Commit Graph

9423 Commits

Author SHA1 Message Date
Maciej Smyk
a14c9e3ae5
DOCS: Libraries for Local Distribution image recreation for master (#14950)
* deployment_full

* Update deployment_full.svg
2023-01-05 23:14:43 +04:00
Tomasz Dołbniak
52f6fdeb52
ONNX CastLike operator tests (#14936) 2023-01-05 17:55:42 +00:00
Roman Kazantsev
a38366a707
[TF FE] Fix Wide and Deep model conversion (#14931)
* [TF FE] Fix Wide and Deep model conversion

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

* Fix build

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-01-05 17:29:39 +00:00
Ilya Lavrenov
10253c1b12
Cross-compilation for ARM on Windows (#14933) 2023-01-05 17:24:08 +04:00
Tomasz Dołbniak
13d01d969b
[BENCHMARK_APP] Help message cleanup (#14786) 2023-01-05 14:21:09 +01:00
Sebastian Golebiewski
99c7ee1c18
DOCS: Hiding Transition to API 2.0 banner - for master (#14949)
Using cookies to keep the banner hidden once the user has closed it.
2023-01-05 13:52:30 +01:00
Sebastian Golebiewski
136e375a93
DOCS: Updating Interactive Tutorials - for master (#14945)
Adding new tutorials:
404-style-transfer-webcam
406-3D-pose-estimation-webcam
2023-01-05 13:49:42 +01:00
Roman Kazantsev
f13e7e1352
[TF FE] Support If and PartitionedCall operations (#14910)
* [TF FE] Support If and PartitionedCall operations

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

* Fix build

* Fix frontend wrapper for tests

* Erase tensor names in body graph before caching

* Apply code-review feedback: recover m_op_translators in Frontend

* Rename test models

* Rename unit-tests

* Correct scripts for test model generation

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-01-05 15:34:15 +03:00
Andrew Kwangwoong Park
efb602e13b
[GPU] Update strided slice impl for non-constant begin/end/stride support (#14619)
* Add strided slice dynamic TCs for gpuFunctests

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

* Update StridedSliceLayerGPUTest for rest inputs's type (parameter)

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

* remove W/A for strided slice

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

* primitive API updates for dynamic begin/end/stride inputs support

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

* Update ocl impl and kernel param, and strided_slice_ref kernel w/o memory_deps

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

* Update TCs for new API w/ vectors on strided_slice_gpu unittests

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

* Apply code review

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

* Apply padding when the size of rest input data is smaller than actual input rank

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

* Update strided_slice_optimize pass to run onyl when all deps are constant

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

Signed-off-by: Andrew Park <andrew.park@intel.com>
2023-01-05 13:31:32 +03:00
Sebastian Golebiewski
3017c8d123
DOCS: Fixing broken links in documentation. (#14935) 2023-01-05 11:25:03 +04:00
Min, Byungil
0d261dbf83
Add decomposing Reduce for Bugfix of byx reduction (#14449)
+ Add transformation to fix accuracy issue of oneDNN reduction : DecomposeReduceForFalseKeepdims
+ Add Reshape to modify output of Reduce and update keep_dims to true : reduce-reshape
+ Add exception logic for unsupported reduce mode by byx conversion

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2023-01-05 15:44:12 +09:00
Jade Cho
9427623046
[GPU] Swap XY axis for 1D conv (#14362) 2023-01-05 14:58:55 +09:00
Wilson Seok
e422b5acb4
[GPU] fix strided_slice_optimize for 5d new axis output, typo in strided_slice cl kernel, avoid handle_reshape when user is only one (#14812)
* fix strided_slice_optimize for 5d new axis output, typo in strided_slice cl kernal, avoid handle_reshape when user is only one

* fix unit test of resample_eltwise_fusing_through/12
2023-01-05 10:36:16 +09:00
Giovanni Saponaro
e07bd74f38
Fix inference pipeline C++ doc: refer to the correct input blob (#14709) 2023-01-05 01:20:05 +04:00
Ilya Lavrenov
a881ce4999
Fixed pattern for CPP API label (#14934) 2023-01-04 17:55:22 +04:00
Vladimir Paramuzov
e23b8492c5
[GPU] Change default infer precision to fp16 (#14752) 2023-01-04 15:55:44 +04:00
Karol Blaszczak
f31ebd4947
Release doc updates_port (#14784) 2023-01-04 11:12:11 +00:00
Aleksandr Voron
45bf23e527
PyPi documentation - add M1 related updates (#14919)
* pypi-openvino-update-m1

* Update pypi-openvino-rt.md

* Update pypi-openvino-dev.md
2023-01-04 15:02:15 +04:00
Alexander Kozlov
0dd7f8ed23
Excluded some CI checks for changes in the tools (#14926)
* Excluded some CI checks for changes in the tools

* Reverted windows CI pipeline
2023-01-04 15:01:26 +04:00
Maciej Smyk
ca447a2eb7
yolo_tiny_v1 (#14878) 2023-01-04 11:11:46 +01:00
Karol Blaszczak
e40e6c26ef
Docs] remove system requirements from install guides port (#14912)
System Requirements removed where OS or hardware is mentioned... Docker articles not included

* include selector tool in install guide
2023-01-04 11:07:20 +01:00
Maciej Smyk
6ef7dccba1
quantization_picture (#14868) 2023-01-04 11:07:05 +01:00
Pawel Raasz
000a634429
Remove code duplicates for shape inference utils (#14721)
* Remove code duplicates for shape inference utils

* Fix typos and comments
2023-01-04 10:56:35 +01:00
Ilya Lavrenov
a0be13be57
Updated Azure pipelines (#14896)
* Updated Azure pipelines

