Commit Graph

3838 Commits

Author SHA1 Message Date
Maria Kaglinskaya
58dd421d58 Fix klocwork issues in pruning transformation (#6175)
* Fix klockwork issues in pruning transformation

* Fixed tabs
2021-06-17 16:11:31 +03:00
Maxim Vafin
64bc081abc Add iSeeBetter to supported PyTorch models list (#6177)
* Add iSeeBetter to supported PyTorch models list

* Apply feedback

* Apply feedback
2021-06-17 15:37:02 +03:00
Taylor Yeonbok Lee
c5b65f2cb1 [IE CLDNN] Disable crop optimization only when the node is inside a loop body program (#6198) 2021-06-16 17:46:33 +03:00
Xie Zhengtian
59ffa90724 [Doc] Add doc for Auto-Device Plugin 2021.4 (#6190)
* Add doc for Auto-Device Plugin

Signed-off-by: Zhengtian Xie <zhengtian.xie@intel.com>

* Update doc for auto-device plugin

Signed-off-by: Zhengtian Xie <zhengtian.xie@intel.com>
2021-06-16 16:51:01 +03:00
Edward Shogulin
cb4dcbce83 [LPT] Empty shape on weights handling (#6169)
* [LPT] empty shape on weights fix

* [LPT] SplitTransformation naming fix

Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
2021-06-16 16:45:43 +03:00
Vladislav Volkov
5670e9d8d0 [CPU] Memory leak in jit_uni_i8i8_pooling kernel (#6189) 2021-06-16 15:55:08 +03:00
Gleb Kazantaev
e47287264c Remove Pruning from MO (#6183) 2021-06-16 14:52:54 +03:00
Szymon Durawa
fe1563f0f0 Fix external_port_id serialization for loop op. (#6168) 2021-06-16 12:03:42 +03:00
Edward Shogulin
e87ab16e7c [LPT] Reshape folding extending (#6148)
* [LPT] Reshape folding extending

* [LPT] tests addition

* typo quick fix
2021-06-16 11:14:26 +03:00
Chenhu Wang
cf5c072cf4 [CPU] Change rounding type in load/store emitters (#6156) 2021-06-16 10:35:13 +03:00
Anton Romanov
6b3a652e54 Added copyrights note in CmakeLists (#6158) 2021-06-15 16:15:41 +03:00
Mikhail Nosov
66eef3c3d9 [Caching] Klocwork fixes (#6162) 2021-06-15 14:58:50 +03:00
Andrey Somsikov
0accd09c45 Add cnpy fuzz test and fix issues (#6109) (#6159) 2021-06-15 11:05:10 +00:00
Edward Shogulin
f339cf70c6 [LPT] FakeQuantize folding fix to support ConvolutionBackpropData with FQ on weights (#6118) 2021-06-15 12:36:41 +03:00
Elena Gvozdeva
2ec6d9590c add single_layer_test for Interpolate-1 (#6133) 2021-06-12 10:47:24 +03:00
Zlobin Vladimir
ca116ab8d1 Fix InferRequest::operator!() (#6140) 2021-06-12 10:46:46 +03:00
Ilya Lavrenov
84e935c0f2 Fixed InferenceEngineConfig.cmake usage in include() (#6136) 2021-06-11 13:10:35 +03:00
Alexander Zhogov
5859d44abc GitHub CI: Check committer email 2021-06-11 11:19:50 +03:00
Alexander Zhogov
7b67a83d8c GitHub CI: Fix checking commits in case of no email 2021-06-10 12:52:22 +03:00
Ilya Znamenskiy
6ec725baac Revert "[IE CLDNN] Use fsv4 when feature-depth is shallow (#4398)" (#6103) 2021-06-09 23:39:51 +03:00
Maxim Shevtsov
d4f323f3dd fix wording (#6108) 2021-06-09 22:22:47 +03:00
Mikhail Ryzhov
1a6392eb53 [GNA] Fixed export/import functionality (#5963)
* Rebase master

* [GNA] Fixed export/import functionality

* Extended import log

* Added logs

* Fixed importing issue for the old models

* Revert "Added logs"

This reverts commit 39a3882d56.

