IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
6,713 Commits 38 Branches 54 Tags
2a1d8d7e9926af4882a7cb7a69f47845c1bce4bb
Commit Graph

6713 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Andrew Kwangwoong Park
2a1d8d7e99 [GPU] Minor fix for dump layer (#10291) 
- Replace find with compare func to avoid dumping all layers that contain layer name

Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
 2022-02-16 12:02:28 +03:00
Nikolay Tyukaev
0c4d50239a update requirements to fix tabs (#10409) 2022-02-16 11:47:11 +03:00
Gleb Kazantaev
709084888a Remove deprecated classes from openvino headers (#10371) 
* Remove deprecated classes from openvino headers

* Fix tests
 2022-02-16 11:41:16 +03:00
Ilya Churaev
0b27fb80b1 Fix for new coverity issues (#10378) 
* Fix for new coverity issues

* Fixed cc coverity

* Fixed code style

* Revert some changes

* Fixed build
 2022-02-16 11:12:24 +03:00
Nikita Malinin
c8ce93290e [POT] Sync mode only for gna_sample (#10355) 
* Sync mode only for gna_sample

* Disable test
 2022-02-16 11:00:13 +03:00
Vladimir Zinoviev
e22a2b3076 [CommonTransformations] Fix default output take from Split/VariadicSplit (#10395) 2022-02-16 10:59:11 +03:00
Mateusz Bencer
0a056857c5 fix handling stride_y (#10398) 2022-02-16 07:57:56 +00:00
Mingyu Kim
c0d54e48bb [GPU] Bugfix for onednn post op optimization (#10416) 
When post-op has pattern like below, binary_mul was ignored previously.
1. binary_add
2. eltwise_linear
3. binary_mul
4. binary_add

It happens when prev_post_op_idx == 2, cur_post_op_idx == 4.
prev_post_op_idx was supposed to proceed to idx 3, but it did not.
 2022-02-16 10:44:42 +03:00
Vladislav Golubev
fa4246d531 [LPT] Security fixes (#10381) 2022-02-16 10:31:17 +03:00
Taylor Yeonbok Lee
cbb5dff9c1 Fix coverity errors (#10384) 2022-02-16 10:10:10 +03:00
Ivan Tikhonov
06eb74b77f Fix MakeStateful transformation: use tensor names instead of friendly names (#8997) 
* Use tensor names instead of friendly names, handle one output tensor to several Result ops case

* fix python tests

* fix python test

* fix incorrect merge

* remove redundant files

* fix variable names generation, fix python test

* Apply review comments

* fix python test
 2022-02-16 09:26:31 +03:00
Jan Iwaszkiewicz
e71f23fc7e [PYTHON] Add __repr__ to main objects (#10365) 2022-02-15 21:30:33 +00:00
Evgenya Stepyreva
d14f1e54a5 MatMul Shape Inference (#10348) 
* Proper dynamic dimension broadcasting

* make shape infer race condition reproducer

* Use ngraph only

* MatMul shape inference

* Style

* Dynamic rank case covered

* Build fix

Co-authored-by: Maksim Kutakov <maksim.kutakov@intel.com>
 2022-02-16 00:22:46 +03:00
Vladimir Dudnik
eda4cbf30e [OMZ] rest of public models with layout (#10293) 
* update OMZ submodule, rest of public models with layout

