Commit Graph

7989 Commits

Author SHA1 Message Date
Tomasz Jankowski
d5bba1a12a
[ONNX FE] Rename OV ONNX FE tests target (#12860)
* Rename ONNX FE Test

* Join source list

* Rename clang target
2022-09-05 15:44:49 +03:00
Irina Efode
a0e4870218
Remove extra files from the repo (#12800) 2022-09-05 14:55:07 +03:00
Denis Orlov
fc7bcaded5
[GNA] Update docs - GRUCell, LSTMSequence and GRUSequence are now supported (#11460) 2022-09-05 10:57:45 +01:00
Ilya Lavrenov
fb1faf8b2d
Generate openvino.pc pkg-config file (#12779)
* Generate openvino.pc pkg-config file

* Added libva-dev as a dependency

* Fixed typo in install_build_dependencies.sh

* samples on CI

* Revert changes in samples; use pkg-config in tests

* Debug print

* Revert changes in fuzz tests

* Fixed TBB usage

* Fixed pkg-config usage for cross-compilation

* Fixed pkg_config_tbb_lib_dir

* Don't use PKG_CONFIG_EXECUTABLE unconditionally

* Fixed copy-patse

* Fixe

* Generate pkg-config file for Apple as well

* Fixes for ubuntu 22.04

* Disable apple
2022-09-05 13:40:21 +04:00
Luo Cheng
89fa308809
[CPU] Fix fakequant injector: mix sse/avx regression in spr (#12802) 2022-09-05 13:39:32 +04:00
Ilya Lavrenov
32ecbb45b9
Enabled LTO for ONNX (#12889) 2022-09-05 13:19:19 +04:00
Maxim Vafin
4757e110e3
Fix issue with Squeeze with empty squeeze_dims (#12700) (#12762)
* Fix issue with Squeeze with empty squeeze_dims

* Rework solution

* Apply code style

* Improve error logging

* Improve formatting

* Add more types

* Apply review feedback

* Add file which was forgotten
2022-09-05 12:52:40 +04:00
Roman Kazantsev
666d53e909
[TF FE] Add loaders: EuclidianNorm, Erf, Bucketize, BroadcastTo, BroadcastArgs, Einsum, Mish (#12882)
* [TF FE] Add loaders: EuclidianNorm, Erf, Bucketize, BroadcastTo, BroadcastArgs

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

* Fix a name for translate_broadcast_args_op

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

* Add loaders for Einsum and Mish

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-09-05 12:51:20 +04:00
Adrian Boguszewski
27c1c6a3d1
[PyOV] Added deprecation function (#12540) 2022-09-05 10:26:37 +02:00
Ilya Lavrenov
836765874e
LTO for frontends and python (#12890) 2022-09-05 08:10:11 +04:00
hyunback kim
57a9d7ce7b
[GPU] Update oneDNNv2.7pc2 submodule. (#12853)
Apply fixed onednn for functional issue.

Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-09-05 10:57:49 +09:00
Ilya Lavrenov
7d7c30dd49
Fixed Android ARM64 post-commit step (#12885) 2022-09-03 14:34:02 +04:00
Ilya Lavrenov
d950d75239
Removed openvino::core linkage (#12883) 2022-09-03 10:50:13 +04:00
Ilya Lavrenov
fb8423dcee
Apple "cross compilation" for protoc (#12881) 2022-09-03 10:50:01 +04:00
Evgenya Stepyreva
ac6e180bdd
WA for Benchmark App: Remote tensor use for internaly dynamic model (#12858)
* WA for Benchmark App: Remote tensor use for internaly dynamic original models (NMS) that turn static due to transformation to legacy op and lack of dynamism support

* Style
2022-09-02 20:14:33 +03:00
Ilya Lavrenov
0ad91f040c
Removed unused files (#12872) 2022-09-02 20:38:59 +04:00
Ilya Lavrenov
142cfd173a
Added python suffix to cython-based libraries (#12862)
* Fixed dependencies in case of debian package building

* Removed duplication of cython-based libraries in wheel

* Fixed that TBB is not part of the wheel

* Fixes for yocto
2022-09-02 19:33:21 +04:00
Roman Kazantsev
e2e01bff32
[TF FE] Implement a loader for ListDiff operation (#12868)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-09-02 17:35:54 +04:00
Ilya Lavrenov
1d3e63c40e
Tuned TBB cmake finding (#12852)
* Tuned TBB cmake finding

