Gleb Kazantaev [Tue, 17 Nov 2020 15:34:05 +0000 (18:34 +0300)]
Fix NMS5 dynamism issues (#3137)
* Fixed ConvertNMS5ToLegacy conversion pass to resolve dynamism as soon as possible; fixed output precision to avoid troubles during convert_precision pass
* Added NMS5ToLegacy conversion for cldnn plugin
* Fixed NMS3 copy method
* Updated NMS5ToLegacy pass to avoid convert precision issues
* Updated nGraph reader and Functional tests
* Removing odd CF call
* removed xfail for test that is expected to pass
* Fixed Convert operations friendly_name
* Removed NMS5ToLegacy from opset1_to_legacy conversion
* Update NMS5 layer tests
* Update NMS5 DSR tests
Edward Shogulin [Tue, 17 Nov 2020 15:06:50 +0000 (18:06 +0300)]
[LPT] implementation were moved from common dir (#3173)
Nikolay Shchegolev [Tue, 17 Nov 2020 14:01:44 +0000 (17:01 +0300)]
[CPU] Normalize node. Broadcast weights from 1 to channels. (#3141)
Ilya Lavrenov [Tue, 17 Nov 2020 13:44:44 +0000 (16:44 +0300)]
Added SECURITY.md back (#3177)
Kate Generalova [Tue, 17 Nov 2020 13:43:56 +0000 (16:43 +0300)]
[DOC] Update Docker install guide (#3055)
* [DOC] Update Docker install guide
* [DOC] Add proxy for Windows Docker install guide
* [DOC] move up prebuilt images section
* Update installing-openvino-linux.md
* Update installing-openvino-docker-linux.md
* Update installing-openvino-docker-linux.md
Formatting fixes
* Update installing-openvino-docker-linux.md
Fixed formatting issues
* Update installing-openvino-docker-windows.md
Minor fixes
* Update installing-openvino-docker-linux.md
Fixed formatting issues
* [DOC] update text with CPU image, remove proxy for win
* Update installing-openvino-docker-windows.md
Minor fixes
* Update installing-openvino-docker-windows.md
Minor fix
* Update installing-openvino-docker-windows.md
Minor fix
* Update installing-openvino-docker-windows.md
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
Roman Vyunov (Intel) [Tue, 17 Nov 2020 13:30:30 +0000 (16:30 +0300)]
[IE][VPU]: Refactoring of SpecialStageProcessor (#2885)
* SpecialStageProcessor refactoring
* Fix for Yolo-v3-pytorch and related test
iliya mironov [Tue, 17 Nov 2020 13:28:27 +0000 (16:28 +0300)]
Fix graph clenup (#3159)
* Fix graph clenup
* Refactoring graph clean up function
* Change wa comment
Co-authored-by: Your Name <you@example.com>
Mikhail Ryzhov [Tue, 17 Nov 2020 11:57:40 +0000 (14:57 +0300)]
Revert "Reduced usage of batch in python samples (#3104)" (#3171)
This reverts commit
23e653858bc5e543afe17dcfdb6ce89047e96788.