* Revert "Extended import log"

This reverts commit 59eb9d6fba.

* Reverted precision import

* Extended tests

* Enabled skipped tests

* Included gna2-common-api header

* Replaced included header

* Centos7 build fix
2021-06-09 20:39:05 +03:00
Ivan Tikhonov
3bedd051dc processing sinks in hetero plugin, update single layer tests (#6090) 2021-06-09 19:03:38 +03:00
Konstantin Satunin
ec1134532a Align logic and feature flag name (#6107) 2021-06-09 18:52:44 +03:00
Elizaveta Lobanova
f4ba0f28a9 [GNA] Convert Matmul with batch size > 8 to pointwise convolution (#5991)
* [GNA] Convert Matmul with batch size > 8 to pointwise convolution.
Support Eltwise split to more than 2 parts.
Fake Quantize support fixes.

* Put convolution split into a separate transformation

* Add separate transformations for cases with bias and fake quantize

* Rollback restriction for diagonal layer reshape
2021-06-09 18:15:39 +03:00
Anton Chetverikov
6a5b6b8b30 Add transformation to normalize negative indices in Gather (#6028)
* Add transformation to normalize negative indices in Gather

* Update transformation name and add constant indices input to the pattern

* Apply comments

* Fix copyright year

* Add more tests

* Update type logic

* Add test with different types and update old ones

* Update pattern and logic to check only axis dimension is static, add appropriate tests

* Fix cdestyle

* Add axis normalization

* Fix wrong value in gather input

* Add related tests

* Add axis_constant to check

* Remove ngraph_check
2021-06-09 17:26:52 +03:00
Daria Mityagina
3bc2c46693 [IE][VPU] Yolo_v5 support (#5976)
Changing the threshold for VPU scales
2021-06-09 16:27:52 +03:00
Evgeny Talanin
8dd914477c Pin mypy dependency (#6098) 2021-06-09 15:06:21 +03:00
Ivan Novoselov
8c74a0a52c [CPU] Fixed reorder for strided both inputs and outputs (#6082) 2021-06-09 14:27:43 +03:00
Ivan Tikhonov
aa0c93300c Update for Python API to create networks with Memory layers (#6079)
* Update python API for Memory

* Run unit tests on CPU only

* add missed import

* Update tests

* fix py tests
2021-06-09 12:19:36 +03:00
iliya mironov
421465adc1 Add ShapeOfConstFolding transform (#5858)
* Add ShapeOfConstFolding transform

* Add unit tests

* Update bom file

* Update transform file

* Hot fix

* Fix midle replaser

* Update unit tests

* Fix get value

* Refactoring Const Folding transformation. Move to back

* Update bom file

* Remove unuse code

* Add some unit tests

* Refactoring unit test

* Hot fix
2021-06-09 12:14:39 +03:00
Nikolay Shchegolev
cbd48cf15f [CPU] Statically found issues on Windows. (#6075) 2021-06-09 10:12:58 +03:00
Ilya Lavrenov
6e2d13937a ImportNetwork with explicit device name only (#5689)
* Import with explicit name

* Fixed LoadHetero_MultiArchs tests

* Fixed MYRIAD tests on Windows

* Fixed compilation in tests

* Updated tesets

* Fixed test

* Removed useless lines

* Removed custom VPU tests, replaced with common ones

* Fixed Windows

* Reverted SKIP_IF_NOT_IMPLEMENTED macro
2021-06-09 10:09:25 +03:00
Roman Kazantsev
2c3abf8f42 Use int64 for TopK indices output (#6085)
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2021-06-09 10:00:20 +03:00
Vladimir Paramuzov
aa4a18dda1 [IE CLDNN] Updated GPU device config (#6040) 2021-06-09 09:02:25 +03:00
Andrey Somsikov
f0cf1dffa7 Add ENABLE_STRICT_DEPENDENCIES for faster parallel builds (#5473) 2021-06-09 08:21:03 +03:00
Egor Duplensky
57850f0a87 [CPU] Allow exec graph serialization to cout or xml via env variable (#5967) 2021-06-08 22:39:08 +03:00
Ilya Lavrenov
246932a5d3 Py code style (#6086)
* GitHub CI: Enable Python for Code style

