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)
Evgeny Lazarev [Wed, 11 Nov 2020 08:53:10 +0000 (11:53 +0300)]
Added support for a new version of the TF OD API pre-processing part (#3063)
* Added support for a new version of the TF OD API pre-processing part of the mode
* Get rid of legacy API usage
* Fix comment and added assert
* Wording
Roman Lyamin [Wed, 11 Nov 2020 05:53:30 +0000 (08:53 +0300)]
[IE CLDNN] Added LogSoftmax-5 operation (#2945)
Gleb Kazantaev [Wed, 11 Nov 2020 04:49:22 +0000 (07:49 +0300)]
Fix wrong statement in ConvertConvolutions transformation (#3056)
* Fixed wrong statement in ConvertConvolution transformation
* Added tests
* FIXME: 42956
Nikolay Shchegolev [Tue, 10 Nov 2020 21:36:38 +0000 (00:36 +0300)]
[CPU] Proposal layer. Check img info input. (#2456)
Andrey Dmitriev [Tue, 10 Nov 2020 17:56:21 +0000 (20:56 +0300)]
[GNA] Added Multiplication 1x1x1 (#2470)
* [GNA] Broadcast power primitive
[GNA] Broadcast power primitive
[GNA] Added Multiplication 1x1x1
[GNA] Broadcast power primitive
Added secondary changes
* Added fix test
Andrey Sokolov [Tue, 10 Nov 2020 16:28:53 +0000 (19:28 +0300)]
[IE][VPU]: support new operation CEILING (#3004)
Add new Operation "Ceiling" for VPU Myriad
task: -42885
Yegor Kruglov [Tue, 10 Nov 2020 14:51:59 +0000 (17:51 +0300)]
Reshape-able SliceConverter (#2954)
* initial commit
* add cast
* data type fix
* added tests
* added test without axes and steps
* remove redundant imports
* discussions resolving
* Add cast to TFSliceToSlice
* layer tests fix
* update unittest
Roman Kazantsev [Tue, 10 Nov 2020 14:24:04 +0000 (17:24 +0300)]
Provide GatherND with original layout for inputs and output (#3002)
* Provide GatherND with original layout for inputs and output
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix code review #1
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
Andrey Dmitriev [Tue, 10 Nov 2020 13:37:03 +0000 (16:37 +0300)]
[GNA] fixed case when input connected to concat from left and const from right (#2874)
* Added test
* Added fix
* Fix comment
* Fix conflict
Andrey Dmitriev [Tue, 10 Nov 2020 13:33:41 +0000 (16:33 +0300)]
[GNA] Added fix for export scores (#3009)
Ilya Lavrenov [Tue, 10 Nov 2020 13:29:37 +0000 (16:29 +0300)]
OneCore toolchain (#3044)
* Added OneCoreUap toolchain file
* Intentation
* Updated OneCore toolchain
* Fixed linkage error with static runtime
* Link reader_api library
* Enable static runtime for ONNX part
* Allow to override flags
* Added flag for clDNN; plus refactoring
* Fix Includes
* Added toolchain check
* Added apivalidator for MYRIAD plugin
* Added commented apivalidator for CLDNN plugin
Ivan Tikhonov [Tue, 10 Nov 2020 12:49:59 +0000 (15:49 +0300)]
Reference implementations for Loop and TensorIterator ops (#2978)
* Loop op ngraph implementation, update IE IR Reader and ngraph to cnn converter
* refactoring SubGraphOp class
* type prop unit tests
* ngraph code style
* update comment
* single layer tests for Loop operation
* fix file name
* Add SpecialBodyPorts attribute in Loop op, update single layer tests
* first debug version
* more tests
* missing test file
* removed not needed shapes from test data
* move test data to new folder
* shape infer tests
* Added execution tests
* add several new tests cases, strict checks in Loop impl, temporary disable single layer tests
* ngraph codestyle, refactoring, clone_new_args test
* resolve review remarks
* fix build
* fix tests
* more execution tests
* add a new constructor of Loop op, resolve review remarks
* execution tests
* synchro with current version
* handle scalars and more tests
* scalar test enabled
* loop reference impl
* bug fixes in tests, onnx importer part and in the ref implementation of the Loop op
* applied remarks
* handle unsupported cases
* rewrite unit tests
* update INTERPRETER manifest
* is_termination_condition_always_true simplification
* [TEST] update python models tests
