IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
13,503 Commits 38 Branches 54 Tags 1.1 GiB
2c6a2a1102
Commit Graph

13503 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Fang Xu
4aa6899b07
update linux oneTBB with version 2021.2.4 (#20675) 2023-10-26 13:14:43 +04:00
Mikhail Ryzhov
4078bd9c19
[GHA] Speed up PyTorch Layer unit tests (#20613) 
* test

* fixed tests

* typo

* fixed tests

* rest of the tests

* fixed rsub test

* tmp fix

* Revert "tmp fix"

This reverts commit b8bf1e9492e13497895da488612c9a137ef840bc.

* fixed test params

* reset thirdparty/pugixml

* Revert "fixed rsub test"

This reverts commit 9b6be34b8666936e8124b6622fcc5185b640de92.

* fixed typo

* fixed test data

* reset test_rsub

* removed unused param

* reverrted runner

* simplified call

* fixed random

* changed logical to auto mode

* Revert "fixed random"

This reverts commit 8a4f20b24641144f823a7e1f1ff92038634acf32.

* fixed test_all

* replaced random_sample with randn

* fixed rebase issue

* reverted logical splitting

* Update tests/layer_tests/pytorch_tests/test_repeat_interleave.py

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

* Update tests/layer_tests/pytorch_tests/test_all.py

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

* Apply suggestions from code review

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

* fixed merge conflict

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
 2023-10-26 13:10:51 +04:00
cecilia peng
3a67d2a722
[CPU] Fix mergeTransposeAndReorder when Transpose and Reorder do oppos… (#20537) 
* [CPU]fix mergeTransposeAndReorder when Transpose and Reorder do opposite permutation to each other as expected, but isOptimized is false due to some reason like inPlace memory. The permuation is asked because the dnnl  reorder primitive requires the source and destination tensors to have the same shape.

* add unit test

* Update src/plugins/intel_cpu/src/graph_optimizer.cpp

Co-authored-by: Maksim Kutakov <maxim.kutakov@gmail.com>

* simplify unit test

* update comments

---------

Co-authored-by: Maksim Kutakov <maxim.kutakov@gmail.com>
 2023-10-26 10:41:34 +02:00
Vitaliy Urusovskij
d532d14540
Range, RDFT, RandormUniform, ReduceOps layer tests to API2.0 (#20692) 
* `Range` to API2.0

* `RDFTLayerTest` to API2.0

* `RandomUniformLayerTest` to API2.0

* `ReduceOpsLayerTest` to API2.0
 2023-10-26 11:07:23 +04:00
Tomasz Jankowski
301ea0beb0
[core] Migrate SpaceToDepth operator to new API (#20530) 
* Drop HostTensor and move to ov namespace

* Drop HostTensor

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-26 08:35:38 +02:00
Sun Xiaoxia
b9c64370fb
Fix memory leak on windows (#20590) 2023-10-26 09:42:50 +04:00
Vladimir Paramuzov
d9c4ca3021
[GPU] Allow setting remote output for dynamic model (#20608) 2023-10-26 09:09:54 +04:00
Gorokhov Dmitriy
63299ec217
[CPU] FullyConnected acceleration with 4bit weights decompression (#20607) 2023-10-26 01:08:07 +04:00
Mikhail Ryzhov
00e2381d04
[GHA] Jobs timeouts (#20601) 
* set linux timeouts

* set win timeouts

* other timeouts

* reverted pugixml

* fixed conformance timeout

* reset omz
 2023-10-26 00:39:31 +04:00
Mikhail Ryzhov
49c5099f5e
[GHA] Removed dependency on git repo in python tests (#20390) 
* Removed repo deps in py tests

* fixed typo

* changed test cmd

* add test_utils to pythonpath

* set test_utils to LD_LIBRARY_PATH

* changed path

* changed path

* source python site-packages

* fixed LD_LIBRARY_PATH

* print pip dir

* changed python install path

* source all openvino dir

* isolate test_utils

* system deps

* reordered deps

* dep conflict

* tests reorder

* changed test_utils path

* cpack test dir

* rebase fix

* fixed env

* frontend tests fix

* removed already installed reqs

* debug

* debug 2

* added python action path

* test

* reset 3rdparties

* set pip install path globally

* reset 3rdparties

* removed parallel code

* moved doc snippets

* switched back 4-core runner

* removed global unused vars

* removed unused requirements.txt

* removed unused requirements

* test

* Revert "test"

