Ilya Sharikov
1a3d0adb3e
Change omz model ( #9551 )
2022-01-11 10:56:50 +03:00
Jade Cho
28e52a0475
[GPU] Fix a bug of logical padding of convolution ( #9518 )
...
* [GPU] Fix a bug of logical padding of convolution
+ Transforms logical padding with wrong axis.
* Fix a typo bug.
2022-01-11 10:37:27 +03:00
Ilya Churaev
e095a90cdf
Handle names collisions for old IR with new API ( #9388 )
...
* Handle names collisions for old IR with new API
* Fixed load model
* Try to fix tests
* Try to fix tests
* Try to fix build
* Try to fix tests
* Fixed tests
* Revert "Fixed tests"
This reverts commit 35da307210
2022-01-11 09:36:13 +03:00
Min, Byungil
e0485c1ad2
Add reshape in front of a fully connected node for using bf input ( #9449 )
...
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-01-11 13:18:40 +09:00
Fedor Zharinov
fc4185e92a
Compiled network loading is fixed ( #9547 )
...
* compiled network loading is fixed
* StyleFix
2022-01-10 23:37:46 +03:00
Vladimir Paramuzov
b4bd4e743b
[GPU] Fixed uninitialized field issue in pooling ( #9542 )
2022-01-10 21:44:11 +03:00
Vladimir Zinoviev
b744c11b88
[LPT] INT16, INT32 leftovers ( #7653 )
2022-01-10 21:09:10 +03:00
Vladimir Paramuzov
0c2b53eba3
[GPU] Moved several module tests to proper folder ( #9544 )
2022-01-10 20:14:22 +03:00
Zhang Yi
c1206ef447
[CPU] SoftMax cache ( #9480 )
...
* [CPUCache]SoftMax cache
* [CpuCache]fix bf16 tests
* [CPUCache]apply review comments
* [CPUCache]fix compilation
2022-01-10 18:46:57 +03:00
Alexandra Sidorova
af105b86f8
[CPU] Fixed Replicate via ov::Model ( #9252 )
2022-01-10 17:51:33 +03:00
Anastasia Kuporosova
8fe5484645
[Python API] Remove offline transformations from old python api ( #9121 )
...
* [Python API] Remove offline transformations from old python api
* try to fix import error
* try to fix pylint
* try to fix pylint2
* Use new api in graph_utils
* Fix pylint
* Try to fix pylint
* Use serialize from pass manager
* try to skip tests
* try to use new ir
Co-authored-by: AlexeyLebedev1 <alexey.lebedev@intel.com>
2022-01-10 17:32:55 +03:00
Svetlana Dolinina
04386bb667
fixed tensor shapes to work correctly if shape of the first arg less then shape of the second arg; ( #9368 )
...
added according unit test
2022-01-10 17:15:21 +03:00
Vladimir Paramuzov
8d8ceeb5d7
[GPU] Fixed invalid vector element access in reduce test ( #9538 )
2022-01-10 15:08:11 +03:00
Yuan Hu
00361b7617
try to fix klocwork issue ( #9207 )
...
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
2022-01-10 14:57:37 +03:00
Yuan Hu
b6951bfb2c
change INT8 to VPUX as first priority ( #9261 )
...
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
2022-01-10 14:54:21 +03:00
Anastasia Popova
aecbd549f8
Support of partial shapes with boundaries in MO IR reader. ( #9223 )
...
* Added support of partial shapes boundaries in MO IR reader.
* Added comments.
2022-01-10 14:36:36 +03:00
Ilya Znamenskiy
371eaba7cd
[GPU] Fix of gws/lws inconsistency for some reorder cases ( #9467 )
2022-01-10 14:04:04 +03:00
Ilya Sharikov
cb0084718a
Update list of OMZ models for stress tests ( #9391 )
2022-01-10 13:50:03 +03:00
Andrei Molotkov
9e41208791
[GPU] QueryNetwork method correction to work with dynamic shapes ( #9462 )
2022-01-10 12:07:12 +03:00
hyunback kim
2a476f6906
[GPU] Enable unet2d enable on DG2 ( #9522 )
...
