Edward Shogulin [Fri, 23 Oct 2020 10:22:55 +0000 (13:22 +0300)]
Es/lpt/lpt to ngraph fixes2 with master (#2671)
* [LPT] Replace creation of dequantization with factory
* [ngraph][LPT] Add ScaleShift replace for dequantization operations
* [LPT] SubtractMultiplyToMultiplyAdd refactoring
* [LPT] Code style fix
* [LPT] Edit SubtractMultiplyToMultiplyAdd transformation for dequantization
* [LPT] Linux compilation quick fix
* [LPT] [WIP] runtime info applying
* [LPT] Concat transformation functional tests extending
* [LPT] MultiplyToConvolution + Subtract to add fusing + improvements in LowPrecisionTransformer
* [LPT] linux compilation error fix
* [LPT] compilation error
* [LPT] MultiplyToGroupConvolution fix: 5D support
* [LPT] Multiply transformation extending: FQ weights support - wip
* [LPT] FQ folding & precision selection
* [LPT] code style fixes
* [LPT] code style fixes
* [LPT] Linux compilation error fix
* [LPT] SubtractMultiplyToMultiplyAdd: refactoring
* [LPT] Tests fixes
* [LPT] MultiplyToGroupConvolution tests
* [LPT] Convert subtract with int inputs to Eltwise sub
* [LPT] Constant folding fix for quant models
* [LPT] 1) Asymmetric quantization improvement 2) tests extending
* [LPT] 2 fixes for se_resnext_50
* [LPT] Add transformation priority branch selection test
* [LPT] AddMultiplyFusion: legacy transformation quick fix
* [LPT] nGraph tests temporary disabling
* [LPT] Fix for eltwise inputs with multiple outputs
* [LPT] Fix for FQ fuse
* [LPT] Reshape by channel, batch temporary disabled
* [nGraph][LPT] MatMul fix for reading FP16 models
* [LPT] 1) Add (not after Convolution/GroupConvolution/MatMul with Constant) to Subtract 2) precision selection fix: MultiplyToGroupConvolution quick fix
* [LPT] DenseNet improvments: AddTransformation: Add to Subtract + tests
* [LPT] AddTransformarion refactoring
* [LPT] AddTransformation tests temporay disabled
* [LPT] ReshapeTransformation improvements: degradation fix
* [LPT] code style fix
* [LPT] Concat tests temporary disabling
* [LPT] tests unification
1) plugin tests: added test-cases and nGraph-validation for clamp, split and variadic split
2) func tests: added test-cases
3) transformNGraph: added the ability to run additional transformations
* [LPT] split & variadic split merge fix
* [LPT] Clamp: added support for asymmetric quantization
* [LPT] added DequantizationAttr run-time attribute
* [LPT] debug info removal
* [LPT] ConcatTransformation: zero point fix
* [LPT] CNNNetwork ReLU transformation quick fix
* [LPT]
1) Concat fix
2) ConcatMultiChannels fix
3) Added "Concat with Split" test-cases
4) Subgraph fix
* [LPT]
1) Concat fix
2) Added "Concat with different precision on childs" test-case
* [LPT] concat fix Ubuntu18
* [LPT] Concat test fixes
* [LPT] Not fp32 FQ input support
* [LPT] MatMul Fix + separateInStandaloneBranch Fix
* [LPT] Fix reference input types in mish fusion tests
* [LPT] Fix cpuFuncTests on CentOS building
* [nGraph][LPT] ScaleShift 2d, 3d nGraph conversion enabling
* [LPT] 1) FullyConnected workaround removing 2) validate_nodes_and_infer_types for LPT
* [ngraph] Add check for childs for ConvertSubtract
* [LPT] Squeeze/Unsqueeze tests unification
* [LPT] Squeeze/Unsqueeze change signature for getReference/getOriginal
* [LPT] Mul & Add -> ScaleShift quick fix
* [LPT] nGraph tests emporary disabling
* [LPT] code style fix
* [LPT] code style fix #2
* [LPT] nGraph tests temporary disabling
* [LPT] code styl fix #3
* [LPT] shared plugin tests temporary disabling
* [LPT] cleanup
* [LPT] nGraph unit_tests tests temproary disabling
* [LPT] nGraph unit tests disabling #2
* [LPT] nGraph tests disabling
* [LPT] nGraph tests temporary disabling
* [LPT] WA removing
* [LPT] CentOS compilation fix
* [LPT] KMB wa to avoid compilation error
* [LPT] functional test temporary disabling
* [nGraph] code style fixes
* [LPT] ConcatTransformation: data movement operation as intermediate handling
* [LPT] FuseSubtractToFakeQuantize after VariadicSplit
* [LPT] ConcatWithSplitTransformation functional test temporary disabling
* [LPT] Clamp and ConcatWithDifferentPrecisionsOnChilds: tests fix
* [LPT] MatMul: bert-nv-mlperf-quantized fix
* [LPT] Add to convolution biases fuse fix
* [LPT] GPU plugin tests fixes
* [LPT] Normalize GPU plugin tests fix
* [LPT] test-commit
* [LPT] CLDNN Plugin FP16 conversion
* [LPT] AvgPool update precision if there is not FQ after + convolution
precision limitation on activation
* [LPT] Convolution fixes
* [LPT] FuseSubtractToFakequantize & FuseMultiplyToFakeQuantize improvement
* [LPT] FuseSubtractToFakeQuantize test fix
