Tomasz Dołbniak
2503183f35
OpenCV build switched off by default [master] ( #12173 )
...
* OpenCV build switched off by default
* Removal of OCV copy from the "install tests" stage
* Switch off OCV dependent tests
* cmake code repositioning
* More OCV-dependent tests disabled
* OCV removed entirely from the C-API tests
* Final cleanup
2022-08-13 13:17:55 +03:00
Ilya Lavrenov
2b69057603
Fixed CVS-89248 ( #12534 )
...
* Fixed CVS-89248
* Fixes for TBB 2018-2019.4
2022-08-13 00:11:13 +04:00
Anastasia Popova
595bdb71a7
Changed update date in MO message. ( #12396 )
...
* Changed update date.
* Changed update date.
* Year update.
2022-08-12 13:29:45 +00:00
Ilya Lavrenov
81e41f7c8e
Added vresion generation as in CI ( #12521 )
2022-08-12 15:43:09 +04:00
Ilya Lavrenov
af05733a3a
Failed plugins search from current directory w/o LD_LIBRARY_PATH ( #12499 )
2022-08-12 12:10:03 +04:00
Ilya Lavrenov
91c192f358
Migrated to xbyak v6.00 ( #9166 )
2022-08-12 11:38:34 +04:00
Ilya Lavrenov
6415fdc6cf
Install python libs for debian explicitly ( #12522 )
2022-08-12 11:37:45 +04:00
Ilya Lavrenov
8b9aea9fad
Fixed missed pugixml in case of system libs + wheel package ( #12464 )
...
* Fixed missed pugixml in case of system libs + wheel package
* Fixes
* Removed useless rpath
2022-08-12 11:35:56 +04:00
Ilya Lavrenov
e0b12009ea
Removed old headers from OV 2.0 API ( #12214 )
...
* Removed old headers from OV 2.0 API
* FIxed clang
* Fixed warning
* Updated OMZ submodule
* Fixed gpu tests build
2022-08-12 11:35:36 +04:00
Ilya Lavrenov
92ef155ed1
Debian packages tests on Azure ( #12469 )
...
* Squashed commit of the following:
commit 036a32290ed795326d51dd41d83b891248b0ac05
Merge: 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#10432 )"
This reverts commit 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
2022-08-12 00:07:21 +04:00
Roman Lyamin
73da7080a3
[GPU] Align StridedSlice parameters with ngraph ( #12414 )
2022-08-11 18:34:55 +04:00
Zhen Zhao (Fiona)
e521f3a7a1
Update to add climits for ULLONG_MAX ( #11958 )
...
Avoid GCC compiling issue ‘ULLONG_MAX’ was not declared in this scope
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
2022-08-11 17:00:48 +04:00
Artur Kulikowski
ab9319ba94
Fix: Refreshing of places after subgraph extraction ( #12494 )
2022-08-11 16:55:06 +04:00
Roman Kazantsev
f23fd569bc
[TF FE] Refactor MaxPool operation translator for xj_feature model ( #12485 )
...
* [TF FE] Refactor MaxPool operation translator for xj_feature model
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Correct MaxPoolV2 since it has three inputs
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-08-11 14:13:23 +03:00
Jan Iwaszkiewicz
4dc713c7eb
[SAMPLES] Fix flake issues in Python speech sample ( #12514 )
...
* Fix flake issues
* Add whitespace
* Add whitespaces in tests asserts
2022-08-11 15:00:27 +04:00
Eddy Kim
b9457b3a31
[GPU] Get rid program_node reference from all primitive_impl classes ( #12211 )
...
* removed references to program_node
* removed member variables in primitive_impl
* removed redundant variables
* removed whithspace at the end of line
* added ctor for updated primitive_impls
* changed init_kernels to require kernels_cache
* removed program_node ref from custom_primitive
* added set_node_params to update the lastest status of program_node
* removed const from get_kernel
2022-08-11 14:14:21 +04:00
Roman Lyamin
85e2229a80
[GPU] Align Tile parameters with ngraph ( #12345 )
2022-08-11 14:08:22 +04:00
Roman Lyamin
e98cdcf496
[GPU] Use int64_t type for axis in GatherElements ( #12317 )
2022-08-11 14:07:08 +04:00
Adrian Boguszewski
fe4e875586
Fixed NameError: name 'ARCH' is not defined on Raspberry Pi ( #12421 )
2022-08-11 13:15:23 +04:00
Jan Iwaszkiewicz
ed39903028
[PyOV] Fix error handling for Debug builds and extend configs for CI ( #12417 )
2022-08-11 10:53:54 +02:00
Mykhailo Hnap
175b00a346
Fixed DFTs documentations. ( #11762 )
2022-08-11 10:29:05 +02:00
Vladimir Paramuzov
5dc8d548e3
[GPU] Replace tensor with PartialShape in layout class. ( #12305 )
...
