IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
3,915 Commits 38 Branches 54 Tags
b76c90374501ac461d89a8fba44335741d066ccc
Commit Graph
3915 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Victor Kuznetsov b76c903745 add pytest html (#7169) 2021-08-20 16:58:39 +03:00
Mikhail Ryzhov 4714b8edb8 [GNA] Set input scale factors for imported model (#7139) (#7140) 
* [GNA] Set custom scale factor for imported model
 2021-08-19 14:48:37 +03:00
Andrey Sapozhnikov 47d1f2147a [GNA] Plugin preparation for transition to the library v3 (#7047) 
* GNA Plugin transition to the library v3

* Embedded device support

* Revert transition, keep preparation for future transition
 2021-08-19 14:46:43 +03:00
Elizaveta Lobanova 61aa366706 [GNA] Fix order of SwapMatMulInput transformations (#7138) 2021-08-19 09:13:55 +03:00
Sergey Shlyapnikov b16ce268eb [GPU] Fix incorrect fusions indexes for eltwise ref kernel (#7026) 2021-08-18 18:23:19 +03:00
Daria Mityagina 629de56910 [IE][VPU] Firmware update (#7102) 
Update FW version from 1717 to 1729
 2021-08-18 16:35:18 +03:00
Victor Kuznetsov dad76527d6 fixed several issues in time tests (#7059) 
* Fixed return in run_timetest
* Fixed parse_stats() argument type notation
* Pass message from timetest exe to test error msg to be uploaded to DB
 2021-08-18 13:15:58 +03:00
Yury Gaydaychuk b86ab12f0f [CPU][Release 2021.4.1] Fix roipooling border proposal computation for 2021.4 (#7116) 
* roi_pooling handles border props correctly

* fix adapted for old test infrastructure
 2021-08-17 23:20:54 +03:00
Yury Gaydaychuk 170e4d2cce [CPU] Interpolate handles inplace child layout (#6961) 2021-08-17 23:10:09 +03:00
Gleb Kazantaev 2a9eec1c3f Enable SplitSqueezeConcatFusion + TransposeSinking in offline transformations (#7087) 2021-08-17 14:39:05 +03:00
Mikhail RyzhovandKrzysztof Bruniecki 92420cd0d5 [Merge] Gna split align convert to conv filter and dependent (#6347 and #5946) (#7083) 
* [GNA] Use stride instead of window for pooling (#5946)

* Use pool stride instead of window size where applicable

* Add test for pooling stride not equal to wnd

* Add more tests and cleanup

* Fix SW_FP32 legacy cnn

* [WIP] Refactor CNN1D

* Remove unused (commented out) code

* Add tests

* Gna split align convert to conv filter (#6347)

* Make unaligned split based on Conv instead of Affine

* Dump Gna2Tensor.Data pointer for debugging

* Apply suggestions from code review

* Reuse conv helpers

* Cleanup CNN fields

* Disable weights reducer on ConvolutionFilter
# Conflicts:
#	inference-engine/src/gna_plugin/backend/am_intel_dnn.cpp
#	inference-engine/src/gna_plugin/optimizer/gna_pass_manager.cpp

Co-authored-by: Krzysztof Bruniecki <krzysztof.bruniecki@intel.com>
 2021-08-17 10:26:40 +00:00
Elizaveta LobanovaandDmitrii Khurtin 886254c5b9 Fixed Eltwise split and batch size selection during 2d reshape, transpose bias (#7099) 
* [GNA] Transpose bias (#6759)

* transpose bias

* removed bias transpose; added bias validation predicate to pattern

* fixed after review; added handling of the case bias_output_shape.size() == 1 and bias_output_shape.at(0) > 1

* moved bias shape size check to matcher pattern; replaced loop with algorithm

* [GNA] Fixed Eltwise split and batch size selection during 2d reshape (#7042)

* [GNA] Fixed Eltwise split and batch size selection during 2d reshape

* [GNA] Added exception if memory isn't allocated for concat filter

* Added assert for minZeroDimSize

* [GNA] Added unit test for GetAlignedSplitSizes()

