Commit Graph
209 Commits
Author SHA1 Message Date
Ilya Lavrenov f205ba9459 Fixed pyngraph compilation with python 3.9.2 (#4940) 2021-03-25 13:15:01 +03:00
Sergey Lyubimtsev 222a709c6c NGraph python api cannot be built w/o onnx importer (#4880)
* NGraph python api cannot be built w/o onnx importer

* add target condition
2021-03-25 12:26:35 +03:00
Alexey Suhov a748c26fee Align copyright notice in cpp and cmake source files (CVS-51320) (#4950) 2021-03-25 02:40:09 +03:00
Mikhail Ryzhov c3fc40052c Python 3.8 support (#4629)
* Python 3.8 support

* Get path from setupvars
2021-03-23 17:32:08 +03:00
Jan Iwaszkiewicz 8ec59ceda4 [CPU][ONNX] Convert FP64 precision to FP32 (#4681) 2021-03-19 19:28:55 +01:00
Ilya Churaev 1334d7d122 Enable OV clang format command for nGraph (#4792)
* Added add_clang_format commands

* Added clang_format targets as dependencies for original targets

* Update CI scripts

* Fixed code-style for nGraph unit tests

* Change job name

* Disable clang-format for Windows

* Fixed nGraph python build

* Fixed comments and enabled code style for ONNX Editor

* Disable code style check on compilation step
2021-03-18 06:38:10 +03:00
Katarzyna Mitrus 5f098e1079 nGraph code style upgrade to clang-format-9 (#4721)
* ngraph clang-format upgrade to 9

* Reformatted files

* Remove comma at the end of test data vector
2021-03-15 22:06:01 +03:00
dependabot[bot] b83b5115a5 Bump flake8 from 3.8.4 to 3.9.0 in /ngraph/python (#4782) 2021-03-15 17:59:29 +01:00
Rafal Blaczkowski dbd3a3d7a4 Enable protobuf-lite in ONNX CI tests (#4487) 2021-03-15 14:34:02 +01:00
Katarzyna Mitrus 95a13e05d5 Enable MatMul 1D multiplication by transformation to GEMM (#4509)
* MatMul tests

* Tests update

* More tests

* IE tetst manifest cleanup

* Enable MatMul 1D multiplication by transofrmation to GEMM

* Add unsqueeze to transform tests

* Fix runtime info

* Update transformation condition

* Remove Xfail from python tests

* Add more tests for ignoring 1D transpose true

* Ignore transpose for 1D in MatMul transformations

* Resolve python api xfails

* Use ngraph::opset namespace

* Style apply

* Add MatMul single layer tests for 1D
2021-03-15 13:44:57 +03:00
Ivan Tikhonov b792214d04 Fix python API for Loop/TensorIterator/Assign/ReadValue operations (#3275)
* update python API for the Loop operation (attempt 1)

* fix code style

* update visitor API, pep8

* codestyle

* delete TensorItertorBuilder

* update visitor API for Loop and TensorIterator

* fix code issues (python)

* update python api:assign/read value

* fix unit tests

* fix python code style

* fix loop unit test

* fix loop unit test

* fix build on centOS
2021-03-11 13:22:24 +03:00
Gabriele Galiero Casayandjdanieck bd949c6baf BinaryConvolution Reference Implementation (#4278)
* Add BinaryConvolution unit tests.

* Changed types to u1.

* Add BIN precision handling in TestCase class.

* Refactored validate and infer types to enhance dynamic shape inference

* Add type_prop test to cover invalid op cases and dynamic shapes

* Fix style

* Disable check for float type of data batch input

* Add type_prop test for incompatible input channels in inputs

* Disable backend unit tests

* Fix style

* Add reference implementation

* Add backend tests

* Add single layer tests

* Add check for float element type of batch data input

* Refactor backend test cases to compare with regular convolution

* Add serialization tests

* Clean up

* Add 1D and 3D tests into op_eval

* Changes in reference implementation to improve readability

* Add ticket information for todo tasks

* Fix implementation misbehavior for filter channels

* Add backend unit tests to cover strides, dilations, padding, channels and batches

* Add end of line into files

* Change name of type_prop unit tests

* Simplified lambda to get spatial dimensions of filters

* Add comment to support filters input as Parameter

* Add namespace details for BinaryConvolution utility functions

* Address review comments

Co-authored-by: jdanieck <jozef.daniecki@intel.com>
2021-03-09 22:58:25 +03:00
Evgeny Lazarev 99f94ca09c Adding v7::Gelu operation (#4497)
* Added support for Gelu-6 to the MO

* Adding Gelu-6 to ngraph and python API + some tests

* Fixed typo in the Gelu approximation mode

* Fixed Gelu-6 reference implementation for Tanh mode

* Added transformation to downgrade v6::Gelu to v2::Gelu

* Added specification for the Gelu-6

* Code style fixes

* The Gelu-6 operation specification update

* Fixed compilation issue in reference implementation for Gelu

* Fix compilation issues for some OSs

* Code style fix

* One more cpplint issue fix

* Fixed Gelu6 reference implementation compilation on Windows.

