Jade Cho
6ce6a7662e
[GPU] Support implicit crop in input transposition. ( #11496 )
...
* [GPU] Support implicit crop in input transposition.
+ Make the crop in front of quantize implicit by changing output format to bfyx.
+ Use implicit concat after quantize nodes.
* Add unit test for implicit crop and concat.
+ remove unnecessary code.
2022-05-13 18:02:13 +09:00
Min, Byungil
5da3162cd1
[GPU] Bugfix for invalid LoadType for planar input ( #11493 )
...
+ Modified jitter Load for planar input of fused eltwise
+ Bugfix in jitter if planar input has LT_ALIGNED_READ
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-05-13 17:31:20 +09:00
Jan Iwaszkiewicz
d19b80a82d
[SoftSign-9][PYTHON] Python API for SoftSign ( #11677 )
2022-05-13 09:55:14 +02:00
Jade Cho
de1db99383
[GPU] Replace out scale attribute of onednn pooling with binary mul ( #11674 )
2022-05-13 13:34:12 +09:00
yanlan song
b1ecd3ea8f
only strip when device start with - ( #11651 )
...
Signed-off-by: fishbell <bell.song@intel.com>
2022-05-12 04:53:38 +00:00
Jan Iwaszkiewicz
62d17a070a
[SoftSign-9] Shell, reference impl and decomposition for SoftSign-9 ( #11546 )
2022-05-11 16:44:15 +02:00
Katarzyna Mitrus
7851020cd3
[ONNX] Enable ONNX ROIAlign-16 (by ov::v9::ROIAlign) ( #11633 )
2022-05-11 11:43:15 +02:00
Wilson Seok
5456631517
Cleanup eltwise skipped testcase in gpu single layer test ( #11525 )
...
* cleanup eltwise skipped test cases in gpu plugin
* update comment clearly
2022-05-11 18:07:36 +09:00
hyunback kim
a7368d2e35
[GPU] Apply hsigmoid decomposition in oneDNN post-opt ( #11603 )
...
* [GPU] Apply hsigmoid decomposition in oneDNN post-opt
Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-05-11 10:07:02 +09:00
Anuj Mittal
01a08c0a97
installing-openvino-yocto: update for 2022.1 ( #11657 )
...
Update the branch to be used for 2022.1 and remove reference to
-staticdev package which isn't generated anymore.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-05-10 18:00:42 +02:00
Kevin Putnam
bdf1d92660
1. Makes transition guide link absolute so it will work for API docs using the same theme ( #11610 )
...
2. Adds # to links that are broken in openvino_docs_get_started_get_started_demos.htm
Signed-off-by: intelkevinputnam <intelkevinputnam@github.com>
Co-authored-by: intelkevinputnam <intelkevinputnam@github.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-05-10 17:59:48 +02:00
Sebastian Golebiewski
4924e33255
Proofreading the Transition Guide ( #11543 )
...
* Update common_inference_pipeline.md
Minor stylistic and grammar corrections.
* Proofreading
Minor stylistic and grammar corrections.
* Update common_inference_pipeline.md
* Update common_inference_pipeline.md
* Proofreading
Minor corrections
* Update preprocessing.md
* Update intro.md
* Update deployment_migration.md
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
* Update intro.md
* Update docs/OV_Runtime_UG/migration_ov_2_0/common_inference_pipeline.md
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
* Update deployment_migration.md
* Update intro.md
* Update common_inference_pipeline.md
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
* Update docs/OV_Runtime_UG/migration_ov_2_0/intro.md
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
* Update intro.md
* Update deployment_migration.md
* Update docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md
Co-authored-by: msmykx <101244365+msmykx-intel@users.noreply.github.com>
Co-authored-by: Maciej Smyk <maciejx.smyk@intel.com>
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2022-05-10 17:59:12 +02:00
Paul Youngsoo Ahn
35b8972da3
[GPU] fix coverity control flow issue ( #11585 ) ( #11585 )
...
- Coverity CID: 1488473
- Coverity CID: 1486904
2022-05-10 09:15:03 +09:00
Bo Liu
eddd31f58f
Liubo/roi align 9 ov core cpu plugin ( #11188 )
...
* roi_align_9: ov_core, transformations, template_plugin
* roi_align_9: CPU Plugin
* keep only constructor with enums which is aligned with spec
* remove evaluate function for ROIAlign_9
* Add op check test for operation ROIAlign-9
* Apply suggestions from code review
* fix version name from 'v0' to 'v3' in transform part
* use common shape_infer function for v3 and v9
* remove'tf_' prefix for ROIAlign::AlignedMode to avoid misleading for models from different platforms
2022-05-10 08:14:37 +08:00
Karol Blaszczak
ad61593aa5
Update Convert_Model_From_TensorFlow.md ( #11425 ) ( #11591 )
...
