IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,621 Commits 38 Branches 54 Tags
3bec32449f7d3cdcf7f09713102b401fb60b3202
Commit Graph
2743 Commits
Author SHA1 Message Date
Maxim Shevtsov 3bec32449f OV Performance Hints (CPU and GPU logic for selecting the actual configs), while AUTO/MULTI are passing them thru) (#6993) 
* rebasing the perf-modes-2021.3 to the 2021.4

Caveats:
the (explicit) setting #streams is not disabled (as it was before for experiments with DLBenchmark), and the logic slighlty differ (streamsSet)

(cherry picked from commit 1ae1edc0ed)

* overriding streams (to force the TPUT mode to the DLBenchnark)

(cherry picked from commit 7f506cda31)

* disabling reducing #streams to fully mimic baseline c4df94d42d of the 2021.3 (before experiments)

(cherry picked from commit 85073dd1dd)

* clang/identation

(cherry picked from commit 050a4155a9)

* splitting the Transformation to general and CPU specific.

Now hopefully,this fully mimics the  baseline c4df94d42d of the 2021.3 (before experiments), as the streams reduce num (as well as early exit on GRU/LSTM/TensorIterator) is deisabled

(cherry picked from commit e98b2c1a67)

* disabling GRU/LSTM/TI + reducing of streams + 5D considered compute-limited only for int8

(cherry picked from commit 32b8d80dee)

* refactored to avoid compute_limited_ratio, reverted the reducing #streams, removed LSTM from limitations

(cherry picked from commit f2b972171b)

* isa-based threshold logic

(cherry picked from commit b218457e1a)

* mode->hint

(cherry picked from commit ec20aa8eca)

* optional PERFORMANCE_HINT_NUM_REQUESTS

(cherry picked from commit 5a3883e3f3)

* moving the perfHints to the common OV config class + initial tests (CPU only, as the actual AUTO/MULTI should be accommodated on the master)

(cherry picked from commit (then fixed)45bafe7d527f466507dea0693aeed51be4ebf776)

* AUTO support for PerfHints

* MULTI support for PerfHints

* Enabling Perf hints for the GPU plugin

* brushing settings output a bit

* disabling "throughput" perf hint being default (until OV 2.0)

* uncommenting the logic which was disabled to force the DLBenchmark to use the throughput mode by default

* removing dead and experimental code, and debug printfs

* clang/code-style

* code-review remarks

* Moved the output of the actual params that the hint produced to the right place

* aligning MULTI's GetConfig beh to HETERO's as captured in the preso (CVS-59960) ratified with the ArchForum

* clang

* benchmark_app brushing

* Update inference-engine/samples/benchmark_app/README.md

* propagating the perf hints thru one more scenario in the merged AUTO-MULTI

* fixed mispint

* Python benchmark_app update for perf hints

* addresssing reviewers comments on the python benchmark_app

* simplifying/brushing logic a bit

* refactor the heuristic to the separate file (to be shared with iGPU soon)

* refactor conversion of modes to the specific GPU config per feedback from Vladimir
 2021-09-13 15:40:36 +03:00
Anton Pankratv 2793963e6f added openvino runtime plugin (#7259) 2021-09-13 14:25:52 +03:00
Ilya Lavrenov b373cb844b Removed information about FPGA plugin (#7474) 2021-09-13 14:01:49 +03:00
serhii-pavlovskyi-altran b11b1d44cb Use one set of parentheses around gcc attribute deprecated arg (#7413) 
Double parentheses break some other compilers which pretend to be gcc.
Single set doesn't seem to break anything.
 2021-09-13 13:56:43 +03:00
Ilya Lavrenov 47aad8e67e Small fixes in cmake (#7472) 2021-09-13 12:57:10 +03:00
Ivan Novoselov cb0d6db4c5 [CPU] Disable NotImpelmented exceptions mechanism for generic node. (#7242) 2021-09-13 11:20:43 +03:00
Chenhu Wang 2093af4f8a [CPU] DO optimization (#6360) 2021-09-13 11:12:03 +03:00
Alexandra Sidorova eae448e74a [CPU] Added inplace support for concat with axis != 1 (#6864) 2021-09-13 10:30:39 +03:00
Irina Efode b3d6d11a99 [IE TESTS] Move SKIP macro from test bodies to SetUp() in InferRequestCancelation & Move Infer_Request_dynamic tests to the correct folder (#7299) 
* try to fix behavior