* Code style fix

* Fixed various ngraph unit tests

* Code style check

* Reverted Gelu-2 to be fused op

* Fixed Gelu6 downgrade transformation

* Added unit test for Gelu6Downgrade transformation

* Update copyright year

* Updated copyright year

* Replaced tab characters with 4 spaces in IR reader tests

* Code style fixes

* Added default value for GeluApproximation mode for Gelu-6 op

* Fixed code style for Gelu-6

* Changed order of parameters for the Gelu evaluate to potentially avoid backward compatibility issues with ARM plugin

* Fixed code style

* Introduced opset7. Moved Gelu6 to opset7

* Fixed non-updated transformation

* Fixed opset version in ngraph Python API for Gelu operation

* Fixed typo in the opset number in the documentation

* Reverted some changes related to Gelu6

* Updated MO to produce Gelu7

* Updated unit tests for Gelu

* Updated Gelu7 specification

* Changed gelu reference implementation. Added opset7 to Python packages

* Updated Python API tests for Gelu operation

* Code style fix

* Marked get_approximation_mode function as const

* Added missing "const" qualifier

* Fixed code style issues in tests

* Added extractor for MxNet operation Gelu

* Spelling issues fix

* Updated MxNet supported symbols

* Added NGRAPH_OP_SCOPE for Gelu7 validate_and_infer_types

* Fixed a typo in the comment
2021-03-09 22:45:45 +03:00
Sergey Lyubimtsev dde565d187 Align builds locations for ngraph and ie python bindings (#4095)
* Align builds folders for ngraph and ie python bindings

* fix merge issue

* Replace hardcoded path in PYTHONPATH with setupvars.sh

* remove unused docker instructions

fix output directory for local wheel build (ngraph_DIR is set)

* add newline at end of file

* fix merge issue
2021-03-09 16:28:23 +03:00
Mikhail Ryzhov 3babad19be Added specific for Python3.8 way how to find libs (#4513)
On Windows, with Python >= 3.8, DLLs are no longer imported from the PATH.
os.add_dll_directory() can be used
2021-03-01 16:01:04 +03:00
Tomasz Dołbniak cadcd7c926 Remove a duplicate xfail marker for ONNX dropout tests (#4522) 2021-03-01 07:17:29 +03:00
Bartosz Sledz b0043bb599 ONNX Slice operator support types dynamically (#4507) 2021-02-26 16:28:51 +01:00
Ewa Tusień f88f81c6ba OnnxBackendNodeModelTest XFAILs cleanup (#4432) 2021-02-26 15:34:24 +01:00
Mikhail Ryzhov 2db51bb0d0 [Python] Fixed issues in runtime wheel (#4359)
* Added rpath for plugins

* Corrected dll pathes for PIP

* Fixed plugin install names

* Put libs to the sub-package

* Corrected libraries path according to the new location

* Added download and home page urls
2021-02-26 10:31:58 +03:00
dependabot[bot] a6989bb047 Bump tox from 3.21.4 to 3.22.0 in /ngraph/python (#4452) 2021-02-22 17:03:23 +01:00
Konstantin Satunin 0682d773ca Unique locations for pdb files (#4446) 2021-02-22 11:41:03 +03:00
Konstantin Satunin 342ae0daa7 unique locations for pdb files (#4445) 2021-02-20 23:48:47 +03:00
Konstantin Satunin 8f5453d70f Pyngraph independent locations for lib files (#4440)
* Make unique location for pyngraph lib files

* fix variable usage
2021-02-20 18:15:57 +03:00
Maxim Andronov f26c82bde3 [CPU] Supporting constant networks (#4379) 2021-02-19 09:38:20 +03:00
Michał Karzyński ec9b5894fb [ONNX] Add support for BitShift operator (#4368) 2021-02-17 16:39:27 +01:00
Michał Karzyński 66634a9939 Update ONNX compliance test list (#4360)
* Update ONNX compliance test list