* [LPT] FuseSubtractToFakeQuantizeTransformation tests
* [LPT] code style fix
* [LPT] AvgPool child recursive extend
* [LPT] AvgPool tests + fix
* [LPT] compilation quick fix
* [LPT] Add to convolution biases fuse fix
* [LPT] Linux issues: MatMulWithOptimizedConstantFakeQuantizeTransformation temporary disabled
* [LPT] Normalize GPU plugin tests fix
* [LPT] test-commit
* [LPT]
1) added the ability to create sub without dequantizationAttribute
2) fixed optimizeMulAfter: added copying rt_info
3) Tests Unification: Convolution transformation
4) added cleanRunTimeInfo into Network Helper
* [LPT] Tests Unification: GroupConvolution
* [LPT] removed debug info
* [LPT] functional tests for Convolution & GroupConvolution extending
* [LPT] [MatMul] Quick fix ubuntu error
* [LPT] MatMulTransformation quick test fix: one constant for both intervals
* [nGraph] code style fix
* [LPT] added output_precision to NormalizeIE
* [nGraph] NormalizeIE fix for LPT support
* [LPT] nGraph WA removal
* [LPT] fixed fillSubgraph for concat multi channels
* [LPT] MatMul fix
* [nGraph] WA removal: 1) nGraph tests enabling 2) LPT extanding: not handle in FP32
* [LPT] nGraph WA removal: function tests skip config rollback
* [LPT] WA removal: precision propagation fix
* [LPT] ConvertMulOrAddFinally transformation extending
* [nGraph] ConvolutionMultiplyFusion rollback (move from legacy to common)
* [nGraph] ConvertMulAddToScaleShiftOrPower: WA removal
* [nGraph] TypeRelaxed: WA removal
* [nGraph] WA removal: TypeRelaxed
* [LPT] WA removal: ConcatTransformation
* [nGraph] WA removal: Eltwise & ConvertMulOrAddFinally fixes to support LPT
* [nGraph] MulAddConversion fix: 2D & 3D ScaleShift are supproted
* [nGraph] VisualizeTree extending
* [LPT] FakeQuantizeDequantization extending: check element wise dequantization operation
* [LPT] FakeQuantizeDequantization extending: SubtractMultiplyToMultiplyAddTransformation & WeightableLayerTransformation
* [LPT] Convolution + test infrastructure update
* [LPT] GPU compilation error
* [nGraph] BatchNorm plugin tests: input tensor definition
* [LPT] LowPrecisionTransformer::isFunctionQuantized was added
* [nGraph] WA final cleanup
* [nGraph] ScaleShiftIE quick fix
* [LPT] Functional tests: added test-cases "Concat with intermediate with constant"
* [LPT] Transformer::isNetworkquantized fix
* [LPT] SubtractMultiplyToMultiplyAdd zero Add remove: fix for ssd300 on gpu
* [LPT] MultiplyToGroupConvolution not transform on Const
* [LPT] workaround for negative scales
* [LPT] Convert standalone dequantization Mul,Sub,Add to ScaleShift
* [LPT] SubtractMultiplyToMultiplyAdd test fix
* [LPT] Clamp transformation: GPU tests fix
* [LPT] Transformer tests
* [LPT] FakeQuantizePrecisionSelectionTransformation was disabled for GPU
* [LPT] TransformerIsFunctionQuantized refactoring
* [nGraph] code style fix
* [LPT] mobilenet_v2_tf_depthwise test update
* [LPT] TMP: dequantization folding
* [LPT] Elementwise transformation fix: dequantization operations constant folding
* [LPT] cleanup
* [LPT] denormal values fix
* [LPT] FuseFakeQuantize test fixed + negative multiply case
* [LPT] FP32 -> FP16 conversion info
* [LPT] FQ dot interval support + swapMultiplyAdd safely division
* [LPT] test fix
* [LPT] Tests for dot interval on FQ + tests for addTransformation enabling
* [LPT] Clamp transformation fix
* [LPT] FQ prec selection test fix
* [LPT] Clamp test case
* [LPT] Concat division precision fix
* [LPT] cleanup
* [LPT] merge fix
* [LPT] WIP: MatMul asymmetric quantization fix (BERT)
* [LPT] MatMulWithOptimizedConstantFakeQuantizeTransformation disabled
* [LPT] GPU Plugin set config fix
* [LPT] Fix merge mistakes
* [LPT] Rollback device specific INT8
* [LPT] ReshapeFullyConnected fix: FullyConnected output fix
* [LPT] bert-base-chinese GPU fix
* [ngraph/LPT] Tests for fix convert_mul_or_add_finally with dequantization
[ngraph/LPT] Fix convert mul_or_add_finally with dequantization
* [LPT] ScaleShift dim < 4 only dequantization conversion
* [LPT] MatMul transformation tests extensing
* [LPT] ReshapeFullyConnected legacy transformation: LPT test case addition
* [nGraph] VisualizeTree extending: property names displying to simplify search
* [LPT] getDequantization extending
* [LPT] MulAddToScaleshiftOrPower: out precision fix & tests
* [LPT] Multiply to ScaleShiftIE: Multiply transformation: remove DEQUANTIZATION if not valid
* [LPT] Concat test case
* [nGraph] try to fix opencv compatibility
* [nGraph] nGraph code style fix
* [LPT] InPlace dequantization folding
* [LPT] Multiply constant folding test
