db527fff41
Fix performance on resnet50 quantized models ( #7670 )
...
* Fix performance on resnet50 quantized models
LP transformations won't work on the model unless the last 4 inputs to FakeQuantize
are constants. In order to meet that requirement, we need to perform constant folding
for those inputs in QuantizeLinear ONNX operator.
Ticket: 65375
* fix "Cannot find blob with name: y" exception during onnx_model_quant_conv_linear
* remove linking with onnx_ngraph_frontend
* fix exclude path
2021-10-13 10:18:37 +03:00
972524f1cc
Use runtime::Tensor instead of Blob in read_model ( #7951 )
...
* Use runtime::Tensor instead of Blob in read_model
* Fixed the memory ownership
2021-10-13 09:13:11 +03:00
4e2cc3e370
[GPU] Add GPU plugin metric to get statistics of GPU memory allocated by engine ( #7758 )
2021-10-13 05:40:51 +03:00
c323775f2c
Add input/output to ov ExecNetwork ( #7650 )
...
* Added template for new tests
* Fixed simple test
* Added output tests
* Removed get_result/get_parameter methods
* Fixed documentation
* Fixed functional tests
* Fixed caching tests
* Added new test for import
* Added new tests
* Fixed code style
* Fixed comments
* Fixed tests
* Fixed code style
* Save version in the function
Fixed pre-post processing
* Change IR version
* Fixed documentation
* Fixed MockICore
* HETERO almost works
* Fixed tests and core logic
* Disabled some CPU tests
* Tmp disable fp16 for template
* Fixed tests and clang-format
* Small fixes
* Fix
* Simplified code in templatePlugin
* Added IE precisions checks
* Simplified hetero plugin
* Added ieImportExportedFunction test
* Added MYRIAD test
* Skip tests directly in tests
* More correct filter for CPU
* Fixed CPU tests
* Template plugin tests
* Some comments
* FIxed clanf-format
* Removed myriad tests
* Fixed comment
* small changes
* Fixed condition
* Fixed unit tests
* clang-format
* Comment
* Hetero plugin update
* Fixed tests
* Moved re-create under ig
* Fixed clang-format
* Fixed some caching_tests
* Disable some caching_tests
* Fixed setLayout with dynamic case
* Fixed clang-format
* Disable execution graph
* Disabled one more CPU test
* Simplified regex
* Disabled GNA tests
Co-authored-by: y <ilya.lavrenov@intel.com>
2021-10-12 13:11:25 +03:00
a3a651ff97
[IE TESTS] Remove `functionRefs` from all tests and add it in necessary places ( #7873 )
...
* gna
* [IE TESTS] Remove functionRefs from some places
2021-10-08 00:29:00 +03:00
cfe18d289c
Scatter update ref impl revision ( #7476 )
...
* add template tests for scatter_update
* rm CT from ref impl
* fix namings
* minor code refactor
* fix style
* change ref impl
* add lambda func
* new tests
* remove CT from reference implementation, add template tests
* fix cpu IE
* refactor template tests
* split template tests
2021-10-07 14:40:15 +03:00
f856ac0203
[GNA] Added ConcatAlignFilter support for Accuracy Aware mode ( #7834 )
...
* Added ConcatAlignFilter support for Accuracy Aware mode
* fails after reviewing and added tests
* moved the test to gna/scale_factors_tests; added comments to test
2021-10-07 12:25:18 +03:00
d11ff04130
Update skip_tests_config.cpp ( #7874 )
2021-10-07 12:09:22 +03:00
4c80b110d0
[CPU] Deformable convolution improvements ( #7168 )
...
* jit impl. optimized
* reviewed
* reviewed
2021-10-07 11:31:08 +03:00
f57dc05c66
[OV20] Convert NV12 to RGB operation + preprocessing ( #7508 )
...