* [GPU] Enable unet2d enable on DG2
Add to support is_os_yx_isa2_osa8_isv8_osv2 format, which is used in
weight reorder.
Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-01-07 18:38:07 +09:00
hyunback kim
89f48e0558
[GPU] Enable implicit concat batch1 in oneDNN. ( #9424 )
...
* [GPU] Enable implicit concat batch1 in oneDNN.
* Use gpu_usm memory offset, enable implicit concat batch1 in oneDNN.
And optimized_out node doesn't always have to be mutable input,
so add to check whether mutable input is existed in optimized node.
* Update to check use_usm condition in implicit concat.
* Add the condition for implicit concat.
* implicit concat's dependency should not be fused_op with eltwise.
* Buffer reuse is required for onednn sum post operation, output padding
did the buffer reuse failure.
Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-01-06 12:41:09 +09:00
Dawid Kożykowski
e89db1c6de
Fix "Unexpected number of outputs after override_all_outputs" ( #9454 )
2022-01-05 12:10:16 +01:00
Min, Byungil
f255c195c5
[GPU] Add functional and pass test-cases ( #8998 )
...
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-01-04 22:09:23 +09:00
Jade Cho
2945232982
Split hard sigmoid into eltw linear and eltw clip ( #9500 )
...
+ cldnn supports hard sigmoid activation function but onednn doesn't.
+ split it into eltwise linear and eltwise clip in
add_onednn_optimization_attributes pass.
2022-01-04 20:22:11 +09:00
Alexey Lebedev
339849fde8
[PYTHON API] add_extension api ( #9339 )
...
* Pass ov::extension in core.add_extension
* fix code style
* revert mock and inherit extension on python side
* Fix code style
* Enable add_extension test
* Fix code style
* Move Extension to openvino.runtime
* use static_cast instead c-cast
* Fix code style
* fix test
2022-01-04 13:54:15 +03:00
Tomasz Dołbniak
326289265b
MO: progress bar implementation for new frontends ( #9381 )
2022-01-03 14:04:45 +01:00
Taylor Yeonbok Lee
c26a904c6e
Disable blocked layout selection for quantize when the user is gemm beacuse no gemm kernels are using blocked format currently ( #9425 )
2022-01-03 09:58:16 +09:00
Maxim Vafin
738a571742
Use layouts in legacy pre-processing ( #9355 )
...
* Use layouts in legacy pre-processing
* Use layouts for batch in MO
* Unify code for channel and batch dimension
* Fix issue when idx is None
2021-12-30 21:01:55 +03:00
Mateusz Tabaka
50a33436d4
Add MatMulMultiplyFusion ( #9023 )
...
* Add MatMulMultiplyFusion
MatMulMultiplyFusion replaces following subgraph:
MatMul->Multiply (with const)
to following:
Multiply->MatMul
where Multiply is applied to MatMul's second input.
2021-12-30 18:13:11 +01:00
Fedor Zharinov
4dbc9ae2e7
benchmark_app with dynamic reshapes and API 2.0 ( #8609 )
...
* API 2.0 changes
* stylefix
* Update samples/cpp/benchmark_app/main.cpp
Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>
* Update samples/cpp/benchmark_app/infer_request_wrap.hpp
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* Update samples/cpp/benchmark_app/utils.cpp
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* fixes
* fix for: gpu headers are moved to another folder... yet again
* fix for mac build paranoia
* function,classes and files renames/change logic to work with inputs()
* stylefix
* 2nd portion of fixes
* stylefix
* Batch warnings
Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
2021-12-30 19:09:12 +03:00
Vladislav Volkov
e52c96389d
[CPU] Bug in jit_convert fixed ( #9485 )
2021-12-30 18:22:16 +03:00
Edward Shogulin
ec5198094a
[CPU] PriorBox & PriorBoxClustered dynamism enabling ( #8597 )
2021-12-30 17:43:16 +03:00
Maxim Andronov
8ba94cfb8f
[CPU] Fix memory allocation for non default shape infer path ( #9475 )
2021-12-30 17:04:33 +03:00
Chen Xu
bea10d6e3c
[CPU] Optimize Broadcast node for case with scalar input ( #9358 )
2021-12-30 16:47:48 +03:00
Mingyu Kim
5beb5dca3d
[GPU] Update onednn to v2.6-pc ( #9479 )
2021-12-30 16:20:35 +09:00
Mateusz Tabaka
c23025dfd2
[GPU] Allow networks with gather to use b_fs_yx_fsv16 format ( #9249 )
...
