IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,953 Commits 38 Branches 54 Tags 1.1 GiB
86f10b5c11
Commit Graph

4953 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Efode, Irina
568116859a Merge remote-tracking branch 'upstream/master' into layer_test_common 2021-10-13 20:19:58 +03:00
Efode, Irina
707d549ce8 Add configure model 2021-10-13 20:19:43 +03:00
Ivan Tikhonov
7b1a418bf4
MakeStateful transformation (#7417) 
* ReplaceInOutWithMemory transformation in ngraph

* add unit tests

* add ReplaceInputsOutputsWithMemory transformation in python

* update codestyle

* rename the transformation

* fix codestyle

* add Dynamic shapes check in the transformation and unit test

* fix codestyle

* rename files

* fix python API

* fix codestyle

* fix codestyle

* update python API

* fix codestyle

* fix build

* codestyle

* fix unit test

* fix RTTI declaration

* Apply suggestions from code review

Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>

* review comments

* openvino codestyle

* change the name of Variable in the transformation

* fix build

* delete MakeStateful transformation from ie_transformations

* Resolve review comments

* codestyle

* fix missprint, codestyle

* delete unused variable

Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
 2021-10-13 19:02:42 +03:00
Svetlana Dolinina
fd97a62263
add selectv2 extractor mapped selectv2 to select (#7847) 
* add selectv2 extractor mapped selectv2 to select (broadcast already implemented in select transformations/implementations)

* added SelectV2 to supported layers list
 2021-10-13 14:53:15 +03:00
Efode, Irina
d09dc07a3f Fix cpuFuncTests 2021-10-13 14:33:14 +03:00
Victor Kuznetsov
9e79f997e4
[Memory tests] Add timeout to proc_exec (#7942) 
* add timeout to proc_exec

* add framework field for db

* upd db fields name
 2021-10-13 14:25:44 +03:00
Elizaveta Lobanova
b746c734f8
[GNA] More precized calculation of Log pwl and pwl with sf < 1 (#7884) 
* [GNA] More precized calculation of Log pwl and pwl with sf < 1

* [GNA] Added tests

* [GNA] Types correction

* [GNA] Added comment for absolute threshold calculation in the test
 2021-10-13 14:14:52 +03:00
Ilya Churaev
02f3a175d0
Fixed build of RTInfoSerialization tests (#7978) 2021-10-13 13:50:30 +03:00
Elizaveta Lobanova
917a29255e
[GNA] Fixes for convolution handling (#7861) 
* [GNA] Fixed errors with convolution handling

* [GNA] Tests added

* [GNA] Fixed the problem with Convolution Filter

* [GNA] Allow scale factors near 0, comments apply
 2021-10-13 13:08:24 +03:00
Taylor Yeonbok Lee
a93a67da78
[GPU] Fix issue of prepare_output (#7783) 2021-10-13 12:50:43 +03:00
Ilya Churaev
50b0dc1182
Deprecated old evaluate methods (#7937) 
* Deprecated old evaluate methods

* Suppress node

* Fixed some warnings

* Fixed documentation and warnings

* Fixed some warnings

* Disable some warnings
 2021-10-13 12:47:14 +03:00
Vladimir Paramuzov
efcdaac4a6
[GPU] Added a couple of supported SIMD size checks (#7919) 2021-10-13 12:22:08 +03:00
Ilya Churaev
82f8f19d11
Moved serialization pass to public (#7862) 
* Moved serialization pass to public

* Fixed unit tests

* Fixed code style

* Fixed tests

* Fix link

* Fix kmb

* Fixed build

* Removed InferenceEngine::Core from ngraph tests

* Add missed models

* Restore IR weights

* Fixed code style
 2021-10-13 11:17:53 +03:00
Victor Kuznetsov
6d9a7a108e
Stress, Memory tests update to comply with new OMZ tools layout (#7886) 
* work with omz: change hardcoded paths for memory_tests, fix paths for memcheck get_testdata.py script

* change paths to omz tools

* revert mo changes

* remove mo from arguments

* remove extra var from cmd string

* remove is_db_used check

* add timeout to proc_exec

* merge master
 2021-10-13 10:42:00 +03:00
Mateusz Tabaka
db527fff41
Fix performance on resnet50 quantized models (#7670) 
* Fix performance on resnet50 quantized models

LP transformations won't work on the model unless the last 4 inputs to FakeQuantize
are constants. In order to meet that requirement, we need to perform constant folding
for those inputs in QuantizeLinear ONNX operator.