Co-authored-by: Dmitrii Khurtin <dmitrii.khurtin@intel.com>
 2021-08-17 10:19:07 +03:00
Vladislav Volkov e75e647ebe [CPU] Memory leaks in gemm module (#7093) 2021-08-17 10:07:59 +03:00
Maksim Kutakov 6e45b62be6 [CPU] Add reorder if the constant memory is not aligned, and isa is SSE (#7095) 2021-08-17 09:01:14 +03:00
Alexander Zhogov 4a70806d10 Azure CI: Remove IB on Windows (#7097) 2021-08-16 21:36:38 +03:00
Dmitrii KhurtinandElizaveta Lobanova 761c645f14 [GNA] Convolution to matmul (#7029) 
* [GNA] Remove transposes around MatMul

* Added tests for transformation HandleTransposesAroundMatMul

* Move IsTransposeSupported function to GNA limitations file

* added TransposeAfterMatmul tests and moved InsertTransposeBeforeMatmul tests to handle_transposes_around_matmul.cpp

* added inifitiry loop checker and memory concat test

* fixed build errors

* changed the conditions for selecting an input of Concat for ScaleFactor calculation when entering an infinite loop

* fixed after review

* s/INSTANTIATE_TEST_SUITE_P/INSTANTIATE_TEST_CASE_P

* .ignore

Co-authored-by: Elizaveta Lobanova <elizaveta.lobanova@intel.com>
 2021-08-16 20:41:14 +03:00
Mikhail Ryzhov e19b3befb7 [GNA] Disabled TransposeReduction (#7011) (#7062) 
* [GNA] Disabled TransposeReduction  (#7011)

* Rebase master

* [gna] Fixed export/import precision

* Revert "[gna] Fixed export/import precision"

This reverts commit d381a2e216.

* Rebase master

* [gna] Fixed export/import precision

* Revert "[gna] Fixed export/import precision"

This reverts commit d381a2e216.

* Fixed transposition error

* [GNA] Added tests for conv wrapped to transpose

* Code review fixes

* Fixed copyright year

* Replaced test suite with case
 2021-08-16 14:04:43 +03:00
Mikhail Ryzhov fb3ceb6aa4 [GNA] Fixed issue for concat connection to memory layer (#6985) (#7058) 
* [GNA] Fixed issue for concat connection to memory layer (#6985)

* Fix for concat connection to memory layer

* reverted merge files

* Replaced opset8
 2021-08-16 11:04:29 +03:00
Paul Youngsoo Ahn 9a8d8440a5 [GPU] Set TBB affinity in load_network (#7049) 2021-08-16 09:14:22 +03:00
Mikhail Ryzhov 543ea75813 [GNA] FQ accuracy fixes (#6924) (#7061) 2021-08-15 22:36:15 +03:00
Maria KaglinskayaandGleb Kazantaev f03763defe Pruning for 2021.4 release (#6987) 
* Fix Pruning for case with INT8 GroupConvolution operation (#6872)

* Added i8, u8 precisions in Gather constant folding (#6195)

Co-authored-by: Gleb Kazantaev <gleb.kazantaev@intel.com>
 2021-08-13 18:23:35 +03:00
Elizaveta Lobanova 114ed1cb4b [GNA] Support bias and FQ in SwapInputMatMul transformation (#6996) (#7027) 2021-08-13 12:07:08 +03:00
Mikhail Ryzhov 3117879c54 [GNA] Added support of FQ layers for outputs (#6999) 
* [GNA] Added support of FQ layers for outputs (#6905)

* [GNA] Fixed FQ pass for several outputs

* Added tests
 2021-08-12 22:54:02 +03:00
Anton Voronov 2f48787fc4 [CPU] gemm inner product - memory access fix (#7009) 2021-08-12 10:15:40 +03:00
Anton Voronov 7848ac7a74 [CPU] fixed conv + dw conv fusing (#6975) 2021-08-12 09:42:06 +03:00
Alexey Lebedev 62f126cdd2 [IE PYTHON] release GIL (#6968) 
* Release GIL in load_network

