IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
9,000 Commits 38 Branches 54 Tags 1.1 GiB
f5e6816633
Commit Graph

9000 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Sun Xiaoxia
f5e6816633
fix compilation of test fails on Android x86 (#14442) 2022-12-06 20:24:18 +04:00
Irina Efode
eb19a7f7ad
[CONFORMANCE] Fix condition for WIN in Conformance runner (#14441) 2022-12-06 20:14:05 +04:00
Tomasz Dołbniak
6da95784c7
Unique-10 tests and improvements (#14315) 2022-12-06 19:09:30 +03:00
Luwei Zhou
79f04a704c
[CPU] Extend AMX deconv int8 to support oscale+eltwise+eltwise post ops pattern (#14026) 
* Extend AMX deconv int8 to support oscale+eltwise+eltwise post ops pattern.

* Add deconv AMX test cases.

* Add multi-eltwise test on deconv AMX int8.

* Applied review comments.

* Update onednn submodule.
 2022-12-06 18:32:02 +04:00
Maxim Vafin
3b86f12c37
Revert "Fix squeeze shape infer to not change axis value (#13975)" (#14430) 
This reverts commit 580c0c6b90.
 2022-12-06 17:32:56 +04:00
Irina Efode
a27d69db75
[CONFORMANCE] FIX ISSUES FOR WIN IN CONF RUNNER (#14439) 2022-12-06 16:06:04 +03:00
Nadezhda Ageeva
23481a5403
Move ReshapePRelu to common transformation to reuse it in NV plugin (#14169) 2022-12-06 16:58:51 +04:00
Irina Efode
462176dfc4
[CONFFORMANCE] Fix hans reporting in conformance tests (#14427) 2022-12-06 16:57:19 +04:00
Irina Efode
4b1d89ba96
[CONFRORMANCE] Fix Hash script according impossible way to get_shape (#14435) 
* [CONFRORMANCE] Fix Hash script according impossible way to get_shape

* add try except
 2022-12-06 16:55:57 +04:00
Karol Blaszczak
e27b2cf119
rewording in supported_model_formats (#14334) 
Merging with a slight rewording of the last suggestion by Andrei. We still want to retain consistency between paragraphs in structure and naming. If any further polishing needs to be done, we can create a new PR, while it can be published ASAP.
 2022-12-06 13:42:33 +01:00
Trawinski, Dariusz
b914a8c71c
fix syntax (#14436) 2022-12-06 16:04:46 +04:00
Luwei Zhou
da5b53e574
[CPU] Fix Deformable Convolution invalid read issue (#14326) 
* Fix MACOS compiling issue when enabling CPU_DEBUG_CAPS.

* Fix Deformable Convolution segment fault caused by invalid access offset index.
 2022-12-06 15:48:28 +04:00
Anastasia Kuporosova
09b24a1932
Fix XML vulnerabilities found by bandit (#14415) 
* Fix vulnerabilities found by bandir

* fix vulnerabilities in tests dir

* fix for mo

* some changes
 2022-12-06 11:46:26 +01:00
Karol Blaszczak
17c55ada85
Create the supported_models page (#14395) 
Merging as is, although further changes may be required. Specifically, the placement in the menu structure.
 2022-12-06 11:46:01 +01:00
Wilson Seok
bdcbdf71fc
revert PR#12456 - removing arg_max_min and experimental_detectron_topk_rois in whiteof program.cpp (#14422) 2022-12-06 19:38:03 +09:00
Wang, Yang
cd9131267e
[AUTO][Benchmark APP] sync config parsing logic of benchmark python version with benchmark c++ version (#14328) 
* sync benchmark Python version with benchmark C++ version.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

* Update tools/benchmark_tool/openvino/tools/benchmark/main.py

Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>

* Update tools/benchmark_tool/openvino/tools/benchmark/utils/utils.py

Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>

* Enable dump/load to support ov::device::properties parsing in benchmark python version.

* Enable benchmark python version to parse configuration file with device properties setting for AUTO/MULTI.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update usage of benchmark dumping/loading configuration in README and help message.

* Update comment.

* Update comments of the code.

* Update format of '-load_config' help message.

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
 2022-12-06 17:28:25 +08:00
Pavel Esir
33ab2fd39a
always remove '_tmp' files even after offline_transformations has failed (#14335) 2022-12-06 13:19:30 +04:00
yanlan song
4f1ad3bf3d
Bell/fix gpu load model file wrong lifecycle (#14347) 
* ensure correct lifecycle with load model file

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

* clang format

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

* enable tests

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

Signed-off-by: fishbell <bell.song@intel.com>
 2022-12-06 11:29:07 +03:00
Luo Cheng
bf0d2cea4b
[CPU] Relax threshold for using brgconv1x1 instead of inner product (#14351) 
* relax condition

