Nikolay Tyukaev
65d1575642
DOCS: ovms integration ( #10528 )
...
* ignore model server pages
* merge
* fixed link to ovms docs
* workbench fix
Co-authored-by: azaytsev <andrey.zaytsev@intel.com>
2022-02-21 18:48:29 +03:00
Vladislav Volkov
1d33c37970
[CPU] Issue in opset name determining ( #10479 )
2022-02-21 18:47:24 +03:00
Egor Duplensky
b7fede89c8
[CPU] Fix uninitialized reorder implementation type (valgrind, asan) ( #10520 )
2022-02-21 18:26:20 +03:00
Mateusz Tabaka
6bb8701651
Add MatMulConstTransposesExtraction transformation ( #10412 )
...
Transformation insert Transpose for MatMul's weights and
sets its transpose_b attribute to true.
If executed by MO, it helps to reduce LoadNetwork time on CPU plugin,
since ConvertMatMulToFC doesn't have to insert Transpose by itself.
Ticket: 78635
2022-02-21 16:08:28 +01:00
Fedor Zharinov
4decf16927
Set Latency performance mode in case of sync mode. ( #10516 )
2022-02-21 18:08:05 +03:00
Yuan Hu
09379dca86
[AUTOPLUGIN] add device priority if set ov::device::priorities ( #10296 )
...
* support config key device priority
for example:
if AUTO:CPU,GPU
the priority of CPU will be higher than GPU
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add test and fix compile and test error
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add an info for device priority and add lost [AUTOPLUGIN] on log
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* parseMetaDevice return all DEVICE of GPU, when use AUTO:GPU
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix compile issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* modify test and add test case, fix code issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix a bug and mutli with HETERO test failed
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix mock test faild issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix misprint
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* Disable AUTO:MYRIAD case
MYRIAD/CoreThreadingTests.smoke_QueryNetwork/targetDevice=MULTI_config=MULTI_DEVICE_PRIORITIES:MYRIAD_
faild on windows
the error is
myriadFuncTests-0 INFO: [E:] [BSL] found 0 ioexpander device
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* use ov::device::priorities key in this PR
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix a logic bug in key_network_priority after enable device priority
add test case cover it
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
2022-02-21 23:06:51 +08:00
Irina Efode
ae42bf1e86
[IE TESTS] Functional test review. Part1 ( #10328 )
...
* [IE TESTS] Move Preprocess&Chacing tests to plugin. Add Cachinf tests for OV2.0
* Conformance
* Fix
* Apply Ilya's comments
* Update caching_tests.cpp
* Fixes
* Update mkldnn_plugin.cpp
* try to skip
* try to fix
* Fix cpu
* tmp
2022-02-21 16:22:01 +03:00
Gorokhov Dmitriy
f53f09f020
[CPU] Fixed legacy post ops behavior ( #10542 )
2022-02-21 16:09:29 +03:00
Ilya Lavrenov
68e873c6c8
Config and hetero ( #10555 )
...
* Updated properties documentation
* Fixed doc refernce
* merged snipet files
* fixed build
* Updated Hetero docs
* Self-review
Co-authored-by: Anton Pankratv <anton.pankratov@intel.com>
2022-02-21 16:01:47 +03:00
Alexey Lebedev
0ce255e56a
[tools][benchmark_app] update readme ( #10518 )
...
* Save work
* update readme
* Name refactoring
* Remove duplicated readme
* Add note about default hint
2022-02-21 15:35:07 +03:00
Maksim Derbasov
11bf540018
Simple patch for fix random bool vector generation ( #10493 )
...
* Dirty patch for fix bool generation
* Bernoulli distribution for bool
2022-02-21 14:24:27 +03:00
Mikhail Ryzhov
5dbf2f7088
[GNA] Compact mode ordering fix ( #10408 )
...
* Compact mode ordering fix
* Fixed comment
2022-02-21 14:05:36 +03:00
Jan Iwaszkiewicz
206442fb19
[PYTHON] Add OV Types support to parameter and constant from opsets ( #10489 )
...
* Add OV Types to parameter and constant node factory, refactor tests and error handling
* Fix name mismatch in docstring
* Fix docs and hints
2022-02-21 12:45:55 +03:00
Yuan Xu
828d9d810a
updating apt, yum, conda installation for 22/1 ( #10219 )
...
* Add Overview page
* update yum installation
* update apt installation
* update conda installation
* Revert "Add Overview page"
* Update docs/install_guides/installing-openvino-apt.md
Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
* update Ubuntu version format
* update as per review comments
* integrate comments
* update version format
* add a configurations chapter
* update
* Update docs/install_guides/installing-openvino-yum.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-conda.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-yum.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-yum.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-yum.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-apt.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-yum.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-yum.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* update comments
* Update docs/install_guides/installing-openvino-apt.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-yum.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* Update docs/install_guides/installing-openvino-yum.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
* update references to OpenVINO Runtime User Guide
Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
2022-02-21 12:15:15 +03:00
Yuan Xu
cd77b33f3a
docker installation updates for 22/1 ( #10341 )
...