* release gil in infer, wait and get_idle_request_id

* release gil in read_network and IECore.__cinit__

* release GIL in properties

* Release GIL in infer_async

* Add test

* Fix test

* Fix test
 2021-08-09 22:34:11 +03:00
Kate GeneralovaandAndrey Zaytsev 4d1c358aa3 doc: refactor docker install guide (#6988) 
* doc: refactor docker install guide

* doc: refactor docker install guide windows

* Update installing-openvino-docker-linux.md

* Update installing-openvino-docker-windows.md

Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
 2021-08-09 17:56:25 +03:00
Maksim Kutakov bf51d49ad1 [CPU] Get/Set Blob overhead has been eliminated. (#6737) (#6933) 
(cherry picked from commit e47a85b427)
 2021-08-06 16:59:00 +03:00
Kate Generalova 6d9699681f doc: fix 58710 issue (#6911) 2021-08-06 12:05:33 +03:00
Vladimir Gavrilov 0b248b68dd Fix for summarize_graph.py. (#6904) 2021-08-05 12:09:31 +03:00
Daria Mityagina d286e0a9ad [IE][VPU] Added support for 2 axis for MVN layer - duplicate (#6748) (#6778) 
Co-authored-by: Polina <polina.brzezinskaya@intel.com>
This PR adds support for Person-reidentification-retail model on VPU device by adding support for {2} axis in MVN layer
 2021-08-04 10:29:40 +03:00
Tatiana Savina 21ed761569 [59449][DOCS] GPU table layout change (#6789) 
* changed argument display

* added br tag to more arguments

* changed argument display in GPU table

* changed more arguments

* changed Quantized_ models display
 2021-08-02 20:00:46 +03:00
Dmitrii Khurtin 2639f35543 fixed crash related to loading model with fq and sigmoid (#6866) 
* fixed crash related with loading model with fq and sigmoid

* renamed multiple_input.* to multiple_input_fq.*; removed two unnecessary FQ layers from smoke_fq_fusion_with_sigmoid test; moved FQ params to test params

* s/INSTANTIATE_TEST_CASE_P/INSTANTIATE_TEST_SUITE_P/
 2021-08-02 12:20:50 +03:00
iliya mironov 1bbd91506b Fixing Split-Concat reverse input channel (#6765) 
* Fix split-concut revers input chennel

* Fix comments
 2021-07-28 15:47:46 +03:00
Alina Kladieva 9a31a3d821 Bump Jenkins library (#6817) 2021-07-27 13:24:53 +03:00
Evgenya Stepyreva 9acc3dfe68 Zero point optimization (#6628) 
* Zero point optimization

* Expand the equality to zero criteria
 2021-07-25 13:33:29 +03:00
Alina Kladieva 205c23b382 Commit to bump Jenkins library (#6781) 2021-07-23 17:16:49 +03:00
Maxim Vafin e48965683b Fix node name issue introduced by #5854 (#6709) (#6736) 
* Fix node name issue introduced by #5854
* Compare names in TransposeFuse tests
 2021-07-23 03:28:34 +03:00
Ilya Lavrenov eaa5a22979 Fixed build with cmake 3.21 (#6757) 2021-07-22 19:55:38 +03:00
Vitaliy Urusovskij bfdd1a199f Develop installation rules for time and stress tests (#6649) (#6738) 
* Develop installation rules for time and stress tests (#6649)

* Prepare `install` rule for time_tests

* Prepare `install` rule for stress tests

* Update path to `gflags`
 2021-07-22 10:43:15 +03:00
Ilya Churaev 096a92dcb3 Port extension fix (#6725) 2021-07-21 11:05:14 +03:00
Andrey Zaytsevbaychubbaychub
 		7a05a12190 Feature/azaytsev/changes from baychub revise demos samples (#6651) 
* Edits to MO