This reverts commit bdf22d22fd6ec5d488930bc362bdb0741c5bea76.
 2023-10-25 20:16:01 +00:00
Andrey Kashchikhin
214e08599b
[CI] [GHA] Switch Windows pipeline to dynamic build and to VS 2019 (#20630) 
* build dynamic in win main; transfer win main to MSVC 2019; use toolchain for win cc

* Update windows_conditional_compilation.yml

use cmake toolchain globally in build stage

* Update windows_conditional_compilation.yml

* Update windows_conditional_compilation.yml

* use quotes

* try w/o protobuf

* do not restore cache

* return

* revert

* add missing shell

* skip Template OpImpl tests

* skip OV C API tests

* rm pr trigger

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
 2023-10-25 22:36:25 +04:00
Irina Efode
e4f4714fca
[CONFORMANCE] Prepare model filelist for SubgraphsDumper (#20617) 
* [CONFORMANCE] Prepare model filelist for SubgraphsDumper

* Improve default and custom scenario

* Update constants.py

* remove extra file

* improveemnt
 2023-10-25 21:52:45 +04:00
Ilya Lavrenov
0d68bb3c14
OpenVINO library expose requirement for C++11 (#20691) 2023-10-25 15:07:48 +00:00
Katarzyna Mitrus
daa2c9ded0
[MO][Opset13] NMSRotated-13 support in MO IR Reader (#20354) 
* nms_rotated mo ir read init

* Fix type infer and clean up

* Update tests

* Update tests

* update package BOM file

* Update type_infer

* Avoid files collision in tests

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-25 12:04:17 +00:00
Siddhant Chauhan
bc463e886b
[PT FE] Add aten::log10 (#20621) 
* Add log10 operator and test

* fix

* Update test_log.py

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
 2023-10-25 14:14:22 +04:00
Vitaliy Urusovskij
04c766e9f1
ReverseSequence, RNNCell, Reverse to API2.0 (#20569) 
* `ReverseSequence` to API2.0

* `RNNCell` to API2.0

* `Reverse` GPU test to API2.0

* Alignment fix
 2023-10-25 09:37:36 +00:00
Evgenya Nugmanova
f2b26962fa
De-Reshape MatMul (#20396) 
* De-Reshape MatMul

* Fixed includes

* Comments resolved

* Style

* comment adressed
 2023-10-25 09:04:04 +00:00
( Nechiforel David-Samuel ) NsdHSO
68538b2b3f
docs 📝 : add the take issue workflow [19006] (#19027) 
* docs 📝 : add the take issue workflow

* chore: add the latest tag from action

Co-authored-by: Przemyslaw Wysocki <przemyslaw.wysocki@intel.com>

* Update .github/workflows/triage.yml

Co-authored-by: Przemyslaw Wysocki <przemyslaw.wysocki@intel.com>

* docs(readme): more descriptive message

Co-authored-by: Przemyslaw Wysocki <przemyslaw.wysocki@intel.com>

* docs(triage): more descriptive message in action

Co-authored-by: Przemyslaw Wysocki <przemyslaw.wysocki@intel.com>

* chore: .github/workflows/triage.yml

Co-authored-by: Andrey Kashchikhin <andrey.kashchikhin@intel.com>

* chore:🌻 rename the file and add new secret

---------

Co-authored-by: Przemyslaw Wysocki <przemyslaw.wysocki@intel.com>
Co-authored-by: Andrey Kashchikhin <andrey.kashchikhin@intel.com>
 2023-10-25 12:50:53 +04:00
Fang Xu
361011c75e
fix coverity scan issue (#20678) 2023-10-25 12:48:43 +04:00
Vladimir Paramuzov
307176e5c6
[GPU] Fixed surfaces shape in create_tensor_nv12 helpers (#20539) 2023-10-25 12:46:47 +04:00
Vladimir Paramuzov
3313d1ce7a
[GPU] FC with 4-bit weights compression support for iGPU (#20572) 2023-10-25 12:45:31 +04:00
Pawel Raasz
b3eb2810d7
[core]Migrate Negative operator to new API (#20609) 
* Migrate Negative operator to new API

* Remove `visit_attributes` is same as base

* Use std::negate instead of lambda

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-25 10:39:50 +02:00
Irina Efode
d138dd2f08
[CONFORMANCE][SUBGRAPHS DUMPER] Fix issue connected with fused_names extractor (#20522) 
* [CONFORMANCE][SUBGRAPHS DUMPER] Fix issue connected with  extractor

