Ilya Lavrenov
19c2ec068a
Updated exclude patterns for nlohmann json ( #13858 )
2022-11-04 21:26:14 +04:00
Alexandra Sidorova
cbf037b9a8
[Snippets] Fixed SnippetsMarkSkipped for dynamic branches ( #13751 )
2022-11-04 16:15:19 +04:00
Sungeun Kim
f1cf1948d5
[GPU] add errata for onednn layout selection ( #13758 )
2022-11-04 15:44:36 +04:00
Pawel Raasz
0646d49d35
Review opset1 squeeze for shape inference aspects ( #13716 )
...
* Review squeeze operator for
- label preserve and propagation
- partial values preserve and propagation
- interval shapes propagation
* Review static shape inference tests
* Add template shape inference for squeeze
* Update include for OV_EXPECT_THROW
* Correct has_static_axes initialization
* remove test_squeeze from xfail 44968
* Fix inference parameter op with no data
- add additional test to check if axes are parameter without data
- revert xfail marks for squeeze tests
* Fix inference parameter op with no data
- add additional test to check if axes are parameter without data
- revert xfail marks for squeeze tests
* Refactor axes acquire logic
2022-11-04 13:42:05 +03:00
Zlobin Vladimir
28a118be39
Apply improvements I found during https://github.com/openvinotoolkit/openvino/pull/13388 ( #13743 )
2022-11-04 14:41:15 +04:00
Zlobin Vladimir
65f83b591e
benchmark_app: --latency_percentile: don't list all values ( #13799 )
...
Ticket 95243
2022-11-04 13:53:05 +04:00
Artur Kulikowski
a48d1558e3
ONNX: Throw exception if attribute reduction is used in ScatterND or ScatterElements ( #13778 )
...
* ONNX: Throw exception if `reduction` attribute has unsupported value
Operators:
- ScatterND
- ScatterElements
2022-11-04 10:40:14 +01:00
Tomasz Adamowicz
5f0b063455
[GNA] Support GNA 3.5 (MTL) target in OV ( #13478 )
...
* Enable TLV
* [GNA] Add smoke test for Conv with padding on MTL
* [GNA] Allow skipping tests based on gna lib version
Co-authored-by: Krzysztof Bruniecki <krzysztof.bruniecki@intel.com> 🥇
2022-11-04 10:26:22 +01:00
Vladimir Paramuzov
8b93e3f2ec
[GPU] Ability to compile OV with OCL 1.2 ( #13706 )
2022-11-04 12:31:01 +04:00
Liubov Talamanova
8789fcda04
[POT] Propagate FQ through Gather ( #13583 )
...
* Add Gather to QUANTIZE_AGNOSTIC_OPERATIONS
* Add test
* Update HW configs path in tests
* Fix tests
* Update CI references
2022-11-04 12:21:20 +04:00
Tingqian Li
f34f35bfc7
[CPU] Enable scratchpad user mode for oneDNN based nodes ( #12038 )
2022-11-04 11:10:26 +03:00
Roman Kazantsev
de687650d2
[TF FE] Fix output names list for meta format ( #13828 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-11-04 11:40:59 +04:00
avoskoboinyk-lohika
6fc23b4768
[CPU] Optimize DFT operation ( #11946 )
2022-11-04 09:46:46 +03:00
Taylor Yeonbok Lee
e9e3044d99
Fix error in calling is_dynamic ( #13769 )
2022-11-04 09:31:41 +03:00
Evan
f1fe3a2f65
Docs: Update "Install OpenVINO Runtime on Windows from Archive File" page ( #13332 )
...
