Roman Kazantsev [Mon, 24 Aug 2020 15:01:45 +0000 (18:01 +0300)]
Disable eager execution affecting TensorFlow 1 concept model handling (#1914)
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
Konrad Dobros [Mon, 24 Aug 2020 14:37:46 +0000 (16:37 +0200)]
[IE CLDNN] Fix concat in place with conv interactions (#1714)
This change fixes concatenation in place optimization where it may
interact with convolution that uses physical padding.
One of such cases is where input to optimized concatenation is also
input to convolution, so it should have padding to enable optimized
implementation.
Previously for all concatenation inputs padding was overriden with only
concatenation axis being padded.
This change fixes this issue by propagating padding across inputs and
output.
Tomasz Socha [Mon, 24 Aug 2020 11:58:38 +0000 (13:58 +0200)]
Add reshaping of dynamic network in python tests (#1850)
Anastasia Kuporosova [Mon, 24 Aug 2020 11:57:55 +0000 (14:57 +0300)]
[Python API] Deprecation of DataPtr.creator_layer and DataPtr.input_to properties (#1905)
Ivan Tikhonov [Mon, 24 Aug 2020 11:31:32 +0000 (14:31 +0300)]
Partial revert a commit with reference implementations of PriorBox(Clustered) ops (#1878)
* partial revert a commit with reference implementations of PriorBox(Clustered), disable references for this ops
* ngraph codestyle
* disable const folding unit tests for PriorBox(Clustered)
* fix arm build
* fix unit test
* Revert "fix unit test"
This reverts commit
1fe59e55d620c430e81c52edd3fc46f2b5b1a9b9.
Evgenya Stepyreva [Mon, 24 Aug 2020 11:30:41 +0000 (14:30 +0300)]
[ MO ] Reinfer shape sub-graphs once (#1908)
* [ MO ] Reinfer shape sub-graphs once
* feedback
* feedback
Liubov Batanina [Mon, 24 Aug 2020 11:16:29 +0000 (14:16 +0300)]
Added test for Pad (#1902)
* Addded test for Pad
* Add builder
Ivan Tikhonov [Mon, 24 Aug 2020 11:11:01 +0000 (14:11 +0300)]
Fix Assign, Matmul ops for correct work with keep_shape_ops feature for Kaldi models (#1885)
* fix assign and matmul ops
* fix unit test
* static shapes by default for kaldi
Vladimir Paramuzov [Mon, 24 Aug 2020 10:03:39 +0000 (13:03 +0300)]
[IE CLDNN] Enabled tensor pitches in topk kernel for 0 input (#1898)
Lukasz Debski [Mon, 24 Aug 2020 10:03:21 +0000 (12:03 +0200)]
[IE CLDNN] Forcing bfzyx format in MVN layer (#1903)
Mateusz Tabaka [Mon, 24 Aug 2020 09:26:15 +0000 (11:26 +0200)]
Reduce number of ops needed to create InstanceNorm (#1896)
* Reduce number of ops needed to create InstanceNorm
InstanceNorm in onnx importer creates the same subgraph for Mean twice - once for Variance and once for actual Mean.
This change makes InstanceNorm to use single Mean which is shared by numerator and Variance.