* # Conflicts:
# docs/template_plugin/tests/functional/op_reference/convert_color_nv12.cpp
# inference-engine/tests/functional/plugin/cpu/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp
# inference-engine/tests/functional/shared_test_classes/include/shared_test_classes/single_layer/convert_color_nv12.hpp
# inference-engine/tests/functional/shared_test_classes/src/single_layer/convert_color_nv12.cpp
# ngraph/core/include/openvino/core/preprocess/input_tensor_info.hpp
# ngraph/core/include/openvino/core/preprocess/preprocess_steps.hpp
# ngraph/core/include/openvino/op/nv12_to_bgr.hpp
# ngraph/core/include/openvino/op/nv12_to_rgb.hpp
# ngraph/core/src/op/nv12_to_bgr.cpp
# ngraph/core/src/op/nv12_to_rgb.cpp
# ngraph/core/src/preprocess/pre_post_process.cpp
# ngraph/core/src/preprocess/preprocess_steps_impl.hpp
# ngraph/test/CMakeLists.txt
* Added more test to cover 100% of code
Allow convert element type for 'multi-plane' color format
* Inherit tensor names for 'convert_color'
* Clang
* Fix tests
* Disable 'int8' preprocessing resize test
* Fix review comments
* Add more restrictions and tests for planes sub-names
* 1) Added check for uniqueness of tensor names generated for nodes
Raise error if user's plane sub-name conflicts with some node in a function
2) Added exception safety to preprocess build. Before, when input #2 fail, only one preprocess will be applied to function and it will be corrupted
Exception guard will restore function to original state if exception occurs
* Fix clang-format
2021-10-06 15:22:05 +03:00
3455dd973f
[CPU] Replace sgemm with MatMul primitive ( #6785 )
2021-10-06 09:57:57 +03:00
acb6aa01ab
Added reporting of unresolved symbols for plugins ( #7810 )
...
* Added reporting of unresolved symbols for plugins
* Added HDDL dependency
* Removed cross-compilation if
* Revert "Removed cross-compilation if"
This reverts commit da644a3afe
2021-10-05 04:26:01 +03:00
bd2b346c62
[IE Tests] Aplly some comments for dynamic shapes ( #7829 )
...
* [IE Tests] Aplly some comments for dynamic shapes
* fix tss
* fix postfix
* remove cout
* Fix crash
* fix ci
2021-10-05 02:40:21 +03:00
0bebd53b4a
Inference chaining: static and dynamic cases ( #7776 )
...
* Fixed precisions conversion in new API
* Added tests
* Fixed old IR cases
* Disable FP16
* Fixed regex for CentoOS
* Refactored tests to use new API
* Temp
* Fixed tests
* Moved smart reshape related sources to ngraph
* Added tests for invalid names
* Moved reshape to tensor_names
* clang-format
* Fixed CC build
* Removed IEConv, IEDeconv from primitives pririty
* Added tests for Inference chaining
* Fixed dynamic chaining for template plugin
* Added test for 2 conflicting names for the single parameter
* Removed invalid test
* Added more tests for dynamism
* Fixed clang-format
* Fixed macosx compilation
* Some simplifications
2021-10-04 14:51:14 +03:00
996b15ccf2
[IE TEST] Enable support of Dynamic shapes in IE TEST infra with examples ( #7718 )
...
* Squashed commit of the following:
commit 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
2021-10-04 14:34:50 +03:00
056515e735
Fixed CVS-66710 ( #7805 )
2021-10-01 22:54:06 +03:00
7fd0b9be48
Exclude sporadic CPU canRun3SyncRequestsConsistentlyFromThreads ( #7706 )
...
* Exclude sporadic CPU canRun3SyncRequestsConsistentlyFromThreads
* Update skip_tests_config.cpp
* Fix lint
2021-10-01 12:37:51 +03:00
faeaf045a9
Graph comparator to ngraph util ( #7729 )
...
* Moved FrameworkNode to nGraph
* Moved graph comparator to ngraph test util
* Fixed build
* Try to fix centos
* Fix export target
* Moved engine utils to separate library
* Removed ONNX util from common library
* Fixed build
* Fixed code style
2021-10-01 07:24:28 +03:00
302eb08dc5
Replaced gtest deprecated macro ( #7779 )
2021-10-01 03:46:32 +03:00
6e05cead11
[OV20] Reference implementation for NV12toRGB and NV12toBGR operations ( #7601 )
...
* Reference implementation for NV12toRGB and NV12toBGR operations
Tests:
- ngraph: visitor + type_prop
- template plugin: reference implementation
- inference-engine: shared tests for plugins
- cpu plugin: compare with ref implementation tests
* Fix clang
* Serialization tests
* Fix clang-format
* Changed 'f32' to 'any supported floating-point type'
Added appropriate shape inference tests
Added error test for >2 inputs
Fixed failed CI tests
* Updates after rebase
+ Try to fix Ninja build
* Fix CI
* Support endianness + potential fix of win32 test fails
* Fix review comment
* Fix review comments
* Fix unit test build
* Fix unit test build #2
* Possible build fix 3
* Simplified reference tests
Observed issue with shuffling Y pixels on little-endian systems, added tests
2021-09-30 16:34:46 +03:00
fab4056ceb
Fixed callback copy count ( #6607 )
2021-09-30 15:09:47 +03:00
757db35528
Dynamism in new API ( #7742 )
...