* Update test_backend.py
2021-02-17 07:40:47 +03:00
Tomasz Socha 185aaacc07 [ONNX] Add support for Softmax v11 in opset 7 models (#4340) 2021-02-16 11:58:39 +01:00
Jan Iwaszkiewicz a3af43c8e4 [ONNX] Minimum op xfail updated (#4332) 2021-02-16 11:43:07 +01:00
Michał Karzyński ccc1a9f357 Rename dunder methods (#4334) 2021-02-15 18:34:21 +01:00
dependabot[bot] 01e4606bd0 Bump tox from 3.21.2 to 3.21.4 in /ngraph/python (#4227) 2021-02-15 11:55:33 +01:00
Mateusz Bencer d821ec47ce [ONNX] Handle optional outputs for Dropout and MaxPool (#4143) 2021-02-15 11:14:20 +01:00
Rafal BlaczkowskiandAlexander Zhogov 3eb0b5c90d Add visible export (#4222)
Co-authored-by: Alexander Zhogov <alexander.zhogov@intel.com>
2021-02-11 19:02:58 +03:00
Jan Iwaszkiewicz 7ff8f8eba4 WA for GCC 7.5 pybind warning (#4277)
* WA for GCC 7.5 pybind warning

* Move compiler flag to ngraph/python
2021-02-11 18:41:23 +03:00
Jan Iwaszkiewicz 63f3a5d99c Change class member init (#4266) 2021-02-10 14:13:16 +01:00
Jan IwaszkiewiczandTomasz Dołbniak 7af2959bd0 [ONNX] Convert to integral type in OneHot op (#4229)
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
2021-02-10 14:03:54 +01:00
Mikhail Ryzhov e2c67bd508 Enabled wheel packaging (#3582)
* Added onnx support for C samples

* Added wheel packaging configuration

* ADD cmake option

* Small refactoring

* Fixes for linux env

* Fixed macOS issues

* removed test code

* Added requirements file

* Added myriad plugin

* [PIP] Runtime wheel packaging v2

* Added rpath logic

* Setting rpath for bindings

* Formatting fixes

* Move target project 1 directory above

* Added target dependencies

* Added blacklist for runtime libs

* Corrected blacklist scope

* Added wheel packaging configuration

* ADD cmake option

* Small refactoring

* Fixes for linux env

* Fixed macOS issues

* removed test code

* Added requirements file

* Added myriad plugin

* [PIP] Runtime wheel packaging v2

* Added rpath logic

* Setting rpath for bindings

* Formatting fixes

* Move target project 1 directory above

* Added blacklist for runtime libs

* Changed lib exstention om macOS

* ADD cmake option

* Revert "ADD cmake option"

This reverts commit 36f98c713bb337a160f9af6c7c79c4371fdfc45f.

* Revert "Changed lib exstention om macOS"

This reverts commit 80086fe1230b64fbcf396de82bc731c10f738eae.

* Revert "Merge branch 'feature/wheel_pack' of https://github.com/mryzhov/openvino into feature/wheel_pack"

This reverts commit 7560d9ab55edc1f8877b83821542570060fb13d8, reversing
changes made to c287798f994dcefc074a06ff7c3ef86222674cc7.

* Revert "Added onnx support for C samples"

This reverts commit 26c595ac136d99bd576d307d33ca15feb15f81e4.

* Fixed merge issues

* Fixed typo in mac tool

* Code review fixes

* Simplified deps and added fatal error

code review fixes

* Removed test data

* Fixed setup.py review comments

* Removed apache 2.0 license

* Review fixes

* fixed pylint issues

* Fixed python api install directory

* Using cmake detected python binary

* Changed wheel build directory

* Renamed subdir from install to wheel

* Removed pylint log

* Made license, description and requirements configurable by cmake options

Those files may be changed in CI

* Changed variable name

* Glob instead of os.walk

* Corrected package name in description

* Added wheel building instructions to readme

* small typo fix

* Changes to support CI build

1) Setup.py can be run without cmake build
2) Wheel metadata can be set by environment variables
3) Cmake build uses configuration from .env file

* Removed unused file
2021-02-08 19:16:28 +03:00
Alexander Zhogovandrblaczko a3dc2649e2 Azure CI: Enable nGaph ONNX check (#2631)
* GitHub CI: Add nGraph ONNX check

* Fix job name

* Fix commands

* Enable nGraph Docker

* Fix

* Fix

* Fix

* Remove Actions

* Decrease a number of workers for executing models tests

* Enable "Docker run tests"