chxd [Tue, 17 Nov 2020 10:45:42 +0000 (18:45 +0800)]
[IE CLDNN] program_impl::replace_all_usages causes invalid memory access. (#138)
Piotr Rozen [Tue, 17 Nov 2020 10:32:14 +0000 (11:32 +0100)]
added ubuntu 20.04 support to speech recognition demo (#3145)
updated speech recognition demo resources URLs to AWS
Krzysztof Bruniecki [Tue, 17 Nov 2020 10:16:15 +0000 (11:16 +0100)]
Print GNA Lib function name when error code obtained (#3129)
Ivan Tikhonov [Tue, 17 Nov 2020 09:38:22 +0000 (12:38 +0300)]
TI and Sequences related transformations: transition from cnn to ngraph versions (#2927)
* sequences to ti transformations, support for seq_lengths input, update reference implemetations, add new tests
* fix python api, update sequences to ti transformation
* transition from cnn to ngraph transformations for cpu, gpu, vpu plugins
* fix convert_ti_to_sequence transformation
* fix naming issue in unroll transformation
* test pure TensorIterator in vpu plugin
* fix sequences to ti transformation
* Update sequences to TI transformation: fix reverse sequence support
* update single layer tests, fix TI reference impl, fix Sequences to TI transformations
* ngraph code style
* fix build
* fix ngraph python api
* resolver review comments, refactoring
* revert vpu changes
* disable/fix tests
* refactoring
* Resolve review remarks
* optimization of LSTMSeq -> LSTMSeq IE: remove unnecessary Transpose ops
* Refactoring of transformation pipeline in cpu and gpu plugins, align GRU/RNN -> GRU/RNN IE with LSTM -> LSTM IE
* update TensorIterator tests, refactoring
* fix typo
* Fix unit tests, delete unnecessary callbacks
* Refactoring: delete commented code
* Add FullyConnected to skipConstInfer list for legacy ConstFolding
* disable legacy cnn unit tests
* delete xfail
* fix for backward compatibility with opset1::LSTMCell
* delete xfail
* fix build, remove Reshape layer from skipConstInfer list
Jan Iwaszkiewicz [Tue, 17 Nov 2020 09:34:33 +0000 (10:34 +0100)]
[nGraph][ONNX] Rename xfails (#3061)
Vitaliy Urusovskij [Tue, 17 Nov 2020 09:07:40 +0000 (12:07 +0300)]
Extend information to submit to a DB in time_tests (#3018)
* Optimize imports in time_tests conftest.py
* Extend information to submit to a DB in time_tests:
1. Add `--manifest` and `--db_metadata` CLI keys
2. Add `prepare_db_info` fixture
* Move `validate_test_case` fixture to a const schema, remove extra checks
* Add `manifest_metadata` fixture to parse and validate manifest only once
* Add OS utils to submit os info to DB
Maxim Vafin [Tue, 17 Nov 2020 08:58:01 +0000 (11:58 +0300)]
Fix ApplyPermutations for the case when more then 1 input with permutes (#3095)
Ilya Lavrenov [Tue, 17 Nov 2020 08:46:05 +0000 (11:46 +0300)]
Removed documents which are ported to OpenVINO WiKi (#3106)
* Removed documents which are ported to OpenVINO WiKi
* More updates
* Removed getting started
* Ported more guides to OpenVINO Wiki
Ilya Lavrenov [Tue, 17 Nov 2020 08:42:34 +0000 (11:42 +0300)]
Connect some ngraph and IE cmake options (#3147)
Roman Vyunov (Intel) [Tue, 17 Nov 2020 08:41:48 +0000 (11:41 +0300)]
[IE][TOOLS] Fix for CCT two IR mode (#3084)
Aleksandr Korolev [Tue, 17 Nov 2020 08:36:23 +0000 (11:36 +0300)]
[IE][VPU]: Fix condition in HW tiling (#3111)
Co-authored-by: kora6 <kora6@github.com>
Aleksandr Pertovsky [Tue, 17 Nov 2020 08:32:52 +0000 (11:32 +0300)]
[ngraph] Fix compare functions for functional tests (#3161)
Vladimir Paramuzov [Tue, 17 Nov 2020 08:18:48 +0000 (11:18 +0300)]
[IE CLDNN] Fixed mem leak (#3153)
Mateusz Tabaka [Tue, 17 Nov 2020 08:08:01 +0000 (09:08 +0100)]
Fix compilation error in gna_wait_test (#3150)
error: converting to ‘std::vector<std::tuple<unsigned int, long int,......