* docs: big update to Windows archive install steps
* docs: apply correct note format
* docs: add link to archives
* docs: minor update
* docs: change archive download link to GitHub
* Update docs/install_guides/installing-openvino-from-archive-windows.md
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
* docs: typo fix
* docs: minor change
* docs: remove "For Python developers" in Software tab
* docs: fix curl command
* docs: clarify that archive install is for C++ users
* docs: add link to PyPI page
* docs: Change back to numbered instructions
* Update docs/install_guides/installing-openvino-from-archive-windows.md
* Update docs/install_guides/installing-openvino-from-archive-windows.md
* Update docs/install_guides/installing-openvino-from-archive-windows.md
* Apply suggestions from code review
* Update installing-openvino-from-archive-windows.md
* Update docs/install_guides/installing-openvino-from-archive-windows.md
* Update installing-openvino-from-archive-windows.md
* Update installing-openvino-from-archive-windows.md
* Update installing-openvino-from-archive-windows.md
* Update docs/install_guides/installing-openvino-from-archive-windows.md
* Update installing-openvino-from-archive-windows.md
* Update installing-openvino-from-archive-windows.md
* Update installing-openvino-from-archive-windows.md
* Update installing-openvino-from-archive-windows.md
* Update docs/install_guides/installing-openvino-from-archive-windows.md
* Update docs/install_guides/installing-openvino-from-archive-windows.md
* Update installing-openvino-from-archive-windows.md
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-11-04 09:01:24 +03:00
Ilya Lavrenov
87f61cf822
Added per component copyright files for debian / rpm ( #13833 )
2022-11-04 08:15:00 +04:00
Roman Kazantsev
954b9d3149
[TF FE][Tests] Add layer tests for SegmentSum and DynamicPartition in the pre-commit ( #13812 )
...
After fixes for TopK and arithmetic operations for integer tensors, we are ready to switch
these tests in the pre-commit
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-11-04 05:02:48 +03:00
Mikhail Ryzhov
7a6960b2f4
[GNA] Added support of the all log levels ( #13359 )
...
* Added GNA logger
* Added GNA logger class
* Replaced old looger by the new one
* Added support of the all log levels in the tests
* Renaming
* fixed cpplint issue
* Reduced error level
* fixed cpplint issues
* Fixed linking error
* Fixed linux build
* Rebase fix
* Removed unused code
* Fixed compile issue after rebase
* Aligned code usage and style
* Fixed default constructor
* Fixed test
* One more rebase
* Added exveption test
* Fixed the old logging tests
* restored static constants
* Removed dublicated log messages
* Removed incorrect log::level comparation
* Fixed generic api test
* Rebased
2022-11-04 04:58:01 +03:00
yanlan song
b04624766e
Bell/conditionally enable threadingtests for getavailabledevices ( #13772 )
...
* passthrough cache_dir for auto/multi
Signed-off-by: fishbell <bell.song@intel.com>
* enable tests for certain glibc version
Signed-off-by: fishbell <bell.song@intel.com>
* Revert "passthrough cache_dir for auto/multi"
This reverts commit 58591a1bce
.
* clean up
Signed-off-by: fishbell <bell.song@intel.com>
* apply the review comment
Signed-off-by: fishbell <bell.song@intel.com>
Signed-off-by: fishbell <bell.song@intel.com>
2022-11-04 02:45:23 +03:00
Jan Iwaszkiewicz
9f2489941f
Bump pybind11 to v2.10.1 release tag ( #13793 )
...
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-11-04 02:12:47 +04:00
Przemyslaw Wysocki
1cc499429a
[PyOV] Upgrade ONNX to 1.12.0 ( #12847 )
...
* Refactor tests for onnx1.12
* Fix ONNX compatibility and numpy warnings
* Upgrade ONNX to 1.12 in cpp
* Skip unsupported ops
* Revert "Fix ONNX compatibility and numpy warnings"
This reverts commit cd8a0e6b8e
.
* Small changes
* Remove unnecessary changes
* Bump Python version in github workflows
* Fix flake error
* Another flake error
* Even more flake errors
* Xfail more tests
* Fix mypy errors
* Change onnx version in tests
* Bump ONNX in MO
* Fix onnx utils in comp
* Minor changes
* Import pathlib
* Add xfails to compatibility tests
* Skip segfaulting tests
* Fix onnx nametuple
* Fix flake
* Try to fix py3.6 onnx
* Fix model importer and reqs
* Add __test__
* Bump OMZ commit
* checkout omz
* Revert omz
* Bump omz
* Bump omz
* Revert omz
* Bump omz
* Change pychecks python version
* Add LayerNorm to expanded ONNX functions
* Apply clang
* Move LayerNorm tests to skip_segfault
* Refactoring
* Minor changes
* Minor changes
* Relax MO reqs
2022-11-03 22:56:57 +04:00
Roman Lyamin
6c7f1f8792
[GPU] Fix performance drop on new API ( #13767 )
2022-11-03 18:34:14 +04:00
Vladimir Paramuzov
ced0eebd13
[GPU] Silence ocl include pragma message ( #13789 )
2022-11-03 18:02:23 +04:00
Ilya Lavrenov
e30a935e6f
Removed conda option from python build ( #13819 )
2022-11-03 15:07:20 +04:00
Roman Lyamin
2b5dd4fac8
[GPU] Pooling refactoring ( #13664 )
2022-11-03 14:53:32 +04:00
Ilya Lavrenov
c11389fa18
Fully define product version in cmake ( #13802 )
2022-11-03 14:22:46 +04:00
Denis Kotov
c949152a43
Added -DDNNL_ENABLE_EXCEPTIONS for Debug build ( #13672 )
2022-11-03 10:01:10 +01:00
Egor Duplenskii
41866ea51a
[CPU][CORE] Move to the most recent xbyak version ( #13753 )
...