* sync with PR-10150

* ac fixes for WB

* fix CVS-78616
 2022-02-15 23:42:41 +03:00
Maxim Shevtsov
317b956d2e fixed possible situation when auto-batching returns zero requests (#10388) 2022-02-15 15:13:25 +00:00
Mikhail Nosov
d5e8e0fb88 Fix coverity findings - add nullptr check before dereferencing (#10375) 
Even though it is not possible to hit into this situation using existing plugins - there is theoretical possibility that some plugin may return 'nullptr' as it is allowed.
So this check shall remain in generic part which should not rely on plugin-specific behavior
 2022-02-15 18:01:05 +03:00
Maxim Andronov
dc905f972a [CPU] AdaptivePooling child edges number check fix (#10372) 2022-02-15 17:59:51 +03:00
Ivan Novoselov
fa6865d569 [CPU] Disable MatMul+FQ(I8 out) if MatMul cant execute in I8 (#10316) 2022-02-15 17:59:06 +03:00
Maxim Vafin
0793a56260 Fix Conv3D translator in TF FE (#10387) 2022-02-15 17:53:13 +03:00
Mikhail Letavin
f150e2ad09 [GPU] Remove debug suffix from OpenCL.dll on Windows (#10361) 2022-02-15 16:43:40 +03:00
Sergey Lyubimtsev
498d865ea6 Correction for install guides: (#10373) 
- OpenVINO installer path for macOS
- Default install pathnon macOS
- Red Hat Enterprise Linux 8.x, 64-bit is not part of IRC installer
 2022-02-15 16:22:26 +03:00
Gleb Kazantaev
b837b7e32c Fix Coverity Isues (#10376) 2022-02-15 15:26:04 +03:00
Pavel Esir
121d59aa80 [MO] move importlib-metadata into setup.py (#10319) 
* handle 'and' marker in requirements

* Revert "handle 'and' marker in requirements"

This reverts commit 952bb949ca.

* moved importlib-metadata from requirements.txt into setup.py
2022.1.0.dev20220215 		2022-02-15 15:01:27 +03:00
Indira Salyahova
f1557c06de [POT] Fix inference sample in fbc when get list prediction (#10159) 
* fix: inference sample in fbc when get list prediction

* update reference metrics
 2022-02-15 14:42:40 +03:00
Wilson Seok
e168c9b1c3 Add slt in template plugin/tensor iterator (#9692) 
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now

* update repo

* add initial op reference code of TensorIterator with LSTM body function

* add GRU/RNN case in setup

* add all other test cases

* add visitor api test

* remove unnecessary header files

* fix clang-format issue

* fix copyright year and remove ngraph_helper namespace

* rename ti.cpp to tensor_iterator.cpp in core unit test

* apply suggestions
 2022-02-15 13:48:18 +03:00
Ivan Novoselov
68c390f679 [Snippets][CPU] MKLDNNSnippetNode adopts canBeInPlace logics from eltwise node (#10334) 2022-02-15 13:13:35 +03:00
Maksim Kutakov
788a5bb9f2 [CPU] Convolution plus sum fusing in the case of dynamic shapes (#10235) 2022-02-15 13:12:07 +03:00
Anastasia Kazantaeva
ccc38d22a8 Upgrade MO message for 2022.1 (#10315) 2022-02-15 13:10:45 +03:00
Alexander Zhogov
2b8e1ec49a Azure CI: no ARM triggers on docs/* (#10322) 
* Azure CI: no triggers on docs/*

* Remove "PR:"
 2022-02-15 13:04:44 +03:00
Taylor Yeonbok Lee
f5283300f0 Reduced available host VRAM & phys mem limitation (#10360) 2022-02-15 19:01:05 +09:00
Mateusz Tabaka
a875f6ed9c Add transformation that aligns elementwise input ranks (#10125) 
* [CPU] Add transformation that aligns elementwise input ranks

* fix tests - check also aBcd16b format

* add support for fq

* add test for sqr diff

* move to moc transformations

* fix tests

* align only for numpy autobroadcast type

* fix fetching autob from fq

* [CPU] Eltwise tests corrected & callback for CPU removed

* remove transformation callback call

* revert changes to getMKLDNNOutputMemoryFormats

* remove comment

* use single wrap_type

Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
 2022-02-15 12:47:54 +03:00
Ilya Znamenskiy
523adff17a [GPU] Fully connected int8 optimizations, some fixes, better fused ops support (#10035) 2022-02-15 12:33:16 +03:00
Andrei Gorbachev
64812fd635 [GPU] disable options in batch compilation (#10311) 2022-02-15 08:50:58 +00:00
Ilya Znamenskiy
0099755434 [GPU] Gemm opt tile_n min size fix (#10369) 2022-02-15 11:48:02 +03:00
Artur Kulikowski
004daca1fa Clear outputs vector after run TestCase (#10279) 2022-02-15 09:41:01 +01:00
wood-ghost
ded2d00711 Add paddle logical and reduce ops support. (#10352) 2022-02-15 16:23:50 +08:00
Anton Pankratov
39c90e9d48 Streams number fix (#10336) 
* Streams number fix