* Update Convert_Model_From_TensorFlow.md (#11425 )
* Apply suggestions by Yuan
The changes are made in the port PR, so will be published with the 22.2 version.
Co-authored-by: Evan <evan.juras@gmail.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-05-09 16:49:15 +02:00
Karol Blaszczak
ab7b9afc14
Docs: Add links to specific examples - port ( #11618 ) ( #11653 )
...
* Docs: Add links to specific examples (#11618 )
* Update docs/OV_Runtime_UG/integrate_with_your_application.md
* Add links to specific examples
This edit adds links to more example applications, making it easier for users to discover how to build an OpenVINO application around their specific model.
* Add links to MO installation and ONNX examples (#11617 )
These edits help make it easier for a new user to find more information on how to convert ONNX models.
* Apply suggestions by Yuan
The changes are made in the port PR, so will be published with the 22.2 version.
Co-authored-by: Evan <evan.juras@gmail.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-05-09 16:48:39 +02:00
Tomasz Dołbniak
53e62d2ac6
ONNX OperatorsBridge - non-static version ( #11578 )
2022-05-09 12:58:51 +00:00
Kelvin Choi
860a074fa9
[GPU] Add tuning cache v2 for yolo_v3 and yolo_v3_tiny ( #11589 )
2022-05-09 17:10:11 +09:00
Mateusz Bencer
99c04c0d6a
additional validation of places ( #11480 )
2022-05-09 07:24:07 +00:00
yanlan song
35ad252003
Bell/rule out device ( #11516 )
...
* Fix batchability check of MAX_BATCH_SIZE
* Applied review comment
* new implementation
Signed-off-by: fishbell <bell.song@intel.com>
* enable device removing
Signed-off-by: fishbell <bell.song@intel.com>
* enable tests
Signed-off-by: fishbell <bell.song@intel.com>
* Update plugin.hpp
cpplint error
Co-authored-by: Taylor Yeonbok Lee <taylor.lee@intel.com>
2022-05-07 17:41:59 +08:00
Mateusz Bencer
c404e7f76d
Handle onnx shape inference exceptions ( #11451 )
2022-05-07 01:04:07 +03:00
Mateusz Bencer
d60deae083
If shape inference - scalar and 1D union handle ( #11499 )
2022-05-07 00:55:36 +03:00
Tomasz Jankowski
e0e916b557
[ONNX] Extract onnx frontend tests from ov core unit tests ( #11535 )
2022-05-06 11:21:55 +02:00
Jan Iwaszkiewicz
6eb9c11d7e
[PYTHON] Infer calls improvement ( #11498 )
2022-05-06 08:58:00 +02:00
yanlan song
912f40e74d
stateful inferface impl for AUTO/HETERO ( #11590 )
...
* CPU for stateful model
Signed-off-by: fishbell <bell.song@intel.com>
* log
Signed-off-by: fishbell <bell.song@intel.com>
* hetero impl
Signed-off-by: fishbell <bell.song@intel.com>
* enable tests
Signed-off-by: fishbell <bell.song@intel.com>
2022-05-06 12:43:56 +08:00
guozhong wang
870455675c
add cumulative_throughput for python ( #11195 )
2022-05-06 12:43:41 +08:00
guozhong wang
0a65f5f607
selectdevice returns MULTI:device in cumulative_throughput ( #11367 )
...
* selectdevice returns MULTI:device in cumulative_throughput
* load multi with throughput and disable cpu helper in cumulative
* disable cpu helper in cumulative_throughput
* add cumulative to bechmark_app help message
* modify benchmark_app.hpp clang-format
2022-05-06 12:42:59 +08:00
Andrew Kwangwoong Park
caccde6a82
[GPU] Add TC for MXNet-style NMS model(decrease_label_id) ( #10624 )
...
- Add TC for decrease_label_id=true to cover MXNet-style NMS models
- Fix segfault issue that occurs when data precision is fp16
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
Signed-off-by: Andrew Park <andrew.park@intel.com>
2022-05-06 10:36:46 +09:00
Artur Kulikowski
1331eabbed
Getting of python version depend on the used shell ( #11614 )
2022-05-05 23:42:54 +02:00
Katarzyna Mitrus
50287625d7
[Eye-9] Python API for Eye-9 ( #11552 )
2022-05-05 16:16:36 +02:00
mei, yang
2d0ffd8fe5
Specify GenerateProposals-9 ( #11004 )
2022-05-05 10:28:18 +02:00
Bo Liu
d560cf19a3
Specify ROIAlign-9 ( #11067 )
2022-05-05 10:27:58 +02:00
cecilia peng
e68613a2fc
Specify MulticlassNonMaxSuppression-9 operation ( #11083 )
2022-05-05 10:27:47 +02:00
Mateusz Tabaka
68ef1555bc
Enable test_loop_simple_precommit on GPU ( #11625 )
2022-05-05 09:55:02 +02:00
Tomasz Jankowski
0babf20bd2
Remove unsued map initialization ( #11621 )
...
