Commit Graph

9096 Commits

Author SHA1 Message Date
Jade Cho
7904b34679 [GPU] Fix a bug to not apply f-axis offset to oneDNN concat (#14595) 2022-12-13 20:28:53 +09:00
Sebastian Golebiewski
bda7227502 post-merge corrections (#14603)
Fixing link to python downloads
Minor grammatical error corrected
Updating software license disclaimer

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-12-13 11:49:24 +01:00
Sebastian Golebiewski
f3964bcea0 DOCS: Proofreading OpenVINO Extensibility for 22.3 (#14510) 2022-12-13 11:19:26 +01:00
Maciej Smyk
8f13a77a15 DOCS: Quantization doc rewrites - port to 22.3 (#14514)
* Update introduction.md
* header fix
* graph-fix
2022-12-13 09:51:12 +01:00
Karol Blaszczak
97ae79fe80 DOCS-menu_recreate_structure_step4 (#14584)
documentation section tweaks
create deployment section for further tweaks
API reference moved
compile tool moved
2022-12-13 08:12:41 +01:00
Maciej Smyk
ed5e237403 Target Operating Systems with Python Version fix (#14568) 2022-12-13 12:24:34 +08:00
mei, yang
7338f4b049 update paddle supported ops (#13923) (#14490)
* update paddle supported ops

* remove paddle tensor array related ops

* remove version information in paddle supported op name

* Update docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

* Update docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

* Update docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md

* Update docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-12-13 11:53:29 +08:00
Wilson Seok
288b5326cb fix PR14422 regression for using arg_max_min opt kernel (#14487) (#14533) 2022-12-12 16:10:00 -08:00
Ilya Lavrenov
6f5edfa942 Adjusted pypi supported OS matrix (#14546) 2022-12-13 01:35:16 +04:00
Maksim Kutakov
ad0ef56665 [CPU] Fix for the convolution node dummy shapes generation (#14521) 2022-12-12 23:08:15 +04:00
Artyom Anokhov
7e1b9353d5 [Deployment Manager Configs] Updated with actual 2022.3.0 structure (#14585) 2022-12-12 22:23:11 +04:00
Pavel Esir
ece291a246 Revert "[IE] keep constants in shape subgraphs in f32 (#14204)" (#14457)
This reverts commit e648001b

Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
2022-12-12 18:10:41 +04:00
Karol Blaszczak
669d35b3e6 DOCS-menu_recreate_structure_step3 (#14574)
Adjusting the benchmarks structure
Restructure menu and adjust content for benchmarks and getting performance numbers
2022-12-12 14:55:46 +01:00
Vladimir Paramuzov
12b019e027 [GPU] Fixed invalid offset for tensor with batch padding (#14459) 2022-12-12 17:37:38 +04:00
Zlobin Vladimir
b07fea664f build_samples.sh: detect cmake3 for CentOS (#14562)
Close https://github.com/openvinotoolkit/openvino/issues/14553
2022-12-12 17:23:56 +04:00
Karol Blaszczak
4f9a8757c8 Docs menu lvl1 expand script (#14567)
* JS for expanding menu lvl1
Script by Kasia Bojarowska
2022-12-12 13:59:26 +01:00
Sebastian Golebiewski
12afd97e14 FaceNet (#14507) 2022-12-12 13:12:22 +01:00
Sebastian Golebiewski
9183d96394 lm_1b (#14506) 2022-12-12 13:10:31 +01:00
Sebastian Golebiewski
2d0f8b4f27 NCF_start images (#14505) 2022-12-12 13:07:39 +01:00
Sebastian Golebiewski
05d8648854 image-fix (#14504) 2022-12-12 13:04:44 +01:00
Sebastian Golebiewski
3914fd8aa8 DOCS: Image fix cutting models - porting #13853 to 22.3 (#14501)
* image fix
2022-12-12 11:21:39 +01:00
Vladislav Golubev
4911f80f37 [CPU] Convolution shape inference fix (#14550) 2022-12-12 13:59:14 +04:00
Roman Kazantsev
53265f0097 [ONNX FE] Support value freezing without specifying type (#14481) (#14554)
* [ONNX FE] Support value freezing without specifying type