Anton Romanov [Tue, 17 Nov 2020 07:50:23 +0000 (10:50 +0300)]
Show help message when -i or -m is not set (#3144)
Chenhu Wang [Tue, 17 Nov 2020 07:42:34 +0000 (15:42 +0800)]
[CPU] Interpolate operation improvements (#2366)
* interpolate improvement
* JITTED cubic mode
* fix 'code is too big' when JIT
* extend test to cover tail code path
* transformation of interpolate1 to interpolate4
* add low precision transformation for interpolate4
Mikhail Ryzhov [Tue, 17 Nov 2020 07:12:33 +0000 (10:12 +0300)]
Reduced usage of batch in python samples (#3104)
* Reduced usage of batch in python sampes
Excluded from hello_classification and object_detection samples
Irina Efode [Tue, 17 Nov 2020 07:11:17 +0000 (10:11 +0300)]
[IE TESTS] Move main.cpp to shared lib from plugin functional tests (#3157)
Irina Efode [Tue, 17 Nov 2020 07:10:45 +0000 (10:10 +0300)]
[IE TESTS][IE CPU] Add smoke prefix for broadcast SLT (#3158)
Maxim Andronov [Tue, 17 Nov 2020 06:33:19 +0000 (09:33 +0300)]
[IE TESTS] Added test for NMS (#2830)
Anton Voronov [Tue, 17 Nov 2020 06:04:49 +0000 (09:04 +0300)]
[CPU] added MergePermuteAndReorder optimization + added test (#2519)
Mateusz Bencer [Tue, 17 Nov 2020 04:16:39 +0000 (05:16 +0100)]
Protect reading external weights from up-dir (#3098)
* introduced path sanitizing
* added tests, folders structure clean-up
* fixed test
* fixed up-dir path handling
* improved sanitizing for windows
* fix Windows test
* move sanitize impl
Ivan Tikhonov [Tue, 17 Nov 2020 04:04:20 +0000 (07:04 +0300)]
LSTM/GRU/RNN Sequences : support for seq_lengths input (#2788)
* sequences to ti transformations, support for seq_lengths input, update reference implemetations, add new tests
* fix python api, update sequences to ti transformation
* fix sequences to ti transformation
* Update sequences to TI transformation: fix reverse sequence support
* update single layer tests, fix TI reference impl, fix Sequences to TI transformations
* ngraph code style
* fix build
* fix ngraph python api
* resolver review comments, refactoring
* Resolve review remarks
* delete xfail
Mateusz Bencer [Tue, 17 Nov 2020 03:57:57 +0000 (04:57 +0100)]
Specification to ONNX external data feature (#2939)
* Added external weights files doc
* review remarks
* review remarks
* review remarks
Co-authored-by: Michał Karzyński <4430709+postrational@users.noreply.github.com>
* review remarks. part 2
Co-authored-by: Michał Karzyński <4430709+postrational@users.noreply.github.com>
* fixed info about nullptr
* Apply suggestions from code review
Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>
* review remarks. part 2
Co-authored-by: Michał Karzyński <4430709+postrational@users.noreply.github.com>
Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>
Tomasz Socha [Tue, 17 Nov 2020 03:57:00 +0000 (04:57 +0100)]
Use std::transform instead of vector constructor (#3151)
Irina Efode [Mon, 16 Nov 2020 19:29:02 +0000 (22:29 +0300)]
[IE TESTS] Remove extra dependency from Shared lib (#3006)
* [IE TESTS][IE CMAKE] Add cmake option for configuration to skip tests
* [IE TESTS] Remove extra dependency from IE tests shared lib
* Revert to add flag
Mikhail Ryzhov [Mon, 16 Nov 2020 18:48:06 +0000 (21:48 +0300)]
Corrected "-i" argument description (#3142)
* Corrected "-i" argument description
According to their usage in samples
Jedrzej Hajduczenia [Mon, 16 Nov 2020 17:56:19 +0000 (18:56 +0100)]
