Commit Graph

12340 Commits

Author SHA1 Message Date
Aleksandr Voron
9b10ef6f6f
[CPU][ARM] Fix inference precision for behaviour tests (#19485) 2023-08-30 09:38:30 +04:00
Taylor Yeonbok Lee
e8f1df495c
[GPU] Fixed reordered memory cache not to contain original weight memory (#19465)
* Fixed reordered memory cache not to contain original weight memory

* Applied review comment

* Applied review comment
2023-08-29 21:54:32 -07:00
Xiuchuan Zhai
36b9de1f25
enable sin/cos && fix top_k_v2 (#17525) 2023-08-30 08:55:57 +08:00
Anton Voronov
49c4c922ff
[CPU][OneDNN] Fix zero pad perf issues (#19417) 2023-08-29 16:55:45 +00:00
Oleg Pipikin
e3e1e8c811
Template plugin tests refactoring (#19397)
* Template plugin tests refactoring

* Apply comments
2023-08-29 13:48:53 +00:00
Aleksandr Voron
84fc6fb626
[CPU][ARM] Disable default fp16 inference precision (#19445) 2023-08-29 17:08:46 +04:00
Andrey Kashchikhin
f6ab1e4833
[CI] [GHA] Introduce GHA Linux Debian Pipeline (#19225)
* add linux debian pipeline

* remove push and pr triggers; prevent the workflow from scheduling of forks

* enclose cron

* rm unnecessary
2023-08-29 12:13:13 +01:00
Roman Kazantsev
928c75623b
[JAX][TF Hub][TF FE] Support XlaConvV2 operation and add JAX test (#19466)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-08-29 12:28:12 +04:00
Ilya Churaev
f30afa9ad3
Finalization of migration core unit tests (#19468) 2023-08-29 11:58:54 +04:00
Maciej Smyk
e6f09ac197
[DOCS] Docker Guide Update for master (#19410)
* docker-update

* id fix

* Update installing-openvino-docker-linux.md

* Update installing-openvino-docker-linux.md

* Update installing-openvino-docker-linux.md
2023-08-29 08:45:14 +02:00
Pawel Raasz
f9aa624099
[Core] Use API 2.0 in evaluate for trigonometric operators (#19414)
* Use API 2.0 in operators evaluate
- Drop ngraph namespace in ops
- Refactor reference implementation for modified ops

* Apply code style

* Fix build issue in reference impl

* Fix code style

* Fix compile warnings

* Add inputs check and set output shape in evaluates
2023-08-29 10:16:07 +04:00
Yuan Hu
915de21626
[CPU] Adopt the static shape inference interface developed by the ngraph (#17719) 2023-08-29 10:15:18 +04:00
Gorokhov Dmitriy
d32b6904bd
[CPU] Fixed has_subnormals behavior for negative zero values (#19360) 2023-08-29 13:53:05 +08:00
Pratham Ingawale
82afb47e36
generator functionality to pytest (#19402)
* trying with pytest

* update as per suggested

* pytest testing on compress_quantized_weights_test

* resolved warning of assert on tuple

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-08-29 03:01:49 +04:00
Pawel Raasz
c0fb4fabce
[ShapeInfer] Remove old API from shape inference sources (#19435)
* Remove old API from shape inference sources

* Fix build issues
2023-08-28 22:03:35 +02:00
Przemyslaw Wysocki
b7d73cbbe3
[PyOV] Limit cython version (#19443) 2023-08-28 17:36:51 +02:00
Sebastian Golebiewski
f306007e59
update-notebooks (#19450)
Add notebook 252-fastcomposer-image-generation. Fix indentation, admonitions, broken links and images.
2023-08-28 14:23:23 +02:00
Wilson Seok
94c21b53b3
fix build error by removing makeDynamicParam (#19431) 2023-08-28 12:10:05 +02:00
Pawel Raasz
2e78eec502
Fix boxes dim calculation when scores dynamic rank (#19097)
* Fix boxes dim calculation when scores dynamic rank

* NMS shape infer improve upper bound calculation

* Calculate boxes if required shapes has static rank

* Optimize shape_infer for NMS v4

* Reorder checks in nms v4 for selected boxes
2023-08-28 13:27:09 +04:00
Ilya Churaev
29ad3e8c92
Moved eval tests to new API (#19364)
* Moved eval tests to new API

* Fixed build

* Fixed eval tests
2023-08-28 10:22:14 +04:00
HARI CHAND BALASUBRAMANIAM
b87709a8a7
Create performance.yml (#18929)
* Create performance.yml

create new performance issue template for customers to report issue that related to performance

* Update performance.yml

Amend based on latest comment

* Update performance.yml

* Update performance.yml

amend based on suggestion
2023-08-28 07:29:04 +04:00
Ivan Tikhonov
0f9734aaa7
Transformation tests API 2.0: part 1 (#19366)
* API 2.0 replace ngraph headers and namespaces in CPU, LPT etc transformations tests

* revert the incorrect renaming

* function -> model in arm transformation tests
2023-08-27 18:52:03 +02:00
Wilson Seok
293c672064
add sqrt activation support in cpu_impl (#19421) 2023-08-25 12:10:01 -07:00
Wilson Seok
f6dca869b2
fix reduce perferred format selection and layout for partial shape (#19319) 2023-08-25 12:09:25 -07:00
Min, Byungil
bcedb0bb9b
[GPU] Resolve accuracy issue from clamp fused prims (#19409)
+ Added condition when clamp activation is added to fused-ops for fp16 overflow
+ Added test-cases