Implement gete_element_type method for ONNX InputModel.
Implement tests with freezing integer input and float models

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

* Update src/frontends/onnx/frontend/src/input_model.cpp

Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>

* Update src/frontends/onnx/frontend/src/input_model.cpp

Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>

* Update src/frontends/onnx/frontend/src/input_model.cpp

Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>

* Return only element type for model inputs and add ONNX FE tests

* Rename variable in the test

* Add syntax mark

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
2022-12-12 10:53:52 +04:00
Karol Blaszczak
3dd6b50bff Docs menu recreate structure step2 (#14551)
model optimization
deploy locally
run inference
remove OVSA from security (it was duplicated)
2022-12-11 14:30:00 +01:00
Sebastian Golebiewski
9b8ab44500 DOCS: Reintroducing APT and YUM installation methods for 22.3 (#14492)
* reintroducing apt and yum

* fix indents and create tabs

fixing indent in apt
creating tabs in yum article

* Update installing-openvino-yum.md

* tabbed content

Inserting installation steps into tabs.
Correcting formatting.

* correcting indents

* correct indent

* indent fix

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

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

* removing non-cpu dev

Removing GNA, NCS2, VPU from Step 5 in YUM article.
Correcting links to Python.

* add apt and yum for installation

* revising openvino-dev installation

* removing opencv from apt

* remove opencv from yum

* removing non-cpu devs

* Update installing-model-dev-tools.md

* update disclaimer

* openvino development tools

correcting the name

* build samples sections

* add architecture

* remove install details yum

* remove install details apt

* reflink fix

* removing ncs2

* add dependencies

* install parametere

* move note

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-12-09 22:03:29 +04:00
Mateusz Bencer
7e87923f0c Added support of custom domain for OpExtension (C++/Python) and ConversionExtension (Python) (#14523) 2022-12-09 15:01:07 +01:00
Eddy Kim
083a17e89e [GPU] Updated to get lockable memories for device inputs in prepare_input() (#14532)
* updated to get ockable memory for device inputs

* gpuFuncTest to set f64 scalar tensor

* aligned type names

* updated to get lockable memory for some specific precisions
2022-12-09 17:00:32 +04:00
Anastasiya(Asya) Pronina
67bbc7361c Extended speech_sample to work on VPUX (#14508) 2022-12-09 15:27:20 +04:00
Artyom Anokhov
0121921068 Added ocl-icd for ubi8 image (#14525)
* install_openvino_dependencies: Added ocl-icd for ubi8 image

* install_openvino_dependencies.sh: Added json-devel to pkgs_dev for ubi8

* install_openvino_dependencies: Added pkgconf-pkg-config to pkgs_dev

* install_openvino_dependencies: Moved pkgconf-pkg-config to high-level pkgs_dev

* install_openvino_dependencies: Fixed with case for centos7

* Update scripts/install_dependencies/install_openvino_dependencies.sh

applied comments

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-12-09 14:11:56 +04:00
Roman Kazantsev
5cfc3cbf5d [TF FE] Break the cycle in the different way (#14480) (#14518)
* [TF FE] Break the cycle in the different way

Earlier solution was incorrect due to inproper handling of forward edges cases
(edges going from parent to grand-child) for which topological sorting
of nodes can be interrupted.