Also enables IE_CPU.onnx_model_instance_normalization test case
* Revert changes to .gitignore
Vladimir Paramuzov [Mon, 24 Aug 2020 05:47:45 +0000 (08:47 +0300)]
[IE CLDNN] FP16 support for some quantized kernels (#1855)
Tomasz Dołbniak [Fri, 21 Aug 2020 14:22:54 +0000 (16:22 +0200)]
Linux clang compilation error fix (#1891)
Evgenya Stepyreva [Fri, 21 Aug 2020 13:27:02 +0000 (16:27 +0300)]
[ MO ] Change layout of Shape sub-graphs once (#1875)
* [ MO ] Change layout of Shape sub-graphs once
Tomasz Dołbniak [Fri, 21 Aug 2020 12:15:27 +0000 (14:15 +0200)]
Accept empty initializers from ONNX models (#1776)
* Accept empty initializers from ONNX models
* Create dummy constants instead of null nodes
* Code formatting
* Test the empty initializers handling in onnx importer
Denis Orlov [Fri, 21 Aug 2020 11:43:01 +0000 (14:43 +0300)]
[GNA] Additional checks (#1018)
Ilya Churaev [Fri, 21 Aug 2020 10:13:44 +0000 (13:13 +0300)]
Added detailed error messages for cases when network has dynamic shapes on the conversion moment (#1890)
Harald Rotuna [Fri, 21 Aug 2020 08:59:12 +0000 (11:59 +0300)]
Add method to classification_result for returning results (#1460)
Gleb Kazantaev [Fri, 21 Aug 2020 02:51:42 +0000 (05:51 +0300)]
Fix addOutput (#1888)
Alexander Zhogov [Thu, 20 Aug 2020 17:53:01 +0000 (20:53 +0300)]
Azure CI: Enable all MklDnnFunctionalTests (#1881)
* Azure CI: Enable all MklDnnFunctionalTests
* Update azure-pipelines.yml
* Disable failed test on Mac: moke_MobileNet/ModelTransformationsTest.LPT/mobilenet_v2_tf_depthwise_batch1_inPluginDisabled_inTestDisabled_asymmetric*
Ilya Churaev [Thu, 20 Aug 2020 15:46:34 +0000 (18:46 +0300)]
Fixed error message for ONNX importer tests (#1880)
Anna Likholat [Thu, 20 Aug 2020 15:45:14 +0000 (18:45 +0300)]
[JAVA] Changed blob costructor (using cArray) in samples (#1863)
Ilya Lavrenov [Thu, 20 Aug 2020 15:34:19 +0000 (18:34 +0300)]
Reuse make_executable_network in ImportNetwork (#1869)
* Reuse make_executable_network for ImportNetwork
* make_executable_network returns ExecutableNetwork cpp wrapper
Anton Potapov [Thu, 20 Aug 2020 15:32:41 +0000 (18:32 +0300)]
Updating ADE version (#1877)
- Fix gcc 9 build warnings
Jedrzej Hajduczenia [Thu, 20 Aug 2020 11:54:54 +0000 (13:54 +0200)]
[IE CLDNN] Add 3d spatials support to conv & pool imad kernels and unblock any in/out feature sizes (#1693)
Evgeny Lazarev [Thu, 20 Aug 2020 10:57:22 +0000 (13:57 +0300)]
ONNX ScatterND MO support (#1813)
* Added extractor for ONNX operation ScatterNDUpdate
* Updated list of supported operations for ONNX
Roman Lyamin [Thu, 20 Aug 2020 10:32:16 +0000 (13:32 +0300)]
[IE TESTS] Added single layer tests HSwish (#1861)
Anton Dudchenko [Thu, 20 Aug 2020 09:56:12 +0000 (12:56 +0300)]
[IE][VPU]: Execution graph via ngraph for VPU plugin (#1572)
* Execution graph via ngraph for VPU plugin
* Enable ExecGraphTests
* Assert throw for multi device in tests
* Assert throw for gna device in tests
Evgenya Stepyreva [Thu, 20 Aug 2020 09:33:44 +0000 (12:33 +0300)]
[ MO ] FloorDiv replacement (#1860)
* [ MO ] FloorDiv replacement
* BOM file
* Review comments
* FloorDiv in SupportedFrameworkList.md
Ewa Tusień [Thu, 20 Aug 2020 09:31:43 +0000 (11:31 +0200)]
Remove Structural Attributes from Proposal op. (#1853)
Ilya Churaev [Thu, 20 Aug 2020 09:27:14 +0000 (12:27 +0300)]
Deprecate nGraph v0 ops and builders (#1856)
* Deprecate nGraph v0 ops
* Fixed build
* Added deprecated defines to fix windows
Evgenya Stepyreva [Thu, 20 Aug 2020 09:06:45 +0000 (12:06 +0300)]
[ MO ] KSO ON by default (#1730)
* [ MO ] KSO ON by default.