[IE CLDNN] Add asymmetric quantization support to fsv16 imad 1x1 convolution kernel (#2941)
Evgeny Lazarev [Mon, 16 Nov 2020 15:50:13 +0000 (18:50 +0300)]
Fix for Reduce extractors and normalizer (#3136)
* Fixed extractor for ONNX ReduceXXX operations and fixed ReduceAxisNormalizer transformation
* Unit test for ReduceAxisNormalizer transformation
Alexey Ershov [Mon, 16 Nov 2020 15:03:19 +0000 (18:03 +0300)]
[IE][VPU]: ExpGenerateProposals: added temporary buffer allocation (#3093)
ExpGenerateProposals: temporary buffer allocation moved from firmware to blob
* Added tmpBuffer
* Changed the amount of allocated memory
* firmware update
Co-authored-by: Ivan Poliksenov <ivan.poliksenov@intel.com>
Andrey Sokolov [Mon, 16 Nov 2020 14:52:27 +0000 (17:52 +0300)]
[IE][VPU]: NMS - fix memory allocation bug (#3133)
Mateusz Tabaka [Mon, 16 Nov 2020 14:23:20 +0000 (15:23 +0100)]
Update tolerance values for ONNX model tests (#3131)
Anton Romanov [Mon, 16 Nov 2020 14:20:54 +0000 (17:20 +0300)]
small refactor samples setBatchSize (#3053)
* small refactor samples setBatchSize
Bartosz Sledz [Mon, 16 Nov 2020 14:20:01 +0000 (15:20 +0100)]
Extend test coverage for ONNX Resize Operator (#3086)
Bartosz Sledz [Mon, 16 Nov 2020 14:16:24 +0000 (15:16 +0100)]
Add ceil_mode for Max and Avg pooling (#2965)
dependabot[bot] [Mon, 16 Nov 2020 13:08:12 +0000 (14:08 +0100)]
Bump wheel from 0.34.2 to 0.35.1 in /ngraph/python (#3120)
Maksim Kutakov [Mon, 16 Nov 2020 12:58:10 +0000 (15:58 +0300)]
[CPU] Broadcast check has been added to the ConvertPowerToPowerIEMatcher transformation. (#3132)
* [CPU] Added broadcast check to the ConvertPowerToPowerIE transformation.
* [CPU] Eltwise single layer test instance extended with a two inputs case.
Ilya Churaev [Mon, 16 Nov 2020 12:30:18 +0000 (15:30 +0300)]
Fixed negative paddings for convolution backprop data (#3117)
* Fixed negative paddings for convolution backprop data
* Fixed code style
* Fixed comments
Bartek Szmelczynski [Mon, 16 Nov 2020 12:19:31 +0000 (13:19 +0100)]
add tests for 5 ops based on model zoo (#3062)
* add tests for 5 ops based on model zoo
* remove unnecessary layers from the test
* add test case with merge_repeated=0
* remove unnecessary layers and add new test casae with do_softmax=0
* remove unnecessary layers from the test
Krzysztof Bruniecki [Mon, 16 Nov 2020 12:05:59 +0000 (13:05 +0100)]
Revert "Erase from unwaited requests container on QoS abort (#3125)" (#3148)
This reverts commit
d7e98f605d157ebf3dd986b4336a9b0a76da7f80.
Krzysztof Bruniecki [Mon, 16 Nov 2020 10:30:48 +0000 (11:30 +0100)]
Erase from unwaited requests container on QoS abort (#3125)
Tomasz Dołbniak [Mon, 16 Nov 2020 10:09:34 +0000 (11:09 +0100)]
Enablement of GatherND tests (nG & ONNX) (#3013)
Ilya Lavrenov [Mon, 16 Nov 2020 09:50:03 +0000 (12:50 +0300)]
Fixed klockwork (#3119)
Anton Romanov [Mon, 16 Nov 2020 09:26:04 +0000 (01:26 -0800)]
Alignment model and input (#3115)
Rafik Saliev [Mon, 16 Nov 2020 08:25:57 +0000 (09:25 +0100)]
[BugFix] Fix compilation error caused by typo in #3109 (#3135)
Roman Kazantsev [Mon, 16 Nov 2020 06:50:41 +0000 (09:50 +0300)]
Improve reshapeability of models with eltwise nodes influencing shapes (#2767)
* Fix ElementwiseInputReshape transformation
Reshape node always needs to be inserted
in order to preserve ShapeOf nodes (reshapability of a model) that can potentially be above
elementwise node.