* Try

* Revert changes

* Update behavior_test_utils.hpp

* Move Deynamic_tests

* fix build

* fix

* Init
 2021-09-13 10:09:36 +03:00
Dawid Kożykowski 0bc17a2f55 update subgraph test classes (#7383) 2021-09-13 07:19:30 +03:00
Dawid Kożykowski 3afc0342eb update shared tests classes (#7385) 2021-09-13 07:18:48 +03:00
Ilya Lavrenov 13321e4ab6 Trying to re-use OpenVINOConfig.cmake (#7467) 
* Trying to re-use OpenVINOConfig.cmake

* Add ngraph
 2021-09-13 07:12:07 +03:00
Anastasiia Urlapova 754ee2eb1a Change PowerIE to ops chain (#7439) 2021-09-10 16:55:11 +03:00
Ilya Lavrenov a952540edf Openvino cmake config (#7419) 
* Added OpenVINOConfig.cmake

* OpenVINOConfig.cmake part 2

* Trying to fix cmake generation

* Fixes

* Export frontends as well

* Fixed condition

* Added OpenVINO cmake package usage: docs, C samples

* Use more OpenVINO config

* Install OpenVINOConfig.cmake

* Trying to fix private plugins

* Trying to fix .tox

* Trying to fix ARM

* Fixed samples build

* Explicit ngraph duplicated targets

* Fixed fuzzing tests build

* Added IR frontend installation

* Removed install directory for IE reader

* Removed IR frontend from export list

* Reverted ngraph_DIR

* Try to fix .tox

* Fixed ieFuncTests with ONNX extensions

* Attempt #2

* Trying to fix ngraph setup.py

* Fix

* Trying to fix ONNX ngraph .tox CI

* Trying to remove spaces

* Fixed ngraph_DIR -> OpenVINO_DIR

* Removed junk files

* Try to fix ngraph wheel

* Try to fix ie_wheel

* Try to fix ngraph wheel
 2021-09-10 15:31:27 +03:00
Gabriele Galiero Casay deeb96440f Revise GatherTree reference implementation (#7275) 
* Add visitor api test

* Review ngraph op shell with type_prop tests

* Add op to list of trusted operations

* Change name of struct with information of inputs

* Add include of array data structure to fix windowds compilation error

* Add template plugin test class

* Remove usage of CoordinateTransform index function call from reference implementation

* Rename SLT test suite

* Add template plugin unit test

* Add serialization SLTs

* Add indentation on GatherTreeParams class data members
 2021-09-10 14:02:49 +03:00
Anton Dudchenko 288a7633bf [IE][VPU] Fix execTimeMcs for VPU (#7442) 
When serializing execGraph, milliseconds were actually written to the execTimeMcs field
 2021-09-10 13:08:13 +03:00
Anton Pankratv 305b86fe4a Added openvino executable network API (#7230) 2021-09-10 11:55:52 +03:00
Fengyi Sun 2a0140d960 [CPU] Fixed sort port bug (#6812) 
if port > port_num, the behavior of res[port] is undefined.