Introduce static_shape MO key, remove keep_shape_ops key usages
* keep_shape_ops -> static_shape
* static_shape = False by default
* Fix Proposal-4 shape infer
* style-apply
* Fix Layout Change for ShapeOf paths
Pavel Rodionov [Thu, 20 Aug 2020 07:59:21 +0000 (10:59 +0300)]
Revert "[GNA] Remove old GNA1 from Cmake scripts (#1686)" (#1864)
This reverts commit
ffe8599c309b32ef4bf6b6e73ea7a2edd2c048c0.
Artyom Anokhov [Wed, 19 Aug 2020 19:21:34 +0000 (22:21 +0300)]
install_NEO_OCL_driver.sh: Added downloading driver functionality after removal NEO from the package (#1872)
Evgeny Lazarev [Wed, 19 Aug 2020 17:18:04 +0000 (20:18 +0300)]
Restore change of i64 parameters to i32 (#1866)
Ewa Tusień [Wed, 19 Aug 2020 15:55:20 +0000 (17:55 +0200)]
Change "run_op_node" helper to use Parameter instead of Constant (#1722)
* Replace Constant with Parameter in run_op_node.
* Pass inputs to function.
* Add func to get shape.
* Make constant if input is scalar.
* Add case for list.
* Fix test.
* Split tests for run_op_node and run_op_numeric_data.
* Split more tests.
* Split more and more tests.
* Mark tests with xfail.
* Mark more tests with xfail.
* Replace scalar with parameter.
* Code formatting.
* Set empty shape for scalar.
* Remove check for list.
Gleb Kazantaev [Wed, 19 Aug 2020 15:55:11 +0000 (18:55 +0300)]
Moved AlgebraicSimplification and NopElimination passes to IE (#1859)
* Moved AlgebraicSimplification and NopElimination passes to IE
* Fixed headerfiles
Vladimir Paramuzov [Wed, 19 Aug 2020 13:19:42 +0000 (16:19 +0300)]
[IE CLDNN] Enable fsv16 format for all quantized models (#1791)
Vladislav Vinogradov [Wed, 19 Aug 2020 13:05:00 +0000 (16:05 +0300)]
[NGRAPH] Fix system protoc version check in CMake (#1852)
Add `OUTPUT_STRIP_TRAILING_WHITESPACE` option to `execute_process` command.
Latest CMake (tested 3.18.1) doesn't strip new line from `protoc --version` call,
which leads to wrong `PROTOC_VERSION` variable and failure on git fetch step.
Evgeny Latkin [Wed, 19 Aug 2020 13:03:37 +0000 (16:03 +0300)]
re-enable the myriadMultipleGraphsTests_nightly (#1836)
* re-enable the myriadMultipleGraphsTests_nightly
* refresh version of Myriad firmware
Anna Alberska [Wed, 19 Aug 2020 13:03:18 +0000 (15:03 +0200)]
[GNA] add support for 4d eltwise (#1353)
* [GNA] add support for 4d eltwise
* cpplint fix
* refactor
* fix FP16 broadcast pass
* change anonymous function to InferenceEngine::details::product
* introduce anonymous function to the pass & add layer checks
* refactor tileBlob lambda
Jedrzej Hajduczenia [Wed, 19 Aug 2020 12:51:24 +0000 (14:51 +0200)]
[IE CLDNN] Fix vector iterators incompatibility issue in prepare_primitive_fusing (#1842)
Gleb Kazantaev [Wed, 19 Aug 2020 11:57:28 +0000 (14:57 +0300)]
Fixed addOutput (#1844)
* Fixed addOutput
* Added tests; removed addOutput second call
Vladimir Paramuzov [Wed, 19 Aug 2020 11:17:45 +0000 (14:17 +0300)]
[IE CLDNN] Mixed precision scale support (#1848)
Evgeny Lazarev [Wed, 19 Aug 2020 10:58:57 +0000 (13:58 +0300)]
Removed MO conversion of i64 inputs to i32 (#1835)
Anton Chetverikov [Wed, 19 Aug 2020 10:23:41 +0000 (13:23 +0300)]
ExtractImagePatches MO implementation and nGraph transformation (#739)