Refactor EltwiseInputReshape_test and EltwiseInputNormalization_test since the logic of maintaining reshape for eltwise has been changed.
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Merge EltwiseInputNormalization and EltwiseInputReshape transformations
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Remove Unsqueeze from Fused_op
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix code after code review #1
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix code after review #2
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix code review #4
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Perform full normalization based on shapes of all inputs to eltwise
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Refactor much to avoid old API and edges with unsqueeze_dims attribute
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix code after review
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
Maksim Doronin [Sun, 15 Nov 2020 23:51:46 +0000 (02:51 +0300)]
[IE][VPU][XLink]: XLink semaphore wrappers impl (#3079)
XLink wrappers for POSIX semaphore functions (refer sem_overview for details). In the description of standard sem_destroy the following is noted:
"Destroying a semaphore that other processes or threads are currently blocked on (in sem_wait(3)) produces undefined behavior."
XLink wrappers use thread-safe reference count and destroy the semaphore only in case if there are no waiters.
* XLink semaphore wrapper impl
* Extend XLink win_synchapi
Ilya Lavrenov [Fri, 13 Nov 2020 16:44:40 +0000 (19:44 +0300)]
Propogate DEVICE_ID for functions working with RemoteContext (#3109)
* Propogate DEVICE_ID for functions working with RemoteContext
* More fixes for RemoteContext
* Fixed tests compilation with VariableState
Anna Alberska [Fri, 13 Nov 2020 16:28:02 +0000 (17:28 +0100)]
[GNA] fix 4d batch size eltwise issue (#3127)
Alexander Perepelkin [Fri, 13 Nov 2020 16:17:27 +0000 (19:17 +0300)]
Enable segfaulting getAvailableDevices, ExecGraphSerializationTest.ExecutionGraph_CPU after segfaults are fixed (#3124)
Kamil Magierski [Fri, 13 Nov 2020 15:12:45 +0000 (16:12 +0100)]
[GNA] 4D concat align pass (#2970)
* [GNA] Fix RemovePermutationsNHWCToNCHWPass in cases that permute input has many outData
* style
* [GNA] linux test fail fix
Maxim Andronov [Fri, 13 Nov 2020 14:56:20 +0000 (17:56 +0300)]
[CPU] fix NMS-5 CentOS7 error (#3083)
Katarzyna Mitrus [Fri, 13 Nov 2020 14:31:29 +0000 (15:31 +0100)]
ONNX LSTM fix get_shape error (#3033)
* ONNX LSTM get dimension only if required
* Test dynamic onnx lstm model import
* Enable LSTM_Seq_lens_unpacked_model import test
* Disable model zoo execution test "MSFT_opset9_LSTM_Seq_lens_unpacked"
* Add missed comma in xfail list
* Update error messages
* init xfail issue
* test zoo models import xfail issue
* Fix SEQ_LENGTH init
* Comments update
* Fix usage of v0::Add by overloaded operator
Vladimir Paramuzov [Fri, 13 Nov 2020 14:24:40 +0000 (17:24 +0300)]
[IE CLDNN] Fixed pad value used for input coords calculation in fsv16 imad conv (#3081)
Tomasz Jankowski [Fri, 13 Nov 2020 14:10:42 +0000 (15:10 +0100)]
nGraph: fix TopK output shape inference (#2967)
* nGraph: Fix TopK output shape inference
* nGraph: Correct TopK output shape inference
TopK lower bound of output shape at the axis was mistakenly calculated
basing on max_lenght instead of min_lenght.
* nGraph: Correct TopK output shape inference
* nGraph: Correct TopK type prop test
The topk_negative_axis_support type properties test was comparing
incompatible variables carrying the same value. So it was passing ok.
* nGraph: Add TopK type prop test
* nGraph: Fix code style
* nGraph: Follow review guidelines
Improve variables meaning.
Enforce rigid test pass condition.
