Ilya Churaev
7ff8ada805
Fixed API for transformations ( #10584 )
...
* Fixed API for transformations
* Fixed code style
* Fixed build
* Fixed typo
2022-02-23 06:29:03 +03:00
Fedor Zharinov
75cca1e9e9
[benchamrk_app] error if -b is set but there's no batch info ( #10592 )
...
* Added code showing error message if -b is provided, but got no batch info for inputs
* stylefix / batch>1 case
2022-02-23 01:30:08 +03:00
Vladimir Dudnik
817550fa0a
[OMZ] update OMZ submodule, docs updated ( #10594 )
...
* update OMZ submodule, docs updated
* rebase to master
2022-02-22 23:37:55 +03:00
Ilya Churaev
3f4e384d5d
Disable reshape for new API ( #10064 )
...
* Disable reshape for new API
* Update cnn_network_ngraph_impl.cpp
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-02-22 23:05:23 +03:00
Ilya Lavrenov
5b3b48aa17
samples overview & model protection: docs ( #10596 )
...
* Renamed hetero md
* Renamed some guides
* Updated OpenVINO_Runtime_User_Guide.md
* Updated plugin's page
* More updates
* Fixed links
* Updated link names
* Fixed links
* Fixed docs build
* Self-review
* Fixed issues in doc snippets
* Updated Samples_Overview.md
* Updated model protection guide
* Renamed ngraph_function creation samples
2022-02-22 20:11:42 +03:00
Liubov Talamanova
37923a9183
[POT] Remove DataFreeEngine ( #10600 )
2022-02-22 18:38:08 +03:00
hyunback kim
14d31d59af
[GPU] Enable deconv with oneDNN ( #10580 )
...
* [GPU] Enable deconv with oneDNN
remove post-op data_type into oneDNN.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Update to use data_type in conv sum post-op.
Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-02-23 00:25:26 +09:00
Ivan Novoselov
b12c3389ee
[Sinppets] Add virt destructors to Emitter and TargetMachine ( #10588 )
2022-02-22 18:18:49 +03:00
Indira Salyahova
e2df6d149b
[POT] Update face detection sample ( #10471 )
...
* support cascade model for sw api
* update mtcnnengine
* delete empty line
2022-02-22 17:46:08 +03:00
Maxim Shevtsov
dab1a34aa2
checking the network batch-ability (internal helper func on top of bat… ( #10446 )
...
* checking the network batchability (internal helper func on top of batch tracking) before doing hetero
* more general logic with respect to batch-ability of the network
* a dynamism check that I've owed from the PR-10560
* using the DO-detached mechanism for early hetero exit, also fixed this flag in the Batching plugin (although minor, as the DO is removed by HETERO)
* adding the dimension tracking logic depending on whether implicitly/expicitly the auto-batching is enabled
* changed the DetectionOutput affinity markup to go over results, also accomodate Convert, so only 2 subgraphs are made by the HETERO
2022-02-22 17:19:23 +03:00
Nikolay Shchegolev
e59739ce88
[CPU] RNN node enforce bf16 mode does not work. ( #9859 )
2022-02-22 16:57:26 +03:00
Mikhail Ryzhov
71a0a6d261
[GNA] Klocwork fixes
2022-02-22 16:54:56 +03:00
Roman Kazantsev
bc0a84a1c1
[MO] Print information about new API 2.0 ( #10567 )
...
* [MO] Print information about new API 2.0
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2022-02-22 16:54:20 +03:00
Indira Salyahova
aced89a655
fix: don't pass parametr inplace_statistic for weights ( #10593 )
2022-02-22 16:53:53 +03:00
Anastasia Kuporosova
5bb8f77c3f
[Python API] Remove get/set_config methods from the PyOV ( #10587 )
2022-02-22 16:51:41 +03:00
Maxim Vafin
435584bb91
Support dynamic Broadcast and new pattern for TI condition ( #9735 )
...
* Support dynamic Broadcast and new pattern for TI condition
* Apply review feedback
* Fix broadcast if statement
2022-02-22 16:46:48 +03:00
Min, Byungil
487bb67995
Resolve onednn fc issue to enable bert-base ( #10177 )
...
+ Enabled bert-base-ber model
+ Resolve failure of onednn fc
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-02-22 22:23:45 +09:00
Maksim Kutakov
850f93f21b
[CPU] INT8 tests for convolution sum fusing ( #10359 )
...
* int8 tests
* Sum second term port selection fix
* Fix after rebase
2022-02-22 15:42:26 +03:00
Tingqian Li
51ef938385
[CPU] fix crash in resnet binary model ( #9761 )
2022-02-22 15:23:20 +03:00
Tatiana Savina
6dc8b8b047
add note ( #10566 )
2022-02-22 14:50:37 +03:00
Anton Romanov
c80a872f73
Fix Coverity in samples ( #10583 )
...
* Fix coverity samples
* Fixed coverity issue in speech sample
2022-02-22 14:49:35 +03:00
Alexey Lebedev
a3004e7d80
[PYTHON API] reshape helper ( #10402 )
...
* Add reshape helper
* add dimension(range)
* Add partial_shape helper
* Fix code style
* fix comments
* Split reshape on several overloads
* Fix code style
* correct exception
* remove range support
* fix code style
* Add exception
* Dimension from str, PartialShape from str, reshape(str) support
* Apply review comments
* Add default init for shape
* Add PS syntax examples
* Remove pshape parsing from benchmark_app
* Update src/bindings/python/src/pyopenvino/graph/model.cpp
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
* Update src/bindings/python/src/pyopenvino/graph/model.cpp
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
* Apply suggestions from code review
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
2022-02-22 14:48:55 +03:00
Ilya Lavrenov
991c9db1c1
Config api docs ( #10563 )
...