Yegor Kruglov [Wed, 19 Aug 2020 09:32:16 +0000 (12:32 +0300)]
[ MO ] Random Uniform Replacer (#1814)
Ilya Lavrenov [Wed, 19 Aug 2020 08:44:29 +0000 (11:44 +0300)]
LoadNetwork interface: executable network is returned as return value (#1840)
* LoadNetwork interface
* Added reference to SOPointer to returned ExecutablNetwork
* Fixed test
Edward Shogulin [Wed, 19 Aug 2020 08:36:48 +0000 (11:36 +0300)]
[LPT] Symmetric quantization support for efficientnet-b0 (#1773)
* [LPT] Symmetric quantization for efficientnet-b0
* [LPT] zero point calculation fix
Co-authored-by: Zinoviev, Vladimir <vladimir.zinoviev@intel.com>
Vladimir Paramuzov [Wed, 19 Aug 2020 07:10:55 +0000 (10:10 +0300)]
[IE CLDNN] Use fsv4 instead of af32 layout for imad case (#1784)
Ilya Churaev [Wed, 19 Aug 2020 06:41:59 +0000 (09:41 +0300)]
Fixed path for pad reference impl (#1846)
Sergey Nesterov [Wed, 19 Aug 2020 06:18:00 +0000 (08:18 +0200)]
[IE CLDNN] added fusing support for ref and b_fs_yx_fsv16 implementations (#1692)
Katarzyna Mitrus [Wed, 19 Aug 2020 05:04:00 +0000 (07:04 +0200)]
Enable HSwish - ngraph op, fusion/decomposition and reference implementation (#1770)
* Add HSwish operator to nGraph
* Add HSwishFusion transformation
* Update check_constant function
* Add reference implementation for HSwish
* Enable reference implemenation in HSwish evaluate
* Add op_eval test
* HSwish fusion transformation test
* Add HSwishFusionWithoutRelu transformation
* Add more hswish fusion tests
* Register HSwishFusion pass in common_optimizations
* Update HSwish reference implementation
* Add HSwishFusion with Relu and Multiply
* Add HSwishDecomposition transformation pass
* Add HSwishDecomposition test
* Add HSwish op to ngraph python API
* Update HSwish fusion transformations
* Remove HSwishFusion from common optimizations
* Update hswish python API
* Add bf16 to evaluate hswish
* Update hswish python API
* Move hswish reference implementation
* UnaryElementwiseArithmetic inheritance
* Enable HSwish callback for clDNN
* Register HSwishDecomposition pass in ConvertOpSet1ToLegacy
* Enable HSwishFusion pass in common optimizations
* Use NGRAPH_RTTI_DECLARATION
* Moved python hswish test to the test_ops_unary
Maxim Vafin [Wed, 19 Aug 2020 04:58:41 +0000 (07:58 +0300)]
Add Range-4 support (#1552)
* Add Range-4 support
* Add type infer and IR Reader extender
* Implement ngraph Range-4
* Implement evaluate for Range-4
* Remove not needed types
* Resolve review feedback
* Add RTTI defines
Ivan Tikhonov [Wed, 19 Aug 2020 04:09:32 +0000 (07:09 +0300)]
Remove ngraph::Lambda class, replace TensorIterator body with ngraph::Function (#1830)
* remove Lambda class, replace TensorIterator body with ngraph::Function
* Fix passing parameters from parent graph to subgraph
Co-authored-by: mbencer <mateusz.bencer@intel.com>
Ilya Lavrenov [Wed, 19 Aug 2020 03:53:17 +0000 (06:53 +0300)]
Return serialization to IR v7 under conditional compilation (#1820)
Ilya Churaev [Wed, 19 Aug 2020 03:37:04 +0000 (06:37 +0300)]
Fixed set/get batch size logic for scalar inputs (#1837)
Mateusz Bencer [Tue, 18 Aug 2020 15:28:57 +0000 (17:28 +0200)]