* Add Overview page
* Revert "Add Overview page"
* update
* update install flows
* update
* Update docs/install_guides/installing-openvino-docker-linux.md
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
* Update docs/install_guides/installing-openvino-docker-linux.md
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
* update structure
* small changes
* improve structure
* Update docs/install_guides/installing-openvino-docker-linux.md
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
* integrate comments
* remove outdated note
* Update docs/install_guides/installing-openvino-docker-windows.md
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
* Update installing-openvino-docker-windows.md
* Update docs/install_guides/installing-openvino-docker-linux.md
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
* Update docs/install_guides/installing-openvino-docker-linux.md
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
* Update docs/install_guides/installing-openvino-docker-linux.md
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
* integrate comments
* adding an issue: Permission Errors for `/dev/shm`
* Update docs/install_guides/troubleshooting.md
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
* update comments
* fix mistake
* fix mistake
* fix a link
Co-authored-by: Ilya Naumov <ilya.naumov@intel.com>
2022-02-21 12:11:08 +03:00
Mateusz Tabaka
430e898c33
Add bf16, f64, i4, u4, i16, u16 types to Equal's evaluate ( #10508 )
...
* Add f64 type to Equal's evaluate
Required by t2t-vit models.
Ticket: 79610.
* add also i16 u16 because prior_box tests fail with "Check eval_status failed at"
* code style
* add i4, u4, bf16 to equal's evaluate
2022-02-21 11:37:17 +03:00
Maxim Andronov
1fa5d44769
[CPU] WA for MergeTransposeAndReorder after conv + sum ( #10466 )
2022-02-21 11:30:24 +03:00
Ivan Tikhonov
33ab7f9063
remove redundant node_context.hpp files, fix handling nodes with several output ports ( #10484 )
2022-02-21 10:27:11 +03:00
Maxim Andronov
31f517a3b4
[CPU] Fix error message for shape infer ( #10522 )
2022-02-21 10:16:29 +03:00
Ivan Tikhonov
e5d6f18366
[TF FE] Fix BatchToSpace op translator ( #10511 )
...
* use shape value, not rank in batch_to_space conversion
* codestyle
* resolve review comment
2022-02-21 10:14:08 +03:00
Tingqian Li
2cc6629624
[CPU] Avoid using xmm0 for input to store_emitter ( #6566 )
2022-02-21 10:02:31 +03:00
Nikita Demashov
f7a85c59fe
[LPT] Disable Move Fake Quantize on shuffle channels pattern ( #10389 )
...
* added shuffle channels check
* refactoring
2022-02-21 10:01:37 +03:00
Ivan Tikhonov
e89c7ed8e5
Describe MakeStateful transformation in MO help ( #10536 )
...
* Update --transform help for MakeStateful transformation
* add quotes
2022-02-21 09:55:26 +03:00
Taylor Yeonbok Lee
73a6d50dbc
[GPU] Fixed batch size again to 8 as a workaround of compiler restriction. ( #10502 )
2022-02-21 09:42:08 +03:00
Roman Lyamin
0ee6959537
[GPU] Replacing get_shape() with get_partial_shape() ( #10525 )
2022-02-21 09:41:24 +03:00
Andrew Kwangwoong Park
a7fff7447c
Fix to extract scores for each class in consideration of background label's id ( #10500 )
...
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
2022-02-21 15:35:44 +09:00
Andrei Molotkov
575ded54a9
[GPU] Move adding biases to the end convolution_bfyx_to_bfyx_f16 kernel ( #10533 )
2022-02-21 09:30:00 +03:00
Xuejun Zhai
ea3bd087c4
[CVS-78727][python version] bug fix for -d AUTO:CPU,GPU the return device should be AUTO only ( #10506 )
...
Signed-off-by: xuejun <xuejun.zhai@intel.com>
2022-02-21 03:21:52 +00:00
Ilya Znamenskiy
7c93902dac
[GPU] Fix issues with floating point fusings support for cldnn / onednn fully connected kernels ( #10519 )
...
* [GPU] Fix of floating point fusings inside fc kernels
* [GPU] Fix for related tests
2022-02-21 12:03:23 +09:00
Maxim Shevtsov
a52c755d21
refactor the perf counters to get really on-demand (rather than on every inference) ( #10526 )
...
* refactor the perf counters to get really on-demand (rather than on every inference)
* removed the (now) un-needed needPerfCounters flag
2022-02-20 20:56:15 +03:00
Maxim Vafin
982942fa5d
Fix typo in CropAndResize translator ( #10541 )
2022-02-20 12:39:52 +03:00
Nikita Malinin
a312dd4a9f
[POT] IEEngine output data order ( #10527 )
...
* IEEngine fix for multiply-output nets
* Update docstrings and docs
* Codestyle changes
* Update docs
* Update docstring
* Pylint
2022-02-20 09:44:04 +03:00
Alexander Kozlov
5c7be85435
[POT] Documentation update ( #10068 )
...
* Updated main README
* Added saturation fix desciption
* Changed Low-precision model representation document
* Added Simplified mode desciption. Updated DefaultQuantization, AccuracyAware, API descriptions.
