IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
9,139 Commits 38 Branches 54 Tags 1.1 GiB
f02c663a1d
Commit Graph

9139 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Sergey Shlyapnikov
f02c663a1d
[GPU] Fix eltwise fusions in case of LT_ALIGNED_READ and vec_size>1 (#14275) 2022-12-20 12:13:15 +04:00
Roman Kazantsev
0b2f3347f6
[Tools] Support NumPy 1.24 (#14728) 
* [Tools] Avoid use of NumPy deprecated types

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

* Revert "[Tools] Avoid use of NumPy deprecated types"

This reverts commit 21ffc167d1.

* Move to 1.24 Numpy

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-12-19 23:51:34 -08:00
Daria Mityagina
d300abf743
[OV][VPUX] - Debug build flags (#14651) 
* [TEST] - Debug build flags

* Remove the pdb config to let each project use own vxx.pdb file.

Co-authored-by: Xin Wang <xin1.wang@intel.com>
 2022-12-20 11:38:43 +04:00
Vladimir Paramuzov
6bc4f00695
[GPU] Refactored GPU verbose utils (#14549) 
* [GPU] Refactored GPU verbose utils

* [GPU] More refacoring

* Fix build
 2022-12-20 11:06:01 +04:00
Egor Duplenskii
e306cbc67a
[CPU] [DEBUG CAPS] Extension for snippets and other ngraph transformations (#14223) 2022-12-20 08:49:37 +03:00
Oleg Pipikin
40e19dec00
Fix clang warnings for transformation tests (#14727) 2022-12-20 08:34:19 +04:00
Roman Kazantsev
a2edb1a483
Use concrete version of numpy for Python binding testing (#14726) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-12-19 22:47:51 +04:00
Maksim Kutakov
1f84eabcec
[CPU][DOCS] Remove recommendation to use partially defined shapes (#14674) 2022-12-19 21:49:46 +04:00
Roman Kazantsev
291eddaecd
[Docs][Install] Update description for default and extras installation of openvino-dev (#14706) 
* [Docs][Install] Update description for default and extras installation of openvino-dev

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

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Apply code-review feedback: no need in new environment for the default installation

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/installing-model-dev-tools.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Update docs/install_guides/pypi-openvino-dev.md

Co-authored-by: Ryan Loney <ryanloney@gmail.com>

* Apply code-review remarks: grammar corrections and avoid confusion

* Apply code-review feedback: clarify compatibility issue case, remove confusing sentence

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
Co-authored-by: Ryan Loney <ryanloney@gmail.com>
 2022-12-19 20:46:23 +04:00
Jan Iwaszkiewicz
c8493bd47b
[PyOV] Update BUILDING.md and minor dev docs fixes (#14357) 2022-12-19 16:03:54 +01:00
Egor Duplenskii
4d44c70c32
[CPU] Improve some error messages (#14668) 2022-12-19 14:56:40 +04:00
Liubov Talamanova
67f467b2f3
[POT] Updated Simplified mode documentation (#14545) 
* [POT] Added image generation doc for Simplified mode

* Fix comments

* Remove version
 2022-12-19 13:26:35 +04:00
Vladimir Paramuzov
ee256e801c
[GPU] Removed legacy public gpu config and related processing (#14707) 2022-12-19 11:19:07 +04:00
Zlobin Vladimir
787ba3de4f
replace benchmark_app imean and iscale parameters (#14621) 
* replace benchmark_app imean and iscale parameters

Tickets 80777 and 80900

* Warn about difference with imean and iscale, note that in help

* Clang format

* Clang format

* mean->scale

* Keep mean scale empty if not set

Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
 2022-12-19 09:27:39 +04:00
Taylor Yeonbok Lee
05159b8cfb
[GPU] Fixed shape infer dep for blocked format (#14646) 
* Fixed shape infer dep for blocked format

* Set preferred format for shape_of to be made from input rank
- ShapeOf should get the original output layout of the previous node, which is not reorderd.
 2022-12-18 20:03:23 -08:00
Sofya Balandina
a7d0b7b010
[Confromance, API2] Remove CPU from heteroDeviceName (#14631) 2022-12-18 03:45:18 +00:00
Andrei Kochin
1a4117b855
[MO] remove deprecated mean_file option (#14137) 
Signed-off-by: andrei.kochin <andrei.kochin@intel.com>

Signed-off-by: andrei.kochin <andrei.kochin@intel.com>
 2022-12-17 15:23:54 +04:00
Oleg Pipikin
b808fb7f4f
Enable warnings for transformation tests (#14699) 
* Remove warning suppression from tests

