IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,861 Commits 38 Branches 54 Tags 1.1 GiB
7343fcc94e
Commit Graph

2861 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Andrey Zaytsev
7343fcc94e
Feature/cherry pick 4635 to master (#4788) 
* Feature/vpu doc fixes 2021 3 (#4635)

* Documentation fixes and updates for VPU

* minor correction

* minor correction

* Fixed links

* updated supported layers list for vpu
 2021-03-16 12:03:41 +03:00
Ivan Novoselov
ec5df02dac
Revise OneHot operation reference implementation (#4330) 
* Auto benchmarks for evaluate(...) and extra unit tests.

* Test suite for manual i/o examination.

* Template on input type. Constant folding tests the 'count_ops_of_type' issue.

* Multidim manual tests

* NgOp&Ref: Unit tests Ok. NB evaluates_map

* Stable. Negative indices as if larger than depth. Benchmarks removed.

* Added Serialization SLT

* I/O shapes consistency checks

* Consistency checks in evaluate(). Removed the ref from evaluates_map.

* removed excessive #include from evaluates_map

* Code style
 2021-03-16 11:28:30 +03:00
Alexey Varyzgin
8cfb63cb56
[CPU] proposal_onnx tensor check was added and test was disabled (#4603) 2021-03-16 11:21:57 +03:00
Ilya Lavrenov
7a533f7abf
Fixed some klockwork issues in C API samples (#4773) 2021-03-16 11:00:59 +03:00
Gorokhov Dmitriy
b934851e9d
[CPU] Disabled FP32 Pooling with FQ fusing due to absense of optimized implementation (#3755) 2021-03-16 09:09:15 +03:00
Mikhail Letavin
c9d1700430
[IE CLDNN] Fix missing variable initializations and types (#4670) 2021-03-16 08:28:00 +03:00
Roman Lyamin
75f9fcd134
[IE CLDNN] Fix StridedSlice for hbonet (#4493) 2021-03-16 08:26:14 +03:00
Katarzyna Mitrus
5f098e1079
nGraph code style upgrade to clang-format-9 (#4721) 
* ngraph clang-format upgrade to 9

* Reformatted files

* Remove comma at the end of test data vector
 2021-03-15 22:06:01 +03:00
dependabot[bot]
b83b5115a5
Bump flake8 from 3.8.4 to 3.9.0 in /ngraph/python (#4782) 2021-03-15 17:59:29 +01:00
Bartosz Lesniewski
43dcc883d3
Revise Concat op - specification (#4542) 
* Add more info on axis attribute possible range

* Added a negative axis example

* Minor edit

* Use back-tick character to wrap all formulas
 2021-03-15 19:27:12 +03:00
Vladimir Zinoviev
7ca7e7d9c4
[LPT] Concat dequantization shape fix (#4702) 2021-03-15 17:47:56 +03:00
Rafal Blaczkowski
dbd3a3d7a4
Enable protobuf-lite in ONNX CI tests (#4487) 2021-03-15 14:34:02 +01:00
Krzysztof Bruniecki
ecee373220
Gna cnn2d with pooling support (#4574) 
* [GNA] Support Pooling 2D

  Refactor Pooling
  Remove unused sum pooling
  Skip ReorderPoolActivation pass when 2D pooling detected
  Enable fusing of Pool2D with other components into GNA Operation

* Support GNA_SW_FP32 mode for Pooling 2D with tests

* Apply review

typo

* Apply review

Restore indentation
 2021-03-15 16:16:45 +03:00
Katarzyna Mitrus
95a13e05d5
Enable MatMul 1D multiplication by transformation to GEMM (#4509) 
* MatMul tests

* Tests update

* More tests

* IE tetst manifest cleanup

* Enable MatMul 1D multiplication by transofrmation to GEMM

* Add unsqueeze to transform tests

* Fix runtime info

* Update transformation condition

* Remove Xfail from python tests

* Add more tests for ignoring 1D transpose true

* Ignore transpose for 1D in MatMul transformations

* Resolve python api xfails

* Use ngraph::opset namespace

* Style apply

* Add MatMul single layer tests for 1D
 2021-03-15 13:44:57 +03:00
Bartosz Lesniewski
635ffc760a
Add a check for negative axis attr out of bounds (#4543) 2021-03-15 13:41:43 +03:00
Ilya Lavrenov
24fb09edb3
Improvements in cmake scripts (#4766) 
1. Find Threads only once in IEDevScripts package
2. Small refactoring in IE Dev Package
 2021-03-15 13:07:38 +03:00
Ilya Lavrenov
753f4d5918
Second attempt to fix CVS-50011 (#4659) 
* Second attemp to fix CVS-50011

