Commit Graph

9400 Commits

Author SHA1 Message Date
Eddy Kim
879a7de889
Update calculateFileInfo for the null string case (#15064)
* updated not to find absPath for null filePath

* changed to cache only std::runtime_error

* fix clang-format error
2023-01-13 17:47:25 +04:00
Ilya Churaev
2d9a51fa6a
Move CoreImpl to separate file (#15088)
* Move CoreImpl to separate file

* Added new files

* Small fixes

* Moved ov::Core

* Fixed typo

* Moved DeviceIDParser

* Try to fix build
2023-01-13 17:10:09 +04:00
Yuan Xu
1ea2d679df
fix step5 (#15065) (#15091) 2023-01-13 19:00:07 +08:00
Przemyslaw Wysocki
cfac7e4ee4
[PyOV] Update requirements for Python 3.11 (#15072)
* Update reqs

* update license whitelist

* Revert gast

* Bump distro package
2023-01-13 14:49:55 +04:00
Ruslan Nugmanov
4601b31bd0
Keras to tflite version of tests (#15042)
* keras to tflite version of tests

* Update tests/layer_tests/common/tf2_layer_test_class.py

Co-authored-by: Evgenya Stepyreva <eva.my.link@gmail.com>

* moved out tf utility functions from modules with tf_layer_test classes to tf_utils module

* moved out tf utility functions from modules with tf_layer_test classes to tf_utils module and tflite_utils modules

Co-authored-by: Evgenya Stepyreva <eva.my.link@gmail.com>
2023-01-13 10:29:50 +00:00
Vladimir Dudnik
9fe4db56fe
[GPU] fix gpu tests --help and memory leak (#15055) 2023-01-13 14:00:43 +04:00
Vitaliy Urusovskij
32e74f339e
RGB to Gray ConvertColor Preprocessor (#13855)
* Add RGB to Gray ConvertColor Preprocessor

* Revert some changes

* Additional updates

* Polish RGBToGray implementation

Move Conv computations to FP32 and add Round for INT cases

* Extend tests - add comparison with OpenCV

* ClangFormat

* Return commented code

* Make `pre_post_process` tests parametrized

* Add shape calculation for RGB ColorFormat. Make RGB->GRAY 4D only

* Update ov_core_unit_tests

* Update ov_template_func_tests

* Clang Formatting

* Fix python preprocess tests

* Fix warning: truncation from 'double' to 'float'
of RGB->GRAY weights

* Fix flake8 issues

* Fix `convert_color_asserts` test

* Treat GRAY as NHWC

* Resolve review issues with tests

* Fix Py preprocess tests after rebase

* Clang Format

* Add case if C < 0

* Add reference link to RGB coefficients

* Add doxygen documentation for ColorFormat enum
2023-01-13 13:50:30 +04:00
Alexander Kozlov
ded9156b98
Added ignored pattern for Stable Diffusion Unet (#14925) 2023-01-13 12:51:27 +04:00
Oleg Pipikin
529f714830
Enable Werror for inference tests (#14614)
* Disable warnings suppression in inference tests

* Fix warnings for ov_inference_unit_tests

* Disable warnings suppression for msvc

* Fix warnings for ov_inference_functional_tests

* Fix warnings for Windows

* Fix comments

* Fix new warning

* Fix 3

* Fix 4
2023-01-13 12:48:32 +04:00
Oleg Pipikin
0ba3a97277
Use unique file names in tests (#15014)
* Add common test api to generate unique test file names

* Use unique file names in ir frontend tests

* Use unique file names in plugin tests

* Fix code style

* fix1

* fix2

* Add unique file names for other tests

* Fix code style 2

* fix3
2023-01-13 12:35:30 +04:00
guozhong wang
9dd08cd929
AUTO CTPUT single device always goes single device logic (#14425)
* AUTO CTPUT single device always goes single device logic

* CreateInferRequest goes single device logic when perf hint is ctput

* Optimize single device logic according to bell opinion

* Add code comments

* merge two isCumulative conditions

* add ctput test case

* Remove the redundant header file of auto_ctput_test.cpp

* Modify the test case according to bell comments
2023-01-13 10:29:44 +08:00
Sebastian Golebiewski
04720f0453
Update installing-openvino-apt.md (#15079)
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2023-01-13 08:51:43 +08:00
Luis Avitia
a6e7cdc895
Update layer limitations for VPU (#13995)
* Update layer limitations

Update layer limitations in Known Layers Limitations document. 
Add "Floor", "ConvTranspose" and "GatherElements" in Known Layers Limitations section. 

