IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
6,861 Commits 38 Branches 54 Tags 1.1 GiB
850f93f21b
Commit Graph

6861 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Nikita Demashov
f7a85c59fe
[LPT] Disable Move Fake Quantize on shuffle channels pattern (#10389) 
* added shuffle channels check

* refactoring
 2022-02-21 10:01:37 +03:00
Ivan Tikhonov
e89c7ed8e5
Describe MakeStateful transformation in MO help (#10536) 
* Update --transform help for MakeStateful transformation

* add quotes
 2022-02-21 09:55:26 +03:00
Taylor Yeonbok Lee
73a6d50dbc
[GPU] Fixed batch size again to 8 as a workaround of compiler restriction. (#10502) 2022-02-21 09:42:08 +03:00
Roman Lyamin
0ee6959537
[GPU] Replacing get_shape() with get_partial_shape() (#10525) 2022-02-21 09:41:24 +03:00
Andrew Kwangwoong Park
a7fff7447c
Fix to extract scores for each class in consideration of background label's id (#10500) 
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
 2022-02-21 15:35:44 +09:00
Andrei Molotkov
575ded54a9
[GPU] Move adding biases to the end convolution_bfyx_to_bfyx_f16 kernel (#10533) 2022-02-21 09:30:00 +03:00
Xuejun Zhai
ea3bd087c4
[CVS-78727][python version] bug fix for -d AUTO:CPU,GPU the return device should be AUTO only (#10506) 
Signed-off-by: xuejun <xuejun.zhai@intel.com>
 2022-02-21 03:21:52 +00:00
Ilya Znamenskiy
7c93902dac
[GPU] Fix issues with floating point fusings support for cldnn / onednn fully connected kernels (#10519) 
* [GPU] Fix of floating point fusings inside fc kernels

* [GPU] Fix for related tests
 2022-02-21 12:03:23 +09:00
Maxim Shevtsov
a52c755d21
refactor the perf counters to get really on-demand (rather than on every inference) (#10526) 
* refactor the perf counters to get really on-demand (rather than on every inference)

* removed the (now) un-needed needPerfCounters flag
 2022-02-20 20:56:15 +03:00
Maxim Vafin
982942fa5d
Fix typo in CropAndResize translator (#10541) 2022-02-20 12:39:52 +03:00
Nikita Malinin
a312dd4a9f
[POT] IEEngine output data order (#10527) 
* IEEngine fix for multiply-output nets

* Update docstrings and docs

* Codestyle changes

* Update docs

* Update docstring

* Pylint
 2022-02-20 09:44:04 +03:00
Alexander Kozlov
5c7be85435
[POT] Documentation update (#10068) 
* Updated main README

* Added saturation fix desciption

* Changed Low-precision model representation document

* Added Simplified mode desciption. Updated DefaultQuantization, AccuracyAware, API descriptions.

* Added Data-free model description. Adjusted other Readmes accordingly

* Revised Configuration file description

* Revised AA method description

* Changed Quantization readme

* Cross-links in quantization methods

* Fixed reference

* Fixed the structure

* Removed data-free

* Update tools/pot/docs/CLI.md

Co-authored-by: Nikita Malinin <nikita.malinin@intel.com>

* Update tools/pot/openvino/tools/pot/api/README.md

Co-authored-by: Nikita Malinin <nikita.malinin@intel.com>

* Applied comments

* Fixed comments

* Applied more comment

* Applied comments

* Fixed build errors

* Fixed build errors

* Small changes

* Fixed a typo

Co-authored-by: Nikita Malinin <nikita.malinin@intel.com>
 2022-02-20 09:43:14 +03:00
Alexey Lebedev
5671ca2cf5
add test (#10531) 2022-02-19 20:19:28 +03:00
Mingyu Kim
af62ff22b1
[GPU] Mixed precision fix for mask rcnn (#10467) (#10535) 
* Select proper layout for fp16-int8 mixed precision network
* Set proper layout in layout propagation for mixed precision
 2022-02-19 21:55:15 +09:00
Alexey Lebedev
661002689f
latency mode is default for sync (#10521) 2022-02-19 05:58:51 +03:00
Maxim Vafin
71fdcdf899
Fix Unpack translator in TF FE (#10494) 
* Fix Unpack translator in TF FE

* Apply review feedback
 2022-02-19 02:52:48 +03:00
Anastasia Popova
2e164b4ddc
AvgPool3D translator, fix of MaxPool translator in TF FE (#10530) 
* Fixed MaxPool translator, added AvgPool3D translator.

