IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
692 Commits 38 Branches 54 Tags 1.1 GiB
18836f53cd
Commit Graph

692 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Andrew Bakalin
f00cdddede
[IE][VPU][GT]: Change begin and end masks serialization for StridedSlice (#1417) 
* In order to support cases when begin and end size is less than input rank, the serialization was changed.
* Add tests
* Update firmware
 2020-07-23 12:20:08 +03:00
Ruslan Garnov
d6c412ca40
Updated fluid to 4.3.0 (#1422) 2020-07-23 12:04:31 +03:00
Vitaliy Urusovskij
6fcad95c71
[Stress] Redesign of MemCheckTests (#650) 
* [Stress] Redesigned MemCheckTests: 1. Added MemCheckPipeline to incapsulate measures and logging. 2. Moved references to array

* [Stress] Added tracking of THREADS in MemCheckTests
 2020-07-23 11:07:13 +03:00
Andrew Bakalin
dce1063526
[IE][VPU][NGraph] Move dynamic NMS from common to vpu folder (#1409) 
* [IE][VPU]: Moves UpgradeNMS4ToNMSDynamic transformation into myriad plugin

* [IE][VPU]: Moves UpgradeNMS4ToNMSDynamic from common to vpu folder

* [IE][VPU]: Moves Dynamic NMS from common folder to vpu

* [VPU]: Makes NMS conversion unconditional

* [VPU][NGraph]: Changes dynamic NMS base class from v3 to v4

* [VPU]: Moves NMS4toDynamic transformation before common optimization
 2020-07-23 10:23:35 +03:00
Vladimir Paramuzov
c69591c0b7
[IE CLDNN] Shrink reshapes (#1362) 2020-07-23 10:14:52 +03:00
Andrey Zaytsev
045fe44d29
Fixes LFS issues (#1440) 
* Removed non-LFS images to reload them to LFS

* Reload images to LFS

* Reload images to LFS
 2020-07-22 22:35:58 +03:00
Nikita Kudriavtsev
5b9a5a6293
[IE Myriad/35383] vpu_profile is removed (#1393) 2020-07-22 17:34:16 +03:00
Adam Osewski
093a02fcef
Test fix import of ONNX model in serialized Protobuf binary format. (#1355) 
* Try fix parsing error.

* Small exception refinements during importing model.

* More exception refinements.

* Skip segfaulting tests.

* More clear error types and messages. Func rename.

* Fix typo.

* Check on CI whether test_onnx will work.

* Add only those file which pass tests or have failing ones skipped.
 2020-07-22 13:52:53 +03:00
Roman Kazantsev
6ccc025a43
Extend nGraph for operation CTCLoss (#1236) 
* Extend nGraph for operation CTCLoss

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fixes as per comments

Co-authored-by: Nikolay Shchegolev <nikolay.shchegolev@intel.com>
 2020-07-22 13:45:42 +03:00
Ilya Churaev
141b24cf44
Replaced copy_with_new_args() to clone_with_new_inputs() (#1395) 2020-07-22 13:44:22 +03:00
Ewa Tusień
821a3dae32
Expose OpSets as part of nGraph PythonAPI (#1261) 2020-07-22 12:02:54 +02:00
Ewa Tusień
b3f55dd0be
Update list of tests passing/failing using TestCase on IE backend (#1161) 2020-07-22 11:42:19 +02:00
Vitaliy Urusovskij
5665ec9b26
[Stress] Small improvement of scripts (#1302) 
* [Stress] Extend CLI with arguments checks for compare_memcheck_2_runs.py

* [Stress] Extend requirements.txt with PyYAML
 2020-07-22 10:24:15 +03:00
Ilya Lavrenov
a773dfbbcc
Removed ie_deprecated.cpp from legacy library (#1419) 2020-07-22 06:44:53 +03:00
Ilya Lavrenov
8e081c8388
Removed CNNLayer entries from ie_common.h (#1420) 
* Removed useless header include

* Removed CNNLayer entries from ie_common.h
 2020-07-22 06:44:05 +03:00
Ilya Churaev
c75ff2a4fc
Removed is_parameter, is_constant and is_output (#1408) 2020-07-22 06:11:28 +03:00
Ilya Churaev
a864c2eb85
Removed redundant licenses (#1392) 
* Removed redundant licenses

* Added protobuf license
 2020-07-21 19:48:25 +03:00
Ilya Lavrenov
79349ae4a6
CMAKE: added ie_libraries target (#1411) 2020-07-21 18:58:20 +03:00
Ilya Znamenskiy
c37f73334c
[IE CLDNN] Gemm int8 with slm optimization. Fused ops fix (#1319) 2020-07-21 17:45:42 +03:00
Roman Lyamin
613d822458
[IE TESTS] Added single layer test Mish (#1401) 2020-07-21 15:11:05 +03:00
Anna Khakimova
eecd03aa85
Pre-processing(GAPI): ARM(NEON) integration + Split, Merge, Color conversion kernels on NEON (#1315) 2020-07-21 14:19:15 +03:00
Ilya Lavrenov
14d371849d
Split CNNlayer validators (#1403) 
* Simplified CNNLayer validators: keep only parsing of arguments