Tickets:
CVS-88871 - Floor op
CVS-75208 - ConvTranspose op
CVS-88690 - GatherElements op

* Update docs/OV_Runtime_UG/supported_plugins/VPU.md

* Update docs/OV_Runtime_UG/supported_plugins/VPU.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2023-01-13 08:51:08 +08:00
Luis Avitia
d87989cd2c
Update VPU plugins layer support (#13997)
Update support "Sign" layer to not supported. 
Update support "Floor" layer to limited support.
2023-01-13 07:56:55 +08:00
Jan Iwaszkiewicz
45934143e5
[PyOV] Add new types to Any dispatcher (#15052) 2023-01-12 22:43:22 +01:00
Pavel Esir
9e3b52eee0
remove deprecated cli arguments from MO (#14937)
* removed deprecated cli arguments from MO

* removed deprecated options from docs

* Update tools/legacy/benchmark_app/README.md

* removed ConcatOptimization.py, removed deprecated args from unit-tests, renamed tensorflow_use_custom_operations_config -> transformations_config; replaced using or cmd_params.data_type -> cmd_params.compress_to_fp16

* added comment why we set internal 'data_type' always to 'FP32' after introducing 'compress_to_fp16'

* removed openvino_docs_MO_DG_prepare_model_Model_Optimization_Techniques from MO_DevGuide

* returned back --data_type argument

* leftovers from recovering

* returned back to package_BOM.txt; fixed NHWC by default for TF

* recovered --disable_nhwc_to_nchw to MO args

* reverted removing --tensorflow_use_custom_operations_config

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-01-12 21:12:56 +00:00
Alina Kladieva
7bb1933649
Disable IB in Win Azure pipeline (#15086) 2023-01-12 12:44:00 -08:00
Taylor Yeonbok Lee
33b2e72048
Fix cl source dump file name not to be overwritten (#15035) 2023-01-12 09:27:57 -08:00
Julio Morero
ee58a7aa38
Change device order in MULTI python snippet (#15057) 2023-01-12 20:27:58 +04:00
Shen, Wanglei
413a461be4
Create README.md for AUTO plugin (#14861)
* Create README.md for AUTO plugin

* link to contribuation guidance

* Update README.md according to developer documentation guidance

* Update for comments

* Update components for review comments

* Update folder for review comments

* update for wording

* update for comments
2023-01-12 23:03:45 +08:00
Evgeny Kotov
78995e9ac2
Transpose sinking binary/split/concat mult consumers case + PRelu (#14670)
* binary: move test classes into namespaces

* add unsing namespacees ov and ov::opset9

* ov::Model -> Model

* use naming for unit tests

* fix unary -> binary

* fix identation

* add tests binary forward consumers > 1

* add binary output consumers > 1 unit tests

* add binary input consumers > 1 unit tests

* binary backward add unit test binary has multiple consumers + fix

* move code to common function CloneNodeWithoutConsumers

* add unit test on backward binary propagation multi consumers

* reorganize binary unit tests

* add backward_input_node_consumers test

* add test output transpose mult consumers

* cleanup

* cleanup unit tests for split

* add forward::mult_consumers::input_node_consumers tests

* add forward::mult_consumers::input_transpose_consumers tests

* add forward::mult_consumers::output_consumers tests

* code indentation fix

* fix unit test split backward input node consumers

* added mult_output_consumers split unit test

* add mult_split_consumers split unit test

* cancat tests using namespaces

* concat add unit tests

* move repeated code into functions

* clang format fixes

* rename TransposeSinkingBinaryElementwise -> TransposeSinkingBinary

* add PRelu

* clang cleanup

* fix prelu tests

* fix using

* clang fixes

* fix NodeVector argument

* fix function descriptions

* fix const ref arg functions

* clang fixes

* prevent backward sinking if not all output nodes are transposes

* fix RemoveSingleOutputConsumers checking output size

* cleanup

* clang cleanup

* disable unary backward with not same transposes

* clang fixes

* remove unneeded functions CloneNodeWithoutConsumers GetNodeIds

* remove unneeded GetTransposeConstant(Input<Node> input) as duplicate of GetTransposeConstant(Node* node)

* cleanup

* add output_transpose_mult_transposes test

* add backward::output_transpose_mult_transposes test

* add unit tests for unary backward multiple transposes; fix problems by adding new transformation