Signed-off-by: fengyi.sun <fengyi.sun@intel.com>
Reviewed-by: Wu, Jiangming <jiangming.wu@intel.com>]
 2021-09-09 15:32:58 +03:00
Vladislav Golubev f5767d4a5b [LPT][Transformations] Dynamic shapes support: functional issues fixes (#7159) 
* [LPT] ReshapeTransformation fix

* [LPT] FQDequantization::empty() fix

* [LPT] ConcatTransformation fix

* [LPT] MVNTransformation quick refactoring

* [TESTS] AddTransformation functional tests: removed unused param

* [nGraph] TypeRelaxed::evaluate

* [nGraph] Tile fix

* [nGraph] Intervals addition: overflow handling

* [LPT] MultiplyTransformation: canBeTransformed fix

* [TESTS] TypeRelaxed::evaluate: added test

* [LPT] MVNTransformation compilation error fix

* TypeRelaxed: evaluate fix

* macos fix

* TypeRelaxed::evaluate: postreview fixes

* ConcatTransformation: postreview fix
 2021-09-09 13:05:32 +03:00
Tomasz Dołbniak f5089912e4 MaxPool-8 python API (#7170) 2021-09-09 11:45:47 +02:00
Andrew Kwangwoong Park c33856b31f [GPU] Improve memory usage management to distinguish allocation type (#7318) 
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
 2021-09-09 07:19:07 +03:00
Anton Pankratv 1c1401b069 Added default exec network result (#7352) 2021-09-08 23:33:12 +03:00
Alexey LebedevIlya ChuraevLyalin, SergeyPolina
 		f89b3d770b [IE PYTHON] dynamic shape api for python (#7282) 
* Added nGraph as a public dependency

* Fixed Windows warning

* Fixed CMake

* Fixed constant op

* Fixed typo

* Added reshape to PartialShape to CNNNetwork

* Added SetShape to InferRequest

* Enable support of DynamicShape in IE Data

* Add support of dynamic shapes to template plugin

* Fixed build

* Enable support dynamic rank

* Fixed test for dynamic rank

* Fixed some tests

* Fix preprocess tests

* Fixed SetBlob

* Fixed code style

* Add more tests

* Fixed accuracy tests

* Fixed documentation

* Added tests for custom operation

* Added new tests

* WIP: move setShape from infer request to Blob

* Returned isApplicable check back

* Removed obsolete tests for InferRequest::SetShape and add new test for Blob::setShape (a trivial one)

* Fixed artifacts

* Break code style

* Revert "Break code style"

This reverts commit 71ee638cd0.

* Added -j8 for fix_all

* Applied code style fixes

* Adde doxygen items

* Fixed style

* Applied codestyle patch

* Reverted unrelevant commit with template extension

* Fixed cmake file for shared func tests (pick from master)

* Revert all changes in template_extension

* Deleted some old stuff that commented and won't be used

* Fixed wrong exception throwing

* Code style fix

* Fixed preprocessing part

* Fixed incorrect blob reshape in GetBlob

* Deleted incorrect assert in GAPI that prevents passing some tests in Debug

* Fixed issues identified during review

* Removed SetShape, replace getLayoutByDims by getLayoutByRank and removed problematic modification from IE preprocessing

* Fixed comments

* Removed obsolete setShape

* [VPU] Fixed allocating dynamic blobs in myriad_infer_request

* Fixed comments

* Fixed CNNNgraphImpl and comments

* add partial reshape for IENetwork

* Add getPartialShape

* Add setShape for Blob

* Add tests

* Add partial_shape property for CDataPtr

* Add partial_shape property for data

* Fix code style

* Fix code style

* Fix test

* Fix code style

* Fix code style

* Fix code style

* Add tests

* Add new lines

* Mark tests

* Fix tests

* call set_shape implicit  only for dynamic inputs

* skip tests on ARM

* remove ngraph dependence from ie_api.pyx

* expand only shape, not array in expand_dims_to_corresponding_layout

* Mark ngraph dependent tests

* remove skip inside test

* code refactoring

* add new line

* Add docstring

* Fix code style

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
Co-authored-by: Lyalin, Sergey <sergey.lyalin@intel.com>
Co-authored-by: Polina <polina.brzezinskaya@intel.com>
 2021-09-08 19:41:20 +03:00
Sergey Lyubimtsev 42b93bed42 Add support of pkgutil-style namespace packages (#7422) 
* Add support of pkgutil-style namespace packages

* fix linter issue (mypy)

* fix linter issue (mypy)

