IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
11,153 Commits 38 Branches 54 Tags 1.1 GiB
84f46bd048
Commit Graph

11153 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Roman Kazantsev
fb38fcef2b
[TF FE] Refer Frontend Extension page in case unsupported operations (#17387) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-05-06 06:20:13 +01:00
Roman Kazantsev
b6098fed90
[TF FE] Provide single tensor names for inputs and outputs in SavedModel (#17370) 
* [TF FE] Provide single tensor names for inputs and outputs in SavedModel

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Fix build issue

* Xfail some cases due to internal problems in TF

* Xfail other layer test

* Extend documentation for function to adjust tensor names

* Use old path of tf2 layer testing for legacy frontend

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-05-06 05:37:47 +01:00
Sebastian Golebiewski
b6bbf3c44c
[DOCS] Fix links (#17353) 2023-05-05 18:15:01 +02:00
Egor Duplenskii
03ad798615
[DOCS] Correct compilation option for paddle-paddle front end (#17386) 2023-05-05 17:25:28 +02:00
Mateusz Tabaka
48281376a0
[TF frontend] use InterpolateMode::LINEAR_ONNX if input rank is 4 (#17381) 
This change mimicks LinearToLinearONNXReplacer transformation in
legacy frontend, where linear interpolate mode is replaced with
linear_onnx due to performance reasons.

Ticket: CVS-108343
 2023-05-05 17:12:18 +02:00
Tatiana Savina
61fc3ae42a
DOCS shift to rst - Model representation doc (#17320) 
* model representation to rst

* fix indentation

* fix cide tabs

* fix indentation

* change doc

* fix snippets

* fix snippet
 2023-05-05 14:44:16 +02:00
Chen Xu
4fd42cdd62
[CPU] Fix kernel precision mismatch in Reduce node (#17371) 
* [CPU] Fix kernel precision mismatch in Reduce node

* Apply review comments
 2023-05-05 14:39:02 +02:00
Taylor Yeonbok Lee
7b4455d748
[GPU] Update dynamic shape document (#17274) 
* Update dynamic shape document for GPU
* Applied review comments
 2023-05-05 13:00:03 +02:00
Sebastian Golebiewski
963f30a2fe
DOCS shift to rst (#17375) 2023-05-05 10:55:40 +02:00
Maciej Smyk
175e169537
DOCS shift to rst - Opsets E for master (#17363) 2023-05-05 10:16:49 +02:00
Karol Blaszczak
909d539698
Update prerelease_information.md (#17374) 2023-05-05 05:46:00 +00:00
Oleg Pipikin
974d2f6f89
Fix OpenVINOConfig.cmake (#17360) 2023-05-04 19:08:26 +01:00
Nikolay Shchegolev
2f9fe67691
[CPU] Fix for SpaceToBatch dead loop. (#17352) 2023-05-04 18:24:47 +02:00
Tomasz Otoka
557b189d83
Fix install guides typos (#17354) 2023-05-04 13:59:32 +02:00
Sebastian Golebiewski
0456528651
DOCS shift to rst (#17345) 2023-05-04 13:29:25 +02:00
Yuan Hu
88c154953e
[CPU] fix coverity issue in multiclass and a bug in matrix_nms (#17180) 
* fix coverity issue in multiclass_nms

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix issue in matrix_nms.cpp

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

---------

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
 2023-05-04 10:34:56 +02:00
PuQing
bc6402fb27
【PaddlePaddle Hackathon 4】add paddle softshrink op (#15845) 
* add softshrink

* Modify the implementation

* fix input unsigned

* fix name typo

* fix unsigned

* fix selct

* add input dtype check

---------

Co-authored-by: Bo Liu <bo4.liu@intel.com>
 2023-05-04 16:18:44 +08:00
Maxim Vafin
c1933fcaf0
[PT FE] Support default strides for avg and max pooling (#17337) 
* Support default strides for avg and max pooling

