Min, Byungil
338aad25db
[GPU] Resolve performance regression by selecting ref kernel ( #8550 )
...
- Not to select fsv16 for u8 to fp32 conv
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2021-11-12 16:39:47 +03:00
Alexey Varyzgin
1f597321de
[CPU][BF16] Concat layer properly handle mixed precision input ( #7715 )
2021-11-12 16:03:16 +03:00
Anastasia Kuporosova
2d27b73de9
[Python API] Integrate pyopenvino into wheel ( #8536 )
2021-11-12 13:34:57 +03:00
Ilya Churaev
7c33a0c609
Fixed clone_with_new_inputs for type_relaxed ops ( #8541 )
...
* Fixed clone_with_new_inputs for type_relaxed ops
* Fixed comment
2021-11-12 13:28:01 +03:00
Steve Yoo
7a7ea100ec
Migrate Movement 1 Operations (StridedSlice-1) ( #8221 )
...
* Migrate StridedSlice-1
* Update generate function to literals for bf16 and f16
* Add shapes to tensors
2021-11-12 12:19:19 +03:00
hyunback kim
e707338909
[GPU] Fix input memory calcuation in allocate_output. ( #8463 )
2021-11-12 12:07:06 +03:00
Ilya Churaev
471211bc4c
Fixed coverity issue ( #8529 )
2021-11-12 11:23:47 +03:00
Ivan Tikhonov
00c7da0f5f
[TF FE] Implement and refactor tensorflow layer tests ( #8051 )
...
* Revert submodule changes
* Fix build on Win
* Fix precommit: set correct shapes for broadcasting; disable check with ref for use_new_frontend mode
* fix precommit
* Fix precommits
* Temporary skip new tests on GPU with FP16
* Resolve review comments, trigger CI
* Resolve review comments
* Resolve review comments
2021-11-12 11:03:45 +03:00
Alexey Varyzgin
6ac18bbd1b
[CPU] Deconvolution fusing for 1x1 kernel and 2x2 stride ( #7958 )
2021-11-12 09:50:32 +03:00
Ilya Lavrenov
e57a455b92
Added support of external modules in static build ( #8518 )
...
* Added support of external modules in static build
* Enable template plugin static run; disabled CPU tests run in dynamic build
* Make FEM library dynamic
* Fixed static build
* clang-format
* Fixed targets
* Python tests fix
* Fixed python API tests skip
* Fixed pattern
* Fixed pattern 2
* Don't run template plugin tests in static build
2021-11-12 08:56:57 +03:00
Vladislav Golubev
0c3cee5e3b
[LPT] Security fixes ( #8436 )
2021-11-12 01:10:02 +03:00
Smirnov Grigorii
8f55d72c93
fixed bug with disabled tests in conv_fusion_test.cpp ( #8482 )
...
* remove /DISABLED_/ from conv_fusion_tests.cpp
* fixed? i changed some shapes in tests data
2021-11-12 00:51:44 +03:00
Edward Shogulin
8686100c80
[LPT] isAsymmetricOnWeights fix: small zero points ignoring ( #8429 )
2021-11-11 22:58:56 +03:00
Eugeny Volosenkov
f46e8bb3f8
Ngraph/fix serializer ( #8461 )
...
* Fix serializer
* Fix code style
* add test for bodies without parameters]
2021-11-11 22:06:19 +03:00
Ilya Lavrenov
894fe21995
Fixed typo in file name ( #8535 )
2021-11-11 14:50:43 +03:00
Victor Kuznetsov
6229e17ebe
switch searchpath for timeline report ( #8454 )
2021-11-11 14:49:28 +03:00
Tomasz Dołbniak
0e7eef3c88
ONNX MaxPool (opset 8+) ( #7100 )
2021-11-11 14:48:32 +03:00
Andrei Kochin
9d42aa22b6
MO: Update reminder message for master ( #8451 )
2021-11-11 14:15:45 +03:00
Ilya Churaev
0017ec71fd
Added hash to type_info ( #8175 )
...
* Added hash to type_info
* Fast hash
* Fixed tests
* Added new tests
* Fixed build
* Fix centos
* Fixed segfault
* Fixed test
* Fixed build
* Revert "Fix centos"
This reverts commit c739e923aa50aec37f956c22d7ecfa
2021-11-11 12:59:37 +03:00
Gleb Kazantaev
abc554513f
Enable SubractFusion and DivideFusion in MOC ( #7949 )
...