* [LPT] Fix plugin test case for MatMulWithOptimizedConstantFakeQuantize
[LPT] Enable MatMulWithOptimizedConstantFakeQuantize plugin test
* [LPT] Convolution transformation: mulConst shape fix
* [LPT] INT8 Constant folding branch for elementwise ops optimization removal
* [LPT] eltwise for const branch fix
* [LPT] linux fix
* [LPT] Multiply test refactoring
* [LPT] Convert Fuse in Constant + tests
* [LPT] function comparation: runtime info comparation rollback
* [LPT] linux build fix
* [LPT] linux build fix2
* [LPT] MatMul transformation limitation was added to be similar as CNNNetwork LPT
* [LPT] Reshape transformation update: don't broadcast by batch
* [LPT] MatMul transformation limitation was added to be similar as CNNNetwork LPT - refactoring
* [LPT] MatMul transformation: transpose input tensors fix
* [LPT] checkElementwise for AddTransformation WA: should be moved to getDequantization
* [LPT] merge fix
* [LPT] MatMul fix & tests
* [LPT] AddTransformation tests
* [LPT] Interpolate transformation enabled
* [LPT] constant folding before LPT
* [LPT] WIP: not completed tests
* [LPT] GPU degradation fix
* [LPT] FuseConvert workaround
* [LPT] code cleanup
* [LPT] Interpolate GPU test quick fix
* [LPT] GroupConvolution fix
* [LPT] Fix fusing multiply for non-dequantization layers
* [LPT] GPU pipeline update: enableInt8 initialization place update
* [LPT] tests compilation fix
* [LPT] merge fix
* [LPT] tests enabling
* [LPT] merge issue resolving
* [LPT] LPT CNNNetwork usage macros: part #1: source code
* [LPT] LPT CNNNetwork usage macros: part #2: cmake files update and tests addoption
* [LPT] LPT workaround from nGraph core removing
* [LPT] previous LPT version tests
* [LPT] inference_engine_lp_transformations was returned back
* [LPT] replace_node rollback
* [LPT] ConvertSubtract fix
* [LPT] GPU: baselineIsFP16 reuse fix
* [LPT] FakeQuantizeTransformation: GPU workaround: I32 -> FP32 Convert is not fused
* [LPT] AvgPool output precision workaround
* [LPT] Group convolution precision + Subtract to ScaleShift const fix
* [LPT] SubMulToMulAdd & Transpose: action-recognition-0001 fix
* [LPT] Transpose: added test with per-tensor quantization
Co-authored-by: Aleksandr Pertovsky <aleksandr.pertovsky@intel.com>
Co-authored-by: Zinoviev, Vladimir <vladimir.zinoviev@intel.com>
Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
Co-authored-by: Gorokhov Dmitriy <dmitry.gorokhov@intel.com>
Egor Churaev [Fri, 23 Oct 2020 10:16:47 +0000 (13:16 +0300)]
[IE CLDNN] Fix linear_onnx Interpolate selection (#2769)
Evgenya Stepyreva [Fri, 23 Oct 2020 10:14:00 +0000 (13:14 +0300)]
[ MO ] KSO=ON for Kaldi (#2028)
* [ MO ] KSO=ON for Kaldi
* [ MO ] Kaldi KSO
* set static_shape for graph cycle making transformation
Tomasz Dołbniak [Fri, 23 Oct 2020 10:13:04 +0000 (12:13 +0200)]
ONNX Reader supportModel() implementation (#2744)
iliya mironov [Fri, 23 Oct 2020 09:35:56 +0000 (12:35 +0300)]
Transformations for hsigmoid op (#2531)
* Add hsigmoid op
* Add tests for hsigmoid
* Add fusion hsigmoid
* Add unit tests for fuse hsigmoid
* Add python api for hsigmoid. Update opset 5
* Update opset5 file
* Add hsigmoid decomposition transformation
* fix
* Move transformations for hsigmoid
* Hot fix
* Fix unit tests
* fix unit tests
* Fix unit test
* Fix code style
* Reverse changes
* Add includes for hsigmoid transformations
* Enable in cldnn
* Refactoring hsigmoid fusion
* Move hsigmoid transforms patterns to cpp file
* Reverse hsigmoid fusion refactoring
* Fix according to code review
* Refactoring transformation
* Hot fix
Piotr Szmelczynski [Fri, 23 Oct 2020 08:39:00 +0000 (10:39 +0200)]
Reference implementation for Tile op (#2641)
Mateusz Tabaka [Fri, 23 Oct 2020 08:25:08 +0000 (10:25 +0200)]
Remove obsoleted Dequantize op (#2780)
* Remove obsoleted Dequantize op
* apply code style
Ilya Lavrenov [Fri, 23 Oct 2020 07:39:55 +0000 (10:39 +0300)]
Fixed -Werror=catch-value= gcc-9 error (#2773)
Mikołaj Życzyński [Fri, 23 Oct 2020 07:16:21 +0000 (09:16 +0200)]
[IE CLDNN] Fix padding in reduce fsv16 kernel (#2787)
Tomasz Dołbniak [Fri, 23 Oct 2020 06:58:12 +0000 (08:58 +0200)]
Fix the model downloader script (#2784)
Roman Donchenko [Fri, 23 Oct 2020 06:17:03 +0000 (09:17 +0300)]
Fix spelling errors in the API and bindings (#2781)
Ilya Lavrenov [Fri, 23 Oct 2020 05:54:48 +0000 (08:54 +0300)]
Openvino extra module adding - refactored (#2754)
* Rename plugin to module
* Added openvino_contrib handling
* Moved NEON flags to common place
* Fixed -Werror=catch-value= gcc-9 error
Ilya Lavrenov [Thu, 22 Oct 2020 13:11:28 +0000 (16:11 +0300)]