Current xbyak has "unresolved external symbols" issue
when built on Windows in 'Debug' (-O0) build type
The issues is fixed in the recent xbyak versions
2022-11-03 12:03:30 +04:00
Ilya Lavrenov
3de3e7b8fa
Updated zlib to be 1.2.13 ( #13803 )
2022-11-03 10:10:41 +04:00
Chen Xu
a11189da66
[CPU] Fix issue about gather int32 in Reduce node ( #13756 )
2022-11-03 09:47:48 +04:00
Vladimir Paramuzov
b7dfc31597
[GPU] Enable more compiler checks ( #13740 )
...
* [GPU] Enable more compiler checks
* [GPU] Disable -Werror for thirdparty
* [GPU] Improved error message when device not found
2022-11-03 09:07:49 +04:00
Ilya Lavrenov
a5a969886b
Preparation for python debian package ( #13800 )
2022-11-03 08:19:18 +04:00
Tetiana Gubanova
a9a064b4b2
[GPU] Add blocked layout support to ExperimentalDetectronTopKRois operation ( #12456 )
...
* Addapt ExperimentalDetectronTopKRois to support blocked layouts
* Reformat arg_max_gpu_test
* Add support and tests to arg_max_min 2D case to support for ExperimentalDetectronTopKROIs operation
2022-11-03 06:14:54 +03:00
Roman Kazantsev
fdee4ac703
[TF FE] Refactor Pad, PadV2, MirrorPad and add layer tests ( #13597 )
...
* [TF FE] Refactor Pad, PadV2, MirrorPad and add layer tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Recover translators for DynamicStitch
* Apply code-review feedback and workaround for i32 paddings
* Return required type for convert_pad_mode function
* Work around IR reader limitation with i32 type for Pad
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-11-03 02:02:36 +03:00
Ilya Lavrenov
838a6503a0
Pdpd tests moved to folder with frontend ( #13414 )
...
* Moved pdpd tests to folder with pdpd frontend
* Restored old requirements.txt for paddle temporarily
* FIxed requirements path for pdpd
* Restore old dependency
2022-11-02 21:23:32 +04:00
Anastasia Kuporosova
efb987d60f
[PyOV] Fix building of wheel on windows from cmake ( #13795 )
2022-11-02 20:18:49 +04:00
Evan
b9e9f0a4d2
Docs: Update "Install OpenVINO Runtime on macOS from Archive File" page ( #13347 )
...
* docs: Update intro and step 1
* docs: finish updates
* docs: fix duplicate section
* docs: fix curl command
* docs: clarify archive install is for C++ users
* docs: add link to PyPI install page
* docs: minor fixes
* docs: add link to Release Notes
* docs: Change back to numbered instructions
* docs: typo fix
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Apply suggestions from code review
* Update installing-openvino-from-archive-macos.md
* Update installing-openvino-from-archive-macos.md
* Update installing-openvino-from-archive-macos.md
* Update installing-openvino-from-archive-macos.md
* Update installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
* Update docs/install_guides/installing-openvino-from-archive-macos.md
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
Co-authored-by: Maciej Smyk <maciejx.smyk@intel.com>
2022-11-02 23:20:47 +08:00
Evan
f5300fdb98
Docs: Update "Install OpenVINO Runtime on Linux from Archive File" page ( #13345 )
...