Optimize Concat operation (#1812)
* 1d case optimization
* code refactor
* concat optimization
* removed using template for concat
* unit tests to concat constant folding
* synchro with current master
Gleb Kazantaev [Tue, 18 Aug 2020 14:40:45 +0000 (17:40 +0300)]
Convert Pad to GroupConvolution transformation (#1826)
* Added ConvertPadToConvolution pass
* Removed NasNet transformation from MO
* Renamed Conv to GroupConv; Added tests
* Fixed typo; Added RTTI
Ilya Lavrenov [Tue, 18 Aug 2020 13:50:37 +0000 (16:50 +0300)]
Ngraph: hide itt.hpp to src (#1834)
* Use proper include for log.hpp
* Hide itt.hpp to src folder
* Removed CodeWriter
Anna Alberska [Tue, 18 Aug 2020 13:41:46 +0000 (15:41 +0200)]
[GNA] Implement ImportNetwork from stream (#1743)
* add ImportNetwork from stream
* add test for importing network from stream
Denis Orlov [Tue, 18 Aug 2020 13:11:10 +0000 (16:11 +0300)]
Merge changes from 2020.4.0.1 (#1809)
* [GNA] Propagate QoS timeout to the calling app (#1188)
* [GNA] Support timeout value set in Wait (#1499)
* [GNA] stored request id for completed sync infer request in order to get status later using wait() (#1458)
* stored request id for completed async infer request in order to get it's status later
* preserved status not started for multiple sequential calls to wait()
Co-authored-by: Denis Orlov <denis.orlov@intel.com>
* [GNA] Fix callbacks (#1607)
Co-authored-by: Eugene Smirnov <eugene.smirnov@intel.com>
Ilya Churaev [Tue, 18 Aug 2020 10:49:30 +0000 (13:49 +0300)]
Add arithmetic operators for bfloat16 (#1831)
Roman Kazantsev [Tue, 18 Aug 2020 10:47:59 +0000 (13:47 +0300)]
Fix a specification for CTCLoss operation (#1786)
Tomasz Dołbniak [Tue, 18 Aug 2020 10:43:54 +0000 (12:43 +0200)]
v1::Pad evaluator (#1771)
* v1::Pad reference implementation
* ut fix: pad_negative_exterior_1d
* ut fix: pad_negative_exterior_1d_check_limits & pad_edge_1d
* Code formatting
* ut fix: pad_edge_1d_top_neg & pad_edge_1d_top_neg_bigger_than_tensor
* More Pad UT fixes
* Pad UT fixes: REFLECT mode
* Fix all Pad UTs
* Switch Pad evaluation in INT backend
* Non-template solution to v1::Pad::evaluate
* Always create v1::Pad with 4 inputs
* VS compilation error fix
* Python test fix
* Remove the v0::Pad constant folding pass
* Some extra checks in v1::Pad evaluator
* Code formatting
* Remove an obsolete CF test
Mateusz Bencer [Tue, 18 Aug 2020 10:10:23 +0000 (12:10 +0200)]
Add ONNX Round op (#1605)
Gladilov, Gleb [Tue, 18 Aug 2020 09:09:06 +0000 (12:09 +0300)]
[IE][VPU]: Reverts nGraph TI Unrolling for VPU (#1824)
Evgeny Latkin [Tue, 18 Aug 2020 09:05:18 +0000 (12:05 +0300)]
[IE][VPU]: Fixed MX firmware memory type patching (#1825)
Fixing Myriad X firmware loader after RTEMS 5 related changes merged into MDK
* Fixed MX firmware memory type patching
* Update firmware
* disable myriadMultipleGraphsTests_nightly
Co-authored-by: Chekhonin Andrey <andrey.chekhonin@intel.com>
Gleb Kazantaev [Tue, 18 Aug 2020 08:10:24 +0000 (11:10 +0300)]
ConvertPrecision for element::boolean (#1772)
* Added bool to u8 conversion
* Added opset1::ShapeOf handler
* Added ReduceLogicalAnd/Or support in ConvertPrecision pass