* review remarks
* added xfail to tiny_yolov3
* missing model test
* revert test data
* fixed numbers of failing tests
* fixed failed test description
* fix test message
* fix xfail test
* reference implementation for ngraph::function
* update loop reference implementation
* Refactor loop reference implementation
* ngraph codestyle
* Refactoring
* Submodule update
* Skip check for Reduce ops in mkl for scalar cases, support for yolov3
* fix ngraph reader tests
* revert ceiling op, renaming
* Add allias(Ceiling) for Ceil op in mkl
* delete xfails
* fix build
* single layer tests for tensor iterarator
* Refactor TensorIterator and Loop ref impls
* revert dynamic tensor creation, disable some dynamic test cases
* fix warning
* Resolve review remarks
* revert Predefined values in Loop tests
Co-authored-by: Mateusz Bencer <mateusz.bencer@intel.com>
Krzysztof Bruniecki [Tue, 10 Nov 2020 10:40:28 +0000 (11:40 +0100)]
Add fix for multiple_activations test (#2984)
* Add fix for multiple_activations test
- Add forbid activation fusing pass for GNA2 library
- Fix get all prev layers fnct
- To enable GNA_NoRegression.smoke_multiple_activations_onGNA_INT16
* Apply Bartek review
Nikita Kudriavtsev [Tue, 10 Nov 2020 09:39:32 +0000 (12:39 +0300)]
[IE][Myriad] Fixing global_lock_fd locking in mvnc (#3024)
Ilya Churaev [Tue, 10 Nov 2020 09:24:53 +0000 (12:24 +0300)]
Set friendly name in order to operate with it on visit attributes and validate stages (#3048)
Mateusz Bencer [Tue, 10 Nov 2020 08:57:06 +0000 (09:57 +0100)]
[ONNX Importer] Resolved problem with incorrect opset version set in subgraph (#2959)
Liubov Batanina [Tue, 10 Nov 2020 08:35:24 +0000 (11:35 +0300)]
[IE TESTS] Replaced size_t with int64_t (#2699)
* Replaced size_t with int64_t
* Fix gpu plugin
Anton Voronov [Tue, 10 Nov 2020 08:25:12 +0000 (11:25 +0300)]
[CPU] fixed strides filling in blocking desc (#2353)
Jesus Espinoza [Tue, 10 Nov 2020 07:57:27 +0000 (23:57 -0800)]
Update get started Linux instructions (#3016)
* Updating broken link on getting started linux doc
Link to build instructions was broken, updated link to the correct location.
* Update get-started-linux.md
* Update get-started-linux.md
* Update get-started-linux.md
* Update get-started-linux.md
Fixed broken links and updated commands
Gorokhov Dmitriy [Tue, 10 Nov 2020 07:56:22 +0000 (10:56 +0300)]
[CPU] Fixed Eltwise node endless loop in case nthreads = 1 (#3008)
Mateusz Bencer [Tue, 10 Nov 2020 07:42:26 +0000 (08:42 +0100)]
Revise Broadcast reference implementation (#2715)
* change tile reference implementation
* remove tile tests from interpreter manifest
* add repeats parameter to tile
* improve tile reference implementation
* add repeats parameter to tile reference call in tile evaluate method
* style apply
* include <numeric>
* add unnamed namespace to helper functions. Change stdio.h to cstdio. Change input_rank to be constant int
* add const reference to parameter repeats in tile reference function
* change createPitches function to use partial_sum instead of accumulate
* change a little bit createPitches function
* style-apply
* fix function naming
* style-apply
* fix calling functions name bug
* Add description of create_pitches function
* first version with debug logs
* reduce footprint
* single layer tests
* added more tests
* fixed handling bool type
* styles applied
* fix tile
* [ONLY DEBUG] print error scenario message
* fixed problem with e2e tests
* fixed casting of start_axis for numpy mode
Co-authored-by: pszmel <piotr.szmelczynski@intel.com>
Andrew Bakalin [Tue, 10 Nov 2020 06:45:14 +0000 (09:45 +0300)]
[ONNX] Return NMS-5 generation (#3003)
* [ONNX] Return NMS-5 generation
* Disable failed models
Evgeny Lazarev [Tue, 10 Nov 2020 06:12:09 +0000 (09:12 +0300)]
Updated MO requirements for numpy (#3034)
Vladimir Gavrilov [Tue, 10 Nov 2020 04:18:40 +0000 (07:18 +0300)]
Apply rest of the comments for NMS-5 review (#3037)
* Commit.