* nGraph: Remove magic numbers
Krzysztof Bruniecki [Fri, 13 Nov 2020 13:32:26 +0000 (14:32 +0100)]
Create u-tests for RESULT_NOT_READY and INFER_NOT_STARTED (GNA QoS) (#3102)
* Create tests for RESULT_NOT_READY and INFER_NOT_STARTED (GNA QoS)
* Suppress deprecated definition errors
* Fix warning
Yegor Kruglov [Fri, 13 Nov 2020 12:36:04 +0000 (15:36 +0300)]
Revert "Reshape-able SliceConverter (#2954)" (#3118)
This reverts commit
b437387bd536532467b9b29d25a082bf0fdc33d1.
Mateusz Bencer [Fri, 13 Nov 2020 12:32:19 +0000 (13:32 +0100)]
Enable CPU and Interpreter Loop tests (#3042)
Katarzyna Mitrus [Fri, 13 Nov 2020 12:15:22 +0000 (13:15 +0100)]
[nGraph] MatMul - Remove fused op and align output shape inference (#2866)
To follow MatMul spec update for 1D tensors this PR removes FusedOp decomposition for MatMul without changing current MatMul output shape inference logic (numpy/onnx aligned).
Based on previous PR #2212 that follows rather current spec logic.
Gleb Kazantaev [Fri, 13 Nov 2020 11:39:07 +0000 (14:39 +0300)]
Improve ConvertBroadcast3 pass to avoid extra Multiply operations for BIDIRECTIONAL mode (#3113)
* Fixed ConvertBroadcast3 pass for BIDIRECTIONAL mode to avoid excess Multiply operations
* Added funcitonal tests for new decompositions
* Return false if mode is unknown; avoid usign node in replace_node
* Added functional tests for cases when TargetShape input is not a Constant
Rafal Blaczkowski [Fri, 13 Nov 2020 09:17:11 +0000 (10:17 +0100)]
[OpenVino ONNX CI watchdog] Small improvements (#3096)
* Small improvements
* Enlarge pending status
Sergey Shlyapnikov [Fri, 13 Nov 2020 08:58:03 +0000 (11:58 +0300)]
[IE CLDNN] Fix for fusing Activation into Eltwise primitive in fused_conv_eltwise primitive case usgae (#2997)
Michał Karzyński [Fri, 13 Nov 2020 08:50:47 +0000 (09:50 +0100)]
Add Dependabot configuration (#3029)
* Add Dependabot configuration
* Update config to Dependabot native
Anton Pankratv [Fri, 13 Nov 2020 07:53:31 +0000 (10:53 +0300)]
Hetero KW warning fix (#3107)
Edward Shogulin [Fri, 13 Nov 2020 07:32:59 +0000 (10:32 +0300)]
[LPT] POT support: absent convert fix & element-wise empty dequantization data (#3067)
Vladimir Paramuzov [Fri, 13 Nov 2020 06:29:28 +0000 (09:29 +0300)]
[IE CLDNN] Cleanup cldnn source tree and README (#3043)
Vladimir Paramuzov [Fri, 13 Nov 2020 06:29:05 +0000 (09:29 +0300)]
[IE CLDNN] Fixed fmt traits map (#3088)
Andrew Bakalin [Fri, 13 Nov 2020 04:50:31 +0000 (07:50 +0300)]
[VPU][NGraph] Extend TopK K propagation (#2943)
* [VPU][NGraph] Support ShapeOf and Gather in TopK K propagation
* [VPU] Save calculated K value
* [VPU][Tests] Introduces tests
* [Tests] Review fixes
Alexander Perepelkin [Thu, 12 Nov 2020 23:26:55 +0000 (02:26 +0300)]
Disable test ExecGraphSerializationTest.ExecutionGraph_CPU (#3097)
* Disable test ExecGraphSerializationTest.ExecutionGraph_CPU as temporary measure to avoid segfault
* Disable segfaulting getAvailableDevices
Artyom Anokhov [Thu, 12 Nov 2020 16:35:19 +0000 (19:35 +0300)]
install_NEO_OCL_driver: Added user to render group. (#3099)
Andrew Bakalin [Thu, 12 Nov 2020 14:30:41 +0000 (17:30 +0300)]
[IE][VPU]: GatherND DTS transformation (#3025)
* Implement GatherND DTS
* Introduce tests on DTS
* Introduce tests on DSR+GatherND
Elizaveta Lobanova [Thu, 12 Nov 2020 14:07:38 +0000 (17:07 +0300)]