* ignore # mypy issue #1422

* E261 at least two spaces before inline comment
 2021-09-08 19:28:00 +03:00
Elizaveta Lobanova 66a14f1ac3 [GNA] Fixed scale factors propagation for Eltwise with very different inputs ranges (#7305) 
* [GNA] Fix scale factors propogation for Eltwise with very different inputs ranges

* [GNA] Added test

* [GNA] Added exception for scale factor <= 0

* [GNA] Disable tests with integer weights

* [GNA] Added assert for CNNLayer in getScaleFactor()

* [GNA] Added check if scale factor is inf

* [GNA] Fixed legacy tests
 2021-09-08 10:48:05 +03:00
Maksim Kutakov 5096fe19f1 [CPU] Dynamic shapes support using fallback on reference (#6882) 2021-09-08 10:33:20 +03:00
Alexey Lebedev d5e063d435 Mark ngraph dependent tests (#7392) 2021-09-07 22:28:57 +03:00
Andrey ZaytsevTrawinski, DariuszTatiana SavinaEdward ShogulinNikolay Tyukaev
 		322c874113 Feature/azaytsev/cherry picks from 2021 4 (#7389) 
* 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 legal info (#6409)

# Conflicts:
#	thirdparty/ade

* Cherry-pick 4833c8db72

[DOCS]Changed DL WB related docs and tips (#6318)

* changed DL WB related docs and tips

* added two tips to benchmark and changed layout

* changed layout

* changed links

* page title added

* changed tips

* ie layout fixed

* updated diagram and hints

* changed tooltip and ref link

* changet tooltip link

* changed DL WB description

* typo fix
# Conflicts:
#	docs/doxygen/ie_docs.xml
#	thirdparty/ade

* Cherry-pick 6405

Feature/azaytsev/mo devguide changes (#6405)

* MO devguide edits

* MO devguide edits

* MO devguide edits

* MO devguide edits

* MO devguide edits

* Experimenting with videos

* Experimenting with videos

* Experimenting with videos

* Experimenting with videos

* Experimenting with videos

* Experimenting with videos

* Experimenting with videos

* Experimenting with videos

* Experimenting with videos

* Additional edits

* Additional edits

* Updated the workflow diagram

* Minor fix

* Experimenting with videos

* Updated the workflow diagram

* Removed  Prepare_Trained_Model, changed the title for Config_Model_Optimizer

* Rolled back

* Revert "Rolled back"

This reverts commit 6a4a3e1765.

* Revert "Removed  Prepare_Trained_Model, changed the title for Config_Model_Optimizer"

This reverts commit 0810bd534f.

* Fixed ie_docs.xml, Removed  Prepare_Trained_Model, changed the title for Config_Model_Optimizer

* Fixed ie_docs.xml

* Minor fix

* <details> tag issue

* <details> tag issue

* Fix <details> tag issue

* Fix <details> tag issue

* Fix <details> tag issue
# Conflicts:
#	thirdparty/ade

* Cherry-pick #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>
# Conflicts:
#	docs/IE_DG/Int8Inference.md
#	thirdparty/ade

* Cherry pick (#6437)

* Q2 changes

* Changed Convert_RNNT.md

Co-authored-by: baychub <cbay@yahoo.com>
# Conflicts:
#	docs/IE_DG/Int8Inference.md
#	docs/install_guides/installing-openvino-conda.md
#	docs/install_guides/pypi-openvino-dev.md
#	thirdparty/ade

* Cherry-pick (#6447)

* Added benchmark page changes

* Make the picture smaller

* Added Intel® Iris® Xe MAX Graphics

* Changed the TIP about DL WB

* Added Note on the driver for Intel® Iris® Xe MAX Graphics

* Fixed formatting

* Added the link to Intel® software for general purpose GPU capabilities

* OVSA ovsa_get_started updates

* Fixed link
# Conflicts:
#	thirdparty/ade

* Cherry-pick #6450

* fix layout

* 4
# Conflicts:
#	thirdparty/ade

* Cherry-pick #6466

* Cherry-pick #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>
# Conflicts:
#	thirdparty/ade