* Optimize clone time

* Removed OMZ build

* Fixed patterns in triggers

* Test

* Include ours branch

* Fixed filters on Windows
2023-01-04 11:00:18 +04:00
Tomasz Jankowski
fc8c1a1193
[Transformations] ConvertMVN1ToMVN6: Limit downgrading downcast (#14669)
* Add anti-downgrade downcast test

* Strengthen limits test

* Allow convert if normalization is off

* Suppress downgrading for F64 only

* Limit eps values to float

* Limit eps values to float

* Add test

* Consider actual double values
2023-01-04 06:58:13 +01:00
Yuan Xu
2188af6e28
Samples overview update (port from #14658) (#14898)
* add ways to find samples for PyPI installation (#14658)

* update github link
2023-01-04 10:30:21 +08:00
Yuan Xu
de474c16f2
Install macos updates (port from #14656) (#14904)
* Update macOS archive installation with ARM64 for 22/3 (#14656)

* update macos archive installation with arm

* update python version

* fix formatting

* fix formatting

* update

* remove note

* update package names & version number

* update version number
2023-01-04 10:27:40 +08:00
Yuan Xu
480d4b16cf
update windows installation & links (#14905) 2023-01-04 10:26:30 +08:00
Liubov Talamanova
39ff705a3e
[POT] Update CI branch (#14916)
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
2023-01-03 17:26:36 +00:00
Maciej Smyk
9c14991ebd
nncf_workflow (#14865) 2023-01-03 17:15:22 +01:00
Szymon Irzabek
c683a72400
Gna namespace (#14877)
* [GNA] Cleanup intel_dnn

* [GNA] Replace GNAPluginNS

* [GNA] Rename headers
2023-01-03 15:06:23 +00:00
Maciej Smyk
f2d93f4a79
deployment_simplified (#14853) 2023-01-03 15:59:34 +01:00
Sun Xiaoxia
4b80b4850c
[CPU] Moved streams number computation to CPU plugin from IStreamsExecutor::Config (#14502) 2023-01-03 14:05:56 +00:00
Shen, Wanglei
367058b89e
enable new method to generate CPU information and CPU map on Linux (#14456)
* enable new method to generate CPU information and CPU map

* fix code style issue

* fix initialization issue of variable-sized object

* fix dependency issue

* add sample of CPU map

* add description and sample for CPU map

* fix code style issue

* fix code style issue

* add comments on using second processor as physical core

* update _cpu_mapping to align with Windows implementation

* update description for better understanding

* update cpu mapping table for scaling.

* add check if system folder is accessible

* merge new CPU resource based on CPU mapping table with previous CPU resource based on calculation

* fix typo in note

* add description for GROUP_ID
2023-01-03 21:56:21 +08:00
Maciej Smyk
29b17e1c23
autoplugin_accelerate (#14838) 2023-01-03 14:55:21 +01:00
Maciej Smyk
b361c132d6
DOCS: The LowLatency Transformation images recreation for master (#14827) 2023-01-03 14:48:59 +01:00
Yuan Xu
9fc0f1cb7d
Install raspbian updates (#14902)
* Update Raspbian OS installation for 22/3 (#14628)

* update Raspbian OS installation

* test formatting

* fix formatting

* Apply suggestions from code review

* update version number & package names

* Updated docs for Raspbian OS (#14816)

* Updated docs for Raspbian OS

* Update docs/install_guides/installing-openvino-raspbian.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

* update version number

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-01-03 17:46:27 +04:00
Georgy Krivoruchko
8dc946af5c
Added TF Convolution layer tests (#14851) 2023-01-03 17:00:25 +04:00
Yuan Xu
4248cdff28
Add CentOS back to install archive page for 22/3 (#14625) (#14903) 2023-01-03 16:07:40 +04:00
Ilya Churaev
40959a410c
Undef DEBUG macro for log level property (#14897)
* Undef DEBUG macro for log level property

* Renamed define
2023-01-03 16:01:35 +04:00
Sebastian Golebiewski
94662fc236
format pre tags (#14889) 2023-01-03 12:23:40 +01:00
Ilya Lavrenov
d3f7adf63a
Add token for labeler workflow (#14908) 2023-01-03 12:54:11 +04:00
Ilya Lavrenov
1d690fbb50
Added workflow to add labels (#14895)
* Added workflow to add labels

* Preserve groups in codeowners files
2023-01-03 12:26:09 +04:00
Ilya Churaev
8a223adf05
Added iterator to any name (#14766)
* Added iterator to any name

* Fixed code style

* Remove constructor

* Revert "Remove constructor"

This reverts commit 134625a651.

* Add new constructor

* Init iterator
2023-01-03 12:22:55 +04:00
Ilya Lavrenov
808a6b7b83
cmake: arm rasp-pi cross-compilation on macOS (#14894) 2023-01-03 11:48:33 +04:00
Karol Blaszczak
af3c7894a6
DOCS]-workflow-article-titles-tweaks (#14892) 2023-01-03 08:02:53 +01:00
Michael Frank Hansen
6690c7c9a5
Update benchmark-data.csv (#14794)
fixes the FP32 and FP16 swap of results.

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2023-01-02 12:43:59 +01:00
Vladimir Paramuzov
5a4dbb6760
[GPU] Enable oneDNN primitives cache (#14835) 2023-01-02 13:44:43 +04:00
Felix Dohyun Kim
9cde294b7f
[GPU][DG2] Fix unit test: test_select_preferred_formats.setting_target_conv_format (#14837)
* Fix wrong weight shape
* Output layout initialization
* Ensure preferred output format is selected
2023-01-02 17:36:18 +09:00
Ilya Churaev
a8fa767f41
Fixed sanitizer flags for Ubuntu (#14763) 2023-01-02 12:33:29 +04:00