Per findings spreadsheet

* macOS changes

per issue spreadsheet

* Fixes from review spreadsheet

Mostly IE_DG fixes

* Consistency changes

* Make doc fixes from last round of review

* Add GSG build-all details

* Fix links to samples and demos pages

* Make MO_DG v2 changes

* Add image view step to classify demo

* Put MO dependency with others

* Edit docs per issues spreadsheet

* Add file to pytorch_specific

* More fixes per spreadsheet

* Prototype sample page

* Add build section

* Update README.md

* Batch download/convert by default

* Add detail to How It Works

* Minor change

* Temporary restored topics

* corrected layout

* Resized

* Added white background into the picture

* fixed link to omz_tools_downloader

* fixed title in the layout

Co-authored-by: baychub <cbay@yahoo.com>
Co-authored-by: baychub <31420038+baychub@users.noreply.github.com>
 2021-07-16 11:41:04 +03:00
iliya mironov 5d39724934 Imironov/add missing descriptions for transformations configs releases (#6521) 
* Add retinanet doc

* Update doc

* Splite some text to several lines

* Update ie_docs
 2021-07-15 18:24:15 +02:00
Dmitry Pigasin 7cec19fe6e Add information about model preparation (#6661) 2021-07-15 10:04:11 +00:00
Andrey ZaytsevandSergey Lyubimtsev 568096ddeb Install guides improvements (#6418) (#6648) 
* Install guides improvements

* add bullet to conda  System Requirements

* fix formating

* - Add conda install command for Ubuntu20

- fix typo /tmp

* added conda prerequisites

* Update installing-openvino-apt.md

* Update installing-openvino-conda.md

* Update installing-openvino-conda.md

CentOS 7.6

* Update installing-openvino-apt.md

APT Repository

* Update installing-openvino-conda.md

Added Introduction & notice about runtime package

* Update installing-openvino-conda.md

Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
# Conflicts:
#	docs/install_guides/installing-openvino-conda.md
#	inference-engine/thirdparty/ade

Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
 2021-07-14 22:31:16 +03:00
Krzysztof Bruniecki 34bda79333 [GNA] Introduce an option to invoke the QoS feature (#6604) 
* cherry picked (#5827)
* Issue 56759
* Introduce HW_WITH_SW_FBACK
* Add unit test for HW_WITH_SW_FBACK
* Enable HW_WITH_SW_FBACK in speech_sample cpp
* Use perf counters to report number of HW delivered frames to the user (eg speech_sample)
* Add GNA frequency for 6/151 CPU family/model
* Update inference-engine/samples/speech_sample/main.cpp
* Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
 2021-07-14 19:14:38 +03:00
Dmitry Pigasin 0da68d9c70 Add a check for existence of output images (#6640) 2021-07-14 12:28:50 +03:00
Pavel EsirTatiana SavinaAndrey Zaytsev
 		a82011199a [doc] corrections for Yolo V1 and V2 coversion (#6284) 
* added corrections for Yolo V1 and V2

* changed order of conversion commands : v1 goes first general last

* aligned line endings

* added commit hash

* clarified about downloaded files location

* added missing <br>

* Apply suggestions from code review

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

Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
 2021-07-13 18:39:02 +03:00
Edward ShogulinandAnastasiya Ageeva 6bbec510b0 [Runtime] INT8 inference documentation update (#6419) 
* [Runtime] INT8 inference documentation update

* [Runtime] INT8 inference documentation: typo was fixed

* Update docs/IE_DG/Int8Inference.md

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>

* Update docs/IE_DG/Int8Inference.md

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>

* Update docs/IE_DG/Int8Inference.md

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>

* Update docs/IE_DG/Int8Inference.md

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>

* Update docs/IE_DG/Int8Inference.md

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>

* Table of Contents was removed

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>
 2021-07-12 20:15:22 +03:00
Tatiana SavinaandAndrey Zaytsev 90eaa2666a [58825][58829][DOCS] Installation docs changes (#6548) 
* install docs fixes

* changed video width

* CMake reference added

* fixed table

* added backtics and table formating

* new table changes

* GPU table changes

* added more backtics and changed table format

* gpu table changes

* Update get_started_dl_workbench.md

Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
 2021-07-12 14:52:17 +03:00