* [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>
# Conflicts:
#	docs/IE_DG/Int8Inference.md
#	thirdparty/ade

* Cherry-pick #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>
# Conflicts:
#	docs/doxygen/ie_docs.xml

* Cherry-pick  (#6789) [59449][DOCS] GPU table layout change

* changed argument display

* added br tag to more arguments

* changed argument display in GPU table

* changed more arguments

* changed Quantized_ models display
# Conflicts:
#	thirdparty/ade

* Sync doxygen-ignore

* Removed ref to FPGA.md

* Fixed link to ONNX format doc

Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Edward Shogulin <edward.shogulin@intel.com>
Co-authored-by: Nikolay Tyukaev <nikolay.tyukaev@intel.com>
 2021-09-07 19:21:41 +03:00
Irina Efode c0a3cebe0b [IE TESTS] Enable Opset8 in Conformance report (#7369) 2021-09-07 14:05:44 +03:00
Ilya Lavrenov 72fb7d207c Merge tools and inference_engine/tools folders (#7359) 
* Merge tools folders

* Fixed docs

* Moved deployment_manager

* Fixed path to benchmark_tool docs

* python_tools -> python_tools_benchmark
 2021-09-07 12:43:33 +03:00
Anastasiia Urlapova f890b12fd5 [XXX-55386] Change nets version to v10 (#7289) 
* CVS-56144 Enable all OMZ scope

* [CVS-55368] Change nets version to v10

* [CVS-55386] Fix some coments

* [CVS-55386] Added float param to LSTM net

* Updated nets

* [CVS-55386] Change to ngraph way
 2021-09-07 12:13:12 +03:00
Mateusz Tabaka 5d6ef444a5 Reenable AddFakeQuantizeFusion and MulFakeQuantizeFusion (#5574) 
* Reenable AddFakeQuantizeFusion and MulFakeQuantizeFusion

* remove unused variable

* is_single_value simplify

* skip transformations for low precision types

* add comment regarding restriction in AddFakeQuantizeFusion

* remove fp16 test

* remove negative const handling
 2021-09-07 11:14:25 +03:00
Evgeny Kotov 8985feff6f [GNA] Rewrite RemoveSingleInputConcatPass using ngraph (#7208) 
* initial matcher pass

* write test implementation; + add unit tests

* base

* add unit tests

* code review fixes

* code review fixes

* fix

* fix

* move RemoveSingleInputConcat before opset to legacy conversion
 2021-09-07 10:56:41 +03:00
Gabriele Galiero Casay 15bef9ec70 Remove deprecated mvn class for SLTs (#7340) 2021-09-06 13:32:05 +03:00
Anastasia PopovaandIlya Churaev d82fed9527 RandomUniform reference implementation. (#7012) 
* Added RandomUniform reference implementation.

* Corrected comments.

* Small correction.

* Code style correction.

* Added has_evaluate() method.

* Added comments, added names to consts.

* Small fix.

* Replaced arrays with vectors.

* Apply suggestions from code review

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

* Code refactoring.

* Corrected tests, code style.

* Added comment.

* Added comments.

* Temporarily added debug output.

* Temporarily added debug output.

* Removed debug output.

* Added comment.

* Added comment.

* Enabled state saving for RandomUniform.

* Code style.

* Used to template to convert types.

* Added comments.

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
 2021-09-06 11:49:27 +03:00
Sergey Lyubimtsev 4978e8e6f8 Fix setup.py paths (#7345) 
* fix paths & setup.py install

* fix linter issues

* remove extra spaces

* fix CI issues

* remove extra lines

* fix indent
 2021-09-06 11:08:26 +03:00
Dmitry PigasinKoyanagi, KenKate Generalova
 		bb84d11313 [IE Python Speech Sample] Add --scale_factor and --performance_counter options (#6663) 
* Adds perf counters, and scale factor args

