Commit Graph

3037 Commits

Author SHA1 Message Date
Sungeun Kim
e40a44202e
[IE CLDNN] Add a byxf format for RegionYolo op. (#4451) 2021-03-09 14:48:00 +03:00
Maksim Doronin
3757c079c1
[IE][VPU]: Fix empty output of CTCGreedyDecoderSeqLen (#4652)
Allow the second output of CTCGreedyDecoderSeqLen to be nullptr in cases when it is not used but calculated in the Myriad plugin. In this case, parse the second output as FakeData
2021-03-09 13:46:39 +03:00
Nikolay Shchegolev
85e493ecb9
[CPU] Statically analyzed issues. (#4636) 2021-03-09 12:52:25 +03:00
Szymon Durawa
3e22f33224
Update spec for ADD operation. (#4366)
* Update spec for ADD operation.

* Change back quote for attribute name and value.

* Update link for auto_broadcast attribute.

* Move detailed description section, add suto_broadcast attribite to examples.

* Remove github link in numpy attribute description and replace it with local link.

* Add brodcast_rules.md for specific broadcast rules.

* Add new line at the end of broadcast_rules.md, modify font for add inputs.

* Change link for Broadcast_1.md

* Add description of broadcast in broadcast_rules.md

* Correct output shape description.

* Add bidirectional broadcast description and  new examples.

* Add description for auto_broadcast types: None and PDPD.

* Add examples for pdpd and bidirectional broadcasts, add pdpd attributte for Add, modify Broadcast ops to refer broadcast_rules file.

* Duplicated 'openvino_docs_ops_broadcast_rules' label change.

* Add example with scalar for bidiretional broadcast.

* Add new lines for examples.
2021-03-09 12:26:08 +03:00
Patryk Elszkowski
e5e7715a52
backend unit-test for divide op (binary_op) (#4540)
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
2021-03-09 06:41:35 +03:00
Ilya Lavrenov
07f1b2511b
Don't allow to create 2 plugin with the same device name (#4665) 2021-03-09 06:31:15 +03:00
Taylor Yeonbok Lee
e2c15a18ff
[IE CLDNN] Fuse reorder to permute. (#4549) 2021-03-08 22:48:06 +03:00
Andrey Somsikov
7f8d3aa638
Catch std::except in fuzz tests (#4610)
Fuzz tests must catch all expected exceptions from IE. IE is using C++ std
library which may raise standard exceptions which IE pass through.
2021-03-06 13:06:40 +03:00
Yegor Kruglov
84cd802ca5
Fix incorrect edge removal in the disconnect() method (#4582)
* added condition to disconnect method

* add unittest, rewrite the fix

* revert the second implementation, update test

Co-authored-by: yegor.kruglov <ykruglov@nnlvdp-mkaglins.inn.intel.com>
2021-03-05 21:57:28 +03:00
Anna Khakimova
3656e1c564
SIMD optimization of 8U3C/4C Resize for ARM via universal intrinsics. (#4331)
* SIMD opt of 8U3C/4C Resize for ARM

* * Fix issue.

* * Applied comments.

* * Applied comments. Step 2.
2021-03-05 19:58:46 +03:00
Roman Kazantsev
3dd5bfcfdd
Add workaround for control edges to support TF 2.4 RNN (#4633)
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2021-03-05 16:41:31 +03:00
Vladislav Volkov
121760476a
Fix for MKLDNN constant layers execution (#4632)
* Single mkldnn::engine for all MKLDNN graphs

* Fix for MKLDNN constant layers execution
2021-03-05 16:28:41 +03:00
Maxim Vafin
278b52ca98
Add documentation on how to convert QuartzNet model (#4422)
* Add documentation on how to convert QuartzNet model

* Apply review feedback

* Small fix

* Apply review feedback

* Apply suggestions from code review

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

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>
2021-03-05 16:18:25 +03:00
Alina Kladieva
4ec201fca6
[.ci/azure] Fix WinCC job name (#4650) 2021-03-05 15:29:11 +03:00
Mikhail Ryzhov
3c3de49ae7
[doc] Updated PyPI support OSes (#4643)
* Updated PyPI support OSes

* Added python versions for win and mac
2021-03-05 15:14:44 +03:00
Alina Kladieva
6af1ab4fca
[.ci/azure] Add windows_conditional_compilation.yml (#4648)
* [.ci/azure] Add windows_conditional_compilation.yml