* Keep changes
* Enabled DivideFusion and ConvertDivideWithConstant in MOC
* Enable SubtractFusion in MOC; Remove eltwise fusion from MO
* Temporary disable fusions
* Temporary disable ConvertDivide folding
* Update ConvertDivide
* Update remove filtering boxes pass execution
2021-11-11 12:20:45 +03:00
Vladislav Golubev
869408075c
[LPT] Added method to insert dequantization and avoid dq propagation to the shapeOf subgraps ( #8214 )
2021-11-11 09:10:40 +00:00
Edward Shogulin
634e933c6d
[LPT] undefined precision for denormal values fix ( #8430 )
...
* [LPT] undefined precision for denormal values fix
* [LPT] FakeQuantize tests extending
2021-11-11 11:34:18 +03:00
Elizaveta Lobanova
73226b0b99
Clamp fusion transformation is updated to combine min and max operations to clamp ( #8467 )
...
* Clamp fusion transformation is updated to combine min and max operations to clamp
* Applying comments
2021-11-11 11:17:43 +03:00
Egor Shulman
a560ba58e6
[CPU] Math dynamic done ( #8290 )
2021-11-11 10:42:19 +03:00
Milana Shhanukova
700beb7d1f
[POT] Update add node name ( #8487 )
...
* Update node name to make ports visible
* proxy algo
* m
* mistype for add node name
* undo_utils
* Update utils.py
* Update algorithm.py
* undo
2021-11-11 10:35:00 +03:00
Egor Shulman
0343babacb
[CPU] ExperimentalDetectronROIFeatureExtractor dynamic done ( #8376 )
2021-11-11 10:28:28 +03:00
Pavel Esir
68badf5165
[MO] add IteratorGetNextCut ( #8040 )
...
* added IteratorGetNextCut, some improvements in graph.py
* added allowed types check
* reused new graph API for ports
* returned back old API 'out_nodes', removed soft-getting name from base class, changed run_after -> []
* correctly used new port API
* corrected IteratorGetNext message
2021-11-11 10:27:51 +03:00
Ilya Churaev
f1ca728ab1
Deprecated set_* methods in desctiption::Tensor ( #8510 )
...
* Deprecated set_* methods in desctiption::Tensor
* Fix code style
* Fixed tests
2021-11-11 09:52:59 +03:00
Ilya Lavrenov
461f746430
Install rules for static libraries case ( #8384 )
...
* Proper cmake install for static libraries case
* Added an ability to skip template plugin
* Added install rules for VPU / GPU
* Install more libraries
* Fixed absolute TBB include paths
* Disable GNA
* Fixed issue with linker
* Some fixes
* Fixed linkage issues in tests
* Disabled some tests
* Updated CI pipelines
* Fixed Windows linkage
* Fixed custom_opset test for static casr
* Fixed CVS-70313
* Continue on error
* Fixed clanf-format
* Try to fix Windows linker
* Fixed compilation
* Disable samples
* Fixed samples build with THREADING=SEQ
* Fixed link error on Windows
* Fixed ieFuncTests
* Added static Azure CI
* Revert "Fixed link error on Windows"
This reverts commit 78cca36fd2
2021-11-10 18:25:51 +03:00
Ilya Znamenskiy
91da09b1e5
[GPU] OneDNN gpu submodule update to version 2.5 ( #8449 )
...
* [GPU] OneDNN gpu submodule update to version 2.5
* [GPU] Updated onednn submodule and added layout optimizer fix
2021-11-10 17:58:11 +03:00
Artur Kulikowski
ba8f9d613e
Remove opset8 from compatibility ngraph python API ( #8452 )
2021-11-10 15:47:12 +01:00
Dmitry Pigasin
331372e7ff
[IE Sample Scripts] Use cmake to build samples ( #8442 )
...
* Use cmake to build samples
* Add the option to set custom build output folder
2021-11-10 17:31:28 +03:00
Victor Kuznetsov
852dd93803
Refactor work with env variables ( #8208 )
...
* del MO_ROOT
* del MO_ROOT from common_utils.py
* add MO_PATH to common_utils.py
* change mo_path
2021-11-10 16:59:58 +03:00
Tomasz Jankowski
cfdc4c1f3d
Avoid redundant graph nodes scans ( #8415 )
2021-11-10 14:50:58 +01:00
Ilya Churaev
54c384db11
Updated common migration pipeline ( #8176 )
...
* Updated common migration pipeline
* Fixed merge issue
* Added new model and extended example
* Fixed typo
* Added v10-v11 comparison
2021-11-10 16:27:23 +03:00
Victor Kuznetsov
9fc64ea726
add performance hint to time infer ( #8480 )
2021-11-10 16:07:08 +03:00
Wilson Seok
35ba404bcb
Migrate ngraph backend test/prior box ( #8227 )
...