* Update formatting

* Fix

* Add cython

* Add upgrade pip

* Update to src/requirements-dev.txt

* Fixed clang code style

Co-authored-by: azhogov <alexander.zhogov@intel.com>
2021-06-08 20:24:11 +03:00
Ilya Churaev
d171b5c4b7 Removed version.in.hpp from nGraph package (#6081) 2021-06-08 19:55:36 +03:00
Ilya Lavrenov
a36d6a0f06 Used setMeanImageForChannel (#6076) 2021-06-08 19:33:51 +03:00
Svetlana Dolinina
de2a163363 Error during Caffe model conversion with Python3.8 (#6056)
* added one more possible reason for Caffe error during caffemodel parser in code + add error description to FAQ
Also added MxNet error to FAQ based on Kate Generalova wording

* review fixes

* wording polishing

* wording polishing

* review fixes

* review fixes

* Update docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* review fixes

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2021-06-08 16:09:04 +03:00
Edward Shogulin
9e34622ac1 [LPT] Concat precision selection fix (#6069) 2021-06-08 15:29:30 +03:00
Irina Efode
a7a9364b41 [IE TESTS] Add local_cache arg to the subgraphDumper (#6063) 2021-06-08 14:23:45 +03:00
Alexandra Sidorova
9214fa72e2 [CPU] Fixed AvgPooling and FQ fusing (#5994) 2021-06-08 14:04:31 +03:00
Andrey Zaytsev
440d3ee0ba Feature/azaytsev/update gpu driver link (#6062)
* Added info on DockerHub CI Framework

* Feature/azaytsev/change layout (#3295)

* Changes according to feedback comments

* Replaced @ref's with html links

* Fixed links, added a title page for installing from repos and images, fixed formatting issues

* Added links

* minor fix

* Added DL Streamer to the list of components installed by default

* Link fixes

* Link fixes

* ovms doc fix (#2988)

* added OpenVINO Model Server

* ovms doc fixes

Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com>

* Updated openvino_docs.xml

* Updated link

* Update installing-openvino-windows.md

Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com>
2021-06-08 13:49:01 +03:00
Andrey Zaytsev
76313a0ffa Feature/azaytsev/update license aggrements link (#6068)
* Added info on DockerHub CI Framework

* Feature/azaytsev/change layout (#3295)

* Changes according to feedback comments

* Replaced @ref's with html links

* Fixed links, added a title page for installing from repos and images, fixed formatting issues

* Added links

* minor fix

* Added DL Streamer to the list of components installed by default

* Link fixes

* Link fixes

* ovms doc fix (#2988)

* added OpenVINO Model Server

* ovms doc fixes

Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com>

* Updated openvino_docs.xml

* Updated the link to software license agreements

* Revert "Updated the link to software license agreements"

This reverts commit 706dac500e.

* Updated the link to software license agreements

Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com>
2021-06-08 13:39:35 +03:00
iliya mironov
ae5608534e Add support resize with 2 inputs (#5927)
* Add support resize with 2 inputs

* Add unit tests

* Hot fix

* Change resize check from port count to connected num port conditions

* Fix conditions

* Refactoring code according to review

* Fix according to review

* Change onnresize11 input condition
2021-06-08 13:15:54 +03:00
Alexander Shchepetov
503d18c80f Enable MYRIAD in stress tests (#6026) 2021-06-08 12:47:20 +03:00
Rafal Blaczkowski
9aa338a0af OpenVINO ONNX CI - set more stable proxy (#5945)
* Set more stable proxy

* Update env

* Add missing chars

* Update proxy

* Additonal try to overwrite proxy

* update proxy

* fix style
2021-06-08 12:37:20 +03:00
Michal Papaj
79e44292c5 Update to speech recognition demo version. (#6060)
The speech recognition demo packages were updated to align
OV python packages requirements. This patch updates packages
version and SHA.
2021-06-08 12:35:26 +03:00