* fix bug TransposeSinkingUnaryBackwardMultiConsumers consumers_more_than
2023-01-12 17:42:46 +03:00
Anastasia Kuporosova
9388560aec
[PyOV][Tests] Fix some tests for M1 (#14555) 2023-01-12 13:51:22 +01:00
Roman Kazantsev
40627c99f5
Fix build for macos and android-arm64 (#15068)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-01-12 15:40:11 +04:00
Liubov Talamanova
b8d51a9e1b
[POT] Add transformer block pattern (#15044) 2023-01-12 15:37:21 +04:00
Sofya Balandina
051597cf2c
[apiConformancForce] creating plugin before setting properties (#14856) 2023-01-12 14:57:22 +04:00
Vitaliy Urusovskij
b4faeebc84
Align RegisterPluginsInRegistry() with RegisterPluginByName() (#15026)
* Align `RegisterPluginsInRegistry()` with `RegisterPluginByName()`

* Add gmock dependency to commonTestUtils

If use macros like OV_EXPECT_THROW, it requires target to be linked
with `gmock`. So add the dependency directly to commonTestUtils

* Add `ThrowOnRegisterPlugin(s)Twice` tests

* ClangFormat
2023-01-12 14:45:36 +04:00
Vladimir Paramuzov
9c7beee5e5
[GPU] Added missing supports_image initialization in EngineInfo. Fix some kernels with image support (#14885) 2023-01-12 12:06:01 +03:00
Ryszard Jezierski
974af13788
[GNA] Add missing metrics to GNAExecutableNetwork (#14680)
* Added NETWORK_NAME, SUPPORTED_CONFIG_KEYS and SUPPORTED_METRICS metrics to GNAExecutableNetwork

* Added unit tests for GNAExecutableNetwork metrics

* Moved model name from GNAExecutableNetwork to GNAPlugin
2023-01-12 09:05:01 +00:00
Oleg Pipikin
d75d5f99ec
Remove ieTests (#14790)
* move cpp_interfaces tests from ieUnitTests to ov_inference_unit_tests

* Fix code style

* Remove ieFuncTests and ieUnitTests

* Remove ieTests from Azure CI
2023-01-12 10:00:08 +01:00
Sebastian Golebiewski
b492eda96a
DOCS: Fixing formatting in 'Install From Apt' article (#15062)
* fixing-formatting-apt

Fixing indentation, faulty code-blocks, numbering.

* fix link

* Update docs/install_guides/installing-openvino-apt.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

* fix link

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2023-01-12 15:54:33 +08:00
Anastasiya(Asya) Pronina
e27c4b0b18
Fixed possible overflows to clean KW scan (#15034) 2023-01-12 11:33:43 +04:00
Andrew Kwangwoong Park
9d574e6041
Fix strided slice for clamped out-of-bounds begin/end with negative stride (#15059)
Signed-off-by: Andrew Park <andrew.park@intel.com>

Signed-off-by: Andrew Park <andrew.park@intel.com>
2023-01-12 07:09:25 +00:00
Wang, Yang
4ddb000c8e
[AUTO] Correct the logic of setting default hint for AUTO. (#14927)
* Correct the logic of setting default hint for AUTO.

* Update.
2023-01-12 14:55:29 +08:00
Eddy Kim
534905fd2d
ImportNetworkThrows case is removed (#15000) 2023-01-11 20:25:42 -08:00
Przemyslaw Wysocki
573a7fb6b5
Disable GitHub Action setupPython in android-arm64 job (#15053)
* Revert arm64

* minor change
2023-01-12 03:12:13 +04:00
Roman Kazantsev
01932428b8
[TF FE] Support While and StatelessWhile operations (#15043)
* [TF FE] Support While and Stateless While operations

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

* Reimplement setting outputs

* Apply code-review: while input number and copy-rights

* Apply code review feedback: correct template and fix typo

* Apply code-review feedback: more strict checks in reorder_ops_by_names

* Specify type for the generated test data

* Minor change to re-run CI

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-01-11 21:51:56 +00:00
Georgy Krivoruchko
0e99a5c44a
Added TF Deconvolution layer tests (#14906)
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-01-11 21:34:08 +00:00
Przemyslaw Wysocki
21267269da
Use Python 3.10 on Azure from GitHub actions (#13550)
* Merge master, use new token

* Minor changes

* Relax Python version

* Apply new python to rest of jobs

* Revert changes to custom images

* Minor changes

* Revert win changes

* Upgrade cython

* Test with lower cython

* Remove venv

* Cleanup

* Relax version spec

* Fix lin

* Revert changes to linux.yml

* Minor changes
2023-01-11 17:46:24 +04:00
Nadezhda Ageeva
a8a59f3cb4
[HETERO] Remove WA for Parameters, Results and Constants. (#15020)
* [HETERO] Remove WA for Parameters, Results and Constants.

