Kelvin Choi
2d996c1354
[GPU] Update GatherND primitive ( #8813 )
...
* Cldnn output memory size at GatherND functional-test is aligned with TensorDesc of output blob
* Add param for rank of input data
* Update unittests to add rank of input data
* Update gpu fusing tests
2021-11-29 11:51:19 +03:00
Yuan Hu
d50f20b977
Add log utils for Auto plugin ( #8309 )
...
* add log utils
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* optimize
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* remove env support in log util
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add IE LOG CONFIG support in auto model
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* Add LOG
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix compile error
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add test
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix set config error
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix code error
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add more log and support no arguments format string
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix some review issue
change name from HDEBUG to LOG_DEBUG and so on
remove redundance code
move log config into log util
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* modify log hpp name
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* try to fix macos support issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* enable env AUTO_LOG_LEVEL
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add comment for WaitActualNetworkReady()
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add error log when all device failed
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix rebase issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix add log in code cause auto_select_device_failed_test failed issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add test code
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* change the Name from AUOT_LOG_LEVEL to OPENVINO_LOG_LEVEL
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* use just GLOB_SOURCES in cmake
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add singleton test
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* try to fix macos compile issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* move printing config info to async loading
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* keep CheckConfig as origin code
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix compile issue caused by icore->GetMetric API change
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* use confMutex instead of a new mutex
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* try to fix windows compile issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
2021-11-29 16:41:48 +08:00
Elizaveta Lobanova
b10409da5b
[GNA] Support NHWC convolutions with 3d transposes ( #8599 )
...
* [GNA] Support NHWC convolutions with 3d transposes
* [GNA] Removed calculation of permutations for unsupported layouts
* [GNA] Added comments
2021-11-29 10:55:31 +03:00
Chen Xu
f38fa4d845
[CPU] Reduce node dynamism support + perf optimizations ( #8555 )
...
* Reduce node feature extension
* Reduce node dynamism support
2021-11-29 10:28:11 +03:00
Ilya Churaev
a148e126b8
Fixed coverage paths ( #8873 )
2021-11-29 09:38:06 +03:00
Bo Liu
25b2131d21
priorbox_8 ngraph and inference-engine parts ( #8114 )
...
* ngraph and inference-engine parts
* add priorbox_8 python api
* remove 'PriorBoxAttrs' and 'PriorBox' from outside of opset namespace
* add common nGraph transformation 'ConvertPriorBox8To0'
* remove redundant alias of PriorBox::Attributes
* use new Tensor api for evaluate method
* change v0operation back to the former api, pass Attribute structure to the reference implement
* use new Tensor api for constant_fold
* add support for dynamic shapes of constant_fold new Tensor api
* fix Node 'create temp tensors' issue when shape==0'
* revert to 'HostTensor' api for PriorBox8
* Apply suggestions from code review and 'template_plugin reference' testcase replaced 'backend INTERPRETER' testcase
* transformation part Apply suggestions from code review
* python init file updated for opset8
* keep backward compatibility to fix CI issue
* rebase to new structure of OpenVINO repo
* revert 'thirdparty/onednn_gpu' mistake changes
2021-11-29 07:28:49 +03:00
Ilya Churaev
07651aa5c0
Fixed some inference-engine paths ( #8878 )
2021-11-29 07:17:36 +03:00
Sergey Shlyapnikov
497aaf9b46
[GPU] Relax batch size limitaions for DO GPU implementation usage for some of Gen12HP dGPUs ( #8801 )
2021-11-29 11:41:39 +09:00
Ilya Churaev
a09f4ded79
Fixed codeowners ( #8875 )
2021-11-29 01:15:56 +03:00
Ilya Lavrenov
c02fe4b813
Static OpenVINO frontends ( #8868 )
...
* Static OpenVINO frontends
* ONNX tests with shared extension CustomOpUser_ONNXImporter
* Resolved issues with ONNX's NCC style check
* Reverted openvino => ngraph for frontend includes install
* Try to fix ONNX / Protobuf
* Try to fix CI
* Try
* Fixed cmake stage with BUILD_SHARED_LIBS
* Fixed export for linkable frontends
* Fixed warnings on Linux
* Fixed after ngraph => src
2021-11-28 21:36:24 +03:00
Mang Guo
cf3c9ae04b
[CPU]Adaptive pooling dynamic shape support ( #8703 )
2021-11-28 17:45:29 +03:00
Chenhu Wang
7edcf47454
[CPU] CTCLoss dynamism support ( #8777 )
2021-11-28 17:44:07 +03:00
Ilya Churaev
77f6a0076b
Move core components ( #8869 )
...