* Fixed precisions conversion in new API
* Added tests
* Fixed old IR cases
* Disable FP16
* Fixed regex for CentoOS
* Refactored tests to use new API
* Temp
* Fixed tests
* Moved smart reshape related sources to ngraph
* Added tests for invalid names
* Moved reshape to tensor_names
* clang-format
* Fixed CC build
* Removed IEConv, IEDeconv from primitives pririty
2021-09-30 15:04:24 +03:00
414c3dc133
[OV2.0] Preprocessing - resize ( #7583 )
...
* Initial version
* Added 'network' layout to preprocessing info
Moved existing resize tests to template plugin
* Fix clang
* More tests for 'resize' reference implementation + CPU tests + error cases
Coverage is 100%
* Align with new base_reference_test implementation
* Fixed comments
* Add assert to check that desired size is not out of bounds
* CPU: skip failed test
2021-09-30 11:41:25 +03:00
4bf8d15793
Import/Export tests enabled for the CPU plugin ( #7735 )
2021-09-30 09:11:01 +03:00
1f5355cd07
Enabled several CPU tests ( #7724 )
2021-09-29 20:51:23 +03:00
4fd59f72ea
Use 'u8' element type in tests ( #7704 )
...
Use 'float32' output for 'compare with reference' tests to avoid IE precisions undesired conversions
Added GPU preprocessing tests skeleton
2021-09-29 09:46:37 +03:00
bd09f70876
Fixed precisions conversion in new API with compile_model(filename) ( #7711 )
...
* Fixed precisions conversion in new API
* Added tests
* Fixed old IR cases
* Disable FP16
2021-09-29 07:00:13 +03:00
a3dfa980ad
[GNA] Improved accuracy on model after Accuracy Aware ( #7576 )
...
* improved accuracy on model after Accuracy Aware
* refactoring+test
* removed unnessary FakeQuantI8/I16
* added comments, moved fake_quantized from UpdateInputScaleFromNetwork(), removed _Np template param from QuantDescTmpl
2021-09-28 11:34:09 +03:00
204c17cc21
Enable SoftmaxFusion inside MOC Transformations pipeline ( #7684 )
...
* Enable SoftmaxFusion inside MOC Transformations pipeline
* Disable SoftmaxDecomposition by default
2021-09-28 10:46:31 +03:00
818f385398
[IE TESTS] Add example for QueryNetwork in SLT ( #7628 )
...
* [IE TESTS] Add example for QueryNetwork in SLT
* Update mul_conv_fusion.cpp
* Skip
* skip[
2021-09-27 11:22:38 +03:00
8262aed30c
Migrate ngraph backend test of arithmetic2 operations ( #7500 )
...
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now
* update repo
* add sin asin template plugin reference test
* add cos template plugin reference test and remove asin/sin/cos ngraph backend test
* update CMakeList.txt
* add template plugin reference test for asinh, cosh, sinh, tanh
* remove ngraph backend test for asinh, cosh, sinh, tanh
* update CMakeList.txt
* add ngraph type prop test for tanh
* add ngraph visitor api test for asin, sin
* add atanh type in activation SLT
* remove boolean from sin/cos/tan/asin/sinh/cosh evaluate
2021-09-27 05:23:52 +03:00
b968c7b813
AutoPlugin: support performance Hint ( #7621 )
...
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
2021-09-25 12:30:21 +03:00
3eb1aa59de
[MULTI] Fixed devices comparison to respect default device id ( #7311 )
...
* [GPU] Fixed default device id
* [MULTI] Fixed devices comparison to respect default device id
2021-09-24 12:32:38 +03:00
f202c45c46
[IE TESTS] Move locale test to shared folder ( #7605 )
2021-09-24 10:27:07 +03:00
f2dda1bbca
Added new tests that config set via ie.SetConfig or LoadNetwork is returned via exe_net.GetConfig and align plugin impl to that ( #7627 )
2021-09-24 10:03:24 +03:00
f8f6e57c39
[CPU] Fix for Int8 models serialization issues ( #7554 )
2021-09-24 09:24:35 +03:00
6159a5b0bc
New ov::Function API ( #7436 )
...
* Generates tensor names
* Implement function helpers for Inputs/Outputs
* Fixed code style
* Share result tensor and add more tests
* Avoid not unique tensor names
* Print tensor name
* Fixed comment
* Fixed matmul transformation
* Fixed function evaluate
* Fixed typo
* Fixed interpreter backend
* Fixed comments
* Removed tensor names check
* Disabled negative tests
* Fixed NetworkContext_CNNNetwork tests
* Fixed GNA tests
* Remove reset names
* Fixed code style
* Temporary disable names generation
* Revert "Temporary disable names generation"
This reverts commit 133315a611
2021-09-24 07:11:02 +03:00
531118c4b0
OV2.0 Preprocessing shared tests - initial version ( #7568 )
...