Ticket: 65375

* fix "Cannot find blob with name: y" exception during onnx_model_quant_conv_linear

* remove linking with onnx_ngraph_frontend

* fix exclude path
 2021-10-13 10:18:37 +03:00
Ilya Churaev
0d020974f9
Removed commonTestUtils from ngraph tests (#7956) 
* Removed commonTestUtils from ngraph tests

* Fixed build
 2021-10-13 09:56:12 +03:00
Ilya Churaev
972524f1cc
Use runtime::Tensor instead of Blob in read_model (#7951) 
* Use runtime::Tensor instead of Blob in read_model

* Fixed the memory ownership
 2021-10-13 09:13:11 +03:00
Min, Byungil
d23ec24fd8
[GPU] Onednn integration for handling reorders (#7764) 
Signed-off-by: Min, Byungil <byungil.min@intel.com>
 2021-10-13 15:06:53 +09:00
Kelvin Choi
e72200dbe1
Allow normalize included model to use fsv16 (#7906) 
(cherry picked from commit 1880d65158)
 2021-10-13 12:38:00 +09:00
Andrew Kwangwoong Park
4e2cc3e370
[GPU] Add GPU plugin metric to get statistics of GPU memory allocated by engine (#7758) 2021-10-13 05:40:51 +03:00
Vladimir Dudnik
9e1231ac8d
limit supported formats by MNIST database only, added lenet.labels file (#7947) 
* limit supported formats by NIST database only, added lenet.labels file

* shortened line

* apply code style fix
 2021-10-12 18:17:58 +03:00
Maxim Vafin
25c2d5c6c4
[MO] Fix axes in FusedBatchNorm -> MVN transformation (#7679) (#7913) 2021-10-12 16:47:29 +03:00
Ilya Churaev
c323775f2c
Add input/output to ov ExecNetwork (#7650) 
* Added template for new tests

* Fixed simple test

* Added output tests

* Removed get_result/get_parameter methods

* Fixed documentation

* Fixed functional tests

* Fixed caching tests

* Added new test for import

* Added new tests

* Fixed code style

* Fixed comments

* Fixed tests

* Fixed code style

* Save version in the function
Fixed pre-post processing

* Change IR version

* Fixed documentation

* Fixed MockICore

* HETERO almost works

* Fixed tests and core logic

* Disabled some CPU tests

* Tmp disable fp16 for template

* Fixed tests and clang-format

* Small fixes

* Fix

* Simplified code in templatePlugin

* Added IE precisions checks

* Simplified hetero plugin

* Added ieImportExportedFunction test

* Added MYRIAD test

* Skip tests directly in tests

* More correct filter for CPU

* Fixed CPU tests

* Template plugin tests

* Some comments

* FIxed clanf-format

* Removed myriad tests

* Fixed comment

* small changes

* Fixed condition

* Fixed unit tests

* clang-format

* Comment

* Hetero plugin update

* Fixed tests

* Moved re-create under ig

* Fixed clang-format

* Fixed some caching_tests

* Disable some caching_tests

* Fixed setLayout with dynamic case

* Fixed clang-format

* Disable execution graph

* Disabled one more CPU test

* Simplified regex

* Disabled GNA tests

Co-authored-by: y <ilya.lavrenov@intel.com>
 2021-10-12 13:11:25 +03:00
Mateusz Bencer
29eaa0af60
Handle PlaceOpONNX and PlaceOutputEdgeONNX by extract_subgraph (#7908) 2021-10-12 11:54:41 +02:00
Sergey Lyubimtsev
a10f40d6d4
Set scikit-image~=0.18.3 for python versions >=3.7 (#7910) 
* Set scikit-image~=0.18.3 for python versions >=3.7