* fix build
 2023-10-25 12:37:04 +04:00
Pawel Raasz
e1a33f10d5
[core]Migrate Slice to new API (#20417) 
* Migrate slice to new API

* Remove visit_attributes, is same as base class

* Move shape checks to shape_infer
- minor refactor Slice op

* Move `get_tensors_partial_shapes` to dev API

* Correct comment

Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>

---------

Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
 2023-10-25 08:19:14 +00:00
Evgenya Nugmanova
7874adb58e
[Symbolic SI] Refactor Table of Equivalence (#20627) 2023-10-25 09:54:47 +02:00
Nikolay Shchegolev
dc4240bc61
[CPU] Removed custom ShapeInference impl for RandomUniform (#20599) 2023-10-25 09:15:03 +02:00
Maciej Smyk
706d657637
[DOCS] Install Guide Update for master (#20677) 
* missing info

* System Requirements

* Update installing-openvino-from-archive-macos.md

* system requirements update
 2023-10-25 09:12:41 +02:00
Wilson Seok
c70f0ca45d
[GPU] skip excessive mem alloc request in build (#20399) 
* skip excessive mem alloc request in build

* update mem check function

* fix os behavior

* update mem size check location

* only dynamic shape case takes check_allocatable

* update check condition
 2023-10-25 09:09:11 +02:00
Wilson Seok
9d56c31581
[GPU] add shape infer in scatter elements update (#20250) 
* add shape infer in scatter elements update

* output shape is same with input shape in dynamic case
 2023-10-25 09:01:52 +02:00
Vitaliy Urusovskij
a71283ea94
RNNSequence, Result, Reshape, ReorgYolo, RegionYolo layer tests to API2.0 (#20644) 
* `RNNSequenceTest` to API2.0

* `Result` to API2.0

* `Reshape` to API2.0

* `ReorgYolo` to API2.0

* `RegionYolo` to API2.0

* Alignment fixes

* Skip more `RNNSequenceTest` cases
 2023-10-25 08:16:28 +02:00
Maxim Vafin
46f46c6cc6
[PT FE] Fix xmod model test (#20682) 2023-10-25 08:00:34 +02:00
Oleg Pipikin
30260e3c7c
Refaсtor ActivationLayerTest (#20180) 
* Refator ActivationLayerTest
 2023-10-25 09:37:29 +04:00
Tomasz Jankowski
973b194776
[core] Migrate DepthToSpace operator to new API (#20515) 
* Move into ov namespace

* Use ov::Tensor in place of HostTensor

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-25 07:10:54 +02:00
Pawel Raasz
84732515b4
Fix check repeats in values in Tile (#20654) 
- no action if any of repeats is zero

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-25 07:27:21 +04:00
Eddy Kim
6fa4f9fd78
[GPU] fixed to create Graphs with different stream_ids (#20626) 
* fixed to create Graphs with different stream_ids

* added num_streams config for auto batch test
 2023-10-24 20:26:36 -07:00
Pawel Raasz
5fee2ef67e
Migrate LessEqual and GreaterEqual to new API (#20645) 
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-25 07:26:31 +04:00
Pawel Raasz
2b65855793
[core]Migrate Less and Greater operators to new API (#20628) 
* Migrate Less operator to new API

* Migrate Greater operator to new API
- use less implementation in greater to reduce bin size

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-25 07:25:05 +04:00
Andrey Babushkin
ee6263a141
[workflows/linux] Switch to sccache and Azure Blob Storage (#20484) 
* [workflows/linux] Switch to sccache and Azure Blob Storage

* Install curl

* Remove --show-config

* Add sccache to other Linux workflows

* sccache to  Android, curl to riscv and CC

* Use sccache action instead of manual install

* Oops, missed sccache manual installation in two places

* Use env vars instead of hardcoded CMAKE_C(XX)_COMPILER_LAUNCHER

* Forgot one more stage in Linux CC pipeline

* Temporarily disable Blob Storage for RISC-V

For some reason sccache has no effect on build time and show 0 hits
and 0 compilation requests despite being in CMake calls

* forgot to add sccache installation to Linux CC

* Revert "Temporarily disable Blob Storage for RISC-V"

This reverts commit b528f41dad583a38b9ef93121e38044b9dccb71b.