[GNA] Added tests for negative memory layer offset and split - trivial permute - concat scenario (#2989)
Pavel Esir [Thu, 12 Nov 2020 12:04:07 +0000 (15:04 +0300)]
add getting nms_threshold / iou_threshold from RetinaNet (#3075)
* added getting nms_threshold/iou_threshold from original TF RetinaNet model
* iou_threshold definition added
* fixed getting iou_threshold for TF NMS V2, some minor corrections
* added box_encoding to NMS extractors
Ilya Churaev [Thu, 12 Nov 2020 11:59:28 +0000 (14:59 +0300)]
Removed const_cast from addOutput method (#3091)
Alexandra Sidorova [Thu, 12 Nov 2020 11:25:42 +0000 (14:25 +0300)]
[CPU] Converted Pad Layer to MKLDNNNode and added more optimized implementations (#2586)
Pad-1: fixed ngraph reference for symmetric mode and added cpu tests
Vladislav Volkov [Thu, 12 Nov 2020 11:00:14 +0000 (14:00 +0300)]
ITT performance counters for first inference (#1741)
* ITT performance counters for first inference
ITT counters for nGraph passes
* RTTI for trnasformation passes
* The MKLDNN plugin first inference counters improvements
Daria Mityagina [Thu, 12 Nov 2020 10:51:48 +0000 (13:51 +0300)]
[IE][VPU][TESTS]: support different modes for Interpolate (#2963)
Ilya Churaev [Thu, 12 Nov 2020 10:34:28 +0000 (13:34 +0300)]
Fixed KW for Windows (#3089)
* Fixed KW for Windows
* Fixed code style
* Fixed compilation
Svetlana Dolinina [Thu, 12 Nov 2020 09:40:43 +0000 (12:40 +0300)]
Move QueryState from ExecutableNetwork to InferRequest (#2818)
* QueryState moved to InferRequest
* deprecate ExecutableNetwork::QueryState,chaged tests (without any check yet)
* fix build
* review fixes + build fix
* build fix + review changes
* remove blank line
* style fixes
* test build fixes
* style fix
* style fix
* fixed build of tests
* fix
* mac build fix
* hddl plugin build fix
* clean up unneeded implementation for method
* fixed tests build
* add implementation for getstate, correct getName for MklDNN
* fixed description of state API in comments
* lint fixes
* Rename MemoryState to VariableState
* added tests for cpu for VariableStates, several small fixes in tests and code
* merge fix
* lint fix
* remove whitespaces
* spaces fix
* fix in test to make it workable for all plugins
* fix typo
* fix test for gna
* remove extra comment
* fix test for gna
Mikhail Treskin [Thu, 12 Nov 2020 09:33:23 +0000 (12:33 +0300)]
Summary report generator for layer and subgraph tests (#2707)
* Initial summary dumper implementation
* Handle Tensoriterator body + add parser script
* Add support of XML reports merging + report OP names with versions
* Remove debug device name change
* Fix windows building issue
* Add --disable_test_skips command line option
* Gtest failure with logging
* Change skipping logic and resolve linkage errors caused by extern
* Get graph body from Loop
* Fix disable_tests_skipping symbol redefinition
* Fix inline for currentTestIsDisabled
* Rollback get_body for Loop
* Handle cases with skip in test SetUp
* Report Loop and TI ops along with ops in subgraph body
* Resolve some PR comments
* Dummy commit to kick pre-commit validation
Co-authored-by: Efode, Irina <irina.efode@intel.com>
Evgeny Lazarev [Thu, 12 Nov 2020 04:33:39 +0000 (07:33 +0300)]
Fixed transformations looking for FusedBatchNorm operation to look for FBNV2 and FBNV3 also (#3078)
* Fixed transformations looking for FusedBatchNorm operation to consider FusedBatchNormV2 and FusedBatchNormV3 also.