* Set scikit-image>=0.17.2 (0.17.2 is not available for >=3.7)
 2021-10-12 11:49:42 +03:00
Vladimir Dudnik
1ba4f4caf6
print hint option (#7876) 2021-10-12 11:48:04 +03:00
Vladimir Dudnik
d790204575
fix typos in README.md (#7887) 2021-10-12 00:45:31 +03:00
Efode, Irina
4df40629b0 fix size of expected 2021-10-12 00:09:10 +03:00
Efode, Irina
4e32737bc2 try adopt softmax 2021-10-11 21:20:58 +03:00
Efode, Irina
c66d8626e4 Init 2021-10-11 18:23:26 +03:00
Vladislav Volkov
6d322722c6
[CPU] Fix for possible uninitialized variable in MKLDNNInputNode constructor (#7882) 2021-10-11 09:59:04 +03:00
Gleb Kazantaev
b80b87b2d9
Split Transformations between MOC and Common pipelines (#7580) 
* Split Transformations between MOC and Common pipelines

* Test

* Split passes

* Fix int8 issue

* Small refactoring
 2021-10-08 19:07:41 +03:00
Maxim Shevtsov
492fdadba9
Resetting the GPU hints baseline to let the validation switch the perf tetsing to these (and see no delta first) (#7868) 2021-10-08 17:26:11 +03:00
Wilson Seok
d50ba1129b
Migration convolution ngraph backend test (#7846) 
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now

* update repo

* add convolution reference test and ngraph backend test

* fix location of ngraph visitor convolution.cpp
 2021-10-08 16:52:00 +03:00
Mikhail Nosov
2592856200
[OV2.0] Leftovers for Preprocessing/input/output (#7893) 
* Pre-process:
- Implicit conversions for element type and layout
- 'convert_element_type' with default argument to network
- Convert_element_type - don't add ops if dst and src types are same
- Convert_layout - don't add ops if dst and src layouts are same
- Custom step - use Output<Node> instead of shared_ptr<Node>
- Support of addressing input by tensor name

Post-process:
- Avoid duplication of tensor names after post-processing

* Fixed IE tests
 2021-10-08 12:58:29 +03:00
Piotr Szmelczynski
d8c6591249
Pszmel/get place by operation name and output port (#7863) 
* update description of get_place_by_operation_name_and_input_port

* create implementation for get_place_operation_name_and_output_port

* fix typo

* updatget_place_by_operation_name_and_input_port and get_place_by_operation_name_and_output_port

* add tests for get_place_by_operation_name_and_input_port and get_place_by_operation_name_and_output_port

* fix style
 2021-10-08 12:33:54 +03:00
Jade Cho
15c98bbf8c
[GPU] Merge prepare_buffer_fusing updates (#7878) 
* [GPU] Merge prepare_buffer_fusing updates

+ Disable choosing implementation using TBB if immad is supported

* [GPU] Apply comments
 2021-10-08 15:31:51 +09:00
Ilya Churaev
ff31ac553a
Introduce new evaluate API (#7848) 
* Introduce new evaluate API

* Removed redundant pointers from new API

* Fixed eval tests

* Fixed comments

* Enable evaluate_lover/upper methods
 2021-10-08 07:29:25 +03:00
Irina Efode
a3a651ff97
[IE TESTS] Remove functionRefs from all tests and add it in necessary places (#7873) 
* gna

* [IE TESTS] Remove functionRefs from some places
 2021-10-08 00:29:00 +03:00
Andrey Somsikov
5eaf029723
Fix coverity linux pipeline (#7879) 
Exclude python, contrib, and samples from the build.
Clean up unnecessary dependencies installation.
Publish artifacts.
 2021-10-07 22:00:39 +03:00
Ilya Lavrenov
ec126c6252
old / new API precisions conversions, old_api_map applying (#7853) 
* Enabled support of IR v11 in IR frontend

* Enabled serialization to v11

* Added indexes for Inputs/Outputs

* Fixed typo

* Fixed code style

* Fixed deserialization tests

* FIxed typo

* Avoid changes in the original serialized function

* Split IRv7 and IRv10 code

* Added preprocessing steps to read network

* Added preprocessing for new API for IR v10

* clang-format

* Updates for compiler flags

* Reverted some changes

* Fixed TI tests

* Removed version from the function and indexes from parameters/results

* Restore function version

* Clone function rt info

* Removed v11 version

* Added serialization of old API map in ngraph.