* [.ci/azure] Fix job name for Win CC build
2021-03-05 13:57:32 +03:00
Gorokhov Dmitriy
23775a7783
[CPU] Supported ANY layout for inputs in inferRequest (#4628) 2021-03-05 12:30:17 +03:00
Anton Pankratv
2fcf92be42
Removed IRelease Interface (#4032) 2021-03-05 12:08:01 +03:00
Evgeny Lazarev
699c63bdaf
Updated copyright year in all MO files (#4630) 2021-03-05 11:57:42 +03:00
Ilya Churaev
972499b991
Fixed KW hits (#4639) 2021-03-05 11:12:52 +03:00
Evgeny Lazarev
7c5c708205
Fixed transformation to pull constants into Loop body (#4591)
* Fixed transformation to pull constants into Loop body

* Improved check that the value for Parameter node is not changed during iterations if the back edge exist

* Added unit tests for common_bfs function

* Stilistic changes

* Fixed typo

* Moved a check into the parameter_unchanged_after_iteration function
2021-03-04 22:00:22 +03:00
Yury Gaydaychuk
88a6e3863f
[CPU BF16] [Tests] Instantiation params for bf16-tests fitted to original task (#4551) 2021-03-04 17:33:41 +03:00
Andrey Zaytsev
78c4874432
Feature/azaytsev/formula fixes (#4622)
* Formula fix
2021-03-04 16:24:44 +03:00
Bartosz Sochacki
3daacb5e09
[GNA] POT enabling (#4358)
* POT enabling for GNA

* POT enabling for GNA

* POT enabling for GNA - accuracy improvements
2021-03-04 16:10:01 +03:00
Edward Shogulin
ed8d3b72d3
[LPT] GPU support3DTensorOnActivations - tests (#4576) 2021-03-04 16:05:02 +03:00
Bartek Szmelczynski
932558b403
Revise sin (#4337)
* rearrenge the spec to match the criteria

* Add Sin to the list of unary operators for unit tests

* add detailed description for sin

* remove latex tags for theta symbol

* add supported input rank for input tensor

* add link to wikipedia

* add description for input a
2021-03-04 15:29:11 +03:00
Victor Kuznetsov
1fef41d083
Fix reference config for MemCheckTests (#4587) 2021-03-04 15:15:07 +03:00
Alina Kladieva
7aa8159331
[.ci/azure] Enable CC build (#4619) 2021-03-04 14:42:20 +03:00
Ilya Churaev
fff0a85910
Fix clone affinity (#4577)
* Added test

* Fixed code style

* Removed propagate_rt_info function

* Revert "Removed propagate_rt_info function"

This reverts commit 514a21b93c.

* Don't skip conflicted RT info

* Fixed code style
2021-03-04 13:01:44 +03:00
Nadezhda Ageeva
2983962449
[IE Tools]: benchmark_app(s) supports BOOL input (#4578)
* [IE Tools]: benchmark_app(s) supports BOOL input

* Fix Windows build
2021-03-04 12:26:15 +03:00
Vladislav Volkov
52706e67fc
Fix for broken CC in CPU plugin (#4594) 2021-03-04 12:22:21 +03:00
Tomasz Dołbniak
a085b68d37
Subgraph extraction in ONNX model editor (#4107) 2021-03-04 10:12:37 +01:00
Mikhail Ryzhov
819bdbe4eb
Corrected PyYAML dependency (#4598)
5.4.2 is absent on PyPI
2021-03-04 09:21:56 +03:00
Anton Pankratv
7239a1aff3
Fixed unsafe macro (#4486) 2021-03-03 21:38:39 +03:00
Andrey Zaytsev
409cebc8e4
Feature/azaytsev/cldnn doc fixes (#4593)
* Legal fixes, removed the Generating docs section
* Removed info regarding generating docs
2021-03-03 20:52:10 +03:00
Andrey Zaytsev
8481e36e8a
Feature/azaytsev/gna model link fixes (#4590)
* 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