* Moved openvino to src
* Moved ngraph and frontends to src
* Fixed cmake generation
* Moved inference_engine libs to src
* Moved C API to src
* Fixed CMake generation
* Moved readers to tests, snippets and preprocessing to common
* Fixed CMake
* Moved transformations and lp_transformations
* Fixed transformations cmake
* Fixed build
* Fixed unit-tests and ci paths
* Fixed docs
* Fixed C API build
* Try to fix static build
* More clear order
* Renamed inference_engine_legacy_api to legacy
* Fixed some cmake scripts
* Fixed path to legacy
* Fixed Myriad plugin
* Fixed v7 reader
* Fixed plugin.hpp
* Fixed developer config
* Fixed ie_parallel
2021-11-27 18:53:12 +03:00
Ilya Churaev
9b3e12006f
Fixed error: expression result unused ( #8862 )
2021-11-27 15:54:35 +03:00
Sergey Shlyapnikov
e76fc14ae1
[GPU] Use b_fs_yx_fsv16 format for OneDNN convolutins in case of FP32 output ( #8808 )
2021-11-27 15:08:06 +03:00
Vladimir Paramuzov
ab3a892d48
[GPU] Fixed typo in cache.json ( #8756 )
2021-11-27 15:06:54 +03:00
Ilya Lavrenov
5719192687
Use ninja multi-config ( #8757 )
...
* Use ninja multu-config
* Reused OV_GENERATOR_MULTI_CONFIG
* Try to use config in api_validator post build task
* Fixes
* Revert "[GPU] Fix multi configuration build of onednn_gpu (#8743 )"
This reverts commit a862331732
2021-11-27 14:58:24 +03:00
Ilya Churaev
b1fba3a675
Rename runtime to src ( #8842 )
...
* Renamed runtime to src
* Removed old paths
* Fixed cmake
* Fixed doc
2021-11-27 11:28:25 +03:00
Ilya Churaev
7cb378c92b
Changed add_output API ( #8833 )
...
* Changed add_output API
* Added C++ tests
* Added bython tests
* Try to fix python tests
* Fixed python tests
* Try to fix build
* Cannot compare pointers
2021-11-27 11:08:48 +03:00
Ilya Churaev
909dea8b5d
Removed preprocessor library ( #8845 )
2021-11-27 10:06:25 +03:00
Ilya Churaev
5e91ef4640
Fixed error message for unrecognized attribute ( #8815 )
2021-11-27 07:34:38 +03:00
Gorokhov Dmitriy
1cc9ca481f
Fixed master build ( #8857 )
...
* [Tests] Added missed ostream operators
* Disabled ROIAlign tests with bf16
Co-authored-by: Alexandra Sidorova <alexandra.sidorova@intel.com>
2021-11-26 23:42:55 +03:00
Steve Yoo
42f5034892
Migrate Sort (MatrixNms-8, MulticlassNms-8, NonMaxSuppression-5) ( #8394 )
...
* Migrate Sort (MatrixNms-8, MulticlassNms-8, NonMaxSuppression-5)
* Add right multiclass_nms.cpp
* Add struct Attributes to matrix_nms
* Add constructors to opset8::MatrixNms::Attributes
* Fix code format of opset8::MatrixNms::Attributes::Attributes
2021-11-26 22:35:43 +03:00
Luo Cheng
38aebd4463
[CPU] MulticlassNms/MatrixNms support dynamic shape ( #8161 )
2021-11-26 20:23:26 +03:00
Vladislav Golubev
f59ece3cde
[CPU] ROIAlign: dynamic shapes support ( #8571 )
2021-11-26 18:45:51 +03:00
Vladislav Golubev
734185c04c
[CPU] LRN: dynamic shapes support ( #8724 )
2021-11-26 17:41:48 +03:00
Jan Iwaszkiewicz
bcf0879785
Fix queue fails on callbacks ( #8809 )
2021-11-26 12:44:11 +01:00
Tatyana Raguzova
31ae69ac2d
[setupvars] Removed unnecessary double brackets ( #8796 )
...
they cause a problem on raspbianOS
2021-11-26 13:42:13 +03:00
Ilya Lavrenov
533bab2b78
Export more enum names from nrgaph ( #8828 )
2021-11-26 13:40:27 +03:00
Anastasia Popova
b3869cb127
Fixed tensors propagation in GlobalPoolingToReduce. ( #8835 )
2021-11-26 13:02:46 +03:00
Liubov Batanina
2d0ae6028a
[POT] Added quantization inside subgraphs ( #8530 )
...