* Added Data-free model description. Adjusted other Readmes accordingly
* Revised Configuration file description
* Revised AA method description
* Changed Quantization readme
* Cross-links in quantization methods
* Fixed reference
* Fixed the structure
* Removed data-free
* Update tools/pot/docs/CLI.md
Co-authored-by: Nikita Malinin <nikita.malinin@intel.com>
* Update tools/pot/openvino/tools/pot/api/README.md
Co-authored-by: Nikita Malinin <nikita.malinin@intel.com>
* Applied comments
* Fixed comments
* Applied more comment
* Applied comments
* Fixed build errors
* Fixed build errors
* Small changes
* Fixed a typo
Co-authored-by: Nikita Malinin <nikita.malinin@intel.com>
2022-02-20 09:43:14 +03:00
Alexey Lebedev
5671ca2cf5
add test ( #10531 )
2022-02-19 20:19:28 +03:00
Mingyu Kim
af62ff22b1
[GPU] Mixed precision fix for mask rcnn ( #10467 ) ( #10535 )
...
* Select proper layout for fp16-int8 mixed precision network
* Set proper layout in layout propagation for mixed precision
2022-02-19 21:55:15 +09:00
Alexey Lebedev
661002689f
latency mode is default for sync ( #10521 )
2022-02-19 05:58:51 +03:00
Maxim Vafin
71fdcdf899
Fix Unpack translator in TF FE ( #10494 )
...
* Fix Unpack translator in TF FE
* Apply review feedback
2022-02-19 02:52:48 +03:00
Anastasia Popova
2e164b4ddc
AvgPool3D translator, fix of MaxPool translator in TF FE ( #10530 )
...
* Fixed MaxPool translator, added AvgPool3D translator.
* Update src/frontends/tensorflow/src/op/avg_pool.cpp
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Code style.
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2022-02-19 02:47:01 +03:00
Pavel Esir
fb6359586d
fix ConvertGroupedStridedSlice.py for XLNet ( #10496 )
2022-02-18 22:40:28 +03:00
Ilya Lavrenov
6b22d0d109
Revert "repair TF FE tests after build ( #10432 )" ( #10523 )
...
This reverts commit 306b7611d9
2022-02-18 19:48:35 +03:00
Yuan Xu
c9bfd3bf8b
Updating installation guide structure for 22/1 ( #10343 )
...
* Add Overview page
* update overview
* update install dev tools page
* Revert "Add Overview page"
* create overview page
* update movidius setup guide
* split the configurations for linux part to a separate topi
* split the general configurations for linux to a separate topic
* create a separate topic for configurations for vpu on windows
* create a separate topic on configurating gpu
* create a separate topic for configurations for ncs2
* update structure
* update structure
* update structure
* restructure
* update overview
* update
* update according to comments
* update structure
* update the structure
* correct naming
* correct naming
* update trademark symbol
* remove .bak file
* update
* test formatting
* update
* update
* fix errors
* add a leading sentence for GPU configurations
* update structure
* delete redundant files
* Update docs/install_guides/configurations-for-intel-gpu.md
Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
* Update docs/install_guides/configurations-for-ncs2.md
Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
* Update docs/install_guides/installing-openvino-config-ivad-vpu.md
Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
* fix formatting
* fix errors
* fix errors
* fix errors
Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
2022-02-18 19:47:00 +03:00
Svetlana Dolinina
d2177cf177
remove old protobuf eggs ( #10473 )
2022-02-18 18:12:23 +03:00
Gleb Kazantaev
b22585a696
Fix Coverity issue ( #10510 )
2022-02-18 18:00:40 +03:00
Alina Kladieva
7985c92095
Revert "[GPU] Mixed precision fix for mask rcnn ( #10467 )" ( #10515 )
...
This reverts commit 10ac5b280b
2022-02-18 16:38:49 +03:00
Anton Voronov
d9b1f10074
[CPU] [OneDNN] disabled unused amx primitives and conv primitives ( #10326 )
2022-02-18 16:36:49 +03:00
Katarzyna Mitrus
f52f129ed8
[Python API] Improvement of dynamic reshape error message in compatibility ie ( #10495 )
...
* Add test_reshape_dynamic to tests compatibility
* Catch OverflowError on dynamic dimension reshape
2022-02-18 14:23:10 +03:00
Zhang Yi
ba9d18f181
[CPU] Parallel copy for output in case data doesn't fit L2 cache capacity ( #10340 )
2022-02-18 13:16:51 +03:00
Ilya Churaev
a18c8076cc
Removed obsolete documentation ( #10504 )
...
* Removed obsolete documentation
* Fixed documentation
* Additional fix
2022-02-18 13:02:55 +03:00
Ekaterina Aidova
e8ff31f4fb
[OMZ]: update submodule ( #10490 )
2022-02-18 12:58:38 +03:00
Roman Kazantsev
20266dd0c3
[MO] Upgrade TensorFlow version dependency due to SNYK hits ( #10487 )
...
* [MO] Upgrade TensorFlow version dependency due to SNYK hits
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Still use 2.5.0 TensorFlow for Python 3.6 and older
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2022-02-18 12:29:58 +03:00