* Moved static map inside function; Updated callbacks
* Removed header
* Fixed tyle relaxed for cases when the same output consumes by multiple inputs in the same operation; added tests; fixed input types setting for already created type relaxed operations
Anna Likholat [Tue, 18 Aug 2020 05:38:48 +0000 (08:38 +0300)]
Java bindings (#506)
* java bindings added
* bulid saples alongside with IE build
* fixes
* fixes
* fixed comments
* fixes
Ilya Lavrenov [Mon, 17 Aug 2020 19:46:12 +0000 (22:46 +0300)]
Removed NGRAPH_API from reference library (#1821)
Tomasz Socha [Mon, 17 Aug 2020 19:14:39 +0000 (21:14 +0200)]
[FIX] Fix data layout for reshaped network (#1748)
* [FIX] Fix data layout for reshaped network
* [PATCH] Don't change compatible layouts
* Add UT for reshaped network
* FIX no. 1
Ilya Churaev [Mon, 17 Aug 2020 16:43:11 +0000 (19:43 +0300)]
Add static library with nGraph reference implementations (#1810)
* Removed reference implementations from public API
* Remove coordinate_transform from public API
* Introduced static library with reference implementations
Roman Kazantsev [Mon, 17 Aug 2020 16:19:59 +0000 (19:19 +0300)]
Extend MO for operation CTCLoss and partly refactor CTCGreedyDecoder (#588)
* Extend MO for operation CTCLoss
* Change sequence length format to a mask format
* Add fixes after first-round review
* Add fixes after the second-round review
* Fixing CTCLossPlusCTCGreedyDecoder transformation
Maksim Doronin [Mon, 17 Aug 2020 14:30:38 +0000 (17:30 +0300)]
[IE][VPU]: Refactor vpu configs (#1334)
* [IE][VPU]: Refactor vpu configs
* [IE][VPU][GT]: Refactor vpu configs usage in GT
* [IE][VPU]: Refactor vpu configs usage in myriad plugin
* [IE][VPU]: Refactor vpu configs usage in tests
* [IE][VPU]: Refactor vpu configs usage in deprecated_tests
* [IE][VPU]: Refactor vpu configs usage in tools
* [IE][VPU]: Use hddl metric vars instead of macros
* [IE][VPU]: style fixes
* [IE][VPU]: Replace MYRIAD_FORCE_RESET with MYRIAD_ENABLE_FORCE_RESET
* [IE][VPU]: Resolve confilcts with MYRIAD_TILING_CMX_LIMIT_KB
* [IE][VPU]: Remove MYRIAD_PLATFORM from tools
* [IE][VPU]: Fix DISABLE_REORDER config in StridedSlice
* [IE][VPU]: Redesign config headers hierarchy
* [IE][VPU]: Clarify comments related to vpu configs
* [IE][VPU]: Leave default values of deprecated configs
* [IE][VPU]: Revert beh tests on VPU_MYRIAD_PLATFORM
* [IE][VPU]: Revert beh tests with deprecated configs
* [IE][VPU]: Resolve conflicts
* [IE][VPU]: Revert opencv dependency
Evgeny Lazarev [Mon, 17 Aug 2020 13:32:53 +0000 (16:32 +0300)]
Enable ReduceL1 and ReduceL2 operations (#1799)
* Initial version of ReduceL1, ReduceL2 and ReduceLp enabling in the MO
* Added operations ReduceL1 and ReduceL2 to nGraph
* Removed ReduceLp. Added ReduceL1 and ReduceL2
* Separated specification of ReduceLp into ReduceL1 and ReduceL2
* Updated ReduceL1 and ReduceL2 specification
* Fixed ReduceL1 and ReduceL2 type prop tests
* Implemented nGraph transformation to decompose ReduceL1 and ReduceL2. Disabled them for CPU and GPU plugins
* Updated supported framework layers
* Added unit tests for ReduceL1 and ReduceL2 reference implementation