Removed obsolete comments from cmake (#2748)
Jan Iwaszkiewicz [Thu, 22 Oct 2020 12:06:23 +0000 (14:06 +0200)]
[ONNX] WA for I64 images (#2411)
Andrew Bakalin [Thu, 22 Oct 2020 12:04:53 +0000 (15:04 +0300)]
[VPU][GT][Tests] Make gemmTranspose pass layout agnostic (#2666)
* [VPU][GT] Make permTranspose pass layout agnostic
* [IE][Tests] Improve MatMul common test class
* [VPU][Tests] Add tests for MatMul
* [VPU][Tests] Review fixes
* [Tests] Add combineShapes for MatMul
* [VPU][GT] Fix assertion condition
Vladimir Paramuzov [Thu, 22 Oct 2020 11:42:42 +0000 (14:42 +0300)]
[IE CLDNN] Base kernels refactoring (#2758)
Ilya Churaev [Thu, 22 Oct 2020 10:22:38 +0000 (13:22 +0300)]
Constant->Result networks (#2639)
* Added tests
* Changed iterator algorithm
* Fixed legacy tests
* Added plugin tests
* Disabled some tests
* Remover parameter tests
* Fixed conversion
* Use old approach for old tests
* Temp commit
* Fixed iterator
* Fixed some tests
* Change logic to compare iterators
* Disabled CPU functional test
* Temp commit
* Disabled test for GPU
* Fixed network copy
* Try to fix test for Windows
* Disabled test for GNA
* Disable plugin tests
* Disable legacy test
* Remove redundant code
Ilya Churaev [Thu, 22 Oct 2020 10:21:23 +0000 (13:21 +0300)]
Added new version of BatchNormInference (#2728)
* Added new version of BatchNormInference
* Fixed code style
* Fixed batch norm inference v5
* Added opset4 and opset5 to IE backend
* Fixed functional test
* Fixed cpuFunc tests
* Fixed transformation order
* Try to fix validation
* Revert some changes
* Updated python API and added tests
* Fixed code style
* Fixed python code style
* Disabled test
Vladimir Paramuzov [Thu, 22 Oct 2020 10:06:27 +0000 (13:06 +0300)]
[IE CLDNN] Extend supported fusing cases for scale and eltwise (#1960)
Mateusz Tabaka [Wed, 21 Oct 2020 10:48:53 +0000 (12:48 +0200)]
Use MVN in GroupNorm/InstanceNorm in ONNX importer (#2711)
* Use MVN in GroupNorm/InstanceNorm in ONNX importer
* Remove mosaic_8 model from xfail list
Jedrzej Hajduczenia [Wed, 21 Oct 2020 10:36:32 +0000 (12:36 +0200)]
[IE CLDNN] Another try to fix multiple-kernel implementations profiling (#2630)
Tomasz Dołbniak [Wed, 21 Oct 2020 08:50:16 +0000 (10:50 +0200)]
Use LogSoftmax-5 in the onnx_importer (#2602)
Anton Pankratv [Wed, 21 Oct 2020 03:40:18 +0000 (06:40 +0300)]
Supported threading command line options for other devices (#2725)
* Supported thrieding command line options for ohter devices
* Fixed python benchmark
Vladislav Vinogradov [Wed, 21 Oct 2020 03:34:35 +0000 (06:34 +0300)]
[NGRAPH] Fix UNITY build (#2732)
Anton Chetverikov [Tue, 20 Oct 2020 15:36:19 +0000 (18:36 +0300)]
Add Round-5 operation (#2328)
* Add Round-5 operation
* Add ONNX Round to supported operation list
* Add ngraph implementation for Round operation
* Update MO part
* Create UnaryElementwise class, update Round Operation
* Fix mode attr in mxnet extractor
* Add tests for Round shape infer
* Update 'enable' attr
* Update MO IR Reader to support UnaryElementwise operations
* Minor test refactor
* Update ngraph Round operation
* Add reference implementation
* Add test for reference implementation
* Add test for shape infer
* Add test for IE IR Reader
* AddRound operation to python api
* Fix missed mode attr
* Update Round operation version
* Fix codestyle
* Add MxNet Round to supported layers list
* Fix error in reference
* Fix comments style
* Update CMake file
* Update Ngraph reference test
* Update IE IR Reader tests
* Return v0::Round operation
* Update shape infer tests
* Fix v0::Round reference
* Fix codestyle
* Enum instead of string
* Fix codestyle
* Add Mode attribute adapter
* Update Mode attr
* Fix reference for v0::Round
* Fix codestyle
* Fix mode attr
* Fix get() method
* Fix codestyle in python api
* Update test info
* Fix ngraph api part
* Ad round v5 to interpreter tests
* Fix codestyle is ie reader test
* Update ngraph python api __init__.py file
* Adde opser5 to dafault opsets in ie_ir reader
* Add parser for Round layer
* Remove redundant spaces
* Add round creator to appropriate list
* Remove redundant import
* Commit to bump infrastructure version
I'm sorry for this, but this commit will be squashed on merge to master anyway and it is needed for your PR to correctly pass the pipeline
* Fix import
* fix codestyle
* Fix ngraph api part
* Add shape infer tests in python api
* Add .upper() for mode attr
* Refactor MO shape infer test for Round op
* Update tests and add comments
* Revert "Commit to bump infrastructure version"
This reverts commit
56e6ae1e4c31439ba0d4636fa76782c03bf30aca.
