IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
11,304 Commits 38 Branches 54 Tags
70e0caca4f4ba1f62e9e0948baeadc54625e830c
Commit Graph

11304 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Sergey Shlyapnikov
70e0caca4f [GPU] Fix dynamic padding processing of static dimension (#17978) 2023-06-12 08:39:42 +04:00
Mateusz Tabaka
8653f1cbd9 Fix static analysis issues in pruning mask propagation (#17910) 
Ticket: CVS-108960
 2023-06-11 10:49:31 +02:00
Mateusz Tabaka
93689cc417 Don't constantfold weights in MatMulConstTransposesExtraction transformation (#17917) 
get_constant_from_source for Transpose node calls evaluate method
twice which is unnecessary in this case.

Ticket: CVS-105967
 2023-06-11 09:49:21 +02:00
Ilya Lavrenov
50c85f01ab ARM static build (#17970) 2023-06-10 23:40:39 +04:00
Ilya Churaev
a0e8d9a630 Deprecate main IE developer API classes (#17983) 
* Deprecate main IE develiper API classes

* Remove legacy snippet

* Fixed warning for VariableState
 2023-06-10 19:25:54 +04:00
Ivan Tikhonov
74100670ac Delete the deprecated LowLatency (version1) transformation (#17965) 
* Delete the deprecated LowLatency (version1) transformation

* detele LowLatency refs from the docs
 2023-06-10 12:24:43 +04:00
Wilson Seok
cff083f83d [GPU] gather nd shape agnostic kernel implementation (#17940) 
* gather nd shape agnostic kernel implementation

* add func test

* fix minor bugs

* minor bug fixes

* fix win build error
 2023-06-10 00:28:00 -07:00
Andrew Kwangwoong Park
c413825845 [GPU] Fuse type conversion only reorders to the prev nodes (#17881) 
* Fuse convert reorder to prev MVN/Concat node

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add dynamic TCs for ov_gpu_unit_test

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add descriptions for changes

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Fix kernel selection failure

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add is_type_conversion_only function for reorder_node

Signed-off-by: Andrew Park <andrew.park@intel.com>

---------

Signed-off-by: Andrew Park <andrew.park@intel.com>
 2023-06-09 16:07:01 -07:00
Egor Duplenskii
36a4c0cb2b [CPU][DEBUG_CAPS] Fix compilation warnings (#17977) 2023-06-10 02:09:59 +04:00
Wang Kai
7b86b427cb fixing some typos (#17980) 2023-06-10 01:13:31 +04:00
Edward Shogulin
8adce06348 [LPT] tests rename for nightly: part #2 (#17926) 2023-06-10 01:12:52 +04:00
Ilya Churaev
724eb94a1d Deprecate plugins config keys (#17974) 2023-06-09 17:55:14 +00:00
Mateusz Tabaka
67f7808fc4 AlignEltwiseInputRanks - fix when output rank is less than constant rank (#17895) 
Fixes an issue when AlignEltwiseInputRanks is applied on FakeQuantize with
scalar as a first input and input/output low/high being Shape{1} constants.
In such case FakeQuantize output is still a scalar, so the difference
between output rank and input/output low/high rank is negative.

Ticket: CVS-112454
 2023-06-09 20:31:20 +04:00
Ilya Churaev
c8e331003f Port some changes from proxy branch (#17961) 
* Port some changes from proxy branch

* Port test changes

* Rewrite approach for compile model and tensor

* Fixed review
 2023-06-09 16:08:53 +02:00
Ilya Churaev
21c2b513d1 Update OMZ to support OpenCV without GAPI (#17972) 2023-06-09 15:48:04 +04:00
Alexey Kazakov
a14a2c0eb0 Move dependencies to the new share (#17825) 2023-06-09 15:15:02 +04:00
Maciej Smyk
1886ca483b Update build_linux.md (#17966) 2023-06-09 15:04:00 +04:00
Wonju Lee
34d4c81b76 [DOCS] Adding Datumaro document into OV Ecosystems (#17944) 
* add Datumaro document
* add datumaro into toctree
 2023-06-09 11:56:30 +02:00
Ilya Churaev
3ef4dac6d5 Update OMZ submodule (#17963) 2023-06-09 13:09:17 +04:00
Sebastian Golebiewski
ae73973c11 [DOCS] Fixing broken code blocks (#17959) 
* code-blocks-fixes
 2023-06-09 09:08:14 +02:00
Ilya Lavrenov
a0119fe33c Android debug build (#17955) 2023-06-09 08:03:10 +04:00
Ilya Lavrenov
2ff430fa80 Try to use system flatbuffers on Android (#17954) 2023-06-08 21:22:33 +04:00
Gorokhov Dmitriy
e564c50d35 [CPU] Fixed KEY_LP_TRANSFORMS_MODE internal propery behavior (#17945) 2023-06-08 21:09:37 +04:00
Zlobin Vladimir
55ddbcaf23 cpp/samples: update build (#17900) 
* cpp/samples: update build

Ticket 111295

* Fix sample_type extraction

* Fix inputLog type

* include <limits>

* Add missing const

* Revert cpp/speech_sample error message

* update azure CI
 2023-06-08 19:30:29 +04:00
Mircea-Aurelian Dan
67c0327cd1 Set default duration to 60 for device VPU (#17952) 2023-06-08 18:55:53 +04:00
Ilya Lavrenov
97532622cb Fixes for deployment manager (#17899) 2023-06-08 18:31:55 +04:00
Sun Xiaoxia
9e8d64bf70 Xiaoxia/update cpu mapping (#17451) 
* generate cpu mapping table pre tbb