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2023-08-25 11:21:09 -07:00
Irina Efode
cddcec8ba8
[CONFORMANCE] Fix for Eye-9 op in the Opset Conformance report (#19404) 2023-08-25 17:22:18 +02:00
Wilson Seok
f962511a84
[GPU] add check condition of input dynamic shape in conv fusing (#19219) 2023-08-25 16:13:53 +04:00
Ilya Churaev
39b75fd213
Moved core tests from root folder to new API (#19381) 2023-08-25 15:23:41 +04:00
Vladimir Paramuzov
a45e5e03c5
[GPU] Added some formats for pvc (#19388) 2023-08-25 15:09:42 +04:00
Xiuchuan Zhai
1bdf4f0ab9
[CPU] Build fix: remove usage of makeDynamicParams from tests (#19412) 2023-08-25 10:29:51 +00:00
Katarzyna Mitrus
decc2e31f3
[ShapeInference] FFT based - revision and tests (part 1) (#19070)
* Reuse common shape validation for fft base

* Align helper names

* Common test class for fft ops

* Move all (I)DFT test cases to the common test class

* More test cases for param axes

* Init labels validation

* More label tests

* Labels validation for non const signal size

* Init label tests for IRDFT

* More label test for irdft

* Labels tests for RDFT

* Remove duplicated tests

* Rename common validation file

* Rename shape infer tests file

* Use node shape infer check

* Headers order alignment

* Add const to the test params vector

* Use this make_op

* Use OV_EXPECT_THROW in common fft tests

* Use OV_EXPECT_THROW iin rdft an irdft tests

* Pass input shapes and use SHAPE_INFER_CHECK

* Shorter error messages

* Update to use ov namespace in typeprop tests
2023-08-25 12:27:18 +02:00
Karol Blaszczak
06003f18d5
[DOCS] speech sample deprecation (#19228) 2023-08-25 12:26:44 +02:00
Ilya Churaev
679369c707
Move Visitor tests to new api (#19379)
* Moved visitor tests to new API

* Fixed build for Windows
2023-08-25 10:50:59 +04:00
Xiuchuan Zhai
350c4d2363
[CPU] Disable convert to BF16 in convert-range pattern (#18971) 2023-08-25 09:00:24 +04:00
Tomasz Jankowski
bcad953f5f
[Ref_Impl] Rename file paths to openvino relative (#19284)
* Move files to new directories

* Use quotes for openvino includes

* Provide proxy calls for transition

of dependant components.

* Correct includes style

* Redo proxies

* Fix deprecated

* Move aliases to proxy files

* Apply code style
2023-08-25 06:43:06 +04:00
Sofya Balandina
20e4c629e9
[conformance] Add shape mode and graph conv logic to test name (#19403) 2023-08-25 01:03:13 +02:00
Maxim Vafin
c5b64e458b
[PT FE] Align bool types and same bit int types (#19399)
* [PT FE] Align bool types and same bit int types

* Fix max value
2023-08-24 22:30:59 +02:00
Artyom Anokhov
eef6b35bef
[packaging] APT/YUM: Added conflicts for 2023.0.2 (#19398) 2023-08-24 19:42:15 +02:00
Chenhu Wang
28a5bf7b04
[CPU][Snippets] Dynamism via recompilation and cache (#15430) 2023-08-24 21:31:42 +04:00
Roman Kazantsev
8df85badf8
[TF Hub][TF FE] Support TensorListLength and TensorListResize operations (#19390)
* [TF Hub][TF FE] Support TensorListLength and TensorListResize operations

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

* Add test with empty tensor list

* remove assert

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-08-24 17:54:13 +02:00
Irina Efode
ba6cca8740
[CONFORMANCE] Add comparator accuracy vs conformance (#19374) 2023-08-24 16:22:13 +01:00
Sofya Balandina
b607c00c95
[conformance] Enable local cache using in SubgraphsDumper tool (#18850)
* [conformance] Fix same name for models

* add model name

* Update hash wwith input_info and graph_priority

* Fix double cache

* Read meta from file

* temp to check

* Move loop with caches and add attr to rename

* [conformance] Enable local cache using in SubgraphsDumper tool
2023-08-24 17:05:37 +02:00
Irina Efode
e0a75b78d1
[CONFORMANCE] Update runner readme (#19393) 2023-08-24 18:41:42 +04:00
Irina Efode
07ca0cd426
[CONFORMANCE] Remove debug code from Conformance runner (#19389) 2023-08-24 16:13:04 +02:00
Pavel Esir
eaeeea9c54
[tests] save into different file in compression_test.py (#19356)
* save into different file in compression_test.py

* reuse existing mechanism for tmp_file
2023-08-24 13:58:14 +02:00
yanlan song
498731f8fd
[AUTO] Fix static code scan issue (#19295)
* fix scan issue

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

* clang

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

* clang

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

---------

Signed-off-by: fishbell <bell.song@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
2023-08-24 10:01:11 +00:00
Ilya Churaev
6deca48413
Moved type prop tests to new API from g to z (#19353)
* Moved type prop tests to new API from g to z

* Fixed build
2023-08-24 12:59:49 +04:00
Kelvin Choi
ce47522165
[GPU] Memory reuse false for dynamic and null impl case (#19354) 2023-08-24 17:32:07 +09:00
Kelvin Choi
c89b9edfe7
[GPU] 7-dimention only supports plain format (#19039)
* Skip concat_input_order opt in case dependancy is dynamic

* Add plain 7d 8d case for jitter pitch size
2023-08-23 20:00:02 -07:00
Ilya Churaev
475ce744af
Remove legacy headers and namespaces from C-F type prop tests (#19332) 2023-08-24 06:56:53 +04:00