reviewdog for clang-format

* Change pipeline

* Add github tocken

* Revert "Add github tocken"

This reverts commit dfe759a56d.

* Revert "Change pipeline"

This reverts commit e7908202e9.

* Fixed code style
2022-10-28 15:15:49 +04:00
Ilya Churaev
fa50e35bb8
Extended error messages (#13647) 2022-10-28 15:14:23 +04:00
Bartek Szmelczynski
464e0aae72
Support Unsqueeze-13, Squeeze-13 in MO (#13391) 2022-10-28 13:01:21 +02:00
Evan
6913a8ad39
Docs: Rewrite "Install OpenVINO Development Tools" page (#13348)
* docs: rewrite intro section

* docs: finish updates

* docs: minor updates

* docs: add that Python is recommended for new users

* Update docs/install_guides/installing-model-dev-tools.md

* Update docs/install_guides/installing-model-dev-tools.md

* Update docs/install_guides/installing-model-dev-tools.md

* Update docs/install_guides/installing-model-dev-tools.md

* Update docs/install_guides/installing-model-dev-tools.md

* Update docs/install_guides/installing-model-dev-tools.md

* Update docs/install_guides/installing-model-dev-tools.md

* Update docs/install_guides/installing-model-dev-tools.md

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
Co-authored-by: Maciej Smyk <maciejx.smyk@intel.com>
2022-10-28 18:09:39 +08:00
Ilya Churaev
eb936e9f34
Fixed build (#13701)
* Fixed build

* Change if opset
2022-10-28 11:35:24 +04:00
Min, Byungil
6ffaa393d5
[GPU] Remove WA for cldnn Reduce fallback (#13663)
+ Use oneDNN reduction when it has fused eltwise

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-10-28 16:23:02 +09:00
Krzysztof Bruniecki
fdd047edb9
[GNA] Fix offset and size computation for Crop (#13400)
Fix GetCropParams
    Add test to reproduce crop isue from ticket
    Use convolution in the test
    Cleanup get dim getters using backoffset
2022-10-28 08:46:19 +02:00
Sebastian Golebiewski
cc1dd0bf1a
Updating the large_batch_approach.svg image (#13704)
Uploading a new version of the image.
2022-10-28 08:24:29 +02:00
Sebastian Golebiewski
cf54cbafac
DOCS: Improving Readability of Further Low-Level Implementation Details - for master (#13522)
* Improving Readability of Further Low-Level Implementation Details

The changes include recreation of the graphics to improve the readability of the article. Minor proofreading corrections have been applied as well.
2022-10-28 07:26:06 +02:00
yanlan song
3f4c53a779
Bell/fix priority (#13667)
* debug only

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

* fix model priority with -d AUTO

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

* add tests

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

Signed-off-by: fishbell <bell.song@intel.com>
2022-10-28 04:58:25 +03:00
Paul Youngsoo Ahn
694d2f73eb
[GPU] Range new shape infer (#13582) (#13582)
- move dynamic functional tests to dynamic folder
2022-10-27 18:29:49 -07:00
Taylor Yeonbok Lee
33c230a40d
Fix reshape calc_output_layout failure in squeeze shape_infer test. (#13698)
Failure: Comparing reshape->output_shape with a new tensor() object was not working as intended.
Since the original intention was to check whether cldnn::tensor type output_shape is set or not,
so replaced the comparision to use size of the output_shape.
2022-10-28 04:17:44 +03:00
Ivan Tikhonov
8714cf643e
Fix UnrollIf transformation to support nested If (#13654)
* Added a recursive call into UnrollIf transformation to support nested If unrolling
2022-10-28 03:49:52 +03:00
Egor Duplenskii
7e2cefab8a
[CPU] Move to oneDNN v2.7 (#12281) 2022-10-28 01:40:07 +03:00
Luo Cheng
4ec5499c5d
[FrontEnd] add control flow, basic tensor array support for paddle faster_rcnn model (#10684)
* support control flow, tensor array

* fix clang error

* support ppdet2.3 model

* 1. code clean; 2. more comments inlined.

* fix after clone ov::Model no more in need.

* support dynamic shape; more comments

* only process same rank

* remove unused function

* simplify the loop logic

* fix review comments

* support shape{1} {}

* disable FoldSubgraphEmptyInputs because loop in loop

* fix review comments

* remove scalar{}->shape{1} testcase

* allow re-infer shape when backedge changes input shape

* fix condition shape to {1}

* support output rank is not same or dynamic

* fix refactor error

* apply review comments

* fix win warnings

* remove TransformEliminateConvert

Co-authored-by: jialipen <cecilia.peng@intel.com>
Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
2022-10-27 18:36:24 +03:00
Ilya Lavrenov
fbd6d14c3b
Several fixes for compilation fixes (#13674)
* Added i386 support

* Cross-compiled wheel package

* Fixes

* Try to use cross-env

* Fixed path to crossenv

* Strict dependency

* Removed numpy dependency

* explicitly activate crossenv

* Don't install ONNX for tests conversions during cross-compilation

* Updates

* Extra improvements

* Fixed compilation with strict flags

* Fixes

* Revert changesin .ci/azure/linux_arm64.yml
2022-10-27 17:30:24 +04:00
Ilya Churaev
84710e4440
Bump CMake for Linux Azure (#13652)
* Bump Cmake for Linux

* Fixed environment

* Change CI script

* Disable some warnings

* Fixed compiler flag

* Enabled Warnings as error for Linux

* Revert "Enabled Warnings as error for Linux"

This reverts commit bfb09efb71.