* Fixed for cmake less 3.24

* Fixes for Android ARM

* Fixed Android build
2022-09-02 10:25:23 +04:00
Ilya Lavrenov
230ae977dc
Replaced hardcoded core component with variable name (#12850) 2022-09-02 10:13:05 +04:00
Ilya Lavrenov
dbae8e0c72
Fixed conformance tests compilation with older gflags version (#12866) 2022-09-02 09:47:06 +04:00
Vladimir Paramuzov
9590a77025
[GPU] Fixed conflicts in fc unit tests (#12857) 2022-09-02 08:16:44 +03:00
Denis Kotov
7a4d463d4d
Renamed CUDA device name to NVIDIA device name (#12719)
* Add NVIDIA device name along to CUDA device name (temporary solution)

* Disable nvidia_plugin along to cuda_plugin in .ci/azure/ (temporary solution)

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
2022-09-01 20:25:11 +04:00
Anastasia Popova
e0974b1e4c
Mo indices fix (#12842)
* Fixed error in indeces processing.

* Small correction

* Small correction
2022-09-01 17:03:09 +04:00
Thomas
885d57424c
Fix ENABLE_UNSAFE_LOCATIONS build flag (#8774)
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-09-01 14:46:49 +04:00
Ilya Lavrenov
e19df6f85f
Updated ia32 toolchain with system / processor (#12784)
* Updated ia32 toolchain with system / processor

* Allow pkg-config during cross-compilation

* added error message

* Search TBB using tbb.pc as well

* WA

* Fix for yocto

* Added print

* Use tbb.pc only when system libs are enabled

* Improved OpenVINOConfig.cmake

* Don't find pkg-config as required
2022-09-01 14:33:47 +04:00
Pawel Raasz
6c4cc81465
Add decomposition transformation for eye 9 (#12806)
* Add eye decomposition transformation

* Fix EyeLike generation when diagonal shift
outside dimensions

* Add batch shape to eye decomposition

* Eye decomposition clean-up

* Remove reference part if no eye decompose in
decomposition tests

* Eye-Like use eye operator

* Disable eye decomposition for CPU plugin

* Use opset9 instead of ops in eye decomposition

* Apply transformations header style
to eye_decomposition.hpp

* Add model reference in eye decomposition tests
- use opset9 instead of ov::op:vX namespace

* Refactor eye decomposition:
- match style of other transformations
- add NodeRegister class to make and collect created nodes
- use `NodeRegister` in transformation for copy runtime info
- use `NodeRegister` in `MatcherPass` to replace new `register_new_node`

* Fix CI LTO optimization issue for Ubuntu 20

* Move NodeRegister to dev API
To fix LTO issue for eye decomposition

* Change NodeRegister to NodeRegistry
2022-09-01 09:59:37 +02:00
Ilya Churaev
2e65ec233f
Use any config for plugins (#12792)
* Changed default config to ov::AnyMap

* Fixed template tests

* Added default implementation for set_properties

* Added copy map of string to any

* Fixed usage
2022-09-01 11:37:05 +04:00
Artur Kulikowski
4ac2ba9c81
Tile reference implementation short circuit (#12805)
* Tile reference impl short circuit

* Add test for Constant folding 2D shape and 0 repeats
2022-09-01 10:14:07 +03:00
Roman Kazantsev
c11151ae9e
[TF FE] Support MobileNetV2 with FakeQuantize by TF FE (#12851)
Avoid extra transposes in conversion of FakeQuantWithMinMaxVars and
add translator FakeQuantWithMinMaxVarsPerChannels.
It allows to convert MobileNetV2 with FakeQuantWithMinMaxVars and
FakeQuantWithMinMaxVarsPerChannels operations.

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

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-09-01 10:36:24 +04:00
Roman Kazantsev
3856d69ae1
[TF FE] Port changes from 2022.2 branch - Add Transpose Sinking for Prelu operation (#12848)
* [TF FE] Add Transpose Sinking for Prelu operation

Now it covers a case with a scalar slope.