* Update HeteroSyntheticTest
2023-01-11 17:45:56 +04:00
Mateusz Bencer
26934332cd
[ONNX FE] Added tutorials about running tests, architecture and adding new ops (#14807) 2023-01-11 12:08:45 +00:00
Vladimir Paramuzov
4feaeaad68
[GPU] Remote context reuse and internal config update (#14635) 2023-01-11 11:14:03 +00:00
Ivan Novoselov
1d59a5a29b
Common test infrastructure suggestions (#14343)
* Common test infrastructure: test helper for partial shapes, data generation fix

* Overload static_shapes_to_test_representation to accept PartialShape vector

* Rename to static_partial_shapes_to_test_representation
2023-01-11 10:50:39 +00:00
Mateusz Tabaka
7fad6f9b29
Fix node names sorting in graph comparator (#14813)
Since Results are sorted by node name it may happen that, e.g
Result with name node_10 is before Result with name node_9,
while we want the opposite.
2023-01-11 11:35:56 +01:00
Mikhail Ryzhov
e811210f33
[GNA] Changed max layer limit tests to avoid SEH exceptions (#15015)
* splitted test model

* Changed test config

* Set SF for all inputs
2023-01-11 13:05:52 +03:00
Anastasiya(Asya) Pronina
358d3a7740
Extended speech_sample to work on VPUX (#14509)
* Extended speech_sample to work on VPUX

* Fixed review comments

* Returned whitespace back
2023-01-11 12:46:08 +04:00
Piotr Krzemiński
f4ff1cbdf3
[BENCHMARK_APP] Align pc reports, revert format print to previous, excel friendly (#14644)
* [Python] Align pc output in Python benchmark, update sorted output to new headers, print floats with 6-digit precision, fix date format printing to excel-friendly

* [PYTHON/C++] Change precision of raports and pc counters report, simplify code

* [C++] Align C++ benchamrk_app report to Python's by setting the precision value to 3

* [C++] Fix CsvDumper precision

* [C++/PYTHON] Align pcand pcsort outputs, merge C++ printSort methods into one

* Update samples/cpp/common/utils/include/samples/common.hpp

Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>

* Update samples/cpp/common/utils/include/samples/common.hpp

Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
2023-01-11 12:38:37 +04:00
Vitaliy Urusovskij
c7a1468fb7
Add support of f64/i64 for tests/ (#15029) 2023-01-11 12:17:47 +04:00
Steve Yoo
2e10a1cb13
Added trucation mode to reorder for convert (#14090)
* Apply convert trucation

* Added trucation mode to reorder for convert

* Added unittest

* convert_long not casting
2023-01-10 22:46:15 -08:00
River Li
8c84faeecd
Add ov::loaded_from_cache checking for CompileModelLoadFromMemoryTest (#15030)
* Add ov::loaded_from_cache checking for CompileModelLoadFromMemoryTestBase

* Skip gna in skip_tests_config
2023-01-11 09:45:11 +03:00
Andrew Kwangwoong Park
e0359d3085
[GPU] Enable Deconv/GroupDeconv shape infer (#15005)
* Update deconv primitive APIs for dilations and output_padding

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add calc_output_layouts for deconv

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add deconv shape inference TCs for ov_gpu_unit_tests

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add deconv dynamic TCs for ov_gpu_func_tests

- Disable pre_replace_deconv for dynamic shape
- Update get_expected_layout for deconv_node during reorder_input
- Add I/O swap of weights for shape infernece

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add group deconv dynamic TCs for ov_gpu_func_tests

- Update op creation for group deconv

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Fix clang-format

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Update test params with swapped I/O dimensions for ov_gpu_unit_tests

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Update for optional output_shape const/param input support

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Update deconv/group deconv dynamic TCs w/ output_shape for ov_gpu_func_tests

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Update deconv/group deconv shape inference TCs w/ output_shape for ov_gpu_unit_tests

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Apply code review

Signed-off-by: Andrew Park <andrew.park@intel.com>

Signed-off-by: Andrew Park <andrew.park@intel.com>
2023-01-10 22:09:47 -08:00