* remove parser for Round layer
* Update Ronund-5 evaluate test
* Resolve review comments
Co-authored-by: User <user@nnlvdp-achetver.inn.intel.com>
Co-authored-by: Andrey Babushkin <andrey.babushkin@intel.com>
Co-authored-by: Anton Chetverikov <anton.chetverikov@.intel.com>
Irina Efode [Tue, 20 Oct 2020 11:31:59 +0000 (14:31 +0300)]
Cleanup single_layer_tests (#2716)
Maxim Vafin [Tue, 20 Oct 2020 10:40:06 +0000 (13:40 +0300)]
Add LogSoftmax-5 to MO and ngraph (#2409)
Co-authored-by: Evgeny Lazarev <evgeny.lazarev@intel.com>
Mateusz Tabaka [Tue, 20 Oct 2020 09:36:46 +0000 (11:36 +0200)]
Remove deprecated Any op from nGraph (#2719)
Mateusz Tabaka [Tue, 20 Oct 2020 09:19:03 +0000 (11:19 +0200)]
[ONNX] Add type conversion for Pow op inputs (#2589)
Co-authored-by: mitruska <katarzyna.mitrus@intel.com>
Roman Kazantsev [Tue, 20 Oct 2020 06:57:55 +0000 (09:57 +0300)]
Implement LookupTableInsert shape inference (#2348)
* Implement LookupTableInsertV2 shape inference
It is needed if other nodes not beeing pruned in the graph
have a conditional dependence on LookupTableInsertV2 node.
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix after core-review #1
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix the code after review #2
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix after code review #3
Anna Likholat [Mon, 19 Oct 2020 16:38:55 +0000 (19:38 +0300)]
[JAVA] Fixed IECore constructor (#2685)
Vladimir Paramuzov [Mon, 19 Oct 2020 15:45:05 +0000 (18:45 +0300)]
[IE CLDNN] DispatchData refactoring (#2508)
Nikolay Shchegolev [Mon, 5 Oct 2020 08:58:54 +0000 (11:58 +0300)]
[CPU] CTCLoss performance improvement.
Anton Potapov [Mon, 19 Oct 2020 09:35:59 +0000 (12:35 +0300)]
[PP GAPI] Extended plug-ins shared precision conversion tests to use (#2677)
`GetBlob()` as well
- test were extended to cover case when input tensors are copied into
Blob return by `InferRequest::GetBlob`
- channel number of input tensor is made a test parameter
Krzysztof Bruniecki [Mon, 19 Oct 2020 09:21:01 +0000 (11:21 +0200)]
Improve GNA MT sychronization (#2553)
* Sync GNA lib calls to avoid multi threads and plugins crash
* Remove TODO
* Enable sync for GNA1
* Fix GNA1 sync
* Add core_threading_tests to GNA Plugin to address story 31709
* Disable and change test description
Vitaliy Urusovskij [Mon, 19 Oct 2020 06:48:38 +0000 (09:48 +0300)]
Remove `memcheck_pregen_irs_tests` MemCheck configs due obsolescence (#2693)
Mateusz Tabaka [Mon, 19 Oct 2020 05:40:04 +0000 (07:40 +0200)]
Revise LRN reference implementation (#2672)
* fix typo in LRN docs
* fix link to reference in LRN doc
* LRN, LRN_IE types alignment with spec
* align LRN ref implementation to plugins behavior
* update LRN docs
* Improve LRN reference implementation performance
* restore LRN constructor with no axes in the input
* apply code format
* revert double->float size_t->int change
* small fix to example in doc
* revert double->float size_t->int in onnx_importer and backend tests
* Changes to docs after review
Ivan Tikhonov [Mon, 19 Oct 2020 03:53:46 +0000 (06:53 +0300)]
[opset5] ngraph implementation of Loop op (#2583)
* 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
* 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
* add a new constructor of Loop op, resolve review remarks
Roman Lyamin [Sun, 18 Oct 2020 17:47:22 +0000 (20:47 +0300)]
[IE CLDNN] Added HSigmoid operation (#2700)
Michał Karzyński [Sun, 18 Oct 2020 15:12:25 +0000 (17:12 +0200)]
Improve python_wheel CMake target (#2688)
Michał Karzyński [Sun, 18 Oct 2020 15:08:06 +0000 (17:08 +0200)]
Tweaks for ONNX scoreboard (#2697)
Alexey Suhov [Fri, 16 Oct 2020 18:03:46 +0000 (21:03 +0300)]
[install_dependencies.sh] install latest cmake if current version is lower 3.13 (#2695)
* [install_dependencies.sh] install latest cmake if current version is lower 3.13
* add shellcheck for Ubuntu
* install python 2.7 for Ubuntu
Jesus Espinoza [Fri, 16 Oct 2020 16:02:41 +0000 (09:02 -0700)]
Updating broken link on getting started linux doc (#2507)
Link to build instructions was broken, updated link to the correct location.