* Use prebuild cmake

* Remove redundant check
2022-10-27 17:08:56 +04:00
Maciej Smyk
44b75c727c
Update dl_workbench_overview.md (#13681) 2022-10-27 14:42:56 +02:00
Roman Kazantsev
d53c2c5e41
[DOCS][MO] Clean-up MO docs sources (#13641)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-10-27 16:06:18 +04:00
Oleg Pipikin
ad1c824e50
Eliminate reader tests (#13409)
* remove reader tests #1

* remove reader tests #2

* remove reader tests #3

* remove reader tests #4

* Add clone_with_new_inputs to visitor tests

* fixes
2022-10-27 14:42:23 +03:00
Liubov Talamanova
ee93ddc453
Update references (#13637) 2022-10-27 10:55:54 +00:00
Irina Efode
dcd3ed18f6
Update third-party-programs according PM requirments (#13610) 2022-10-27 13:39:20 +04:00
Pawel Raasz
d96c25844d
Review opset1 unsqueeze for shape inference aspects (#13538)
* Use non-blocking assertions in unsqueeze tests
for independent properties

* Review unsqueeze interval shape propagation:
- extend partial shape propagation tests
- add invalid axis value tests
- fix issues when repeated axes on input

* Shape inference test, unsqueeze using default ctor
- private fields set by setters

* Review unsqeeze bounds propagation:
- preserve and propagate labels
- bounds propagation lowe/upper

* Add template shape inference for unsqueeze
- extract current implementation and unify it for shape types
- add unit test for static shape inference
- add unsqueeze in/out indexes

* Unify axes normalization

* Use common fixture for static shape inference

* Fix build issue in GPU plugin
- include unsqueeze shape inference

* Remove enum with in/out indexes
Due to build issue on Windows

* Remove make move iterator
minor changes validation util

* Add test for label propagation
- expand static shape inference tests

* Add common validation for axes input

* Fix build issues

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
2022-10-27 10:28:24 +03:00
Maciej Smyk
d8f7e791ec
DOCS: Port from 22.2 - Security Add-on directive fix (#13261)
* Update ovsa_get_started.md
2022-10-27 08:25:45 +02:00
Artyom Anokhov
65293b1492
Added frontends RPMs generation (#13618)
* cmake/packaging/rpm.cmake: Added Frontends

* rpm_post_build: Added link to Fedoraproject wiki with rpmlint errors info

* RPM: Throw warning for rpmlint findings instead of FATAL ERROR till there is no filtering/suppression of errors

debian.cmake: Added one more error to suppress
thirdparty/CMakeLists.txt: added CentOS(RHEL) for gflags shared libs case
install_openvino_dependencies: Added gflags installation

* Fixed gflags issues for RHEL/CentOS

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-10-27 10:08:54 +04:00
Taylor Yeonbok Lee
728c9631b7
Dynamic shape : remaining changes to run bert (#13306)
* Initial dynamic shape smoke test for GPU

* Bert dynamic runs without crash

* Additional fix to resolve error in bert-large-uncased-whole-word-masking-squad-emb-0001

* Fix error in unfusion function: input nodes of the current (fused) node need to be updated with the latest dependency if they are fuesed to other nodes

* Several fixes
(1) Fix program to clear _kernels after all build_program steps finished
(2) Fix update_kernel not to init_kernel when impl_cache hit
(3) Fix update_kernel to clear kernels_cache::_kernels after adding the new impl to impl_cache
(4) No longer need to remove kernel from kernels_cache::_kernels after the corresponding impl is dropped from impl_cache

* Fix crash of bert_emd_4layer

* Applied review comment

* Applied review comment : fix add_required_reorder

* Fix broadcast to propagate dynamic shape properly & reverted change on constant

* Added a new unfusion unittest

* Fix broadcast single input case to use predefined shape properly

* Fixed count_non_zero output to result only one element of count

* Removed output_layout str for gather_nonzero
Removed unused ov_input_rank for count_nonzero

* Fixed create_host_blob to use usm if the target layout is not dynamic.
(Previous impl has an error when the network is dynamic but the output is static)
Moved dyn shape smoke test under dynamic directory

* Fix lint error
2022-10-27 07:20:18 +03:00
Kelvin Choi
a7a14a89c8
[GPU] Support dynamic shape for one-hot and reshape operations (#13516) 2022-10-26 17:12:17 -07:00
Mateusz Tabaka
154850e8ca
Eliminate dequantization shift when zero point == 0 (#13353)
Ticket: 91111
2022-10-27 01:37:13 +02:00
Alexey Lebedev
554af81085
[tools][benchmark_app] --extensions parameter (#11289)
* Replace -l and -c by --extensions

* revert -c

Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
2022-10-26 23:26:51 +02:00
Pawel Raasz
dd11d57fc5
Fix core tests warnings as errors and ONNX CI (#13648)
* Fix gather type_prop test build issue on windows

* Add pytest-forked to test requirements

* Update src/bindings/python/requirements_test.txt

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

* Remove warning suppression for core tests

Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
2022-10-26 22:14:25 +03:00
Irina Efode
92300d641d
[CONFORMANCE] Fix Gelu op in the report && opset10 to all slt related files (#13596)
* [CONFORMANCE] Fix Gelu op in the report && opset10 to all slt related files

* Remove debug code

* fix defines
2022-10-26 18:18:55 +03:00
Irina Efode
9adbbfb98f
[API CONFORMANCE] Remove skips from ie_executable_network (#13574)
* Remove skpps from ie_executable_network

* fix heder file

* fix build
2022-10-26 17:53:49 +04:00
OlehKravchyshyn
dc1a8b7795
[GPU] added optimized blocked formats support for 5d interpolation liner onnx and nearest modes (#12977)
This commit contains two features which are split into two commits:
1) linear onnx interpolation of 5d formats
2) Optimize blocked formats for linear_onnx and nearest formats
   - contain correspondent unit and single layer tests
2022-10-26 21:53:38 +09:00