* Fix code style

* Remove changes from other ticket
 2023-05-04 09:27:10 +02:00
Oleg Pipikin
ec90869969
Fix config mapping for runtime and frontend targets for RelWithDebugInfo config (#17312) 
* Fix samples RelWithDebugInfo config binding

* Fix1:

* Add default config map for openvino::runtime

* Fix2

* Fix3

* Fix4
 2023-05-04 11:26:23 +04:00
Maxim Vafin
1d59dab362
[PT FE] Improve exception when decoder cannot trace or script the model (#17338) 
* [PT FE] Improve exception when decoder cannot trace or script the model

* Add exception in convert_model

* Add test
 2023-05-04 07:58:40 +02:00
yanlan song
3a0fa86ef9
add doc update (#17223) 
Signed-off-by: fishbell <bell.song@intel.com>
 2023-05-04 12:49:24 +08:00
Taylor Yeonbok Lee
9062b81edb
[GPU] Fix bug in reorder_redundant_reorder (#17329) 
* Fix bug
1) reshape w/ fused primiitive should not be optimized out
2) Wrong usage of slice mem / concat mem in loop
3) LWS not set in lstm_elt

* Added unittest
 2023-05-03 16:43:34 -07:00
Roman Kazantsev
7464b4d396
[MO][TF FE] Recover MOC TF FE unit-tests in the pre-commit (#17233) 
* [MO][TF FE] Recover MOC TF FE unit-tests

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Fix python environment to get test_util

* Correct Python environment for MO UT tests

* Correct Python env for linux-debian

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-05-03 23:39:46 +00:00
Paul Youngsoo Ahn
0afe835811
[GPU] update padding info for optimized out node (#17286) 
* [GPU] update padding info for optimized out node

* [GPU] Fix padding propagation issue for crop's user nodes(#17286)
- Fix unit test failure
 2023-05-03 11:01:23 -07:00
Irina Efode
7aea8d6641
[CONFORMANCE] Remove extra print from op_summary (#17336) 2023-05-03 12:31:05 +00:00
Evgenya Stepyreva
9291e5ecd2
NMS-5 calculate upper-bound (#17313) 
* NMS-5 calculate upper-bound

* Test
 2023-05-03 11:42:20 +00:00
Irina Efode
e616bcbad8
[CONFORMANCE] Remove duplications from API Conformance report (#17339) 
* [CONFORMANCE] Remove duplications from API Conformance report

* remove extra prints
 2023-05-03 12:01:56 +01:00
Ivan Tikhonov
52f32ae437
Fix the names copying in TransposeSinking backward transformations (#17283) 
* Fix tensor names copying in TS transformations

* added a check that sinking is available for all consumers in TS backward transformations

* codestyle

* Apply review comments, add result sorting by tensor names in graph comparator

* delete debug code

* fix RemoveConsumers method implementation

* fix snippet tests

* use reference instead of raw pointer

* add new transformation tests

* fix transformation tests
 2023-05-03 14:59:05 +04:00
Sofya Balandina
bda41b7321
[ie tests] Move CheckOperationInProfilingInfo to common part (#17282) 2023-05-03 14:42:03 +04:00
Sofya Balandina
96c5cd16d5
[conformance] Rebalance props tests (#17124) 2023-05-03 14:22:43 +04:00
Irina Efode
fd2ccab93b
[CONFORMANCE] Add message to explain passrates in report (#17314) 2023-05-03 12:54:39 +04:00
Egor Duplenskii
f22aaaf239
[CPU] Clean up primitive desc creation in prepareParams (#16739) 2023-05-03 09:51:03 +02:00
Vladimir Paramuzov
e282a25d94
[GPU] Minor binary size reduction (#17308) 2023-05-03 09:07:52 +04:00
Ilya Lavrenov
4d7947efc8
Increment minor OV version (#17299) 2023-05-02 22:32:18 +02:00
Piotr Krzemiński
1c286e4636
[PT FE] Add aten::all implementation (#16901) 
* [PT FE] aten::all implementation with tests