* Clarified OpenCV dependencies

* Fixes
 2021-03-15 13:04:20 +03:00
Irina Efode
8e080d4504
[IE TESTS][Conformance] Add conformance tests runner (#3694) 
* [IE TESTS][Conformance] Add conformance test target

* Handle creashes. Added crashed tests to the report

* Fix report and flags

* Apply comments

* Apply comment

* Remove flag, fix

* copyrights

* Generate in

* Remove extra code

* fix mac

* CI fixes

* fix win

* Fixes

* Input fixes

* fix flag

* Add generate in

* Fix compare

* Fixes CI
 2021-03-15 12:20:53 +03:00
Maksim Doronin
4f43598da4
[IE][VPU]: Decrease non-execute tasks priority (#4756) 
* Only executor threads now have top task priority. Other runtime threads have lower priority. Other non-runtime tasks (which do not participate in inference) have much lower priority.
 2021-03-15 12:10:07 +03:00
Vladislav Golubev
87afe28040
[LPT] ConvolutionTransformation: shape normalize of dequantization constant after convolution (#4696) 
* [LPT] normalizeDequantizationShape added to NetworkHelper

* [LPT] ConvolutionTransformation: added shape normalize of dequantization constant after convolution
 2021-03-15 11:12:51 +03:00
Anna Khakimova
7e572dba76
* GAPI: Fix for issue for ARM64 (#4752) 2021-03-13 18:18:34 +03:00
Nadezhda Ageeva
f41634eaba
[IE Tools] Fix seed for random generator in benchmark_app(s) to have reproducable data between runs of the same application (#4757) 2021-03-13 16:41:39 +03:00
Irina Efode
11f591c168
Unique Subgraphs\Operations extractor (#3742) 
* Initial Subgraphs Dumper and IR runner test inplementation

* Implement matchers configuration

* Refactor MatcherConfig

* Add OP cloners factory

* Remove IR runner test (to be added in separate PR)

* Use different nodes comparison method

* Remove extra include of <any> which fails build with old glibc

* Add README.md

Co-authored-by: Mikhail Treskin <mikhail.treskin@intel.com>
 2021-03-12 17:22:38 +03:00
Mingyu Kim
e6757dbd00
[IE CLDNN] Clarify ocl build error message (#4748) 
As current short_msg is usually irrelevant actual error, do not print it.
Instead, suggest to use srcdump.
 2021-03-12 16:33:18 +03:00
Ilya Lavrenov
96933c5598
Reflected that plugin on OSX are also .so (#4754) 2021-03-12 15:25:43 +03:00
Tomasz Dołbniak
6ac849eed3
Fix handling of the QuantizeLinear op connected to multiout ops (#4741) 2021-03-12 11:01:37 +01:00
Elizaveta Lobanova
39ae56d71f
[GNA] Move weights transposition from NCHW to NHWC to GNA pass after FQ passes (#4614) 2021-03-12 12:12:41 +03:00
Ilya Lavrenov
c88e1f7a59
Added check for shared library to ie_add_vs_version_file (#4738) 2021-03-12 10:06:04 +03:00
Mikhail Letavin
ad4cfbfceb
[IE CLDNN] Fix NormalizeL2 creation in QueryNetwork (#4310) 2021-03-12 09:44:12 +03:00
Mateusz Tabaka
13066a0bc6
Propagate input rank for dynamic output shape in BatchToSpace,DepthTo… (#4588) 
* Propagate input rank for dynamic output shape in BatchToSpace,DepthToSpace,Pad,SpaceToBatch,SpaceToDepth

* Add tests for SpaceToDepth, DepthToSpace dynamic input
 2021-03-12 07:17:24 +03:00
Patryk Elszkowski
1799df4cc8
Drop comparison of inputs and outputs for SubGraph. (#4716) 
SubGraph might have inputs and outputs in different order and still be
the same Function.

Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
 2021-03-12 07:11:25 +03:00
Patryk Elszkowski
18dd574864
Update spec for DIVIDE operation. (#4536) 
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
 2021-03-12 07:05:18 +03:00
Ilya Lavrenov
d77a07bd6a
Deprecated IE::Parameter <-> ngraph::Variant (#4734) 2021-03-12 06:36:28 +03:00
Victor Kuznetsov
3a703d546c
[Stress] MemCheck add FP16 models to configs (#4503) 2021-03-12 01:14:40 +03:00
Maxim Shevtsov
e588bf4681
Docs update master (#4736) 
* Updated latency case desc to cover multi-socket machines

* updated opt guide a bit

avoiding '#' which is interpreted as ref

Update CPU.md

Update docs/optimization_guide/dldt_optimization_guide.md

Co-authored-by: Alina Alborova <alina.alborova@intel.com>

Update docs/optimization_guide/dldt_optimization_guide.md

Co-authored-by: Alina Alborova <alina.alborova@intel.com>

Update docs/optimization_guide/dldt_optimization_guide.md

Co-authored-by: Alina Alborova <alina.alborova@intel.com>

Update docs/optimization_guide/dldt_optimization_guide.md

Co-authored-by: Alina Alborova <alina.alborova@intel.com>

Update docs/optimization_guide/dldt_optimization_guide.md

Co-authored-by: Alina Alborova <alina.alborova@intel.com>

Co-authored-by: Alina Alborova <alina.alborova@intel.com>
 2021-03-11 18:20:21 +03:00
Mingyu Kim
9de861d2e1
[IE CLDNN] Use fsv4 when feature-depth is shallow (#4398) 2021-03-11 16:45:11 +03:00
Ilya Lavrenov
7ac7e90880
Fix for BlockedDims (#4718) 
* Fix for BlockedDims

* Added test for HWC layout
 2021-03-11 16:29:30 +03:00
Elizaveta Lobanova
fd311e60f5
[GNA] Map 2d convolution to 1d if kernel width/height is equal to input width/height (#4471) 
Fix transposition info handling for a crop layer
Throw exception for 1d convolution padding
 2021-03-11 15:22:33 +03:00
Ivan Tikhonov
b792214d04
Fix python API for Loop/TensorIterator/Assign/ReadValue operations (#3275) 
* update python API for the Loop operation (attempt 1)

* fix code style

* update visitor API, pep8

* codestyle

* delete TensorItertorBuilder

* update visitor API for Loop and TensorIterator

* fix code issues (python)

* update python api:assign/read value

* fix unit tests

* fix python code style

* fix loop unit test

* fix loop unit test

* fix build on centOS
 2021-03-11 13:22:24 +03:00
Evgeny Lazarev
56a179c6a3
Added support for attribute 'pad_to_max_dimension' for TF OD API models (#4720) 
* Added support for attribute 'pad_to_max_dimension' for TF OD API models

* Restored line removed by mistake
 2021-03-11 13:21:20 +03:00
Anna Khakimova
61389b5e51
Fix for compilation issue for ARM 32-bit (#4717) 2021-03-11 12:13:11 +03:00
Anastasia Popova
8070c416be
Added specification for Roll operation. (#4469) 
* Added specification for Roll operation.

* Small text correction.

* Added examples, corrected types, opset num, made axis required.

* Renamed axes param, fixed formula, added negative shift example.

* Apply suggestions from code review

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

* Added missed bracket.

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>
 2021-03-11 11:24:05 +03:00
Mikhail Ryzhov
98dbab27a4
Added mo.py to wheel packages (#4723) 2021-03-11 11:10:45 +03:00
Svetlana Dolinina
5c4e862257
cherrypick from 2021.2 release branch: added draft version of doc for networks with state (PR #3372) (#4072) 
* added draft version of doc for networks with state (#3372)

* added draft version of doc for networks with state

* update code snippet

* update example

* review fixes

* fixed png

* review fixes

* image fix

* minor fix

* LowLatency documentation

* apply review comments

* Apply suggestions from code review

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

* review fixes

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>
(cherry picked from commit 99c746f2c3)

* take latest changes from 2021.2
 2021-03-11 11:02:53 +03:00
Ilya Churaev
192e66e013
Restored folded Operations for QueryNetwork (#4686) 
* Restored folded Operations for QueryNetwork

* Fixed comment

* Add unfolded constant operations to supported layers map
 2021-03-11 10:41:52 +03:00
Anton Chetverikov
4e6ec54b43
Add STN to list of supported models (#4708) 2021-03-11 10:26:40 +03:00
Evgeny Lazarev
761b748de2
Updated documentation about the supported YOLOv3 model from ONNX (#4722) 2021-03-11 09:39:53 +03:00
Patryk Elszkowski
a0df0c98ea
Update spec for subtract (#4692) 
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
 2021-03-11 09:36:16 +03:00
Patryk Elszkowski
6d24629843
add backend tests (#4611) 
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
 2021-03-11 09:27:03 +03:00
Patryk Elszkowski
98cc6e634a
add spec - cleanup (#4715) 
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
 2021-03-11 07:12:15 +03:00