* modify new shape due to threshold changed

* rename M to an exact name

* apply review comments
 2022-12-06 09:23:32 +01:00
Karol Blaszczak
f12765ebef
Docs - benchmarks new solution (#14396) 
* add bench csv
* Update custom.css
* images and scripts
 2022-12-06 08:19:03 +01:00
Karol Blaszczak
d47033cc05
reintroduce benchmarks for ovms (#14403) 
port from: #14271
Recreate performance_benchmarks_ovms.md and add it to TOC of performance_benchmarks.md
 2022-12-06 08:03:40 +01:00
Vladimir Paramuzov
d0a6122cb2
[GPU] Fixed incorrect explicit transpose op inserted for MatMul (#14400) 2022-12-06 09:50:14 +04:00
yanlan song
0d1659c443
Bell/fallback singledevice network with dynamicoutput (#14291) 
* change default value

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

* load to single device with stateful/dynamic model

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

* refine

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

Signed-off-by: fishbell <bell.song@intel.com>
 2022-12-06 11:45:28 +08:00
guozhong wang
796ce53371
change AUTO default hint to Latency (#14236) 
* change AUTO default hint to Latency

* Change the comment tput to latency according to wangyang opinion

* fix testcase for MULTI, the hint default value returned by MULTI is throughput

* Remove the redundant testcase and modify the name of the testcase that returns the default value of hint

* Code optimization according to bell opinion, add comments to testcase

* Correct the comments of testcase

* When user sets num_streams, AUTO/MULTI does not set the default hint to HW plugin

* Fix the problem that smoke_AUTO_MULTI_ReturnDefaultHintTest fails to run

* add num_streams and default hint mock testcase

* add auto default perf hint mock testcase
 2022-12-06 11:41:43 +08:00
Evan
e1acaf67c5
Docs: Update Get Started page (#13917) 
* docs: Change subtext on intro blocks

* docs: Rewrite GSG

* Update docs/get_started.md

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

* Update docs/get_started.md

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

* Update docs/get_started.md

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

* Update docs/get_started.md

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

* docs: change links to markdown format

* Apply suggestions from code review

* Update docs/get_started.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Update docs/get_started.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Update docs/get_started.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Update docs/get_started.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* docs: remove header links

* docs: edit "Install OpenVINO" sentence

* Update docs/get_started.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
 2022-12-06 11:34:40 +08:00
Evan
72414851b8
Docs: Update Benchmark Tool example outputs (#13555) 
* docs: revise example and update outputs

* docs: revise example and update outputs

* docs: typo fix

* docs: rectify changes

* docs: add <a> tag

* Update README.md

* docs: change example to use asl-recognition model

* docs: fix <a> tag

* docs: update sample outputs

* docs: change example to use asl-recognition model

* docs: revise example to use asl-recognition model

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
 2022-12-06 05:54:06 +03:00
hyunback kim
2483f4a0db
[GPU] Fix dead lock from exceeded max size of host memory allocation. (#14364) 
* [GPU] Fix dead lock from exceeded max size of host memory allocation.

Dead lock hang issue because remote_context ignore the exception and
return null. Use lock_guard.

Signed-off-by: hyunback <hyunback.kim@intel.com>
 2022-12-06 11:30:22 +09:00
yanlan song
df814fe668
keep the behavior of setting batch config through auto/multi (#14398) 
Signed-off-by: fishbell <bell.song@intel.com>

Signed-off-by: fishbell <bell.song@intel.com>
 2022-12-06 10:21:21 +08:00
Ilya Lavrenov
0357a97c40
Don't install scripts which are not used (#14414) 2022-12-05 23:35:02 +04:00
Roman Kazantsev
a945597802
[TF FE] Use _output_shapes attribute for Placeholder (#14383) 
* [TF FE] Use output_shapes attribute for Placeholder

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

* Add test model

* Apply code-review feedback and remove compile warnings

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-12-05 23:13:53 +04:00
Ilya Lavrenov
fcc4e60441
Amazon linux 2 support (#14412) 
* Use prebuilt cmake in install-dependencies steps

* Removed building of custom python to save Azure CI time

* Adjusted conditions in cmake

* Download VPU custom kernels compiler only for x86

* Removed -pyver argument

* Improvements

* Detect glibc version

* Usage of new glic variable

* Fixed typo

* Increased glibc version for MYRIAD case

* Made OpenVINO cmake Linux flavors agnostic

* Detect glibc version on RedHat

* Use clcompiler only since ubuntu 18.04

* Universal way to detect glibc version

* Revert some changes

* Added support of AmaZon Linux 2

* Amazon Linux 2 support
 2022-12-05 21:38:52 +04:00
Kevin Putnam
afa95b87f7
Moves nav items from top of page to left nav (#14295) 
Removes nav items from top of page and moves to left nav.
Uses a redirect to home.html to replace index.html.
Restores path variables
Removes debug print statement
Fixes path.