Refactored layouts comparison methods
2022-08-11 11:45:50 +04:00
Felix Dohyun Kim
48b7814871
[GPU] Pass activation unit tests on DG2 ( #12227 )
2022-08-11 14:32:44 +09:00
Luo Cheng
2c06c36366
[CPU] Default enable brgconv AVX512 ( #12406 )
2022-08-11 09:19:16 +04:00
Roman Baranchuk
3e648f2788
[CPU] NormalizeL2: uniform application of eps ( #12077 )
2022-08-11 06:11:00 +03:00
Tomasz Dołbniak
90463c1812
Undefined Behavior sanitizer fixes ( #12333 )
2022-08-10 22:35:56 +03:00
Vladimir Paramuzov
52b57fa860
[GPU] Use partial shape in some ops factories ( #12353 )
2022-08-10 19:51:55 +04:00
Artur Kulikowski
91ce7406ad
Remove unused private methods from LSTMSequence ( #12397 )
2022-08-10 14:18:04 +03:00
Mateusz Tabaka
c328db5aac
Set dontReverseIndices to Gather if its indices come from NMS v9 ( #12478 )
...
Ticket: 86909
2022-08-10 11:31:39 +02:00
Min, Byungil
6e4a8b0d2e
[GPU] Fix network loading time related to onednn engine creation ( #12375 )
...
+ Creation of onednn_engine in ocl_engine is changed to on-demand.
+ benchmark cache_dir option takes longer than cl_cache_dir env in loading network.
+ For clDNN execution, benchmark cache_dir created onednn_engine if just ONEDNN_ENABLE config is ON.
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-08-10 16:27:26 +09:00
Oleksandr Kramskyi
10ccf50ee0
[GPU] Add unit tests for activation functions for blocked layouts ( #11948 )
2022-08-10 16:18:29 +09:00
Roman Kazantsev
e2080cd8a4
[TF FE] Implement conversion for Attention OCR model ( #12428 )
...
* [TF FE] Implement conversion for Attention OCR model
The following scope of work is done to make Attention OCR convertable:
1. Refactored translators for BiasAdd, Slice, and ArgMax operations. Add translation for StopGradient operation.
2. The previous traversing algorithm to compute topological sorted nodes list was incorrect. Now it is implemented based on topologically_sorted function from core/graph_util.hpp.
3. The unsupported data types are now preliminary converted to undefined type for the purpose of to have them cut off.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Revert workaround for support of non-frozen models
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Correct third-party dependencies
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply feedback from code-review
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply code-review feedback from PR12444
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply the rest of comments from the code-review
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-08-10 09:06:26 +03:00
Mateusz Tabaka
277666cdc6
Revert "Disable fusings_gpu/deconv_scale_activation_quantize_i8_eltwise_quantize_u8.basic/4 ( #11777 )" ( #12400 )
...
This reverts commit 4650ecd0b5
2022-08-10 13:32:41 +09:00
yanlan song
a81eca55c5
refine auto config and enable default config values ( #12452 )
...
* initial draft
Signed-off-by: fishbell <bell.song@intel.com>
* enable tests
Signed-off-by: fishbell <bell.song@intel.com>
2022-08-10 11:13:34 +08:00
Ilya Lavrenov
92d28a6ea5
Fixed MINOR version ( #12475 )
...
Tested via product-config
2022-08-09 19:25:23 +04:00
Felix Dohyun Kim
ae1066a74c
[GPU] Fix perf regression of #12113 ( #12451 )
...