* Moved the preprocessing functions for NMS-5 to Interpreter backend.
* Code style fix.
Ilya Lavrenov [Mon, 9 Nov 2020 17:48:46 +0000 (20:48 +0300)]
Removed legacy dependency in template_extensions (#3026)
Alina Kladieva [Mon, 9 Nov 2020 16:17:19 +0000 (19:17 +0300)]
[Jenkinsfile] Get rid of dldtPipelineEntrypoint (#3012)
* [Jenkinsfile] Get rid of dldtPipelineEntrypoint
* [Jenkinsfile] Add library_version parameter
Co-authored-by: akladiev <akladiev@nncv-akladieva.inn.intel.com>
Anna Alberska [Mon, 9 Nov 2020 13:40:31 +0000 (14:40 +0100)]
[GNA] Add support for SubstituteSoftSign for pattern with addition (#2789)
* [GNA] add changes for SubstituteSoftSign for IRv10
* cpplint fix
* [GNA] add requested changes & change SoftSign test validation
* [GNA] SubstituteSoftsign refactor
* [GNA] enable 3d input tests for softsign
Maxim Shevtsov [Mon, 9 Nov 2020 11:42:18 +0000 (14:42 +0300)]
fix for hetero example (https://jira.devtools.intel.com/browse/CVS-33836) NB: the FPGA (even though deprecated) continues to be the only viable example foir the HETERO plugin, so leaving that (#2982)
Rafal Blaczkowski [Mon, 9 Nov 2020 09:55:15 +0000 (10:55 +0100)]
Fix versions (#3027)
Have some concerns on numpy version, probably should be revisited further
Maxim Andronov [Mon, 9 Nov 2020 05:52:54 +0000 (08:52 +0300)]
[CPU] Refactored pushInput (#2910)
Ilya Churaev [Mon, 9 Nov 2020 03:39:52 +0000 (06:39 +0300)]
Remove legacy files (licenses and some scripts) (#2952)
* Remove legacy files (licenses and some scripts)
* Removed LISENSE and install rules for licenses
Vladimir Gavrilov [Fri, 6 Nov 2020 18:00:55 +0000 (21:00 +0300)]
Extend MO for the operation NonMaxSuppression-5 (#2356)
* Commit.
* Written draft of NonMaxSuppression-5 class.
* Written conversion of the value of the second output of MO NonMaxSuppression-5 into TF format.
* Fixed type infer for the port 1 of NonMaxSuppression-5.
* Added Reshape to [1] for 0D inputs of NMS-5.
* Small fix.
* Corrected assert for number of inputs.
* Fixed docstrings for transformations TFNonMaxSuppressionNormalize and NonMaxSuppressionNormalize.
* Now the transformation TFNonMaxSuppressionNormalize uses find_and_replace_pattern().
* Moved model-optimizer/extensions/front/onnx/non_max_suppression_normalize.py to model-optimizer/extensions/front/non_max_suppression_normalize.py, to delete duplicate code.
* Deleted commented code.
* Fixed BOM-file.
* Deleted out_ports_count from NMS.
* Fixes in type_infer of NMS-5.
* Small changes.
* Added some comment.
* Small fix.
* Some fixes.
Vladimir Gavrilov [Fri, 6 Nov 2020 16:11:04 +0000 (19:11 +0300)]
Enable NonMaxSuppression-5 operation and various transformations (#2450)
* Some code style fixes.
* Started to write the method v5::NonMaxSuppression::evaluate().
* Started to write nGraph reference implementation of NMS-5.
* Some additions.
* Written preprocessing of boxes data.
* Started to write the function non_max_suppression() that calculates NonMaxSuppression-5 operation.
* Written postprocessing of the evaluate().