Ilya Churaev [Fri, 16 Oct 2020 15:12:20 +0000 (18:12 +0300)]
Small fix for python doc (#2696)
Andrey Dmitriev [Fri, 16 Oct 2020 12:34:22 +0000 (15:34 +0300)]
[GNA][Speech sample] Add option to specify blob names (#1529)
* Added output names
* Add input, output, ref names
* Added zero scale factor
* Adding support for multiple reference files
Kamil Magierski [Fri, 16 Oct 2020 10:23:32 +0000 (12:23 +0200)]
[GNA] Fix remove layer + identity layer insertion (#2626)
* [GNA] Fix remove layer + identity layer insertion
test stub
Test impl
style
hpp style
* disable FP16 for GPU
Michał Karzyński [Fri, 16 Oct 2020 09:34:26 +0000 (11:34 +0200)]
Remove segfault marks form test_unary_op_scalar and test_range tests (#2692)
Co-authored-by: Ewa21 <ewa.tusien@intel.com>
Tomasz Dołbniak [Fri, 16 Oct 2020 09:30:20 +0000 (11:30 +0200)]
Avoid unnecessary Reshape in ONNX Softmax impl (#2686)
Tomasz Dołbniak [Fri, 16 Oct 2020 09:30:00 +0000 (11:30 +0200)]
Use GatherND-5 in the onnx_importer (#2634)
Ilya Lavrenov [Fri, 16 Oct 2020 07:58:38 +0000 (10:58 +0300)]
Added apiValidator post-build checks for WCOS compliance (#2657)
* Added apiValidator post-build checks for WCOS compiance
* WA for cmake
* Additional checks for old WDK version
Egor Churaev [Fri, 16 Oct 2020 07:14:22 +0000 (10:14 +0300)]
[IE CLDNN] Add FP16 axes precision to Interpolate-4 (#2681)
JIRA: 40805
Michał Karzyński [Fri, 16 Oct 2020 06:44:03 +0000 (08:44 +0200)]
Workaround for Cython issue on Python 3.8 (#2684)
azhogov [Fri, 16 Oct 2020 05:19:46 +0000 (08:19 +0300)]
Set chmod +x for model_zoo_preprocess.sh
Vladislav Vinogradov [Fri, 16 Oct 2020 03:57:30 +0000 (06:57 +0300)]
[NGRAPH] Fix UNITY build under Windows (#2678)
Gabriele Galiero Casay [Thu, 15 Oct 2020 20:30:12 +0000 (22:30 +0200)]
Reference Implementation for RegionYolo operator (#2474)
Michał Karzyński [Thu, 15 Oct 2020 20:15:33 +0000 (22:15 +0200)]
Update nGraph Python API build instructions (#2610)
Evgenya Stepyreva [Thu, 15 Oct 2020 18:39:42 +0000 (21:39 +0300)]
Broadcast visit_attributes fix (#2649)
* Broadcast visit_attributes fix
* Broadcast: Python API adjustment
* Revert back deserialization change
Tomasz Socha [Thu, 15 Oct 2020 17:04:43 +0000 (19:04 +0200)]
[ONNX] Replace global poolings with reduce operations (#2650)
Mateusz Tabaka [Thu, 15 Oct 2020 13:47:20 +0000 (15:47 +0200)]
Update test_shufflenetv2 tolerance values (#2674)
* Update test_shufflenetv2 tolerance values
* Update model path
* Update models xfails
* Update mounting volumes to container
Co-authored-by: rblaczko <rafal.blaczkowski@intel.com>
Katarzyna Mitrus [Thu, 15 Oct 2020 10:42:21 +0000 (12:42 +0200)]
ReorgYolo reference implementation (#2384)
* Align ReorgYolo to the spec (vector strides -> int stride)
* ReorgYolo ref impl
* ReorgYolo evaluate method
* ReorgYolo tests
* Tests update
* Style apply
* Add some coments
* Code refactor
* Comment update
* Style apply
* Build fix, mark evaluate as override
* Revert "Align ReorgYolo to the spec (vector strides -> int stride)"
* Use int_executable instead of evaluate
* Use char* instead of templates
* Code refactor
* Comment update
* Code review comment
* Add constructor aligned with spec
* Update shape validation
* Update attributes tests
* Add type_prop tests
* Update backend tests
* Add single layer tests
* Update the spec
* Remove wrong transformation test
Vladimir Paramuzov [Thu, 15 Oct 2020 07:28:00 +0000 (10:28 +0300)]
[IE CLDNN] Fixes for GatherTree and ReverseSequence (#2660)
iliya mironov [Thu, 15 Oct 2020 04:41:46 +0000 (07:41 +0300)]
Add hsigmoid op to ngraph (#2647)
Roman Kazantsev [Thu, 15 Oct 2020 04:40:58 +0000 (07:40 +0300)]
Extend MO for operation GatherND (#2540)
* Extend MO for operation GatherND
* Update documentation
* Rename GatherNd.py to gathernd.py
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
Anastasiya Ageeva [Wed, 14 Oct 2020 18:50:02 +0000 (21:50 +0300)]
Fixed CVS-35316 (#2072)
Vitaliy Urusovskij [Wed, 14 Oct 2020 17:05:52 +0000 (20:05 +0300)]
Time tests improvements (#2642)
* Remove extra functions from run_timetest.py
* Add `log.debug` of raw and aggregated statistics in run_timetest.py
* Implement storing of models locally for test_timetest.py
Evgeny Lazarev [Wed, 14 Oct 2020 16:12:25 +0000 (19:12 +0300)]
Loop-5 operation specification (#2291)
The Loop-5 operation specification
Andrey Somsikov [Wed, 14 Oct 2020 15:35:21 +0000 (18:35 +0300)]
Fix itt build (#2662)
Artyom Anokhov [Wed, 14 Oct 2020 15:33:17 +0000 (18:33 +0300)]
setupvars.sh: Updated setting pyenv error to warning. (#2663)
Vladimir Gavrilov [Wed, 14 Oct 2020 13:47:43 +0000 (16:47 +0300)]
nGraph implementation of NMS-5 (without `evaluate()`) (#2651)
* Written nGraph NMS-5 without evaluate().
* Used NGRAPH_RTTI_DECLARATION.