* change function name

* fix proc_type_table is wrong in RPL

* add getCpuMapFromCores test, fix comments

* modify test case

* fix comments

* fix code style

* add throw an exception

* fix numa_nodes=0 on ARM

* modify numa_nodes

* fix ExportOptimalNumStreams failed on ARM

* fix comments

* add discription of get_cpu_mapping_from_cores

* update for numactl support

* fix cores is wrong

---------

Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
 2023-06-08 22:28:35 +08:00
Daria Mityagina
6ad0e5a1e7 Update comments and help text (#17707) 2023-06-08 13:47:40 +00:00
Alexandra Sidorova
385cfee24a [Snippets] Fixed copy runtime info which contains PortDescriptors (#17774) 2023-06-08 12:22:48 +00:00
Ilya Lavrenov
b1b1014a34 Enable python API in deb / rpm packages (#17923) 
* Enable python API in debian package

* Enable python API in debian package
 2023-06-08 15:35:27 +04:00
Ilya Lavrenov
ad5b8f8687 Align tabs in install archives Linux (#17947) 2023-06-08 15:00:25 +04:00
Sergey Shlyapnikov
58d79aa3a6 [GPU] Add shape_of subgraphs markup and initial cpu implementations (#17762) 
* [GPU] Add shape of subgraphs markup and initial cpu implementations for some of primitives

* Apply review comments

* Exclude eltwise with boolean mode types from shape of subgraphs and fix leftovers
 2023-06-08 13:46:21 +04:00
Alexandra Sidorova
eb3e6a65eb [Snippets] Add support of MHA Tokenization for different precisions (#15647) 2023-06-08 08:05:14 +00:00
Ilya Lavrenov
bdfa970c7a Support different names for ITTAPI (#17889) 2023-06-08 11:08:58 +04:00
Sebastian Golebiewski
912e4b6f0d update-deployment-manager (#17903) 2023-06-08 10:32:08 +04:00
Taylor Yeonbok Lee
f246015dd7 [GPU] Fix issue in runtime buffer fusing (#17909) 
* There were two issues in runtime buffer fusing
1) Missing condition in matcher for dyanmic tensor
2) If the node is marked as can_be_optimized = true at build time and then turned out to false at runtime, the kernel compilation has been skipped becuaes it was checking node->can_be_optimized
=> To resolve this issue, added can_be_optimzied to impl_param and let the impl create check can_be_optimized in impl_param instead of that in node.

* Fixed primtiive::can_be_optimize to be set through function
 2023-06-07 19:39:26 -07:00
Mingyu Kim
0b06d15178 [docs] typo fix (#17915) 2023-06-08 10:27:26 +09:00
Tatiana Savina
0a94aeb1bb [DOCS] Port release doc fixes (#17939) 
* [DOCS]  Model optimization paragraph fix  (#17907)

* fix mo guide paragraph

* fix format

* fix paragraph

* remove extra line

* fix archive link (#17918)

* [DOCS]  Add sudo to uninstall (#17929)

* add sudo to uninstall

* Update uninstalling-openvino.md
 2023-06-07 18:57:42 +02:00
Zlobin Vladimir
7fe13f341b Update open_model_zoo submodule (#17927) 
Catch up https://github.com/openvinotoolkit/open_model_zoo/pull/3782
 2023-06-07 19:20:42 +04:00
Edward Shogulin
655c21adf1 [CPU] Quantized MHA extension for SmoothQuant (#17906) 2023-06-07 14:31:06 +00:00
Anton Voronov
2547301fa7 [CPU] gemm convolution: fixed bias offset (#17357) 2023-06-07 17:15:01 +04:00
Georgy Krivoruchko
ee659c1ce8 [TF FE] Workaround for Broadcast/Concat issue with empty tensors (#17864) 
* Added transformation for Concat

* Added test

* CI fix

* Fixed behavior of the "empty tensor list" test
 2023-06-07 14:17:20 +04:00
Tomasz Otoka
323dbec93c Adds configuration file for cspell (#17355) 
the file for future use with cspell
 2023-06-07 12:16:28 +02:00
Tomasz Otoka
d8a78137a7 Adds Python wheel requirements info to docs (#17922) 2023-06-07 10:13:15 +00:00
Ilya Lavrenov
6df054b073 Added cmake_policy call to allow IN_LIST in if() (#17916) 2023-06-07 14:12:54 +04:00
Pawel Raasz
f023f5d672 Add interpolate from all opsets to cpu shape infer (#17875) 2023-06-07 11:28:45 +02:00
hyunback kim
13028397b7 Optimize permute gemm onednn (#17621) 
* [GPU] Optimized out permute in permute-gemm(onednn) pattern.

Permute can be optimized out when permute's in and out are compatible and onednn gemm.

Signed-off-by: hyunback <hyunback.kim@intel.com>
 2023-06-07 16:20:59 +09:00
Chen Xu
3a1326fb58 [CPU] Reduce node improve parallelism (#17615) 2023-06-07 05:11:18 +00:00
Wang Wangwang
84bd391369 [AUTO] Support setting log_level from config (#17569) 
* [AUTO] Support setting log_level from config

* Add test cases

---------

Co-authored-by: Chen Peter <peter.chen@intel.com>
 2023-06-07 10:31:27 +08:00
Wanglei Shen
4ca8d40e43 update scheduling core type value (#17771) 
* update scheduling core type value

* update for comments

* update for comments

* fix code style issue
 2023-06-06 22:14:40 +08:00