* Unset parallel execution

* Add cloning models

* Update model_zoo_preprocess.sh cmd

* Fix model_zoo_preprocess.sh cmd

* Add share

* ls -alR /mnt/onnxtestdata

* Change path

* move clone models

* Update script

* Add wget

* Update

* Update to master

* Update

* Update

* clone into tmp

* Enable clone

* Fix

* Use model_zoo_preprocess

* Add copy to share

* Enable tests

* Get MSFT

* Run tests

* Try 16 cores

* rub tests

* list models

* run tests

* Run tests, no --model_zoo_xfail

* Run tests, -n 8

* Run tests, -n 1

* Run tests, -n 4

* Run tests, -n 2

* Run with -n 1

* Update info

* First try to run onnx ci:
 * disable MSFT models for first try,
 * try to align onnx_models

* Enable steps

* Update cmake

* Add destination for cmake build

* Try to fix cmake build

* set ninja and instal dependencies

* Revert changes from Blaczkowski, Rafal

* Add swapfile 15 GB, run on AMD CPU 16 cores, 64 GB RAM

* Enable model_zoo_preprocess.sh

* Add reference-if-able

* Update

* test_zoo_models.py -n 8

* Fix clone

* Set LIN_VMSS_VENV_EPHEMERAL_WU2, F8s_v2

* git clone --single-branch

* test_zoo_models.py -n 6, D16as_v4

* -n 4

* clean

* -n 2

* -n 4, swap 48 GB

* E16ds_v4 (16-128), -n 8

* -n 8

* Set LIN_VMSS_VENV_ONNX_WU2

* -n 4

* del -n 16 for ut

Co-authored-by: rblaczko <rafal.blaczkowski@intel.com>
2021-02-05 17:48:16 +03:00
Tomasz Socha 65e2b4af3f [ONNX Importer] Switch to opset6 (#4112) 2021-02-05 11:15:13 +01:00
Tomasz Socha 937c332978 [ONNX][Tests][Python][Models] Increase tolerance for some models (#4150) 2021-02-04 15:54:11 +01:00
Maxim Vafin e80e5e7ae5 Add python API for MVN-6 (#3816)
* Add python api for MVN-6

* Fix code style

* Fix codestyle

* Apply feedback

* Fix test
2021-02-04 17:36:19 +03:00
iliya mironov 1419e05032 Add python api for CTCGreedyDecoder (#3947)
* Add python api for CTCGreedyDecoder

* Fix code style

* Fix unit test

* Fix code style

* Fix unit tests

* Fix python tests

* Fix python tests

* Fix python tests

* Fix according to code review

* fix

* Fix api

* fix unit tests

* Fix unit test

* Fix python api
2021-02-03 14:53:53 +03:00
Maxim Vafin 0b3ff5edc2 Add MO support for MVN-6 (#3772)
* Add MO support for MVN-6

* Apply review feedback

* Apply review feedback

* Enable MVN-6 decomposition

* Fix shape_infer issue

* Fix MVN6 decomposition

* Fix build

* Fix tests

* Small fix

* Add MVN-6 reader test

* Apply feedback

* Apply review feedback

* Fix onnx test failure
2021-02-02 17:45:56 +03:00
Michał Karzyński 3a86b3a17e Update ONNX dependency to v 1.8.1 (#4114) 2021-02-02 07:05:26 +03:00
Nikolay TyukaevandNikolay Tyukaev 0ecc360664 fix comments ngraph api - master (#3519)
* fix comments ngraph api

* remove whitespace

* fixes

Co-authored-by: Nikolay Tyukaev <ntyukaev_lo@jenkins.inn.intel.com>
2021-02-02 07:01:58 +03:00
Ilya Lavrenov 117c04def1 Fixed compilation of ngraph python on some compilers (#4015)
* Fixed compilation of ngraph python on some compilers

* Fixed ONNX importer dependencies compilation for gcc 5.4.0 and 5.5.0
2021-01-28 18:58:10 +03:00
Mateusz Bencer b90f908c58 Enable Bersquad-10 in ONNX CI (#3889) 2021-01-27 10:22:16 +01:00
Bartosz Sledz 247606baf6 Add support for nonconstant optional NMS-5 inputs (#3640) 2021-01-26 14:41:28 +01:00
Gorokhov Dmitriy d58b4c65c8 [CPU] Plugin migration on oneDNN (v1.6) (#3725) 2021-01-26 16:31:10 +03:00
dependabot[bot] c203e7e95f Bump tox from 3.20.1 to 3.21.2 in /ngraph/python (#4003) 2021-01-26 10:25:35 +01:00
Nikolay Shchegolev 245bc33e8a [CPU] GatherElements implementation. (#3860) 2021-01-26 09:53:20 +03:00