* Fixed ReduceXXX operations reference implementation by adding support for a new parameter 'keep_dims'
* Fixed constant folding for v0::Any
* Added ReduceL1 and ReduceL2 to Python API
* Implemented ReduceL1 and ReduceL2 decomposition tests and fixed ReduceL2 decomposition
* Added specific creator for ReduceXXX operations instead of NodeBuilders
* Fixed conversion ReduceXXX to CNNLayer
* Fixed parser for ReduceLogicalXXX operations
Mikhail Letavin [Mon, 17 Aug 2020 13:27:33 +0000 (16:27 +0300)]
[IE CLDNN] Export runtime graph as nGraph function (#1684)
Gleb Kazantaev [Mon, 17 Aug 2020 12:39:58 +0000 (15:39 +0300)]
FGTT for CF (#1792)
* Added FGTT for ConstantFolding
* Added test for CF disabling
Maxim Vafin [Mon, 17 Aug 2020 11:38:41 +0000 (14:38 +0300)]
Fix problem with renaming outputs from network (#1546)
Vladimir Paramuzov [Mon, 17 Aug 2020 11:34:49 +0000 (14:34 +0300)]
[IE CLDNN] All input layouts support in ref pooling (#1782)
Maxim Andronov [Mon, 17 Aug 2020 11:25:53 +0000 (14:25 +0300)]
[CPU] fix conv + concat case and add tests (#1747)
Ilya Churaev [Mon, 17 Aug 2020 10:37:00 +0000 (13:37 +0300)]
Removed template headers for Fused Ops (#1780)
Anastasia Kuporosova [Mon, 17 Aug 2020 09:41:54 +0000 (12:41 +0300)]
[Python API] Deprecate IENetLayer class (#1731)
* [Python API] Deprecate IENetLayer class
* update samples
* undo changes in samples
Vladimir Paramuzov [Mon, 17 Aug 2020 09:39:30 +0000 (12:39 +0300)]
[IE CLDNN] Set arguments once (#1699)
Mateusz Bencer [Mon, 17 Aug 2020 08:13:06 +0000 (10:13 +0200)]
Add reference implementation to VariadicSplit (#1698)
* implementation of variadic split ref impl
* Added tests
* added unit tests
* refactor
* review remarks
* fixed ie tests
Evgeny Latkin [Mon, 17 Aug 2020 08:02:00 +0000 (11:02 +0300)]
[IE][VPU][GT]: fix pool 3d to 2d reduction (#1760)
* Fix minor error in pooling 3D to 2D conversion
Ilya Znamenskiy [Mon, 17 Aug 2020 07:09:18 +0000 (10:09 +0300)]
[IE CLDNN] Gemm floating point unit-tests fix (#1797)
Sergey Shlyapnikov [Mon, 17 Aug 2020 06:56:23 +0000 (09:56 +0300)]
[IE CLDNN] Fix for DepthToSpace fusing into convolution (#1724)
Nikolay Shchegolev [Mon, 17 Aug 2020 03:10:51 +0000 (06:10 +0300)]
[NGraph] CTCLoss reference implementation. (#1453)
Ilya Churaev [Mon, 17 Aug 2020 03:05:08 +0000 (06:05 +0300)]
Remove nGraph layout (#1763)
Pavel Esir [Sun, 16 Aug 2020 12:49:49 +0000 (15:49 +0300)]
add preliminary support of Proposal-4 in nGraph (#1448)
renamed logits -> bbox_deltas
updated ngraph unittests for Proposal
removed validate_and_infer_types Proposal-4
removed validate_and_infer_types Proposal-4
changed validate_and_infer_types in parent class of Proposal
removed get_output_size
successfully inferred Proposal on SSH and Faster-RCNN
added unittests for Proposal-4
added unittests for Proposal-4
added unittests for Proposal-4
returned back default namespace for Proposal
reduced number of outputs in v0::Proposal
correct conversion of Proposal-4 -> propodal_ie with 2 outputs
removed creator for proposal v0
removed converter for proposal v0
added Proposal-4 to MO
removed `for_deformable` attribute
added Proposal-4 to MO and nGraph Python API
removed typo in Proposal-4 specification