* Shared preprocessing tests for plugins.
Comparing inference with reference implementation
* Moved evaluate tests to template plugin
* Fixed clang-style
* CPU tests: Set IE precision manually in SetUp. Also allow rounding to integer mismatch
* Added acceptable threshold depending on particular test
2021-09-23 23:17:59 +03:00
634759210f
Introduced OpenVINO RTTI and add version string to operations ( #7288 )
...
* Introduced OpenVINO RTTI and add version string to operations
* Fixed build
* Try to fix build
* Removed get_type_info_static
* Fixed tests
* Moved ov operations to new macros
* Fixed type_info_static
* Introduce new header only declaration
* Deprecate type_info static member
* Introduced OPENVINO_OPERATION macro
* Fixed ngraph lib with new RTTI
* Fixed unit tests
* Fixed code style
* Fixed VPU common
* Fixed all target for macOS
* Changed macto to OPENVINO_OP
* Changed cldnn
* Fixed typo
* Fixed some unit tests with old operations
* Fixed DiscreteTypeInfo
* Fixed type relaxed operations
* Fixed legacy tests
* Fixed naming style
* Fixed cpuTests
* Disabled deprecation to pass CI
* Added compatibility to internal operations
* Added BWDCMP for internal ops
* Deprecate type_info
* Fixed Slice RTTI
* Fixed Myriad
* Applied patch from PR 7573
2021-09-23 13:29:39 +03:00
ab34701590
Added OpenVINO runtime macro ( #7586 )
...
* Fixed typo
* Moved ie::Parameter to new API
* New OpenVINO API macro
* Used OpenVINO Plugin API for some plugins
* Used OPENVINO_RUNTIME_API
* Revert "Moved ie::Parameter to new API"
This reverts commit fef5e3b487
2021-09-23 10:39:20 +03:00
538d492a70
Removed dependencies scripts ( #7569 )
2021-09-22 12:17:41 +03:00
f5e7c9646d
[IE TESTS] Separate conformance tests to 3 targets: op_conformance, api_conformace and conformance_infra ( #7503 )
...
* [IE TESTS] Separate conformance tests to 3 targets: op_conformance, api_conformace and conformance_infra
* Small fixes
* small fix
* try fix ci
2021-09-22 11:00:37 +03:00
c29edb1f4e
remove deprecated test classes ( #7390 )
2021-09-21 15:15:48 +03:00
db385569c2
Throw ov::Exception from ov::runtime ( #7536 )
...
* Exceptions
* Throw ov::Exception from ov::runtime
* code style
* Fixed function name
2021-09-21 14:26:01 +03:00
2349caa482
[GNA] Plugin transition to the library v3.0 Master ( #7386 )
...
* GNA Plugin transition to the library v3.0 Master
* [GNA] Enable 2D convolution decomposition on GNA 3.0
* [GNA] Fix cpplint
* [GNA] Fix cpplint
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
2021-09-21 10:59:35 +03:00
fadb768fcd
[LPT] INT16, INT32 Quantization support ( #7199 )
...
* [LPT] INT16, INT32 Quantization support
* [LPT] Support build on platforms with size_t == unsigned int
* [LPT] Test and fix wrong constant
* Fix build for size_t = unsigned int
2021-09-21 10:00:35 +03:00
07d9b51121
Replace IR Reader With IR Frontend ( #7249 )
...
* Replace IR Reader With IR Frontend
2021-09-20 23:17:22 +03:00
55fb542bc6
Added OpenVINO util library ( #7481 )
...
* Added OpenVINO util library
* Fixed code style
* Fixed build
* Fixed build
* Added methods from IE utils
* Fixed style
* Fixed Windows build
* Fixed linux build
* Fixed windows build
* Try to fix dladdr
* Try to fix windows
* Fixed typo
* Fixed detection dynamic libs from static library
* Revert some changes
* Revert changes in windows loader
* Revert network reader
* Removed some methods from plugin API
* Fixed fluid tests
* Fixed typo
* Fixed include
* Try to fix CI
* Try to fix centos
* fix typo
2021-09-20 18:37:32 +03:00
660c106233
[GPU] Performance counters fix ( #7143 )
2021-09-17 13:12:25 +03:00
ac8db25864
Enable CPU accelerate FIL in MULTI ( #7380 )
...
* Enable CPU accelerate FIL in MULTI
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add configure to device
KEY_PERFORMANCE_HINT_NUM_REQUESTS
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
2021-09-17 11:17:54 +03:00
Mateusz Tabaka