* Fix warnings MSVC ov_transformations_tests

* Fix warnings MSVC ov_lp_transformations_tests

* Fix code style
 2022-12-17 01:54:24 +03:00
Oleg Pipikin
8e3c3f5c04
Enable clang-format for tests (#14667) 2022-12-17 01:54:07 +03:00
Sebastian Golebiewski
73771a09f0
DOCS: Homepage - openvino workflow section update - for master (#14655) 
Removing raw html directive
Updating/improving css
adding new diagram
updating css
 2022-12-16 19:49:06 +01:00
Tomasz Dołbniak
56606ec46f
ONNX Adaptive average pooling implementation (#14682) 2022-12-16 15:39:40 +01:00
Oleg Pipikin
e9812caff5
Change compile options for transformation tests to fix CVS-97900 (#14608) 
* Change compile options for transformation tests to fix CVS-97900

* Disable cpplint

* Remove changes for RelWithDebugInfo config
 2022-12-16 17:09:46 +04:00
Jan Iwaszkiewicz
4479585d47
[PyOV] Rewriting properties tests as hardware agnostic (#14684) 2022-12-16 12:29:20 +01:00
Maxim Vafin
fce4641a25
Preserve input constant in Squeeze and Unsqueeze shape infer (#14432) 
* Preserve input constant when Squeeze and Unsqueeze shape infer is sone in MO IR Reader

* Fix bom test

* Add tests

* Fix value

* Fix test

* Apply suggestions from code review

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2022-12-16 15:08:28 +04:00
Pawel Raasz
b850f422ba
Review logical ops for shape inference aspects (#14393) 
* Review dims and labels propagation for logical not

* Review dims and labels propagation
for logical and, or, xor

* Remove duplicated tests

* Expand logical ops tests by numpy broadcast
and inputs order

* Review template shape infer of logical ops
 - add static shape inference test
 - add default ctor test

* Default ctor test for LogicalNot op
 2022-12-16 14:37:47 +04:00
Katarzyna Mitrus
72c39c3e32
[Shape Inference] ScatterUpdate - add evaluate_label (#14381) 
* Add ScatterUpdate type_prop tests

* Add evaluate_label for ScatterUpdate

* style update

* Reuse has_no_labels

* Adjust the logic to the single output

* Remove redundant size_check

* Migrate from HostTensor to ov Tensor

* Remove deprecation macro

* Use auto instead of HostTensorPtr

* Adjust tensor element type

* Update to reuse labels vector

* Use sizeof size_t to set element type

* Ensure static shapes on inputs
 2022-12-16 14:34:25 +04:00
Katarzyna Mitrus
e0c21ce302
ScatterUpdate CPU shape_infer by entryFirstPassthrough (#13950) 
* ScatterUpdate shape_infer tests

* Add ScatterUpdate to entryFirstPassthrough

* Headers cleanup

* Style update

* namespace update
 2022-12-16 14:28:16 +04:00
Przemyslaw Wysocki
4bc80ca446
[PyOV] Make graph tests hardware agnostic - part 3 (#14639) 2022-12-16 11:23:35 +01:00
Anastasia Kuporosova
544c1acd2b
[PyOV] remove opencv from requirements (#14617) 2022-12-16 10:05:34 +01:00
Mateusz Tabaka
43164a6b25
[CPU] RDFT kernel optimizations (#14060) 2022-12-16 11:18:27 +03:00
Maciej Smyk
7facf8b90b
DOCS: Low Precision Transformations proofreading port to master (#14069) 
* Attributes
* Update lpt_attributes.md
* defines fix
* Update docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/lpt_attributes.md
 2022-12-16 10:24:14 +03:00
Maciej Smyk
9b7148c924
Fixing links to API (#14558) 2022-12-16 08:15:29 +01:00
Maciej Smyk
3b726cc0c0
Fixing Python API links (#14561) 2022-12-16 08:14:48 +01:00
Nadezhda Ageeva
539f17df62
[HETERO][nGraph] Fix ConstantFolding fused_names handling (#13766) 
* [HETERO][CPU][GPU][TEMPLATE][nGraph] Fix ConstantFolding fused_names propogation. Add tests for QN. Fix for unsupported comsumers in QN

Fix ConvolutionMultiplyFusion for CPU

Enable fused_names check for Constants

Fix memory formats rt info for CPU

* Update src/plugins/intel_cpu/src/utils/rt_info/memory_formats_attribute.hpp

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

* Update src/tests/unit/inference_engine/query_model_test.cpp

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

* Update src/plugins/intel_cpu/src/utils/rt_info/memory_formats_attribute.hpp

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

* Update src/plugins/intel_cpu/src/ngraph_transformations/convert_matmul_to_fc.cpp

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

* Update src/core/src/rt_info.cpp

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

* Update src/core/src/rt_info.cpp

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

* Fix review comments

* Fix test

* Code style

* Review comments

* Don't add Parameters/Inputs/Results to supported due to supported consumers/sours. Add tests for that.