* Update src/frontends/tensorflow/src/op/avg_pool.cpp

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

* Code style.

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
 2022-02-19 02:47:01 +03:00
Pavel Esir
fb6359586d
fix ConvertGroupedStridedSlice.py for XLNet (#10496) 2022-02-18 22:40:28 +03:00
Ilya Lavrenov
6b22d0d109
Revert "repair TF FE tests after build (#10432)" (#10523) 
This reverts commit 306b7611d9.
 2022-02-18 19:48:35 +03:00
Yuan Xu
c9bfd3bf8b
Updating installation guide structure for 22/1 (#10343) 
* Add Overview page

* update overview

* update install dev tools page

* Revert "Add Overview page"

* create overview page

* update movidius setup guide

* split the configurations for linux part to a separate topi

* split the general configurations for linux to a separate topic

* create a separate topic for configurations for vpu on windows

* create a separate topic on configurating gpu

* create a separate topic for configurations for ncs2

* update structure

* update structure

* update structure

* restructure

* update overview

* update

* update according to comments

* update structure

* update the structure

* correct naming

* correct naming

* update trademark symbol

* remove .bak file

* update

* test formatting

* update

* update

* fix errors

* add a leading sentence for GPU configurations

* update structure

* delete redundant files

* Update docs/install_guides/configurations-for-intel-gpu.md

Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>

* Update docs/install_guides/configurations-for-ncs2.md

Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>

* Update docs/install_guides/installing-openvino-config-ivad-vpu.md

Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>

* fix formatting

* fix errors

* fix errors

* fix errors

Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
 2022-02-18 19:47:00 +03:00
Svetlana Dolinina
d2177cf177
remove old protobuf eggs (#10473) 2022-02-18 18:12:23 +03:00
Gleb Kazantaev
b22585a696
Fix Coverity issue (#10510) 2022-02-18 18:00:40 +03:00
Alina Kladieva
7985c92095
Revert "[GPU] Mixed precision fix for mask rcnn (#10467)" (#10515) 
This reverts commit 10ac5b280b.
 2022-02-18 16:38:49 +03:00
Anton Voronov
d9b1f10074
[CPU] [OneDNN] disabled unused amx primitives and conv primitives (#10326) 2022-02-18 16:36:49 +03:00
Katarzyna Mitrus
f52f129ed8
[Python API] Improvement of dynamic reshape error message in compatibility ie (#10495) 
* Add test_reshape_dynamic to tests compatibility

* Catch OverflowError on dynamic dimension reshape
 2022-02-18 14:23:10 +03:00
Zhang Yi
ba9d18f181
[CPU] Parallel copy for output in case data doesn't fit L2 cache capacity (#10340) 2022-02-18 13:16:51 +03:00
Ilya Churaev
a18c8076cc
Removed obsolete documentation (#10504) 
* Removed obsolete documentation

* Fixed documentation

* Additional fix
 2022-02-18 13:02:55 +03:00
Ekaterina Aidova
e8ff31f4fb
[OMZ]: update submodule (#10490) 2022-02-18 12:58:38 +03:00
Roman Kazantsev
20266dd0c3
[MO] Upgrade TensorFlow version dependency due to SNYK hits (#10487) 
* [MO] Upgrade TensorFlow version dependency due to SNYK hits

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

* Still use 2.5.0 TensorFlow for Python 3.6 and older

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2022-02-18 12:29:58 +03:00
Anton Voronov
7a82bb2acb
[CPU] fixed including <cpuid.h> on android (#10482) 2022-02-18 11:50:38 +03:00
Andrey Somsikov
dea35b8e6e
Upgrade protobuf to 3.18.2 (#10435) 
* Upgrade protobuf to 3.19.4

* Upgdate precompiled protoc version

* Update protobuf to v3.18.2

Updating further peding this fix to be released
https://github.com/protocolbuffers/protobuf/pull/9437