* Missing container option for CC build

* Remove curl installation

* Remove CCACHE* variables which have no effect on sccache

* Revert sccache changes for Linux RISC-V workflow
 2023-10-24 20:52:56 +01:00
Oleksii Khovan
984e4dbf35
[GPU] NMSRotated-13 (#20411) 
* Add Rotation support to primitive and kernel

* Add unit tests

* Add transformation for NMSRotated

* add single-layer tests

* Fix: angle value for the same box may have its sign changed several times passing through iterations of batch and class loops.

* fix review comments
 2023-10-24 21:36:02 +02:00
Siddhant Chauhan
eb55360f10
[ONNX] Extend ONNX Frontend with BlackmanWindow, HammingWindow and HannWindow operators (#19428) 
* ONNX BlackManWindow enabled

* added a test periodic

* Add the license statement

* ONNX HammingWindow, HannWindow enabled

also added basic tests for each

* minor tests added

* made reviewed changes

* made reviewed changes

used output_datatype directly, returned y_values directly

* fixed clang-format

* add OPENVINO_SUPPRESS_DEPRECATED_START

* include math.h

* float fix

* fix

* fix namespace to set_1

* test fixes

* fix cast to output_datatype

* fix, replace cast with ov::convert

* fix, use element::f32

* major fixes

* fixes

* Update onnx_import.in.cpp

* Update onnx_import.in.cpp

---------

Co-authored-by: Przemyslaw Wysocki <przemyslaw.wysocki@intel.com>
 2023-10-24 21:45:50 +04:00
Evgeny Kotov
22184c32f4
fix random layer names and count (#20323) 
* add sorting for fix sporadic failure in SharedOpOptimization shared_node_optimization

* fix Output and Input comparison

* remove unneed sorting from transformation

* add unit test

* code review fixes

* code review fixes

* code review fixes

* code review fixes

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
 2023-10-24 18:18:50 +02:00
Ilya Churaev
124f2bc5c9
Remove NF4 Convert from public API (#20666) 
* Remove NF4 Convert from public API

* Fixed build
 2023-10-24 19:19:16 +04:00
Ilya Lavrenov
337e225dbd
Removed linux.yml AZure pipeline (#20341) 2023-10-24 16:59:17 +02:00
Sergey Shlyapnikov
26cab79988
[GPU] Improve OOOQ synchronization between ShapeOf subgraph's CPU impls and GPU kernels (#20595) 
* [GPU] Add ITT counters for primitive inst

* [GPU] Improve OOOQ synchronization between ShapeOf subgraph's CPU impls and GPU kernels
 2023-10-24 18:49:41 +04:00
Andrei Gorbachev
20bd58759a
[GPU] Refactor grn, gru_cell, group_convolution, group_convolution_backprop_data, is_inf, log_softmax, logical, mat_mul, lrn, lstm_cell (#20520) 
* grn

* gru_cell

* group_convolution

* group_convolution_backprop_data

* is_inf

* log_softmax

* logical

* mat_mul

* lrn

* lstm_cell

* fix after review
 2023-10-24 18:48:29 +04:00
Aleksandr Voron
c6707aab86
[CPU] Add input type check into in-place condition (#20529) 2023-10-24 18:45:48 +04:00
Irina Efode
63fff9d270
[IE TESTS][CONFORMANCE] Move Calculate reference over TEMPLATE plugin instead of interpreter (#12532) 
* [CONFORMANCE] Enable template calculation reference

* Move convert init to cpu

* skip gpu
 2023-10-24 16:34:37 +02:00
Evgeny Kotov
251602636c
Fuse GeLU (#20428) 
* add transformation + test

* move transformation to GeluFusion

* add comments

* code review fixes

* fix

* code review fixes

* code style fix

* fix windows build warning
 2023-10-24 18:23:14 +04:00
Pawel Raasz
5ffde7d8d6
[core]Migrate Minimum operator to new API (#20597) 
* Migrate Minimum op to new API

* Refactor evaluates to reduce binary size
- add infer_broadcast_shape, get shapes from tensors reduce OV_ASSERT
- refactor Evaluate structures to reduce binary size

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-24 14:48:09 +02:00
Vitaliy Urusovskij
e977a6ed9b
Fix COPY_INSTEAD_OF_MOVE issue in Hetero (#20667) 2023-10-24 12:44:01 +00:00