* Updated unit test for FusedBatchNormTraining
* Fixed unit test
Maksim Doronin [Wed, 11 Nov 2020 19:04:59 +0000 (22:04 +0300)]
[IE][VPU]: Implement VPU Ngraph EIP->ReorgYolo transformation (#3066)
* We need to convert ExtractImagePatches op to ReorgYolo to restore the working capacity of myriad plugin while compiling Yolo-v2 models.
* It was previously removed in #2687
Ilya Lavrenov [Wed, 11 Nov 2020 17:31:44 +0000 (20:31 +0300)]
Don't build extra module if it doesn't have cmake files (#3074)
Edward Shogulin [Wed, 11 Nov 2020 15:50:37 +0000 (18:50 +0300)]
[LPT] Dequantization constant output precision handling extending (#2987)
* [LPT] moveDequantizationAfter fix
* [LPT] ConcatTransformation fix: only intermediate operations are handled
Maxim Kurin [Wed, 11 Nov 2020 14:40:37 +0000 (17:40 +0300)]
[IE][VPU]: Optimize swish layer and remove swish replacement pass (#2993)
* Swish layer optimization
* Update VPU firmware 1468
Vladimir Gavrilov [Wed, 11 Nov 2020 14:31:00 +0000 (17:31 +0300)]
retinanet onnx model has Upsample error (#3052)
* Commit.
* Fixed infer function of ONNXResize11 operation.
* Small fixes.
* Written unit tests for shape calculation for ONNXResize11.
Tomasz Dołbniak [Wed, 11 Nov 2020 12:49:40 +0000 (13:49 +0100)]
Removal of obsolete constant folding passes (#2902)
* Redundant op::Max CF removal
* Redundant op::Min CF removal
* Redundant op::Sum & op::Product CF removal
* CF Min and Max using evaluate()
* Arithmetic reduction CF pass removal
* Quantize op CF pass removal
* Convert op CF pass removal
* Logical reduction CF pass removal
* Select op CF pass removal
* OneHot CF pass removal
* Code formatting
* ScatterElements CF pass removal
* Gather CF pass removal
* Disable a Quantize op test that fails in CI
* CF pass cleanup
* Convert op cleanup and test adaptation to spec
* Possible fix for failing VPU tests
* Limit the types used in OneHot::evaluate
* Quantize op evaluator removal
* Refactor of Gather evaluator
Roman Donchenko [Wed, 11 Nov 2020 12:35:39 +0000 (15:35 +0300)]
Fix spelling errors in samples and documentation (#2795)
* Fix spelling errors in samples
* Fix spelling errors in the documentation
Edward Shogulin [Wed, 11 Nov 2020 11:56:58 +0000 (14:56 +0300)]
[LPT] CNNNetwork LPT removal (#3035)
* [LPT] CNNNetwork LPT removal
* Fixes for LPT removal
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Roman Kazantsev [Wed, 11 Nov 2020 11:47:00 +0000 (14:47 +0300)]
Fix GatherND to output dynamic rank tensor (#3073)
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
Andrew Bakalin [Wed, 11 Nov 2020 10:52:42 +0000 (13:52 +0300)]
[IE][VPU][Tests]: Fix NMS DTS outputs naming + tests (#3040)
* Fix dynamic output case in interpreterFunction. For dynamic output cases, we can't call get_shape on the result because it's shape is dynamic, instead, we should take the real output shape from output HostTensor
* Fix outputs naming as it's done in other DTS transformation for operations with multiple outputs (Split, TopK, etc).
Ticket - #-42421
Jedrzej Hajduczenia [Wed, 11 Nov 2020 09:38:45 +0000 (10:38 +0100)]
[IE CLDNN] Add asymmetric quantization support to reference convolution imad kernel (#2994)