* Disable fs_b_yx_fsv32 fusing for onednn case too
2022-08-09 17:12:16 +09:00
Taylor Yeonbok Lee
751337d428
W/A for compilation issue ( #12346 )
...
Previously INPUT/OUTPUT_SIZES was declared as an unnamed array macro.
However current ocl compiler deals with the value obtained from such an array non-constant, so that it results in a side effect in compiler optimization.
Here, a workaround for this issue is applied, i.e., declare the INPUT_OUTPUT_SIZES as a __const array instead of jit constants.
2022-08-09 08:42:32 +03:00
Min, Byungil
f6a7d72a92
[GPU] resolve WA of using clDNN reduce ( #11823 )
...
+ Resolved layout mismatch of unreduced axes in creating onednn descriptor
+ Removed redundant reduce in ngraph
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-08-09 09:52:30 +09:00
Ilya Lavrenov
db41a71ea9
Trying to fix CVS-85530 ( #12455 )
2022-08-08 23:06:54 +03:00
Vladimir Paramuzov
3b5cc98b1c
[GPU] Replaced shared_ptr with const ref for impl_params ( #12399 )
2022-08-08 20:55:57 +03:00
Pawel Raasz
93dbffafd4
Add gtest_main_manifest target to avoid duplicates ( #12438 )
...
- Add gtest_main_manifest target as main application for google test using manifest file to ignore tests
- Use new target in frontends tests
2022-08-08 19:31:29 +02:00
Andrew Kwangwoong Park
b03e903621
[GPU] Disable TCs for OVClassHeteroExecutableNetworkGetMetricTest ( #12433 )
...
Signed-off-by: Andrew Park <andrew.park@intel.com>
2022-08-08 20:04:14 +04:00
Vladimir Paramuzov
2e92d33acc
[GPU] Added format::adjust method. Minor refactoring ( #12261 )
2022-08-08 16:21:41 +04:00
Bartek Szmelczynski
1b5a1309cd
[PyOV] Expose ConvertSequenceToTensorIterator transformation ( #12362 )
...
* check style CI
* remove space
* remove space
* expose ConvertSeqToTensorIterator transformation
* revert accidental changes
* fix namings
* revert adding transformation to MO
2022-08-08 13:34:28 +02:00
Ilya Lavrenov
6ca47b074d
Library versions & made tests relocatable ( #12416 )
...
* Fixes for cases when TBB_DIR env var is set
* Don't use make in build_samples.sh script
* First version of Windows installer
* WIndows NSIS installer
* Improved version of debian packages
* Improvements
* Improvements
* Debian packages now look good
* Library versioning
* Fixed tests to run against debian packages
* Fixed frontend tests
* Fixed code style
* FIxed Windows
* Fixed python tests
* Fixed paths in tests
* fdvfdv
* Fixes
* USe versioning only for debian packages
* Relocatable tests
* Fixed
* Fixed all tests
* Fixed clang-format
* Fixed more tests
* Fixed some tests
* Absolute paths in .ci
* Fixes
* Added support of OpenCV 3.4
* Trying to fix gnaUnitTests
2022-08-08 13:59:24 +04:00
Felix Dohyun Kim
b9126fe6ea
[GPU] Fix convolution unit test for onednn ( #12389 )
...
* no goiyx to bfyx convert when using onednn
2022-08-08 18:13:33 +09:00
Roman Kazantsev
76e78c3400
[TF FE] Refactor translators for Conv2d and Conv3d ( #12444 )
...
It allows to convert CNN-Transformer model. Padding was previously incorrect.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-08-08 12:29:31 +04:00
Artur Kulikowski
b3341defce
Method Node::constant_fold uses new evaluate method with TensorVector ( #12423 )
...
* Method Node::constant_fold uses new evaluate method with TensorVector
* Simplify conditions for creating tensor
* Add test for evaluate with TensorVector
* Add line at EOF
2022-08-08 11:22:55 +03:00
Ekaterina Aidova
c541208d43
[OMZ]: update submodule ( #12447 )
2022-08-08 11:04:36 +03:00
Krzysztof Czugala
ef00498385
[MO] Result edges naming issue ( #12154 )
...
* the first approach to fixing the Result edge naming issue
* more robust approach, not depending on the split
* out_nodes_ids type change
* missing if clause
2022-08-08 10:55:00 +04:00