* Changed order type to int64_t.

* Fixed uint64_t error, added comments.

* Apply suggestions from code review

Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>

* Read old_api_map

* Added tests with undefined type and empty order.

* Fixed reprocessing

* Updated gitignore

* Updated serialize / deserialize tests

* Added set, get and has methods.

* Fix in tests.

* Applied old_api_map tests

* Fixed empty convert_layout

* Allow Layout from empty string

* Fixed clang-format

* Export FEM::load_by_model

* Apply suggestions from code review

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

* Made inline methods, changed to shared_ptr.

* Small fix.

* Moved methods to header file.

* Small fix.

* Applied post-processing

* Fixed review comments

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
Co-authored-by: Anastasia Popova <anastasia.popova@intel.com>
Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
 2021-10-07 18:59:24 +03:00
Eugeny Volosenkov
05cd830de5
Move eval tests to template tests (#7132) 
* Add If implementation with reference

* fix test

* fix comments

* Fix validate_and_INFER_TYPES

* rewrite tests for dynamic cases

* Fix ci failed

* add comentaries for validate_and_infer_types

* fix api

* Added ngraph checks and delete copied op from opset8

* code style fix

* fix code style

* add checkers to reference

* add has_evaluate

* fix eval

* Fix code style

* fix code style

* Add template plugin tests

* fix code style

* delete boolean

* fix IfParams

* Fix comments

* intermediate commit

* delete eval test

* add common header

* Fix codestyle

* fix set_invariant_input/set_body_output

* fix code_style

* fix codestyle

* delete validate_and_infer_types from type prop tests

* delete comments
 2021-10-07 18:40:57 +03:00
Egor Duplensky
465304a108
[CPU] Remove get_friendly_name WA (#7589) 
The ngraph issue has been fixed.
WA is not needed anymore.
 2021-10-07 18:32:09 +03:00
Anton Dudchenko
bdc8208dd3
[IE][VPU] Update FW (#7499) 
Update FW with revert changes for 256MB
 2021-10-07 15:57:13 +03:00
Bartek Szmelczynski
cfe18d289c
Scatter update ref impl revision (#7476) 
* add template tests for scatter_update

* rm CT from ref impl

* fix namings

* minor code refactor

* fix style

* change ref impl

* add lambda func

* new tests

* remove CT from reference implementation, add template tests

* fix cpu IE

* refactor template tests

* split template tests
 2021-10-07 14:40:15 +03:00
Mateusz Tabaka
126943800e
Add support for ONNX op "com.microsoft.EmbedLayerNormalization" (#7837) 2021-10-07 11:28:27 +02:00
Dmitrii Khurtin
f856ac0203
[GNA] Added ConcatAlignFilter support for Accuracy Aware mode (#7834) 
* Added ConcatAlignFilter support for Accuracy Aware mode

* fails after reviewing and added tests

* moved the test to gna/scale_factors_tests; added comments to test
 2021-10-07 12:25:18 +03:00
Dmitrii Khurtin
6f43b8d0af
[GNA] Fixed failed to inserting reshape around MatMul (#7833) 
* Fixed failed to inserting reshape around MatMul.

* remove unnecessary

* added comments
 2021-10-07 12:18:22 +03:00
Alina Kladieva
d11ff04130
Update skip_tests_config.cpp (#7874) 2021-10-07 12:09:22 +03:00
Yury Gaydaychuk
4c80b110d0
[CPU] Deformable convolution improvements (#7168) 
* jit impl. optimized

* reviewed

* reviewed
 2021-10-07 11:31:08 +03:00