* fixed perfomance hint

* fixed format

* removed dbg

* simplified code

* reverted becnhmark_app
 2022-02-15 08:04:45 +00:00
Bartek Szmelczynski
2b03d5fe66 [MO args][ONNX FE]fix cutting graph with input, output or both (#9698) 
* fix cutting graph with input, output or both

* fix collisions

* add regex

* revert changes to regex, fix decond_name_with_port function

* fix collisions

* optimize try_get_node function

* swap bool with enum

* revert accidental import

* optimize the code

* Update tools/mo/unit_tests/mo/moc_frontend/moc_extractor_test_actual.py

Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>

* Update tools/mo/unit_tests/mo/moc_frontend/moc_extractor_test_actual.py

Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>

* Update tools/mo/unit_tests/mo/moc_frontend/moc_extractor_test_actual.py

Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>

* Update tools/mo/unit_tests/mo/moc_frontend/moc_extractor_test_actual.py

Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>

* Update tools/mo/unit_tests/mo/moc_frontend/moc_extractor_test_actual.py

Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>

* remove redundant check

* fix wrong nodes returns

* fix decode_with_port_name implementation, add comments

* reduce code duplicates

* remove redundant imports

Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>
 2022-02-15 10:55:40 +03:00
Vladislav Golubev
d48dd1f26c [Transformaitons] BatchNormDecomposition fix (#10310) 
* [Transformaitons] Changed BN decomposition

* matcher updated to cover dynamic shape in opset1 case

* BatchNormDecomposition: added positive test-cases

* removed WA
 2022-02-15 10:48:30 +03:00
Alexey Lebedev
e85c473d59 [tools] fix bin processing in benchmark app (#10366) 
* fix bin reading

* Remove unsupported type
 2022-02-15 10:34:14 +03:00
Indira Salyahova
acf6185bf3 Update load image in sample (#10223) 2022-02-15 10:18:27 +03:00
Mingyu Kim
13c024b7a3 Remove unnecessary cout message (#10346) 2022-02-15 16:14:56 +09:00
Ilya Churaev
8020a7abcc Disabled LTO for frontend_common (#10362) 2022-02-15 06:03:20 +00:00
bell
f75e50cc88 limit gpu compiling threads (#10349) 
* limit gpu compiling threads

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

* switch to 2.0

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

* clang format

Signed-off-by: fishbell <bell.song@intel.com>
 2022-02-15 08:52:49 +03:00
Maxim Andronov
c3c52bae63 [CPU] Convolution caching support (#9954) 2022-02-15 08:47:03 +03:00
Anton Chetverikov
84ee38d89e [MO] Move redundant checks in ScatterUpdate operation shape infer (#10306) 
* Add extender for ScatterUpdate operation

* Remove scatterupdate extender

* Remove redundant checks in Scatter shape inference function

* Move checks to ScatterElementsUpdate operations

* mava checks to appropriate place
 2022-02-15 04:55:38 +03:00
Jacek Skowron
a0ad849c19 [DOCS] add install guides minor changes (#10317) 
* [DOCS] add minor changes to install guides

[DOCS] add minor changes to install guides

[DOCS] add minor changes to install guides

[DOCS] add minor changes to install guides

[DOCS] add minor changes to install guides

[DOCS] add minor changes to install guides

* [DOCS] add minor changes to install guides
 2022-02-15 02:43:50 +03:00
Maxim Andronov
1ab9c07ccd [CPU] Skip dynamic tests which executed via legacy API (#10358) 2022-02-15 00:45:50 +03:00
Daniil Lyakhov
2f9c5df271 [Ngraph transformation][Pruning]Matmul ops pruning support (#10211) 
* Linear pruning support

* Minor fix

* Fix types

* Fix: stop 1d multiply propagation
 2022-02-14 22:00:29 +03:00
Mikhail Nosov
2f876e3b5b Fix ONNX's PriorBoxClustered accuracy (#10091) 
* Fix ONNX's PriorBoxClustered accuracy
If step_heights == 0 and step_heights == 0, but 'step' is 16, then we should treat this as both = 16

* Removed workaround for ONNX frontend
 2022-02-14 20:55:41 +03:00