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now
* update repo
* add op reference test of prior_box/prior_box_clustered/reorg_yolo and remove ngraph backend test
* remove related backend test file
2021-11-10 15:28:41 +03:00
Indira Salyahova
a788dc31e2
fix: delete fq if node precision bool ( #8336 )
2021-11-10 15:27:45 +03:00
Tagir Rakipov
ac0582c2d9
[POT] get_num_levels function ( #8393 )
...
* added function for calculating the number of discret levels in the input tensors and tests for this function
* added function for calculating the number of discret levels in the input tensors and tests for this function
* fixed pylint issues
* changed the function for delta estimation from mean to min
* added empty delta array processing in get_num_levels func and tests for it
2021-11-10 15:27:09 +03:00
Indira Salyahova
dd5efdca85
style(telemetry): change telemetry constructor ( #8428 )
2021-11-10 15:26:02 +03:00
Egor Shulman
f76d969bcb
[CPU] LogSoftMax dynamic done ( #8254 )
2021-11-10 15:07:56 +03:00
Vladislav Golubev
07d5ac167b
[CPU] CumSum: dynamic shapes support ( #8409 )
2021-11-10 14:54:59 +03:00
Andrey Noskov
f5767df023
[GNA] Added mode for Split and concat tests ( #7773 )
...
* added gna_mode to existing tests
* removed from tests_deprecated
* Commit for CI restart
2021-11-10 14:45:14 +03:00
Andrey Noskov
123efe2ecc
added gna_sw_fp32 mode for eltwise tests ( #7774 )
2021-11-10 14:44:23 +03:00
Andrey Sapozhnikov
286fefb956
[GNA] ActivationLayer tests enabled ( #7920 )
...
* [GNA] ActivationLayer tests in integer precision enabled
* Enabling some FP32 and FP16 ActivationLayerTests | Limiting Sign activation input values
* Refactoring activation tests
2021-11-10 14:20:43 +03:00
Tomasz Dołbniak
aa5a220ea0
Pad reference implementation fix so that it doesn't segfault the ONNX tests runner ( #8483 )
2021-11-10 14:02:15 +03:00
Andrey Noskov
e7b28e83ac
Added Import/Export functions to C_API ( #8353 )
...
* initial commit
* [GNA] added export/import for c_api (need fixes)
* [GNA] import/export with file
* [GNA] fixed tests and function with memory
* deleted unnecessary testing changes
* fixed bug with const
* fixed review comments
* [GNA] changed testing model
* Put memory buffer to istream directly
* Replaced blob with array of bytes
* Make config optional
* Reverted load_network change
* Fixed tests with null parameters
* Changed path to models
* Made config optional for other methods
* Update ie_c_api.h
* Deleted core param from export
* Changed export signature
* Reverted import changes(not needed)
* fixed test
Co-authored-by: mryzhov <mikhail.ryzhov@intel.com>
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
2021-11-10 13:45:24 +03:00
Mingyu Kim
9b52f64445
benchmark_app bugfix for filling input ( #8433 )
...
Benchmark_app created mismatching buffer because of transposition of
width/height. Input was not fed into network in case of non-square form.
2021-11-10 13:19:31 +03:00
Ilya Churaev
6a89eb2844
Change frontends namespace to ov ( #8434 )
...
* Changed namespace from ngraph to ov for OV Frontends
* Fixed python
* Fixed ONNX Editor for windows
* Try to fix centos
* Fixed code style
* Revert frontend loader
2021-11-10 12:48:37 +03:00
Anton Chetverikov
c8e1c8e3eb
[MO|nGraph]GatherND_8 ( #7743 )
...
* Add GatherND_8 operation
* Update shape infer function and tests
* Initial commit for nGraph GatherND_8 operation
* Add GatherNDBase class implementation
* Fix base class errors
* Add missrd header
* Update base class
* Update GatherND_8 implementation
* Fix codestyle
* Fix wrong rank
* Implement tests for gatherND_8 shape inference function
* fix codestyle
* Add limitation to doc
* Siplyfy check in shape inference
* Add more test cases
* Update shape inference function
* Add more test cases to cover all case with dynamic input shapes
* Update shape inference function
* Refactor tests
* Add visitor tests for gatherND_8 operation
* Correct comment
* Add additional check is shape inference function
* Update shape inference implementation for gathernd operartion
* Fix codestyle
* Remove restriction for data is fully defined
* Update shape inference functon
* Fix missed check for nonetype
* Remove redundant checks for batch_dims
* Fix codestyle
2021-11-10 11:54:52 +03:00
