IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
8,954 Commits 38 Branches 54 Tags 1.1 GiB
331b1883a1
Commit Graph

8954 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Roman Kazantsev
f80babff51
[Layer Tests][TF FE] Activate layer tests for FusedBatchNorm in training mode in the precommit (#14240) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-11-26 00:25:00 +03:00
Roman Kazantsev
1353a23f12
Fix leftovers from PR14211 (#14238) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-11-25 20:29:23 +03:00
Wilson Seok
aea83d3d8b
[GPU] add output_partial_shape in calc_output_layout of reshape primitive and add single layer test of strided_slice for the fix (#14209) 2022-11-25 17:28:53 +04:00
Sofya Balandina
7e812b7d77
Update jinja version to 3.x+ (#14200) 2022-11-25 15:44:57 +03:00
Mikhail Ryzhov
fc2d957a0e
[GNA] Added unit tests for wrapped validators (#14193) 
* Added unit tests for wrapped validators

* review commnets

* review fixes

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update src/plugins/intel_gna/tests/unit/ops/util_test.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* FIxed typo mistake

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>
 2022-11-25 13:24:58 +03:00
Edward Shogulin
cdb711a069
LPT: element-wise ops fuse extension to support updatePrecisions (#14141) 2022-11-25 13:49:03 +04:00
Yuan Xu
04df4195a0
update with installing dependencies (#14237) 2022-11-25 12:54:51 +04:00
Mikhail Ryzhov
c0941aba74
[GNA] Fixed order of Assign layers (#14066) 2022-11-25 11:21:57 +03:00
Krzysztof Bruniecki
b5557fc211
[GNA] Fix 2D->1D mapping of Convolutions (#14162) 
* [GNA] Fix 2D->1D mapping of Convolutions where transpose BTW H and W is not applicable
 2022-11-25 09:13:53 +01:00
Sergey Shlyapnikov
637f1cdf8f
[GPU] Fix lockable memory allocation (#14134) 
* [GPU] Fix lockable memory allocation

* Apply review comments

* [GPU] Replace usm handle sharing with independent blob creation

* Prohibit all other remote blob types

* [GPU] Fix for nullptr impl
 2022-11-25 12:07:47 +04:00
Taylor Yeonbok Lee
823ea7c68a
[GPU] Fixed node.is_dynamic() check to check regardless output size is valid or not (#14173) 
* Fixed node.is_dynamic() check to check regardless output size is valid or not

* Additional fixes & added unittest
 2022-11-25 11:54:42 +04:00
Vladimir Paramuzov
fdf504738d
[GPU] Replace cl2.hpp with opencl.hpp in cmake search for docs and benchmark_app (#14158) 2022-11-25 11:37:51 +04:00
Eddy Kim
d436206019
[GPU] Removing OneDNN patch file for GPU model caching (#14214) 
* updated not to use default c-tor for onednn desc

* onednn patch file is removed
 2022-11-25 11:37:30 +04:00
Ilya Lavrenov
8dd8262b77
Added Debian, Raspbian, Ubuntu 22.10 support to install dependencies (#14226) 
* Added Debian, Raspbian, Ubuntu 22.10 support

* Updated dependencies.cmake

* Fixes in script

* Added RHEL 9.1 support

* Added proper comments

* Compilation of rpm packages for aarch64 is fixed

* Proper generation of requirements.txt files when ENABLE_WHEEL=OFF

* samples build improvements

* Proper name for json library

* Proper condtion in samples
 2022-11-25 11:13:43 +04:00
Ivan Tikhonov
4f0b846d1a
Move GRUCellFusion and SequenceFusion transformations before NopElimination (#14213) 2022-11-25 10:57:45 +04:00
Ilya Lavrenov
6954838582
Conda fixes for Windows (#14219) 2022-11-25 10:57:00 +04:00
Ilya Lavrenov
923409164f
Excluded MYRIAD from debian / rpm packages (#14227) 2022-11-25 10:56:07 +04:00
Mateusz Bencer
87715978dc
PullThroughReduce and ReduceReshapeFusion transformations - handle more than one consumers (#14101) 2022-11-25 09:26:00 +03:00
Roman Kazantsev
db81e50a02
[TF FE] Support unknown and dynamic rank Placeholder shape (#14211) 
* [TF FE] Support unknown and undefined Placeholder shape