* Added validators as is

* Removed parsing arguments

* Removed Backetize validator
 2020-07-21 13:57:56 +03:00
Nikita Kudriavtsev
a482e32911
[IE][VPU]: Added Gelu layer (#1195) 
* Implement Gelu stage in GraphTransformer
* Disable GeLU decomposition in the nGraph transformations
 2020-07-21 11:36:35 +03:00
Ilya Lavrenov
f7d6711137
Removed addLayer implementation from ngraph impl (#1400) 2020-07-21 06:36:18 +03:00
Ilya Churaev
54ae67414e
Remove redundant node methods (#1324) 
* Remove placement

* Removed validate and infer eltwise

* Remove is eltwise

* Remove support broadcast and decompose

* Removed is_op, is_parameter, is_pattern

* Fixed code style

* Added is_constant and is_output

* Removed is_communicative and is_null

* Fixed code style

* Fixed typo

* Fixed comments

* Fixed typo

* Revert is_parameter, is_output, is_result for OpenCV build
 2020-07-21 06:02:00 +03:00
Anna Khakimova
898f0626ad
Fix for issue (#1335) 2020-07-20 20:09:23 +03:00
Vladislav Volkov
41f8086765
Header length for supported model detection is increased (#1363) 2020-07-20 18:11:22 +03:00
iliya mironov
399c7bf39a
Add mish op to ngraph (#1187) 
* Add mish op to ngraph

* Update mish op

* Set v4 namespase for tests

* Add mish to cmake

* Add comments for mish op.

* Refactoring code style

* Update version to v1 for Mish op

* Add value propogation test for Mish op

* Refactoring mish op according to review

* Fix mish version

* Update cmake file

* Fix mish value propogation unit test

* Add unit test for mish op

Co-authored-by: Your Name <you@example.com>
 2020-07-20 17:43:32 +03:00
Nikolay Tyukaev
ef45b5da8d
Doc Migration (master) (#1377) 
* Doc Migration from Gitlab (#1289)

* doc migration

* fix

* Update FakeQuantize_1.md

* Update performance_benchmarks.md

* Updates graphs for FPGA

* Update performance_benchmarks.md

* Change DL Workbench structure (#1)

* Changed DL Workbench structure

* Fixed tags

* fixes

* Update ie_docs.xml

* Update performance_benchmarks_faq.md

* Fixes in DL Workbench layout

* Fixes for CVS-31290

* [DL Workbench] Minor correction

* Fix for CVS-30955

* Added nGraph deprecation notice as requested by Zoe

* fix broken links in api doxy layouts

* CVS-31131 fixes

* Additional fixes

* Fixed POT TOC

* Update PAC_Configure.md

PAC DCP 1.2.1 install guide.

* Update inference_engine_intro.md

* fix broken link

* Update opset.md

* fix

* added opset4 to layout

* added new opsets to layout, set labels for them

* Update VisionAcceleratorFPGA_Configure.md

Updated from 2020.3 to 2020.4

Co-authored-by: domi2000 <domi2000@users.noreply.github.com>
 2020-07-20 17:36:08 +03:00
Ivan Tikhonov
4037613db3
Added default constructor for RNNCellBase, fix conversions (#1370) 2020-07-20 14:15:37 +03:00
Rafal Blaczkowski
06119efdf2
ONNX CI: add docker image cleanup (#1394) 
* change stage name
 * add docker image cleanup
 2020-07-20 13:42:52 +03:00
Jan Iwaszkiewicz
d4c9af91d8
Add getting/setting friendly name for Node wrapper Py API (#1286) 2020-07-20 10:31:49 +02:00
Tomasz Dołbniak
8d6238a3d7
Reference implementations for ReduceLogicalAnd & ReduceLogicalOr (#1333) 2020-07-20 10:20:05 +02:00
Jozef Daniecki
eca80086ac
Add Acosh operator to ONNX importer opset4 (#1351) 2020-07-20 10:18:03 +02:00
Vitaliy Urusovskij
57779511d6
[Stress] Integrate compare_memcheck_2_runs call in run_memcheck.py (#1036) 
* [Stress] Define Database constant arguments in memcheck_upload.py only

* [Stress] Simplify computations using HashableDict in `compare_memcheck_2_runs`

* [Stress] Add comparison using pandas
 2020-07-20 10:23:51 +03:00
Ilya Lavrenov
2ddf08d14b
Removed tests for old IR reader (#1368) 2020-07-18 12:42:40 +03:00
Ilya Churaev
cc19e57a06
Removed v0 fused operations (#1263) 2020-07-17 19:51:04 +03:00
Anton Chetverikov
dca2ee2bcc
ReduceLp operation specification (#1205) 
* Add ReduceL2 operation specification