* Small fixes.
* Small fix.
* Added include for ngraph/shape.hpp.
* Written the function intersectionOverUnion.
* Some additions.
* Small fix.
* Continued to write the function non_max_suppression().
* Small fixes.
* Small fixes.
* Some changes.
* Some additions.
* Some replacements size_t by int64_t.
* Added casts to float in the construction of selected_score variable.
* Code style fixes.
* Written draft of NMS-5 nGraph reference implementation.
* Code style fixes.
* Started to write tests for void op::v5::NonMaxSuppression::validate_and_infer_types().
* Added tests for scalars/nonscalars.
* Fixes in the test type_prop.nms_v5_output_shape.
* Fixes in tests nms_v5_output_shape_2 and nms_v5_output_shape.
* Written tests for validate_and_infer_types() of NMS-5.
* Code style fixes.
* Now NMS-5 evaluate() can have outputs with calculated shapes.
* Small fixes.
* Corrected tests for NMS-5 validate_and_infer_type().
* Code style fixes.
* Started to write inner version of NMS-5 with static output shapes.
* Written draft of the inner operation NonMaxSuppressionIE3.
* Started to write conversion of op::v5::NonMaxSuppression into NonMaxSuppressionIE3.
* Small changes.
* Some additions.
* Small fixes.
* Fixed typo.
* Fixed typos.
* Written draft of the transformation ConvertNMS5ToLegacyMatcher that converts ngraph::opset5::NonMaxSuppression into op::NonMaxSuppressionIE3.
* Written header file for the transformations from NMS-1, NMS-3, NMS-4 to NMS-5.
* Started to write conversion of NMS-4 to NMS-5.
* Added include for ngraph/opsets/opset4.hpp.
* Started to write conversion of NMS-3 to NMS-5.
* Small fixes.
* Written draft of the conversion of NMS-3 into NMS-5.
* Fixed typo.
* Started to write conversion of NMS-1 to NMS-5.
* Written draft of the conversion NMS-1 to NMS-5.
* Started to write tests for the conversion nGraph NMS-5 to inner NMS.
* Started to write the test ConvertNMS5ToNMSIEStatic.
* Written tests for conversion of nGraph NMS-5 to inner NMSIE3.
* Started to write tests for conversion of previous NMS to nGraph NMS-5.
* Written tests for conversion of old nGraph NMS to NMS-5.
* Started to write tests for opset5::NonMaxSuppression::evaluate().
* Some additions.
* Small fix.
* Written tests for op::v5::NonMaxSuppression::evaluate().
* Used NGRAPH_RTTI_DECLARATION for NonMaxSuppressionIE3.
* Used NGRAPH_RTTI_DECLARATION for NMS-5.
* All static local constants and functions for NMS-5 were moved into non-named namespace.
* Some code style fixes.
* Moved some file.
* Small fix.
* Code style fix.
* Now NMS-5 supports all floating types in inputs 0 and 1.
* Moved some files.
* Fixed include directive in the file convert_nms_5_to_legacy.cpp with transformations NMS-1, 3, 4 -> NMS-5.
* Small changes.
* Deleted conversion NMS-3 -> legacy.
* Small changes.
* Fix in op::v5::NonMaxSuppression::evaluate: output shape [1] instead of [] in the output port 2.
* Code style fixes.
* Deleted conversion of NMS-4 into legacy NMS.
* Deleted redundant ifs.
* Added NMS-5 to Python API.
* Code style fix.
* Small change.
* Fixed element type for constants in the conversion of NMS-5 to NMSIE3.
* Deleted support of f64 in NMS-5.
* Added checks for input element types for inputs #0, #1, #3, #4, #5.
* Small change.
* Now get_floats throws an exception for unsupported types.
* Now nGraph NMS-5 supports 0D and 1D tensors in inputs #2, #3, #4, #5.
* Small fix in test_non_max_suppression.
* Deleted using namespace std
* Fixes in test_non_max_suppression().
* Small fixes.
* Added 'import PartialShape' in test_reduction.py.
* Deleted creating fake inputs in the ctor of op::v5::NonMaxSuppression.
* Deleted creating fake inputs in op::v5::NonMaxSuppression::clone_with_new_inputs.