Details:
- Unused variable removed.
- Added pytest markers declaration to avoid useless warnings.
Tickets:
70158
2022-05-05 00:50:34 +02:00
Mateusz Tabaka
b92e10ff6e
Fix setting default affinity property in cpuFuncTests ( #11609 )
...
CPU plugin sets default affinity to HYBRID_AWARE
if it's running on AlderLake, so we need to reflect that
in cpuFuncTests.
2022-05-04 12:42:43 +02:00
Tetiana Gubanova
7dd8fbd47e
[GPU] Einsum with repeated labels and ellipsis support ( #11615 )
...
* Einsum test helper
* Einsum single layer tests
* Add Einsum decomposition with repeated labels and ellipsis support
to GPU transformations pipeline
Co-authored-by: Oleksii Khovan <okhovan@lohika.com>
2022-05-03 20:46:22 +09:00
opoluektov-lohika
1ed03bbe6b
Fix conformance test runner handling of input directories ( #11611 )
...
Check first whether the path specified by --input_dirs is a directory.
Otherwise the argument is always treated as a .lst file,
and in case it is a directory it silently fails,
which causes the test runner to not execute any tests intended.
2022-05-02 22:00:21 +09:00
Artur Kulikowski
26aa197cb1
Expand ONNX functions in Graph ctor ( #11599 )
...
* Expand ONNX function in constructor of class Graph
* Add test to expanding function GreaterOrEqual inside If op
2022-05-02 10:12:41 +02:00
Jan Iwaszkiewicz
8d221d1e06
Add lower bound for wheel package ( #11595 )
2022-04-28 13:02:46 +02:00
Sebastian Golebiewski
844fbde328
Update installing-openvino-windows-header.md ( #11221 )
...
* Update installing-openvino-windows-header.md
* Update docs/install_guides/installing-openvino-windows-header.md
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2022-04-27 13:09:31 +02:00
Karol Blaszczak
f5781b1255
DOCS-cpu_language_review-port ( #11537 )
...
* DOCS-cpu_language_review
Co-Authored-By: Yuan Xu <yuan1.xu@intel.com>
* Update docs/OV_Runtime_UG/supported_plugins/CPU.md
* Update docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-04-27 13:07:38 +02:00
Mateusz Tabaka
54e5af95da
Disable two cases from smoke_Conv_3D_FP32_fusingScaleShiftAndFakeQuantizePerChannel ( #11536 )
...
They sporadically fail in precommit.
Ticket: 84153
2022-04-20 14:34:46 +02:00
Mateusz Tabaka
e53f702f81
Handle negative axis in SimplifySecondInputOfReshape ( #11524 )
...
Fixes #11501
2022-04-19 12:20:21 +02:00
Karol Blaszczak
22398ac9cd
sphinx google search ( #11439 ) ( #11506 )
...
porting from 22.1 as per Andrey's request from 04.08
* sphinx google search
* fixes
* fixes
* fix version tabs
Co-authored-by: Nikolay Tyukaev <nikolay.tyukaev@intel.com>
2022-04-13 12:39:36 +02:00
Karol Blaszczak
1b5756a4d7
Docs benchmarktool python correction - port ( #11505 )
...
* DOCS-benchmarktool_python_correction
add info on tool installation
* Update docs/OV_Runtime_UG/Samples_Overview.md
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
2022-04-13 11:14:39 +02:00
Karol Blaszczak
1e1735b022
Fixed operation names ( #11447 ) ( #11507 )
...
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
2022-04-13 11:14:24 +02:00
Alexandra Sidorova
9dffa706fb
Added shell for Eye-9 ( #11210 )
2022-04-12 12:49:07 +02:00
Przemyslaw Wysocki
76610393a0
[PYTHON] Change dependabot schedule ( #11497 )
2022-04-12 11:17:29 +02:00
Katarzyna Mitrus
5bedbbe05d
[ONNX] Add Scan operator to ONNX Frontend ( #11053 )
2022-04-12 10:35:15 +02:00