Signed-off-by: Kevin Putnam <kevin.putnam@intel.com>
 2022-12-05 17:13:40 +01:00
Ilya Lavrenov
77f3ad9c26
Fixed typo in Windows Azure steps names (#14404) 2022-12-05 18:51:48 +04:00
Anastasia Kuporosova
2daf145c97
[Docs] Add missed documentation for opset9 and opset10 (#14406) 2022-12-05 18:50:25 +04:00
Egor Duplenskii
b585393fee
[CPU] Disable memfd kernel memory allocation in oneDNN (#14358) 
to avoid segfaults and std::bad_alloc issues
 2022-12-05 18:42:53 +04:00
Trawinski, Dariusz
d5a4d169d7
prepare install NEO script for rhel8.7 and ubi8.7 (#14408) 
* enable install scripts for rhel8.7

* fix syntax error
 2022-12-05 18:42:28 +04:00
Irina Efode
b1be628861
[IE TESTS] Add step logging in case of Conformance tests (#14302) 
* [IE TESTS] Add step logging in case of Conformance tests

* fix code style

* align

* one more

* Update ov_subgraph.cpp
 2022-12-05 17:19:30 +03:00
Nikolay Shchegolev
3959890691
[CPU] Unique operation implementation. (#14250) 2022-12-05 17:45:20 +04:00
Ilya Churaev
8c3425ff69
Fixed i420 tests (#14390) 
* Fixed i420 tests

* Disable GPU i420 tests
 2022-12-05 13:13:26 +00:00
Zlobin Vladimir
67d25d7099
Add benchmark samples (#13388) 
* Add sync_bnehcmark

* Fix Unix comilation

* niter->time

* Explain main loop

* samples: factor out common

* Code style

* clang-format -i

* return 0; -> return EXIT_SUCCESS;, +x

* Update throughput_benchmark

* Add READMEs

* Fix READMEs refs

* Add sync_benchmark.py

* Add niter, infer_new_request, -pc

* from datetime import timedelta

* Fix niter and seconds_to_run

* Add disclaimer about benchmark_app performance

* Update samples/cpp/benchmark/sync_benchmark/README.md

* Add dynamic_shape_bert_benhcmark

* Add dynamic_shape_detection_benchmark

* Adopt for detr-resnet50

* Remove sync_benchmark2, throughput_benchmark2, perf counters

* clang-format -i

* Fix flake8

* Add README.md

* Add links to sample_dynamic_shape_bert_benchmark

* Add softmax

* nameless LatencyMetrics

* parent.parent -> parents[2]

* Add bert_benhcmark sample

* Code style

* Add bert_benhcmark/README.md

* rm -r samples/python/benchmark/dynamic_shape_bert_benhcmark/

* rm -r samples/cpp/benchmark/dynamic_shape_detection_benchmark/

* bert_benhcmark/README.md: remove dynamic shape

* Remove add_subdirectory(dynamic_shape_detection_benchmark)

* flake8

* samples: Add a note about CUMULATIVE_THROUGHPUT, don’t expect get_property() to throw, don’t introduce json dependency for samples/cpp/common

* / namespace

* Add article

* namespace -> static

* Update README, seconds_ro_run 10, niter 10, no inter alinment

* percentile->median

* benchmark samples: use generate(), align logs, update READMEs

* benchmakr samples: remove percentile()

* samples/python/benchmark/bert_benhcmark/bert_benhcmark.py: report average sequence length and processing time

* Python samples: move requirements.txt to every sample

* Remove numpy from requirements.txt

* Remove Building section from Python samples, install only required extras from openvino-dev, set up environment for bert_benhcmark, report duration for bert_benhcmark

* Install openvino-dev for Hello Reshape SSD C++ Sample
 2022-12-05 15:12:53 +04:00
Przemyslaw Wysocki
a96f2af2f4
[PyOV] Upgrade mistune and remove import-order (#14356) 2022-12-05 10:16:24 +01:00
Maciej Kwapulinski
86c7b588cf
Unit test corevage for race at GNAPlugin destruction (#13905/SHA-1:57293a6833) (#14346) 2022-12-05 09:04:50 +00:00
Pavel Zamelin
d9ef9266c3
Move inference_engine_snippets to core component (#14338) 2022-12-05 11:37:19 +04:00
Ilya Churaev
1e5247e5bb
Disabled constant folding for branch with Range operation (#14389) 2022-12-05 11:33:43 +04:00
hyunback kim
507585b526
[GPU] Fix to access from not allocated memory (#14289) 
During constant propagation, unexpected to access not allocated memory in input_layout_inst

Signed-off-by: hyunback <hyunback.kim@intel.com>
 2022-12-05 16:25:00 +09:00
Maksim Doronin
c636d1dbfc
R20 MX firmware update (#14376) 2022-12-05 07:15:19 +01:00
Ilya Lavrenov
331b1883a1
Use prebuilt cmake in install-dependencies steps (#14368) 2022-12-05 10:10:31 +04:00
Vladimir Paramuzov
48c0897b0f
[GPU] Adjust default num streams (#14308) 2022-12-05 09:59:03 +04:00
Tatiana Savina
b76168b32b
[DOC] Conditional compilation developer guide review (#14340) 
* conditional compilation review

* additional fixes

* apply comment from review
 2022-12-05 08:35:06 +04:00
Ilya Lavrenov
1af95fb3f8
Fixed C samples build on Windows (#14386) 2022-12-05 01:33:42 +04:00