* Corrections in int64_t op::v5::NonMaxSuppression::max_boxes_output_from_input() const.
* Corrected functions float op::v5::NonMaxSuppression::soft_nms_sigma_from_input() const, float op::v5::NonMaxSuppression::score_threshold_from_input() const, float op::v5::NonMaxSuppression::iou_threshold_from_input() const.
* Small fixes.
* Deleted commented code.
* Fixes in nms_v5_scalar_inputs_check.
* Some changes.
* Small fixes.
* Code style fixes.
* Small changes.
* Small changes.
* Small fix.
* Deleted commented code.
* Some refactoring in ConvertNMS4ToNMS5 ctor.
* Small fix.
* Common part of conversions NMS-1 -> NMS-5, NMS-3 -> NMS-5, NMS-4 -> NMS-5 was moved into the separate function.
* Now conversions NMS-1 -> NMS-5, NMS-3 -> NMS-5, NMS-4 -> NMS-5 support both 2 inputs, and 5 inputs.
* Now transformations NMS-1 -> NMS-5, NMS-3 -> NMS-5, NMS-4 -> NMS-5 are called from 'umbrella' transformation.
* Now the transformation ConvertNMS5ToLegacyMatcher supports NMS-5 with 2, 3, 4, 5, or 6 inputs.
* The transformation ConvertNMS5ToLegacyMatcher was rewritten using Reshape instead of Unsqueeze.
* Started to rewrite tests for the transformation ConvertNMS5ToLegacyMatcher.
* Some fixes.
* Small fixes.
* Corrected tests for the transformation NMS-5 -> NMSIE3.
* Small formatting fix.
* Now methods max_boxes_output_from_input(), iou_threshold_from_input(), score_threshold_from_input(), soft_nms_sigma_from_input() of op::v5::NunMaxSuppression are public.
* Started to move op::v5::NonMaxSuppression::evaluate() into ngraph/test/runtime/interpreter.
* Added NMS-5 to ngraph/test/runtime/interpreter/int_executable.
* Small fixes.
* Code style fixes.
* Written draft test nonmaxsuppression_center_point_box_format_backend in ngraph/test/backend.
* Small fix.
* Written draft tests of NonMaxSuppression in ngraph/test/runtime.
* Some changes.
* Small changes.
* Disabled IE_CPU tests for NMS-5.
* Deleted op_eval tests for NMS-5.
* Deleted evaluate() method of NMS-5.
* Now all nGraph functions in tests of the transformation NMS-5 -> NMSIE3 have one output.
* Now preprocessing and postprocessing of the calculation of NMS-5 in reference implementation.
* Code style fixes.
* Some fixes in tests for the transformation NMS-5 -> NMSIE3.
* Replaced precision i64 -> i32 for some constants in tests for the transformation NMS-5 -> NMSIE3.
* Written creating CNNLayer for NMS-5.
* Added creating CNNLayer for NonMaxSuppressionIE3.
* some changes.
* Now conversions NMS-1, NMS-3, NMS-4 -> NMS-5 and NMS-5 -> NMSIE3 generate NMS nodes with 5 inputs.
* Fixed ctor in MKLDNN NonMaxSuppressionImpl: validation of number of output edges.
* Added conversion of output_type for NMS-5.
* Fixes in the transformation NMS5 -> NMSIE3.
* Fixes in the conversion of NMS-5 to NMSIE3.
* Fixes in MKLDNN NMS ctor.
* Small fix.
* Fixed tests for the transformation NMS5 -> NMSIE3.
* Fixed tests for conversions NMS-1, NMS-3, NMS-4 -> NMS-5.
* Small fixes in MKLDNN NMS ctor.
* Rewritten create_layer() functions for NMS-5 and NMSIE3 as addSpecificCreator() functions.
* Disabled tests for IE IR reader for NMS-4.
* Deleted debug code.
* Added comment about disabling tests IE_CPU.nonmaxsuppression.
* Written IE IR Reader test for NMS-4.
* Deleted function float_from_constant_node.
* Small fixes.
* Deleted functions function_from_model and construct_weights.
* Small fix.
* Replaced push_back with emplace_back in the conversion of NMS-5 to legacy.