Gather is an alternative approach used by model optimizer
to implement --reverse_input_channels option.
Currently, if it's in use, convolutions in GPU plugin
may use other formats that leads to choosing less performant kernels.
2021-12-30 09:34:19 +09:00
Maxim Gordeev
b144089ef7
[IE_Samples] Updating information about methods in README.md according new API 2.0 ( #9477 )
2021-12-29 23:50:19 +03:00
Sergey Lyubimtsev
f1a25b398c
Clean up setupvars scripts ( #9410 )
...
* Clean up setupvars scripts
* align opencv
* fix opencv location
* fix env windows
* fix env windows
* check upper bound for supported python version
* remove ROOT var
* revert PYTHONPATH
* fix error message
* fix pyver option
* revert OpenCV
* okay -> true
2021-12-29 17:57:56 +03:00
Pavel Esir
8c145a25c9
[MO] mo_version getting fix ( #9135 )
...
* mo_version getting fix
* hardcoded major minor version in MO
* Update check_ie_bindings.py
hard error in version comparison fixed
2021-12-29 17:31:05 +03:00
Ekaterina Aidova
9802a4cb5d
[OMZ]: update submodule ( #9472 )
2021-12-29 13:48:59 +00:00
Anton Chetverikov
adce58d126
[MO] Add check for Python version to NetworkX dependency ( #9226 )
...
* Add check for python version to networkx dependency
* Update condition, task CVS-72806
* Update check to not break old Python versions support
* Update POT NetworkX dependency
* Allign requirements list format with setuptools documentation
2021-12-29 16:26:40 +03:00
Kelvin Choi
4505f5d7e2
[GPU] Remove remainder handling to read in reduce kernel to improve performance ( #9359 )
...
Signed-off-by: Kelvin Choi <kelvin.choi@intel.com>
2021-12-29 22:25:34 +09:00
Maxim Gordeev
39a1b98799
changed C++ samples due to OpenVINO style ( #9463 )
...
I'll merge this. We need to talk with someone who know openvino build system better than we to "use cmake function ov_ncc_style_check to perform such check automatically". As far as I can see, currently it used only in one place, so it is not common approach for openvino components
2021-12-29 15:36:33 +03:00
Nikita Malinin
010877d06c
[POT] Update dtype for BC Parameters ( #9468 )
2021-12-29 15:11:56 +03:00
Vladislav Volkov
1ee8007764
[CPU] NV12toRGB and NV12toBGR operations for CPU plugin ( #8628 )
2021-12-29 13:46:02 +03:00
Maxim Andronov
2e433620b7
[CPU] General fixes for dynamic shapes. Part 3 ( #9338 )
2021-12-29 13:43:35 +03:00
Irina Efode
9234f4177d
[IE TESTS] Test movement ( #9429 )
...
* [IE TESTS] Movement of some tests in shared lib. Movement of 'QueryNetwork' validation to ApiConformance suite
* Update read_ir.cpp
2021-12-29 12:28:58 +03:00
Vladimir Paramuzov
3ee00e018a
[GPU] Moved onednn_gpu to plugin folder ( #9458 )
2021-12-29 11:06:14 +03:00
Roman Lyamin
9f69daf0f3
[GPU] Remove batched key from config ( #9451 )
2021-12-29 09:58:48 +03:00
Yegor Kruglov
8b6a065948
[MO][IR READER] Updated MO and IR Reader to keep the second MaxPool output in restored IR ( #9180 )
...
* updated MO to save second MaxPool output in restored IR
* blank line at the end of file
2021-12-29 09:44:10 +03:00