* [POT] Support subgraphs
* Add support for inplace statistics
* Fixed cascade models
* Fixed bug
* Fixed import
* Fix name
* Add test
* Fix comments
* Replace test model
* Replace test model
* Add recursively flag
* Fix pylint
* Updated AA node names
* Fix adding results to node
* Disable subgraph quantization
* Disable recursion search in graph
* Skip test with subgraphs quantization
2021-11-26 12:42:33 +03:00
Mateusz Tabaka
7f6b004a33
[VPU] filter out unused outputs in RNN layer handler ( #8778 )
...
[VPU] Filter out unused outputs in RNN layer handler
Ticket: 60540
2021-11-26 12:31:21 +03:00
Anton Pankratov
bd3e4fbe78
Added openvino any ( #8288 )
2021-11-26 12:23:25 +03:00
Indira Salyahova
e32a569fb4
fix: quantize only one input mvn operation ( #8822 )
2021-11-26 12:17:43 +03:00
Indira Salyahova
8db9168d41
[POT] Check node is not None ( #8732 )
...
* fix: check the node is not None
* input port is not None
2021-11-26 12:10:33 +03:00
Nikita Malinin
d8d9954ad6
Fix bug with the outputs naming ( #8556 )
...
(cherry picked from commit 13c99e8882
2021-11-26 12:08:01 +03:00
Svetlana Dolinina
5b3c3bc149
Dragan: random uniform fix ( #8716 )
...
* fix random uniform input constant layout
* added test for 4D
2021-11-26 11:45:05 +03:00
Vladimir Paramuzov
7a16de290a
[GPU] Fixed NHWC interp. Added exec precision to impl name in perf counters ( #8803 )
2021-11-26 11:35:03 +03:00
Polina Brzezinskaya
8f636ed104
[VPU]Fix dynamic shape API Mac build error ( #8821 )
2021-11-26 11:25:10 +03:00
Vladislav Golubev
68cf41cbdf
[CPU] TopK: dynamic shapes support ( #8474 )
2021-11-26 11:00:09 +03:00
Katarzyna Mitrus
bf504c00d3
[ONNX FE] Support for ONNX ATen (embedding bag) ( #8802 )
2021-11-26 08:30:45 +01:00
Vladimir Paramuzov
60fb05bb6a
[GPU] Fix strided slice -> crop replacement. Int8 support in strided slice ( #8764 )
2021-11-26 10:17:07 +03:00
Ivan Tikhonov
1ac1720df0
Use new headers and namespaces in Paddle FrontEnd ( #8834 )
2021-11-26 07:18:56 +03:00
Ilya Churaev
d01e6368ec
Added pp header to util library ( #8814 )
...
* Added pp header to util library
* Fixed code style and typo
* Fixed arm
2021-11-26 06:27:23 +03:00
Piotr Szmelczynski
387c35cc6e
Pszmel/bind preprocessing ( #8791 )
...
* Use reference_wrapper for preprocess bindings
* Update tests
* add bindings to I420_SINGLE_PLANE and I420_THREE_PLANES
* remove init from all classes except PrePostProcessor and add RGBX and BGRX to ColorFormat enum
* update test name
* add test for taking input and output by name
* move ref_wrapper to common.hpp
* add common.hpp include to PrePostProcessor
* update comment on ref_wrapper
2021-11-25 23:40:19 +03:00
Zhang Yi
342d835552
[CPU] Dynamic shape for ctc_greedy_decoder & ctc_greedy_decoder_seq… ( #8671 )
2021-11-25 20:50:21 +03:00
Gorokhov Dmitriy
3743552ea7
[CPU] Enable brgemm primitives ( #8169 )
2021-11-25 19:39:31 +03:00
Vladislav Golubev
c66c378073
Failed test disabled ( #8823 )
2021-11-25 17:26:00 +03:00
Artur Kulikowski
78eb1aa85f
[Python API] Expose missing methods of class Function ( #8733 )
2021-11-25 14:54:40 +01:00
Ilya Churaev
afd811890a
Added note about Graphviz ( #8827 )
...
* Added pp header to util library
* Added note about Graphviz dependency for VisualizeTree pass
* Revert "Added pp header to util library"
This reverts commit a5d16d6236
2021-11-25 16:44:46 +03:00