* Small changes.
* Some fixes.
* Refactored reference implementation of NMS-5.
* Moved structure NMSAttributes to unnamed namespace.
* Code style fixes.
* Small fix.
Maxim Vafin [Fri, 6 Nov 2020 16:04:46 +0000 (19:04 +0300)]
Fix the NHWC->NCHW transformation for dynamic weights (#2848)
* Fix the NHWC->NCHW transformation when weights and data comes from same input
* Simplify code
Katarzyna Mitrus [Fri, 6 Nov 2020 15:41:36 +0000 (16:41 +0100)]
MatMul spec update (#2765)
Aligned specification with nGraph MatMul shape inference operation. Affects description of the behavior for 1D tensors.
Edward Shogulin [Fri, 6 Nov 2020 13:15:27 +0000 (16:15 +0300)]
[LPT] integration branch: Reshape fix, Concat generalization, runtime info usage extending (#2930)
* [LPT] Concat transformation generalization
* [LPT] Reshape transformation fix
* [LPT] Legacy callback fix
* [LPT] * added rt_info propagation
* functional tests: added rt_info
* functional tests: added MoveDequatnizationAfter tests
Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
Ivan Tikhonov [Fri, 6 Nov 2020 11:11:11 +0000 (14:11 +0300)]
Low Latency transformation (#2869)
* initial draft of adding sinks to ngraph::Function
* style fixes
* code style fixes
* code style fixes
* code style fix
* review fix+build fix
* code style fix
* fix build
* API changed according to latest discussion
* review fixes
* review fixes + tests
* initial draft of adding sinks to ngraph::Function
* style fixes
* code style fixes
* code style fixes
* code style fix
* review fix+build fix
* code style fix
* fix build
* API changed according to latest discussion
* review fixes
* review fixes + tests
* added 1 more ctor
* style fixes
* used new api in ir parser
* fixed build
* update low latency transformation, fix unroll transformation, add unit tests, modify subgraph tests
* fix low latency transformation
* Update low latency transformation, unit and sub-graph tests
* update LowLatency transformation and tests
* ngraph codestyle
* fix build, update description
* resolve review remarks
Co-authored-by: Svetlana Dolinina <svetlana.a.dolinina@intel.com>
Maxim Kurin [Fri, 6 Nov 2020 10:45:45 +0000 (13:45 +0300)]
[OpenCL] movi-cltools-20.09.2 (#2912)
Alexandra Sidorova [Fri, 6 Nov 2020 10:22:02 +0000 (13:22 +0300)]
[CPU] Added LogSoftmax-5 support (#2743)
Mateusz Tabaka [Fri, 6 Nov 2020 08:36:33 +0000 (09:36 +0100)]
Remove deprecated v0::TopK (#2947)
* Remove deprecated v0::TopK
* Remove using SortType and using Mode from TopK
* apply code format
* Revert "Remove using SortType and using Mode from TopK"
This reverts commit
ee2f99ea89583f0cc5c34fe633dfbe900f4d1741.
Mateusz Tabaka [Fri, 6 Nov 2020 08:34:23 +0000 (09:34 +0100)]
Remove deprecated v0::Softmax (#2917)
Andrey Zaytsev [Fri, 6 Nov 2020 08:07:53 +0000 (11:07 +0300)]
Feature/azaytsev/layout updates (#2985)
* Reconfigured the layouts with importing the dedicated POT layout and Accuracy Checker and Model Downloader items from the OMZ layout
* updated
* test
* test
* Moved the Model Downloader from ie_docs.xml to openvino_docs.xml
* Renamed optimization_docs.xml --> pot_docs.xml
* Added Model Server to the layout
* Minor fixes
Vladimir Paramuzov [Fri, 6 Nov 2020 07:24:48 +0000 (10:24 +0300)]
[IE CLDNN] Removed unused conv kernels (#2995)
Maxim Andronov [Fri, 6 Nov 2020 05:59:23 +0000 (08:59 +0300)]
[CPU] Added support NMS-5 (#2768)
Vladimir Paramuzov [Thu, 5 Nov 2020 20:44:45 +0000 (23:44 +0300)]
[IE CLDNN] Plugin-side kernels caching (#2871)