* Link Fixes

Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com>
2021-03-03 19:03:40 +03:00
Vladislav Volkov
e0573e7e7b
Constant nodes outputs sharing between streams (#4561) 2021-03-03 16:57:15 +03:00
Andrew Bakalin
430adbc191
[IE][VPU]: Fixes for Yolo-V3 (#4517)
* Fix negative axis processing for StaticShapeTopK
* Preserve output names in MergeSubsequentDSROperations
* Do validate_and_infer_types every time it's called in StaticShape* operations. It's needed to infer the correct output type in case it was changed from the last call moment (e.g. the ConvertPrecision pass have been called)
2021-03-03 16:47:42 +03:00
Edward Shogulin
7aed4ab3e7
[LPT] GPU support3DTensorOnActivations (#4562) 2021-03-03 16:18:25 +03:00
Alexander Zhogov
d76b4da77a
[Azure CI] Disable real CC build 2021-03-03 15:56:37 +03:00
Alina Kladieva
e8aa8e3efc
Add cc azure pipeline (#4586)
* [.ci/azure] Add linux_conditional_compilation.yml

* Update linux_conditional_compilation.yml

* [.ci/azure] Update config for lin cc build
2021-03-03 15:27:38 +03:00
Piotr Rozen
bf467e097f
[GNA] Fixed issue with multiple connections between pair of nodes (Split=>Concat) (#3953)
* fixed: gna split-concat-concat sequence issue
fixed: gna permute-conv-maxpool-permute issue

* fix issue with multiple connections between split|crop|memory & concat
fix issue with serializing IR V7 model

* fixed: gna split-concat-concat sequence issue
fixed: gna permute-conv-maxpool-permute issue

* fix issue with multiple connections between split|crop|memory & concat
fix issue with serializing IR V7 model

* fixed issues after rebase

* Fix for the test TEST_F(FP32NonQuantizedTest, LSTMCellPropagateForward)

Input x[96] = 0.1
Scaled input = 0.01
Affine output = 64 * 0.01 * 0.1 + 0.1 = 0.164
Sigmoid(Affine output) = 0.541
Tanh(Affine output) = 0.163
Sigmoid(Affine output)*Tanh(Affine output) = 0.088

Sigmoid(Affine output)*Scaled input = 0.005

H = Sigmoid(Affine output)*Tanh(Affine output) + Sigmoid(Affine output)*Scaled input = 0.093
tanh(H) = 0.093

Result = H + Sigmoid(Affine output)*Scaled input = 0.093 + 0.541*0.093 = 0.093 + 0.050 = 0.143

* Updated copyright date

* [GNA] Added tests for cases connection split->concat

* [GNA] Added fix memory -> concat case

* fixed inf loop during quantization

* fixed code formatting

* fixed failing test smoke_concat_quant_memory_requant/ConcatQuantDuringMemoryRequantTest.CompareWithRefs/netPRC=FP16_IS=128_HS=128_targetDevice=GNA

* fixed removed & mark from pass manager main for loop

* added split=>concat case to InsertCopyLayerPass

Co-authored-by: Andrey Dmitriev <andrey.dmitriev@intel.com>
2021-03-03 12:54:09 +03:00
Mikhail Ryzhov
aadf4f4da6
Updated PyPi documentation (#4423)
* Updated documentation

* Added documentation for dev package

* Added separate documents for PyPI

Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
2021-03-03 12:09:09 +03:00
Vladislav Golubev
a719534889
[LPT] matmul with qdq on weights tests (#4283) 2021-03-03 12:07:49 +03:00
Vladislav Golubev
c206830e7b
[LPT] Integration branch with fixes for release 2021.3 (#4544)
* [LPT] ClampTransformation segfault fix
[LPT] Clamp with non dequantization multiply functional tests

* [LPT] StridedSliceTransformation: handling Dq without batch

* [LPT] MVN-6 support

Co-authored-by: Zinoviev, Vladimir <vladimir.zinoviev@intel.com>
2021-03-03 11:36:26 +03:00
Gleb Kazantaev
ffade0d1d8
Fix FakeQuantizeMulFusion for cases with NUMPY broadcasting (#4570)
* Fix FQMul fusion

* Added transformation test

* Removed wrong test
2021-03-03 11:34:29 +03:00
Gleb Kazantaev
c1925cc220
Fix klocwork hits (#4573) 2021-03-03 11:27:47 +03:00
Pavel Esir
29612f15e3
Fix StridedSlice replacer order and input permutation when strides are not specified (#4545) 2021-03-03 11:16:56 +03:00
Vladimir Paramuzov
92d750747c
[IE CLDNN] Restored optional conversion of quantized model to fp32 (#4485) 2021-03-03 09:28:53 +03:00
Alexandra Sidorova
ebe63f557c
[CPU] Fixed strides for Pad after optimized Split (#4556) 2021-03-03 09:28:01 +03:00