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

* Break the cycle by NextIteration inputs

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

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-12-09 10:28:38 +04:00
Karol Blaszczak
85506f263c Docs menu recreate structure step1 port (#14527)
* Initial TOC config

TOC depth
prev-next btn
TOC initial links

* extensibility section

header changed to section
section populated

* media processing and CV lib

header changed to section
no content in the node article... needs to be added later

* openvino security

header turned into section
intro article used as the section parent

* ecosystem

header turned to section
section populated

* menu padding adjustment

* benchmarks and release notes

benchmarks moved to resources
release notes moved to top level
case studies link

* OpenVINO IR

IR articles put in a section
the parent article will require more content
2022-12-09 08:23:09 +08:00
Ilya Lavrenov
36c6d58fb2 Added extra dependencies for debian / rpm packages (#14528) 2022-12-09 03:49:45 +04:00
Zlobin Vladimir
690a10c386 samples/cpp/build_samples_msvc.bat: don't ignore cmake error (#14499) (#14524)
Ticket 98429
2022-12-09 03:47:52 +04:00
Artemy Skrebkov
bceb7dbfe1 Fix segfault on windows with MSVC (#14517)
* MSVC compiler cannot handle copying empty AnyMap
2022-12-08 21:00:07 +04:00
Roman Kazantsev
57d8e96a30 [TF FE] Support dynamic shape Placeholder freezing and PlaceholderWithDefault (#14450) (#14482)
* [TF FE] Support dynamic shape Placeholder freezing and PlaceholderWithDefault

Also, this PR contains reorganization of python unit tests for TF FE that
covers conversion and inference of different models in pbtxt.
This mini-infrastructure will be used in the future for TF FE support.

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

* Revert debug info

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

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-12-08 17:43:22 +04:00
Alexandra Sidorova
2d072e8129 [CPU] Fixed segfault in Generic node creation for dynamic models (#14488) 2022-12-08 17:13:34 +04:00
Zlobin Vladimir
36ab5c2192 Update OMZ submodule (#14471)
* Update OMZ submodule

This update includes models publication for 2022.3
Tickets 95909 and 95910

* Update OMZ submodlue: remove numpy upper bound
2022-12-08 11:26:07 +00:00
Vladimir Paramuzov
afa9bdde93 [GPU] allow softmax_bf for axis=Y && X==1 case (#14461) 2022-12-08 14:10:48 +04:00
Vladimir Paramuzov
970d53b420 [GPU] Use transformed gemm shapes for layout optimizer checks (#14462) 2022-12-08 14:10:38 +04:00
Anastasiia Pnevskaia
633fe397a3 Fixed type check in convert_model(). (#14477) 2022-12-08 13:54:35 +04:00
Anastasiia Pnevskaia
5c33eff533 Fixed double printing of errors in MO. (#14474) 2022-12-08 12:46:22 +04:00
Xiping Yan
8680791ffe [CPU] Fix conditional compilation for oneDNN brgemm Convolution primitive 2022-12-08 12:06:41 +04:00
Ilya Lavrenov
edb3f3e820 Expose IE_THREAD definition to end users (#14476) 2022-12-08 12:05:42 +04:00
Karol Blaszczak
0eebb124c9 DOCS-top-menu-items_port_22.3 (#14465)
create top menu navigation
tweak css to display navigation properly
2022-12-07 19:34:42 +01:00
Karol Blaszczak
cc886509c6 Update benchmarks articles (#14438) (#14464)
Update performance_benchmarks_faq.md
Update performance_int8_vs_fp32.md
2022-12-07 11:20:43 +01:00
Karol Blaszczak
a9ad74b690 DOCS- add telemetry info page (#14463) 2022-12-07 11:15:24 +01:00
Andrey Babushkin
6947916541 Update branch to take other repos from for Azure pipelines (#14447) 2022-12-06 22:46:21 +04:00
Irina Efode
eb19a7f7ad [CONFORMANCE] Fix condition for WIN in Conformance runner (#14441) 2022-12-06 20:14:05 +04:00
Tomasz Dołbniak
6da95784c7 Unique-10 tests and improvements (#14315) 2022-12-06 19:09:30 +03:00
Luwei Zhou
79f04a704c [CPU] Extend AMX deconv int8 to support oscale+eltwise+eltwise post ops pattern (#14026)
* Extend AMX deconv int8 to support oscale+eltwise+eltwise post ops pattern.

* Add deconv AMX test cases.

* Add multi-eltwise test on deconv AMX int8.

* Applied review comments.

* Update onednn submodule.
2022-12-06 18:32:02 +04:00