style corrections
style corrections and removed some redundant code
rename proposal Python api test
removed 'attrs' context from visitor
returned back AttrVisitor to check if passes OpenVINO ONNX pipeline
Should pass OpenVINO ONNX pipeline (returned back AttrVisitor just to check)
python api for Proposal-4 works ok
(style correction) python api for Proposal-4 works ok
parametrized proposal_ie some other corrections
removed 'attrs.' context from nGraph Python API tests for Proposal
minor corrections in replacer proposal->proposal_ie
corrected Python API OpenVINO-ONNX tests should pass
Improved workaround for AttributeVisitor for Proposal
Add additional check of im_info tensor shape to Proposal node in MKLDNNPlugin
😠 removed 4 extra spaces from test_dyn_attributes.py to match The Style
added new nGraph RTTI declarations, removed throwing exception in transformation
added new nGraph RTTI declarations, removed throwing exception in transformation, corrected exception in MKLDNNplugin
corrected im_info size checking in Proposal node of MKLDNNPlugin
Anton Pankratv [Sat, 15 Aug 2020 11:44:13 +0000 (14:44 +0300)]
Added split test into template plugin (#1669)
* Added split test into template plugin
* Fixed split test
* Fixed test parameters style
Alexander Zhogov [Fri, 14 Aug 2020 22:31:34 +0000 (01:31 +0300)]
Azure CI: Pipeline improvements (#1790)
* Azure CI: Pipeline improvements
* Fix checkout
* Fix path
* Fix "Install IncrediBuild"
* Add "submodules: recursive"
* Fix test run
* Fix work dir
* Fix issue
* Increase timeout
Anastasiya Ageeva [Fri, 14 Aug 2020 15:47:58 +0000 (18:47 +0300)]
Added OpenVINO Get Started Guide for Windows (#1631)
Gleb Kazantaev [Fri, 14 Aug 2020 15:35:11 +0000 (18:35 +0300)]
Removed deprecated MulAddFusion pass (#1789)
Andrew Bakalin [Fri, 14 Aug 2020 15:10:57 +0000 (18:10 +0300)]
[IE][VPU][GT]: Add pass for marking fast stages (#1579)
It was discovered that it is sometimes useful to mark fast stages (e.g. stages that process less than 100 elements) in order to be able to parse them from final performance report and estimate its contribution into performance.
* Added pass for marking fast stages
* Introduced unit tests
Alexander Chaiko [Fri, 14 Aug 2020 13:02:37 +0000 (15:02 +0200)]
[IE CLDNN] Disable non-performant fp32 batches FC layer (#1737)
Mikhail Letavin [Fri, 14 Aug 2020 11:50:33 +0000 (14:50 +0300)]
[IE CLDNN] dp4a check that works both with old and new drivers (#1766)
Gleb Kazantaev [Fri, 14 Aug 2020 10:47:02 +0000 (13:47 +0300)]
opset4 Convolution/GroupConvolution -> Multiply fusion (#1754)
* Added new predicates for smart pattern matching
* Added ConvMul and GroupConvMul fusion passes based on opset4; Added CPU functional tests for comparing fusion accuracy
* Improved ConvMultiply fusion to support scalars; Added positive and negative tests
* Added ConvolutionBackprop/GrouConvolutionBackprop Multiply fusion; Added functional tests
Ilya Lavrenov [Fri, 14 Aug 2020 09:11:54 +0000 (12:11 +0300)]
Simplified plugin interfaces (#1745)
* 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
* Fixed exception catch / throw
* Fixed clang issue
* Fixed python tests on macOsx