* [PT FE] Add non-dynamic type check

* [PT FE] Update tests, temporarily turn off uint8 tests

* [PT FE] Fix dtype for uint8

* [PT FE] Apply suggested optimizations

---------

Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
 2023-05-02 21:12:12 +02:00
Sofya Balandina
56290fee01
[apiConformance] Fix rebalance missing changes (#17270) 2023-05-02 15:42:19 +00:00
Maxim Vafin
89d3eaa67f
Fix issue with Pow when both inputs are scalars (#17305) 
* Fix issue with Pow when both inputs are scalars

* Fix code style
 2023-05-02 16:49:42 +02:00
Roman Kazantsev
35cae6251c
[MO][TF FE] Handle constant with undefined value (#17311) 
Since TF 2.10 the native model freezing can produce constants with undefined value,
i.e. tensor shape can be any and value is []. In this case the tensor just fills up with
the default value (0 - for numerics, "" - for strings)

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-05-02 14:02:36 +00:00
Anton Voronov
d9b04be3ae
[DOC] small fix for sparse weights decompression feature documentation (#17315) 2023-05-02 15:50:37 +02:00
Sergey Shlyapnikov
3b8bb1fb17
[GPU] Use BFS processing order for out_of_order queue (#17250) 2023-05-02 15:14:38 +04:00
Yuan Hu
82ec92dd98
[CPU][coverity] fix coverity issue in concat and graph_optimizer (#17191) 
* fix coverity issue in concat

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix coverity issue in graph_optimizer.cpp

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix review issue

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix the mistaken that there are two throw

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

---------

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
 2023-05-02 12:27:05 +02:00
Tatiana Savina
93980873a0
update OTE and Datumaro links (#17269) 2023-05-02 11:49:25 +02:00
Sebastian Golebiewski
f6600665ba
DOCS shift to rst - Opsets H & I (#17284) 
* update

* update

* cpp
 2023-05-02 11:15:23 +02:00
Przemyslaw Wysocki
89167ddcf5
Bump OMZ submodule (#17117) 
* Bump submodule sha

* Bump pybind

* Bump OMZ

* Skip transformers[onnx]

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Co-authored-by: gklodkox <gracjanx.klodkowski@intel.com>
 2023-05-02 10:55:21 +02:00
Maxim Vafin
82dbca998a
Do not fuse Pad with negative pads (#17239) 
* Do not fuse Pad with negative pad values

* Update src/common/transformations/tests/common_optimizations/pad_fusion.cpp

* Update src/common/transformations/tests/common_optimizations/pad_fusion.cpp
 2023-05-02 10:49:53 +02:00
Andrew Kwangwoong Park
583f3e243c
[GPU] Remove temporary W/A for GPU NMS shape inference (#17306) 
Signed-off-by: Andrew Park <andrew.park@intel.com>
 2023-05-02 12:23:13 +04:00
Vladimir Paramuzov
b6761beb55
[GPU] Don't throw exception if no devices are found (#17288) 2023-05-01 13:57:06 +00:00
Roman Kazantsev
14e146b7c8
[TF FE] Extend pre-commit for SpaceToBatch after CPU crash (#17278) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-05-01 17:29:50 +04:00
Roman Kazantsev
b253342ea6
[TF FE] Use original input types for SavedModel (#17295) 
Also, refactor TF FE unit-tests

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-05-01 15:46:29 +04:00
Piotr Krzemiński
b7311d8907
[PT FE] Fix aten::chunk for dynamic shapes (#16902) 
* [PT FE] Add replacer for chunk+getitem

* [PT FE] Fix missing replaced nodes, fix incorrent chunk size calculation

* [PT FE] Fix incorrect item shape, reduce tests count

* [PT FE] Convert back with frontend

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
 2023-05-01 09:32:10 +00:00