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

* Fix mistake in the test

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-11-25 09:22:42 +03:00
Luo Cheng
21b09e0ac9
[CPU][TESTS] Added test cases for 3D FC Node: brg, brg<->ip, multiple weights (#14144) 2022-11-25 09:54:52 +04:00
Ilya Churaev
4e3f9515e0
Fixed Project root for exceptions (#14178) 2022-11-25 08:26:44 +03:00
Eddy Kim
36e37a8b0a
[GPU] GPU driver version and architecture properties (#14187) 
* added gpu driver version and gpu architecture properties

* deleted unnecessary header inclusion

* reverted to use gfx_ver for architecture string

* device_id is added to caching_properties
 2022-11-25 09:20:15 +04:00
danylo-lebediev-capgemini
1f15d2b1e2
Fix in generate_inputs for Proposal-4 (#12462) 2022-11-25 05:45:25 +03:00
Anastasia Kuporosova
822e069a3e
One more tbb path in setupvars.bat (#14228) 2022-11-25 04:25:41 +04:00
Egor Duplenskii
7f27cd57eb
[CPU] Fix ports configuration for bf16 RNN primitives (#14111) 2022-11-24 19:13:22 +04:00
Denis Kotov
b53a5c3aff
Added BenchmarkLayerTest class for simplifing of benchmarking (#12552) 
* Added BenchmarkLayerTest class for simplifing of benchmarking

* Added example of using BenchmarkLayerTest for GenerateProposals operator

* Added report to file and also updated validate methods

* Switch from using json to xml for BenchmarkLayerTestReporter

* Remove smoke prefix from BenchmarkLayerTest usage example

Co-authored-by: Oleh Kurachenko <oleh.kurachenko@capgemini.com>
Co-authored-by: Irina Efode <irina.efode@intel.com>
 2022-11-24 17:20:51 +03:00
Irina Efode
6aea7540b4
[CONFORMANCE] Update Conformance ReadMe according new features (#14043) 
* [CONFORMANCE] Update Conformance ReadMe according new features

* fix some mistakes

* Update README.md

* ff

* Apply tsavina comments

* lost changes

* d

* fix comments. part 2

* fix args

* dd
 2022-11-24 16:35:19 +03:00
Alexandra Sidorova
d6750f8e74
[CPU] Fixed dynamic Loop with explicit Concat Result (#14041) 2022-11-24 16:47:08 +04:00
Sergey Shlyapnikov
06cfa2abc4
[GPU] Support of surface input reordering to buffer (#13223) 
* [GPU] Add surface input reordering

* [GPU] Add batched nv12->bfyx conversion reorder fusion
 2022-11-24 16:20:38 +04:00
Katarzyna Mitrus
87ad175b69
[Transformation] Fix ConvertBroadcast-3 transformation for boolean input (#14085) 
* Tests with boolean type for ConvertBroadcast3 transformation

* Extend support of bool input in ConvertBroadcast3 transformation

* New tests redundant ngraph namespace cleanup
 2022-11-24 12:57:58 +01:00
Roman Kazantsev
e082d183b1
[Core] Fix Pad shape inference for Edge and Reflect modes (#14185) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-11-24 14:54:51 +03:00
Irina Efode
fa76c1df10
[CONFORMANCE] Fix OpImplCheck inheritance (#14167) 
* [CONFORMANCE] Fix OpImplCheck inheritance

* fix parameters
 2022-11-24 14:49:45 +03:00
Evgenya Stepyreva
1b038c58dc
[ScatterUpdate] Partial Value Evaluation (#14055) 2022-11-24 11:43:43 +00:00
Marcin Kusmierski
358cb9241c
[GNA][FIX] Add verification if custom scale factor can be applied (#14092) 
* Added checking if imported model version is <= 2.7. Only in such case
    custom scale factor will be applied, otherwise there will be only logged
    warning message
* Added unit tests for validation of scale factor
 2022-11-24 11:33:02 +00:00
Katarzyna Mitrus
166f2e6513
[Unique-10] Reference implementation fixes (#14160) 
* Add more tests for Unique op reference impl