* Disable warnings for protobuf
 2022-02-18 11:43:19 +03:00
Nikita Semaev
03862e780f
Fixing SetUp for SLT tests of ShapeOF (#10323) 
* Fixing SetUp for SLT tests of ShapeOF

* Attempting to pass outputPrecision into the test

* Correcting deficiencies, taking into account in the name of the test of the output precision
 2022-02-18 10:37:39 +03:00
Jacek Skowron
3a89c87f52
[DOCS] update install guides gifs (#10444) 2022-02-18 10:31:42 +03:00
Maxim Shevtsov
dcd6e3e961
removed unsed var and fixed mixup from code shuffling (#10492) 2022-02-18 10:05:23 +03:00
Xuejun Zhai
2ac15eae3d
[CVS-78727] bug fix for -d AUTO:CPU,GPU the return device should be AUTO only (#10417) 
Signed-off-by: xuejun <xuejun.zhai@intel.com>
 2022-02-18 09:56:56 +03:00
Edward Shogulin
17311c46b3
[LPT] checkElementwise extending for 1D tensor (#10498) 2022-02-18 09:41:17 +03:00
Anton Romanov
b8ac041da9
Fixed coverity issues in samples (#10421) 
* Fixed coverity issues

* Fixed coverity isuues samples part 2

* Fixed code style

* Delete goto

* update after comments
 2022-02-18 08:08:09 +03:00
Vitaliy Urusovskij
76ade7a7d0
Update docstrings with information about static build (#10488) 2022-02-18 07:48:58 +03:00
Xuejun Zhai
9b36daf23b
Modify for CVS-69023(python version): hint configuration (#10312) 
Signed-off-by: xuejun <xuejun.zhai@intel.com>
 2022-02-18 09:40:27 +08:00
guozhong wang
2d88e67616
Guozhong/remove format time (#9923) 
* remove formatTimeMilli from time_utils.cpp

* add traceCallStacks test case

* add traceCallStacks test case in format_test.cpp

* add param:"test" to function TraceCallStacks()

* rollback file in master branch

* add traceCallStacks test case in format_test.cpp

* remove formatTimeMilli from time_utils.cpp and add traceCallStacks test case in format_test.cpp
 2022-02-18 09:36:01 +08:00
Mingyu Kim
10ac5b280b
[GPU] Mixed precision fix for mask rcnn (#10467) 
* Select proper layout for fp16-int8 mixed precision network
* Set proper layout in layout propagation for mixed precision
 2022-02-18 10:27:54 +09:00
hyunback kim
215db2dad8
[GPU] Enable shuffle and fsv32 in implicit concat (#9888) 
[GPU] Enable shuffle and fsv32 in implicit concat

* Support shuffle fsv32
* Check feature depths in first input depedency.
* Add to select onednn convolution in case block format in get_preferred_impl_type func.

Signed-off-by: hyunback <hyunback.kim@intel.com>
 2022-02-18 09:40:14 +09:00
Vladislav Volkov
b6a75d7d91
CPU plugin namespaces and files renaming (#10248) 2022-02-17 23:48:26 +03:00
Nikolay Tyukaev
7fa9d07a1f
ignore api/reference.rst warnings (#10491) 2022-02-17 23:13:09 +03:00
Maxim Vafin
f482f9765e
Fix values reading from protobuf (#10391) 
* Fix values reading from protobuf

* Remove exception

* Small fix
 2022-02-17 21:42:49 +03:00
Maxim Vafin
ac880f601c
Fix getting attribute in TF FE (#10458) 
* if attribute is not present and default value provided it should return default value
 2022-02-17 20:30:04 +03:00
Anton Grishin
b8bbe056b1
Improve l-capturing (#10468) 2022-02-17 19:17:07 +03:00
Artur Kulikowski
73caba0f67
Fix ONNX boolean tests (#10404) 2022-02-17 15:31:11 +00:00
Nikita Malinin
a090abbc92
Update remove_converts pass with shape inference (#10474) 2022-02-17 18:17:07 +03:00
Yegor Kruglov
6e5eb87340
Add note to YOLO-v3 conversion instructions (#10428) 
* added note to yolo v3 conversion instructions

* fix typo

* Update docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_YOLO_From_Tensorflow.md

style fix

Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>

Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
 2022-02-17 18:00:38 +03:00