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

* Add unit-tests for Transpose sinking of Prelu

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

* Fix non-scalar slope case

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

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-09-01 10:29:17 +04:00
Roman Baranchuk
4b104f0a13
[CPU] uni_planar_convolution optimization (#12659) 2022-09-01 09:50:32 +04:00
Roman Lyamin
c173f7e374
[GPU] fully_connected/gemm shape infer support (#12772) 2022-09-01 09:04:55 +04:00
Sergey Shlyapnikov
2fc59bf3d2
[GPU] GPU Plugin OVInferRequestIOTensorTest and SqueezeUnsqueezeLayerTest tests fixes (#12830) 2022-09-01 09:04:27 +04:00
PuQing
d7f119d8f2
【PaddlePaddle Hackathon 3】Add Paddle tile operator (#12277)
* add paddle op tile

* merge two test fun

* add i32 i64 utest and fix tile

* add high dim
2022-09-01 07:26:31 +04:00
Andrew Kwangwoong Park
7f665502b6
[GPU] Baseline InferRequest changes for dynamic shapes support (#12415) 2022-09-01 02:29:41 +03:00
Roman Kazantsev
c6d1d2aed1
[TF FE] Fix BatchToSpace translator (#12815) (#12834)
According to the specification we must have the same type for block_shape and crops inputs

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

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

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-08-31 18:17:29 +03:00
Jade Cho
d9d4b6d89b
[GPU] Fixed a bug of eltwise to support blocked layout when broadcast. (#12770)
+ Support bs_fs_yx_bsv32_fsv32 format
2022-08-31 23:02:08 +09:00
Vladimir Paramuzov
382028e9c2
[GPU] Dynamic FC unit test and several fixes (#12563) 2022-08-31 18:01:35 +04:00
Tomasz Jankowski
5a8f5b630b
[ONNX FE] Combine ONNX FrontEnd tests (#12680)
* Move onnx_tests target dir

* Move onnx_frontend_tests target dir

* Move standalone_build target dir

* Move onnxImporterUnitTests target dir

* Combine onnx edytor tests

* Remove excessive target

* Merge onnx tests into one binary

part 1 : onnxImporterUnitTests into onnx_tests

* Merge onnx tests into one binary

part 2 : onnx_frontend_tests into onnx_tests

* Fix code style

* Update CI files

* Move onnx model test files

* Rename onnx tests target

* Avoid plurarity in target name

Rationale: Letter s and the end tells about implementation and
structure, while the purpose is singular - to validate OpenVINO ONNX
Frontend.

* Avoid loosing manifest filter flag

Issue occurred when gtest_filter was provided from command line

* Remove conflicting dependency

Linking to gtest_main (from googletest) via commonTestUtils caused
conflict while choosing main() function. OV defined in gtest_main_manifest
is prefered here as consider manifest file along with CLI arguments.

* Use proper naming
2022-08-31 17:39:21 +04:00
Ilya Lavrenov
e34dfb7fe6
Ported changes related to versiong handling (#12841) 2022-08-31 17:38:57 +04:00
Chen Xu
1e6447c26a
[CPU] Reduce node improve performance for nspc layout (#12638) 2022-08-31 14:48:45 +04:00
Gorokhov Dmitriy
1f5c73014e
[DOC][CPU] Updated CPU suppported i/o precisions map (#12839) 2022-08-31 09:50:45 +00:00
Vladimir Paramuzov
5c11f09adc
[GPU] Remove duplicated precision conversion function (#12827) 2022-08-31 11:09:48 +04:00
Ilya Lavrenov
a6b455876b
Fixed frontend tests on OSX (#12836) 2022-08-31 10:56:13 +04:00
Roman Lyamin
93d82cde4a
[GPU] Squeeze/Unsqueeze shape infer support (#12724) 2022-08-31 09:38:39 +04:00
Oleksii Khovan
85549cb404
[GPU] Assign-3/ReadValue-3 for GPU plugin (#12828)
* Enable v3 ops for GPU plugin

* Add single-layer tests for v3 ops
2022-08-31 09:36:51 +04:00
Mateusz Tabaka
f83cc881e7
Explicitly link onednn with tbb for tbb version in [2018,2019.4] (#12789)
Ticket: 89800
2022-08-31 01:15:05 +04:00
Ilya Lavrenov
8a4cb9b332
Arm cross compilation (#12807)
* Fixed ARM out-of-box cross-compilation

* Improvements

* Fixed HDDL plugin
2022-08-30 22:23:14 +04:00
Ilya Lavrenov
675cce8325
Changed SOVERSION scheme (#12809)
* Changed SOVERSION scheme

* Simplified condition
2022-08-30 22:18:06 +04:00