* Renamed hetero md
* Renamed some guides
* Updated OpenVINO_Runtime_User_Guide.md
* Updated plugin's page
* More updates
* Fixed links
* Updated link names
* Fixed links
* Fixed docs build
* Self-review
* Fixed issues in doc snippets
2022-02-22 14:32:57 +03:00
Sofya Balandina
3f15afb926
[IE TEST] Continue run after crash ( #10037 )
2022-02-22 13:55:51 +03:00
Pavel Esir
3d223ebc2a
[MO] update error message when reverse infer was not successful ( #10576 )
...
* update error message when reverse infer was not successful
* corrected message when there are several undefined Parameters
2022-02-22 13:51:10 +03:00
Andrey Zaytsev
efd3c119fa
Update Yocto documentation ( #10547 ) ( #10591 )
...
* installing-openvino-yocto: fix documentation links
Point to the new Yocto docs website.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
* Update installing-openvino-yocto.md
* installing-openvino-yocto: add step to checkout specific branch
Request users to checkout specific branch of meta-intel where this
version of OpenVINO is available.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
Co-authored-by: Anuj Mittal <anuj.mittal@intel.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-02-22 13:33:44 +03:00
Ivan Novoselov
6500ec775d
[Snippets] Check for cyclic dependencies during ternary merge. ( #10374 )
2022-02-22 13:30:15 +03:00
Alexey Varyzgin
a3887f3328
[CPU] Transpose node optimized with Reorder ( #10551 )
2022-02-22 13:05:19 +03:00
Irina Efode
b7ead46943
[IE TESTS] Functional tests Review. Part 2 ( #10476 )
...
* [IE TESTS] Functional tests Review. Part 2
* tmp
* revert set_blob changes
2022-02-22 13:02:05 +03:00
Irina Efode
d57fb75ba6
migration to OV2.0 ( #10562 )
2022-02-22 12:58:07 +03:00
Mikhail Letavin
171ad9536f
[GPU] Disable unrolling by default for LSTMsequence and TensorIterator having length>=16 ( #10406 )
2022-02-22 12:45:32 +03:00
Egor Duplensky
3f56438d06
[CPU] Align return types handling for all the new API parameters ( #10363 )
2022-02-22 12:42:24 +03:00
Ivan Tikhonov
472ebc0cd9
[TF FE] Add translators for ScatterND, Conv3DBackpropInputV2 ops ( #10550 )
...
* Add translators for ScatterND, ConvBackpropInputV2 ops
* add a new line
2022-02-22 12:20:32 +03:00
Maxim Shevtsov
5247fdfcaf
avoiding layouts ( #10560 )
2022-02-22 12:15:19 +03:00
Nikolay Tyukaev
100fff83bf
dynamic title tag ( #10575 )
...
* dynamic title tag
* dynamic title tag
2022-02-22 12:05:55 +03:00
Evgenya Stepyreva
4afd8667cf
DO detachment ( #10577 )
2022-02-22 12:05:18 +03:00
Egor Duplensky
4075f8ed51
[CPU] Fix ScaleShift and FQ merge optimization ( #9244 )
2022-02-22 11:38:02 +03:00
Taylor Yeonbok Lee
746b77c74a
[GPU] Revised unique ID setting scheme. ( #10548 )
...
* Revised unique ID setting scheme. Previously it was using program id to distinguish the loop body networks' id.
However, it results in cl cache miss for same network loaded multiple time, because program ids are differnt.
Now revised it to use parent primitive id instead of program_id for unique id of nodes in body networks.
* Revised adding unique_id to entry points to have a temporal number as unique id
* Revert the canceld change
* Added test to check whether two networks loaded from same function creates same cl cache
2022-02-22 09:34:46 +03:00
Liubov Talamanova
1891967ad3
[POT] Add quantization templates to wheel ( #10557 )
2022-02-22 09:11:43 +03:00
Andrew Kwangwoong Park
33062bef7a
[GPU] Fix permute performance degradation ( #10559 )
...
* [GPU] Fix permute performance degradation
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
* add description for update
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
2022-02-22 11:35:04 +09:00
Andrey Zaytsev
aea0532d76
Fixed POT docs ( #10574 )
2022-02-22 02:15:58 +03:00
Edward Shogulin
5be402750a
[LPT] FuseConvert transformation extension ( #10558 )
...
* [LPT] FuseConvert transformation extension
* [LPT] Tests
* [LPT] Cleanup & tests refactoring
2022-02-22 02:02:11 +03:00
Mikhail Letavin
d7ad1bd9cd
[GPU] Extra graph transformation passes in case of Dynamic Batch for correct optimization behavior ( #10561 )
2022-02-22 00:40:26 +03:00
Maxim Gordeev
e7145bd343
[IE Samples] Changed input's tensor preprocessing for speech sample ( #10552 )
...
* Changed input's tensor preprocessing
* improved processing
2022-02-21 23:29:38 +03:00
Ilya Lavrenov
d26fd3aa22
Ability to fully override OUTPUT_DIR ( #10524 )
2022-02-21 22:39:26 +03:00
Mikhail Nosov
f82533005b
[OV2.0] Preprocessing documentation ( #10451 )
...
* [OV2.0] Preprocessing documentation - first draft
* Small update
* Added ov::Layout overview
* Fix code style
* Preprocessing details - ~50% done
* Corrected links
* Fixed comments, added more docs
* Minor updates
* Couple more links
* Fixed comments
* Remove 'future' link
2022-02-21 19:20:23 +03:00
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