* Adding defined choices for arch type for -a/--arch option

* changing print to logger, frequencies are now global consts

* change to log info formatting

* Fix style issues

* doc: Update inference-engine/ie_bridges/python/sample/speech_sample/README.md

* doc: Update inference-engine/ie_bridges/python/sample/speech_sample/README.md

* doc: Update inference-engine/ie_bridges/python/sample/speech_sample/arg_parser.py

* doc: Update inference-engine/ie_bridges/python/sample/speech_sample/arg_parser.py

Co-authored-by: Koyanagi, Ken <ken.koyanagi@intel.com>
Co-authored-by: Kate Generalova <kate.generalova@intel.com>
 2021-09-03 23:23:00 +03:00
Ilya Lavrenov 005e7da325 Removed auto plugin (#7310) 
* Try to remove auto plugin

* Auto is registered as MULTI

* Register MultiDevicePlugin as AUTO

* More explicit config
 2021-09-03 22:01:18 +03:00
Dmitry PigasinandKate Generalova 6fa6e48893 [IE Python Speech Sample] Enable -oname for a imported model (-rg option) (#7254) 
* Enable `-oname` for a imported model

* Refactor `get_output_layer_list` func

* refactor: Update inference-engine/ie_bridges/python/sample/speech_sample/speech_sample.py

Co-authored-by: Kate Generalova <kate.generalova@intel.com>
 2021-09-03 18:50:13 +03:00
Krzysztof Bruniecki 6dd14bfe91 [GNA] Fixes for GNA 3.0 library (#7236) 
* Cherry-picked (PR #7180) (ce21344585) from releases/2021/4 branch
* Pass compileTarget to am_intel_dnn
* Enable tests for GNA lib version prefix 3.0
* Fix conv split transform for 2d cnn tests
* Apply review
 2021-09-03 12:56:51 +03:00
Egor Duplensky bf8113c056 [CPU] Fix graph serialization, use ngraph serialization directly (#7261) 2021-09-03 11:05:20 +03:00
Michał Karzyński d748f2aa99 Remove references to prototxt from documentation and docstrings (#7346) 2021-09-03 08:32:43 +03:00
Dawid Kożykowski e0c178e431 Update SLT classes functions to use parameters passed by reference (#7256) 
* update single layer tests

* add missing update to squeeze_unsqueeze
 2021-09-03 07:28:21 +03:00
Ilya Churaev b78f228fa5 Moved op utils to ov namespace (#7274) 
* Moved ngraph::Node to ov namespace

* Fixed code style

* Fixed VPU

* Fixed GNA

* Fixed tests

* Added aliases for backward compatibility

* Fix clDNN

* Try to fix build

* Fixed comment

* Renamed RTTI macros

* Moved op utils to ov namespace

* Fixed ngraph library build

* Fixed unit-tests

* Changed src folder

* Fixed recurrent_sequence

* Changed low latency

* Fixed serialize

* Fixed ieFuncTests

* Try to fix windows

* Remove custom operator<< from tests

* Fixed build
 2021-09-03 00:58:26 +03:00
Ilya Lavrenov 46646059f8 Removed speech demo docs (#7350) 2021-09-02 23:14:56 +03:00
Kelvin Choi 30adf04d31 [GPU] Fuse reorder to convolution (#6396) 2021-09-02 20:02:16 +03:00
Mikhail Ryzhov 2cf7065f6e [GNA] Fixed import of model with several inputs (#7277) 2021-09-02 17:48:07 +03:00
Evgeny Kotov 6cbeb18b0e use 1D convolution (#7291) 2021-09-02 17:09:34 +03:00
Elizaveta Lobanova 98eaa9359f [GNA] Fixed accuracy degradation caused by the input quantization restriction (#7258) 
* [GNA] Fixed accuracy degradation caused by the input quantization restriction

* [GNA] Put scale factor calculation into a separate function
 2021-09-02 14:35:49 +03:00
Irina Efode fc92eea000 [IE TESTS] Remove verified refs highlighting from report (#7285) 
* [IE TESTS] Remove verified refs from report

* Remove from header
 2021-09-02 14:31:48 +03:00