* Fix rt_info propogation for ConstantFolding

* Fix test build

* Code stye

* Review comments. Adds ShapeOfBase.

Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
 2022-12-16 10:16:50 +04:00
Roman Kazantsev
e09995bc60
[TF FE] Support models with topologically unsorted nodes (#14652) 
* [TF FE] Support models with topologically unsorted nodes

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

* Fix conversion for models with cycle

* Fix code-style

* Fix code-style

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-12-16 08:50:40 +03:00
Eddy Kim
b46dd308d6
[GPU] Updated to get lockable memories for device inputs in prepare_input() (#14418) 
* updated to get ockable memory for device inputs

* gpuFuncTest to set f64 scalar tensor

* aligned type names

* updated to get lockable memory for some specific precisions

* add a function to get a supported precision
 2022-12-16 09:12:47 +04:00
Vladimir Paramuzov
fa1cddf278
[GPU] Use ASSERT_* instead of EXPECT_* in most of the cases (#14535) 2022-12-16 09:09:57 +04:00
Przemyslaw Wysocki
07a61d4862
Fix python versions in docs (#14672) 2022-12-15 21:46:57 +01:00
Anastasia Kuporosova
f288baf2b3
Remove unused variables in pytests from azure (#14618) 2022-12-15 21:26:36 +01:00
Ilya Naumov
a0ce891915
benchmark_app python: fix incorrect -i argument parsing for wavernn-rnn input names (#14349) 
* benchmark_app python: fix incorrect -i argument parsing for wavernn-rnn input names

* fix for Windows paths
 2022-12-15 19:20:14 +03:00
Roman Kazantsev
e44a4fc6d2
[TF FE] Support Assert with string tensors (#14640) 
* [TF FE] Support Assert with string tensors

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

* Update src/frontends/tensorflow/src/op/const.cpp

* Update src/frontends/tensorflow/src/op/const.cpp

* Apply code-review feedback: better to use UnsupportedConstant

* Correct unit-test

* Replace Op with Node

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2022-12-15 19:28:34 +04:00
Maxim Vafin
9c0ec2c9b4
Add reverse infer (#14348) 
* Add reverse infer

* Add more convolutions and include transformation in normalize of tf fe

* Fix code style

* Add activations and eltwise support

* Fix code style

* Add deprecation supression

* Fix pad type

* Remove eltwise

* Remove ngraph namespace usage

* Fix code style

* Apply review feedback

* Add tests for activations and eltwise

* Make transformation friend of tensor to avoid deprecated API

* clang fix all

* Update src/common/transformations/include/transformations/common_optimizations/reverse_shape_and_type_infer.hpp

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2022-12-15 19:26:58 +04:00
Maxim Vafin
7df9031411
Support Dilated convolution in dynamic case (#14615) 
* Add Mod evaluate method

* Fix mo transformation for dynamic case

* Fix build
 2022-12-15 14:52:15 +00:00
Alexander Kozlov
bc685ac8a0
[Documentation]: Added description for NNCF PTQ (#14437) 2022-12-15 16:10:40 +03:00
Maciej Smyk
ece0341377
DOCS: Quantization doc rewrites - port to master (#14374) 2022-12-15 13:55:06 +01:00
Maciej Smyk
9ba4610797
Stateful models (#14660) 2022-12-15 13:53:26 +01:00
Nadezhda Ageeva
08e46a20e2
[TESTS] Fix QN tests for case when device id is reported (#14601) 2022-12-15 15:41:51 +04:00
Oleg Pipikin
33b0ca885a
Disable clang format for transformation test for fix CI (#14657) 2022-12-15 11:22:34 +01:00
Oleg Pipikin
161a0a6319
Disable clang format for lp transformation test for fix CI (#14629) 2022-12-15 11:12:35 +01:00
Alexandra Sidorova
5eed405478
Fixed Transpose spec (#14623) 2022-12-15 13:51:36 +04:00