Commit Graph

6268 Commits

Author SHA1 Message Date
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
Anton Chetverikov
8dc7669156
[MO] Deprecate TensorFlow 1.x environment support by MO (#8970)
* Remove tf1 requirements file and add deprecation message then tf1 used while compression

* Added tf requirements file

* Update docs and warning message

* Update install scripts

* return tf configuration

* Add compat.v1 to code snippets in docs

* fix typo

* Moved back tf2 file

* Apply review comments

* Fix missed eol

* Fix missed eol

* Apply review comments in docs

* Remove tf version and fix error in script tag

* Remove tf version

* Remove unused import

* Add note about python and TF version
2021-12-29 09:43:52 +03:00
Maksim Kutakov
2870dc7d3f
[CPU] Cache for runtime data (#9192)
Caching added for Eltwise and MatMul nodes
2021-12-29 09:19:45 +03:00
Vladislav Volkov
cb9fe0910d
[CPU] Broken support for Layout::ANY in CPU plugin (#9434) 2021-12-29 09:09:56 +03:00
Luwei Zhou
ce753f41dc
[shape_infer]shape inference implement of Select Detectionoutput and Shufflechannels OPs (#8348)
* Implement detection_output shape infer

* revise and update the code flow

* update based on review.

* Update based on review

* Implement the shuffle_channels Op shape inference.

* Fix CI coding style issue.

* Implement the select OP shape inference.

* Update based on the review  comments

* Update based on the review comments.

* Add pragma once for the shape inference head.

* Add new shape_infer test file for detection_output OP.

* Ensure the header would only be included once.

* Add shuffle_channels OP shape infer test.

* Add shape_infer() invocations into shape_inference() API

shape_inference() API support Select, ShuffleChannels, DetectionOutput OPs
Fix extra pragma, unnecessary friend function declaration.

* Update based on the review comments.

* Move the shape infer API helpers into new folder.

* Applied review comments.

* Applied 2nd review comments

* Applied review comments

* Fix coding style.

* Update

* Applied review comments.

* Fix comipling issue of unused variable.

* Fix the CI issue.

* Update the coding style

* Move test cases into new folder

* Applied  review comments.
2021-12-29 05:39:50 +03:00
Pavel Esir
a51a735d9f
[MO] cli_parser.py fix to accept scalar value for freezing (#9395)
* cli_parser.py fix to accept scalar value for freezing

* update cli help

* fixed unit-tests, clarified help for specifying data type

* typos correction
2021-12-29 01:33:49 +03:00
Anton Chetverikov
3e6951c1da
[MO] Support for common rt_info attribute in MO IR Reader (#9272)
* Support for common rt_info attribute in MO IR Reader

* Add missed change

* Moved back wrong change

* Change attr name

* Add support for rt_info for out ports

* Add emitting for rt_info

* Fix restoration error

* Add support for rt_info for input ports

* Add more comments

* Set correct layout attr to restored graph
2021-12-29 00:59:48 +03:00
Milana Shhanukova
3cef513495
[POT] Check type for layers' renaming (#9276)
* change in installation

* develop mode

* change in install guide

* style change

* change declare

* add type checking

* revert changes

* rename directly in nx_model

* Update README_dev.md
2021-12-28 18:08:36 +03:00
Roman Kazantsev
b2aff0cd56
[MO SDL] Test MO and IR Reader on attacking inputs (#8947)
* Test MO and IR Reader on attacking inputs

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

* Add test to check IR Reader against untrusted well-formed IR

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

* Refactor IR Reader tests with corrupted IR

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

* Test for regular expression denial of service

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

* Remove undesired word like bomb

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

* Move tests to new location

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

* Use correct import

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

* Revert blank line

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2021-12-28 17:49:48 +03:00
Jade Cho
da1261a1d8
[GPU] Fix a bug in post-operation optimization (#9443) 2021-12-28 17:48:29 +03:00