Evgeny Lazarev [Wed, 14 Oct 2020 13:43:29 +0000 (16:43 +0300)]
Leaky relu transformation refactor (#2640)
* Refactored LeakyRelu transformation
* Added unit test for LeakyRelu transformation + removed duplicate test function valued_const
Maksim Doronin [Wed, 14 Oct 2020 11:30:59 +0000 (14:30 +0300)]
[IE][VPU]: Added DSR_Reshape tests with dynamic output shape descriptor (#2607)
* Added DSR_Reshape tests with dynamic output shape descriptor
Andrew Bakalin [Wed, 14 Oct 2020 10:35:17 +0000 (13:35 +0300)]
[IE][VPU]: TopK: Relax requirement for supporting Sort::None mode if K==1 (#2653)
* Update firmware
* Add TopK tests
* Disable some cases
Andrey Somsikov [Wed, 14 Oct 2020 10:08:06 +0000 (13:08 +0300)]
Use ittnotify built from sources (#2577)
* Use ittnotify built from sources
ITT tracing was only possible on the platfroms supported by VTune.
Building ittnotify from sources removes VTune dependency.
ITT traces was found significantly slowdown tests execution time.
Disabling ENABLE_PROFILING_ITT by default. This is also
a current behavior of Intel Distribution of OpenVINO.
* Fix missprint
* Add include directories to itt
Mateusz Bencer [Wed, 14 Oct 2020 09:30:53 +0000 (11:30 +0200)]
Provide ONNX external data mechanism to ReadNetwork (#2588)
* added unit test
* added python test
* using pword approach
* Added passing path to onnx reader
* support for wstring
* Added more tests
* Apply suggestions from code review
Co-authored-by: Michał Karzyński <4430709+postrational@users.noreply.github.com>
* fix build for Windows
* styles applied
* Fixed Windows tests
* styles applied
* fixed styles in tests
* review remarks
* cmake order
* Used target_compile_definitions instead of add_definitions
* Move ONNX_TEST_MODELS to other scope
Co-authored-by: Michał Karzyński <4430709+postrational@users.noreply.github.com>
Roman Kazantsev [Wed, 14 Oct 2020 09:20:22 +0000 (12:20 +0300)]
Extend nGraph for operation GatherND-5 and implement reference (#2587)
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
Mateusz Bencer [Wed, 14 Oct 2020 08:17:44 +0000 (10:17 +0200)]
Fix using numpy scalars in Python API (#2520)
* fixed numpy scalars
* reverted tests changes
* python style fixed
Andrew Bakalin [Wed, 14 Oct 2020 08:02:21 +0000 (11:02 +0300)]
[IE][VPU]: Support DTS for Split (#2576)
* [IE Tests] Remove unnecessary cout
* [VPU] Add DTS for split
* [VPU][Tests] Add tests
Gleb Kazantaev [Wed, 14 Oct 2020 07:58:01 +0000 (10:58 +0300)]
Move legacy transformations and ops to legacy library (#2624)
* Initial movement
* Divided transformations to common and legacy
* Changed ngraph visibility to ie_api.h
* CommonTransformaitons to Internal
* New trasnformations location structure
* fixde typo; move convert_quantize_dequantize to common
* Added control_flow folder
Ilya Lavrenov [Wed, 14 Oct 2020 07:43:24 +0000 (10:43 +0300)]
used native LTO support from cmake 3.9.6 (#2625)
* used native LTO support from cmake 3.9.6
* Removed compilation flags push / pop
* Fixes
* Fixes for VPU unit tests
* Temp WA for old gcc
Ilya Churaev [Wed, 14 Oct 2020 06:42:39 +0000 (09:42 +0300)]
Do reshape only if input shapes will be changed (#2632)
* Added private reshape
* Removed incorrect check
Anton Chetverikov [Wed, 14 Oct 2020 05:10:05 +0000 (08:10 +0300)]
Round-5 nGraph implementation (#2652)
* Implement nGraph Round-5 operation
* Remove reference implementation
* Add shape infer tests
* Fix codestyle
Maxim Vafin [Wed, 14 Oct 2020 05:08:27 +0000 (08:08 +0300)]
Add LogSoftmax-5 to ngraph (#2645)
Maksim Derbasov [Wed, 14 Oct 2020 03:46:12 +0000 (06:46 +0300)]
General code fixes (#2609)
Irina Efode [Tue, 13 Oct 2020 21:58:28 +0000 (00:58 +0300)]
[IE TESTS] Remove some deprecated single layer tests (#2646)
* [IE TESTS] Remove some deprecated single layer tests
* Gather Tree
Vladislav Vinogradov [Tue, 13 Oct 2020 14:35:55 +0000 (17:35 +0300)]
[IE][NGRAPH][BUILD] Enable UNITY build for more targets (#2592)
* Avoid symbols clash due to source merging.
* Tested on Ubuntu 20.04 with GCC 9.3.0.
Ilya Lavrenov [Tue, 13 Oct 2020 14:22:51 +0000 (17:22 +0300)]
Plugin interface refactoring (#2591)
* Simplified plugin interface
* Allow not implemented
* Fixes
* Fixed CPU plugin tests
* Fixed tests dependencies
* Fixes
* Fixed GPU plugin compilation
* Renamed plugin
* Fixes
* Removed tests for plugin base
* Fix2
* Fix 2
* Define a macro to define plugin creation function
* Clean-up
* Fixed OSX build
* Fixed CentOS
* Removed statuscode from IExecutableNetworkInternal interface
* Interface
* Removed not used macro
* QueryNetwork returns result using return value
* LoadNetwork interface
* Fixed compilation with private plugins
* Fixed compilation when NGRAPH_INTERP is not enabled
* Return ExecutableNetwork from ImportNetwork with fileName
* Updated GetContext method
* Return exec graph information as return value
* Message about deprecation of Export with file name
* Message about deprecation of QueryState
* Updated ExecutableNetwork::GetConfig signature
* Updated ExecutableNetwork::GetMetric signature
* Updated docs
* WIP createIR
* Simplified IR creation
* CreateInferRequest returns value
* Removed GetExecutor from ExecutableNetworkThreadSafeDefault
* execDataPreprocessing is protected
* Fixed mock test
Jedrzej Hajduczenia [Tue, 13 Oct 2020 13:40:30 +0000 (15:40 +0200)]
[IE CLDNN] Revert fix for profiling of multiple kernel implementations (#2219) (#2595)
Alexander Zhogov [Tue, 13 Oct 2020 10:27:34 +0000 (13:27 +0300)]
GitHub CI: Add files_size.yml (#2570)
* GitHub CI: Add files_size.yml
* Update job name
Vladislav Vinogradov [Tue, 13 Oct 2020 08:37:30 +0000 (11:37 +0300)]
[IE][BUILD] Fix C5208 warning under Windows (#2628)
* C++ feature in C `typedef struct` code.