* Add example

* Update operation specification

* Update operation specification

* Update operation specification

* Update operation specification

* Update types in operation specification
 2020-07-17 16:13:19 +03:00
Tomasz Socha
28227dcd9f
[nGraph][Py][Tests] Remove backup of old models (#1349) 2020-07-17 15:12:11 +02:00
Alexander Zhogov
17287f20a0
CODEOWNERS: Add .ci & docs 2020-07-17 15:07:58 +03:00
Andrew Bakalin
5cda3938d8
[IE][VPU][GT]: Use topological order in shape allocation (#1281) 
* Some pass creates datas duplicate with a different order from time to time (because of unordered_set usage). It leads to a different order in model->datas() list and affects the shape allocation process which relies on this order.
* Make shape allocation be relied on topological order of datas which is stable and doesn't depend on order datas creation during different passes.
 2020-07-17 11:47:37 +03:00
Ilya Lavrenov
ee3fafceda
Fix unsafe use of CPU_ISSET_S macro. (#1357) 
Don't increment mapped_idx via prefix increment within the argument of the
potentially unsafe CPU_ISSET_S macro. If the macro is expanded so that the
increment expression is evaluated multiple times, it will return unexpected
results.

While the glibc implementation of CPU_ISSET_S macro seems to be safe, the musl
libc (v1.1.23) version is unsafe and will evaluate the first argument of
CPU_ISSET_S three times.

Co-authored-by: Christian Priebe <cp3213@ic.ac.uk>
 2020-07-17 10:51:56 +03:00
Ilya Churaev
29816f7a44
Remove get_arguments (#1323) 
* Removed get_arguments

* Fixed code style
 2020-07-17 09:50:06 +03:00
Nikita Kudriavtsev
73ee68afb2
[IE][VPU]: CMX limit compile option (#1268) 
In some networks, mvTensor would request a large CMX-DMA transfer (<512K). That starves DMA for other timing critical tasks such as SIPP. Limit CMX-DMA request size as an option in myriad_compile:
* Add compile option TILING_CMX_LIMIT_KB
* Declare compile option TILING_CMX_LIMIT_KB in IE tools (compile_tool and vpu_compile)
* Add tests for compile option TILING_CMX_LIMIT_KB. Small fix for naming behavior tests.
 2020-07-16 19:54:53 +03:00
Alexander Zhogov
d9927a9f35
Azure CI: Fix cloning git submodules (#1356) 2020-07-16 19:29:54 +03:00
Andrey Somsikov
9df6a8f6a0
fix: inference-engine/ie_bridges/python/sample/requirements.txt to reduce vulnerabilities (#1007) 
The following vulnerabilities are fixed by pinning transitive dependencies:
- https://snyk.io/vuln/SNYK-PYTHON-NUMPY-73513

Co-authored-by: snyk-bot <snyk-bot@snyk.io>
 2020-07-16 18:58:26 +03:00
Irina Efode
bfd318cbd3
[IE TESTS] Add PReLu single layer test (#1306) 
* [IE TESTS] Add PReLu single layer test

* [IE TESTS] Small refactoring of test infrastructure

* [IE TESTS] Add shape for activation
 2020-07-16 18:16:57 +03:00
Rafal Blaczkowski
e7861c7455
Revert "Header length for supported model detection is increased (#1340)" (#1354) 
This reverts commit 5b2ec7840a.
 2020-07-16 18:09:45 +03:00
Ilya Lavrenov
949fee3cfc
Remove implicit conversion from getInputTo, getLayerCreator (#1274) 
* Added ctor for CNNNetworkImpl to convert from ngraphImpl

* Re-use in all places instead of manual conversion

* Hide convertToCNNNetworkImpl usage

* Removed conversion from getCreatorLayer

* Fixes 2

* Fixes 3

* Fixes 4

* Fixed ieFuncTests

* Fixed more tests

* Fixed LPT tests

* Remove useless test

* Fixed GNA

* Fixed Gleb's comments

* Fixed Core integration tests

* Trying to fix python

* Fixed GPU tests

* Small fixes

* Fixed QueryNetwork after removing implicit conversion

* Fixed Core integration tests for QueryNetwork

* Fixed python; MULTI device QueryNetwork

* Fixed MULTI QueryNetwork

* Removed unused methods

* Enabled LPT FullyConnectedTestModel test

* Fixed typo in python
 2020-07-16 16:44:48 +03:00
Vitaliy Urusovskij
930d687ed9
[Stress] Specify OMZ develop branch in get_testdata.py (#1318) 
Since in validation OMZ is used from a package (and OMZ is from develop branch), align OMZ default for get_testdata.py
 2020-07-16 15:28:25 +03:00