* Use stable sort to preserve elements order

* Update tensor comparator and unify approach for sorted

* Slices comparator revert and test

* Fix slices_ascending_order comparator
 2022-11-24 11:03:52 +01:00
Oleg Pipikin
7c8e93f6d2
Move inference test from ieFuncTests and ieUnitTests. Fix warnings (#14017) 
* Move inference test from ieFuncTests and ieUnitTests

* Enable tests in Azure CI
 2022-11-24 14:02:10 +04:00
Anastasiia Pnevskaia
8f17bd6f21
copy() and deepcopy() tests for PartialShape. (#14190) 
* Added tests of copy() and deepcopy() for PartialShape.

* Code reformat.
 2022-11-24 13:28:20 +04:00
Tingqian Li
b7d4deb2d8
enable jit debug_trace() only when non-zero ONEDNN_JIT_DUMP is exported (#14058) 2022-11-24 13:11:08 +04:00
Ilya Churaev
005f8ca497
Fixed documentation build (#14208) 2022-11-24 12:41:37 +04:00
Zlobin Vladimir
e038902585
benchmark_app: remove -progress (#14127) 
* benchmark_app: remove -progress

Tickets 80781 and 80903

* tools/benchmark_tool/requirements.txt: remove py-cpuinfo and progress
 2022-11-24 10:50:07 +04:00
Sergey Shlyapnikov
d464d079b2
[GPU] Add blocking option for cldnn::memory::copy_*() functions (#14012) 2022-11-24 10:37:11 +04:00
Roman Kazantsev
cc219d085e
[TF FE] Optimize and correct FusedBatchNorm translator - avoid Transposes (#14135) 
* [TF FE] Optimize FusedBatchNorm translator - avoid Transposes

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

* Fix FusedBatchNorm: correct compute for batch_mean and batch_variance

* Add layer tests and fix based on them

* Mark failing test cases and bind to issue tickets

* Work around tests for FusedBatchNorm in inference mode

* Use separate fictitious constants for reserved outputs

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-11-24 02:49:29 +03:00
Pawel Raasz
a0a6e1c141
Review opset1 equal for shape inference aspects (#14006) 
* Review equal shape inference:
- check dimension propagation
- check labels propagation
- check default ctor

* Review equal static shape inference
- add unit test for static shapes

* Correct typo in the variadic split method

* Remove leftovers and fix typos

Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>

Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
 2022-11-24 01:15:58 +03:00
Katarzyna Mitrus
2817d58b90
Remove braces around scalar initializer (#14191) 2022-11-23 22:01:51 +04:00
Pavel Esir
ad7fc2e846
fix out of bound indices of Gather reference (#14131) 
* bugfix for out of bound indices of Gather

* updated comment
 2022-11-23 18:27:44 +03:00
Vitaliy Urusovskij
57e630bd8f
Filter out samples tests on GNA for Debian (#14195) 
Since GNA isn't a part of Debian package, no need to run tests on it
 2022-11-23 19:20:26 +04:00
Anastasiia Pnevskaia
de7e59b4a2
Added telemetry initialization before running main subprocess. (#14155) 2022-11-23 16:30:04 +04:00
Marcin Kusmierski
3f1f798911
[FIX][OV]GNA]Fix GNA plugin crashes when running conformance tests (#13988) 
* [GNA] added dims size validation to avoid segfault in orientation helper
* [GNA] fixed matmul transformation test to not access data from empty container
* [OV] fixed padd Tile to TileIE and added assertion to ngraph to CNN conversion.
 2022-11-23 11:15:47 +01:00
Irina Efode
2bd2d266f1
[CONFROMANCE] Fix OV Path in new conformance runner (#14129) 
* [CONFROMANCE] Fix OV Path in new conformance runner

* filelist

* dd

* try

* one

* Update run_conformance.py

* sss

* revert extra

* f

* Update run_conformance.py
 2022-11-23 13:24:22 +04:00
Zlobin Vladimir
8d5df45d9f
benchmark_app: reuse shapes string representation (#13783) 2022-11-23 13:19:26 +04:00