* The warning can be promoted to error in dependent projects.
C5208: unnamed class used in typedef name cannot declare members other than
non-static data members, member enumerations, or member classes
helmutg [Mon, 12 Oct 2020 20:24:24 +0000 (22:24 +0200)]
add build option USE_SYSTEM_PUGIXML (#2502)
It allows skipping inference-engine/thirdparty/pugixml and using the
system copy instead.
Thanks to @Osse for helping understand cmake scoping rules.
Co-authored-by: Helmut Grohne <helmut.grohne@intenta.de>
Alexander Zhogov [Mon, 12 Oct 2020 16:23:00 +0000 (19:23 +0300)]
Azure CI: Fix nGraph ONNX
Alexander Zhogov [Mon, 12 Oct 2020 16:20:28 +0000 (19:20 +0300)]
Azure CI: Disable steps in nGraph ONNX
azhogov [Mon, 12 Oct 2020 15:46:14 +0000 (18:46 +0300)]
Azure CI: Add linux_ngraph_onnx.yml
Nikita Kudriavtsev [Mon, 12 Oct 2020 13:37:31 +0000 (16:37 +0300)]
[IE Myriad] Fix layer tests for logical_and (#2622)
Ilya Lavrenov [Mon, 12 Oct 2020 11:16:30 +0000 (14:16 +0300)]
Fixed ODR for LTO with gcc5 (#2615)
Pavel Esir [Mon, 12 Oct 2020 11:10:27 +0000 (14:10 +0300)]
[MO] [Kaldi] Add TDNN Component (#1870)
* [MO] [Kaldi] Added TDNN Component
* TdnnComponent replacer graphical comment updated
* Added SpecAugmentTimeMaskComponent
* some refactor of memoryoffset shape_infer
* moved memoryoffset splitting to the middle stage
* some corrections
- set `need_shape_inferenc`=False in split_memoryoffset
- use cycle instead of pattern in tdnn_replacer
* separated splitting of MemoryOffsets in LSTM and TDNN blocks
* set transpose_weights=True in TdnnComponent
* Corrected Supported_Frameworks_Layers
* corrected comments
* separate naming for tdnn and lstm memoryoffset splits
* corrected BOM file
* corrected generaldropout_ext.py and removed 'has_default' for tdnn_component
* corrections after PR review
* renamed LSTM -> recurrent; added setting element_size for paired nodes of tdnn_memoffset and othe minor changes
* Update split_tdnn_memoryoffset.py
* corrected partial infer with new API in elemental.py and split_tdnn_memoryoffset.py
Anastasia Kuporosova [Mon, 12 Oct 2020 10:52:49 +0000 (13:52 +0300)]
[IE TOOLS] Support of models with output port in names (#2594)
Pavel Esir [Mon, 12 Oct 2020 06:55:45 +0000 (09:55 +0300)]
[MO] Fix ONNX Clamp-11 shape infer with no min/max inputs (#2603)
Ilya Znamenskiy [Mon, 12 Oct 2020 05:36:57 +0000 (08:36 +0300)]
[IE CLDNN] TopK registry spill avoiding for sort-by-value mode (#2590)
Mateusz Tabaka [Mon, 12 Oct 2020 04:36:19 +0000 (06:36 +0200)]
Tests and docs for registering custom ONNX operators (#2416)
* Add tests, examples and documentation changes for custom ONNX operators registration mechanism
* Change snippet paths
* fix CoreThreadingTests.ReadNetwork - data race in ops_bridge
* Make TemplateExtension::Operation externally visible
* changes after review
* apply code format
* use std::int64_t
* forward declare get_attribute_value specializations
* introduce unregister_operator in onnx_importer
* onnx_custom_op - lock mem first then take a buffer
* func tests - create template_extension via make_so_pointer
* fix build with NGRAPH_ONNX_IMPORT_ENABLE=OFF
* remove exports from Operation and Extension
* Move multithreaded AddExtension test to different directory to it can be excluded when NGRAPH_ONNX_IMPORT_ENABLE=OFF
* Dont include Extension tests if ENABLE_MKL_DNN=OFF
* fix excluding onnx_reader tests
* include extension tests only if mkl is enabled
* add comment on empty blob
* use register_operator conditionally in template_extension
* fix docs after review
* create static library from onnx_custom_op
* add additional test for unregister_operator
* move model example after register step
* revert changes to unit tests
* update ngraphConfig.cmake.in header
* add headers to onnx_custom_op
* changes to docs CMakeLists
* remove redundant onnx_importer dependency
* remove extension directory from func tests
* make onnx_importer a component of ngraph package
* docs fixes
* update header of ngraph/cmake/share/ngraphConfig.cmake.in with ngraph_onnx_importer_FOUND