* docs: begin updates to install instructions
* docs: change instructions for downloading and unpacking archive
* docs: finish changes to Step 2 and Step 3
* docs: change whats next section
* docs: minor updates and fix typos
* docs: change link to GitHub archive page
* docs: typo fix
* docs: minor change
* docs: replace wget command with curl
* docs: clarify archive install is for C++ users
* docs: add link to PyPI page
* Update docs/install_guides/installing-openvino-from-archive-linux.md
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
* Update docs/install_guides/installing-openvino-from-archive-linux.md
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
* Update docs/install_guides/installing-openvino-from-archive-linux.md
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
* docs: add link to Release Notes
* docs: Change back to numbered instructions and remove Debian from OS list
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* docs: change wget commands to curl
* docs: change wget commands to curl
* Update docs/install_guides/installing-openvino-from-archive-linux.md
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
* Update installing-openvino-from-archive-linux.md
* Update installing-openvino-from-archive-linux.md
* Update installing-openvino-from-archive-linux.md
* Update installing-openvino-from-archive-linux.md
* Update installing-openvino-from-archive-linux.md
* Update installing-openvino-from-archive-linux.md
* Update docs/install_guides/installing-openvino-from-archive-linux.md
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-11-02 18:09:43 +03:00
Alexandra Sidorova
db0e2be481
[Snippets] Fixed input and output original precisions in Subgraph ( #13451 )
2022-11-02 18:45:54 +04:00
Konstantin Beluchenko
c6528ee4ea
[GPU] Matrix NMS ( #13137 )
2022-11-02 18:16:57 +04:00
Krzysztof Bruniecki
f8b12b4f1a
[SAMPLES] [GNA] Remove port assertion in speech_sample when importing ( #13687 )
...
* [SAMPLES] [GNA] Remove port assertion in speech_sample when importing the GNA fromat model
* Fix code style
2022-11-02 15:53:04 +03:00
Karol Blaszczak
764525ba6f
adjust footer content to meet legal requirement ( #13720 )
2022-11-02 11:25:10 +01:00
Sebastian Golebiewski
30759eb350
Fixing indentation in Local Distribution - for master ( #13376 )
...
A minor fix that corrects the indentation of note admonition in the unordered list of Libraries for Execution Modes.
Porting:
https://github.com/openvinotoolkit/openvino/pull/13338
2022-11-02 11:15:41 +01:00
Sebastian Golebiewski
d63362b81a
Fix pot best practices for master ( #13304 )
...
A minor fix that corrects an ordered list in "Tuning Hyperparameters of the Default Quantization" section.
2022-11-02 11:10:08 +01:00
Mateusz Tabaka
063ff5a5c5
[GPU] Insert transpose for gemm input if its trans attr is set ( #8460 )
...
If gemm input dimensions are not multiple of 16 and any of
transpose_a/transpose_b attribute is set - cldnn picks
'gemm_ref' kernel in favor of faster 'gemm_tiled_opt'.
By emplacing explicit permute operation on the gemm input that it requires,
we make cldnn to pick 'gemm_tiled_opt', which in result improves
performance.
For some input shapes, transpose(s) + gemm_tiled_opt can be slower than
just gemm_ref. Based on benchmarks - the cutoff point was set for inputs shapes > (64, 64).
Ticket: 67271
2022-11-02 10:42:52 +01:00
Sebastian Golebiewski
378e334ee6
DOCS: API 2.0 Inference Pipeline Fix - for master ( #13384 )
...
* Update common_inference_pipeline.md
2022-11-02 10:15:29 +01:00
Sebastian Golebiewski
a098845c5a
Fixing snippet in Optimization for Throughput - for master ( #13378 )
...
A minor fix that corrects the code snippets.
Porting:
https://github.com/openvinotoolkit/openvino/pull/13341
2022-11-02 10:11:53 +01:00
Maciej Smyk
e1dba9870c
DOCS: Port to master - fix for archive installation docs ( #13298 )
...
* Fix
* Update installing-openvino-from-archive-linux.md
* fix
* Python 3.10 fix
2022-11-02 17:04:06 +08:00
Sebastian Golebiewski
4f67a3587a
Fixing list in Deployment Manager Tool - for 22.2 ( #13379 )
...
A minor fix that corrects the numbered list of steps in Deploying Package on Target Systems
2022-11-02 10:00:22 +01:00
Sebastian Golebiewski
6b4fa954b7
Model-Formats-fix ( #13386 )
...
Standardized Additional Resources section for Supported Model Formats along with fixing some ref links in articles.
2022-11-02 09:58:49 +01:00