Anton Chetverikov [Thu, 27 Aug 2020 10:10:44 +0000 (13:10 +0300)]
Update priorbox extenders (#1925)
Evgeny Lazarev [Thu, 27 Aug 2020 08:56:52 +0000 (11:56 +0300)]
MO fusing activations (#1942)
* Added HSwish operation
* Added HSwish fusing transformation
* Fixed BOM
* Added unit test for HSwish fusing transformation
* Fixed unit tests for transformations using 'build_graph_with_edge_attrs' function to build the graph
* Added fusion transformation for Swish operation
* Added fusing transformation for Softplus operation
* Added fusion transformation for Mish operation
* Added check for the node name in the unit tests
* Fixed Mish fusion pattern
* Updated Mish fusion transformation. Added unit test
* Updated HSwish fusing transformation
* Updated Swish fusion transformation and tests
* Fixed unit tests
Evgenya Stepyreva [Thu, 27 Aug 2020 08:52:04 +0000 (11:52 +0300)]
ExperimentalDetectron* shape infer old-style (#1962)
* ExperimentalDetectron* shape infer old-style
* nGraph reshape tests
Vladimir Paramuzov [Thu, 27 Aug 2020 08:43:24 +0000 (11:43 +0300)]
[IE CLDNN] Mixed mode support for proposal primitive (#1857)
Evgenya Stepyreva [Thu, 27 Aug 2020 06:45:08 +0000 (09:45 +0300)]
[MO] Relax Reshape layer hardcode under MatMul (#1921)
* [MO] Relax Reshape layer hardcode under MatMul
* Memory fix
Evgeny Lazarev [Thu, 27 Aug 2020 05:46:34 +0000 (08:46 +0300)]
Added workaround for logical elementwise operations to change the constant input data type if it does not match the other one (#1955)
Jedrzej Hajduczenia [Wed, 26 Aug 2020 17:58:51 +0000 (19:58 +0200)]
[IE CLDNN] Fix fused ops in 1x1 conv fsv16 kernel (#1948)
Vladimir Paramuzov [Wed, 26 Aug 2020 17:58:21 +0000 (20:58 +0300)]
[IE CLDNN] Fixed memory allocation for case when usm is not available (#1952)
Ilya Churaev [Wed, 26 Aug 2020 17:45:54 +0000 (20:45 +0300)]
Fixed mean image support for IR v10 (#1926)
* Fixed mean image support for IR v10
* Fixed comments
Mikhail Ryzhov [Wed, 26 Aug 2020 15:53:24 +0000 (18:53 +0300)]
Modified samples to support ONNX models (#1680)
* Modified samples to support ONNX models
- Removed manual loading of IR .bin files (hello_classification, object_detection_sample_ssd)
- Corrected comments
- Added Note in README files
* Modified samples to support ONNX models
- Removed manual loading of IR .bin files (hello_classification, object_detection_sample_ssd)
- Corrected comments
- Added Note in README files
Artyom Anokhov [Wed, 26 Aug 2020 14:25:33 +0000 (17:25 +0300)]
[SCRIPTS] install_NEO_OCL_driver.sh: Added verifying current driver version (#1951)
* install_NEO_OCL_driver.sh: Added verifying current driver version
* install_NEO_OCL_driver.sh: Updated removal oldest driver on Ubuntu. Updated logic on defining
* install_NEO_OCL_driver.sh: Fixed function name
Roman Kazantsev [Wed, 26 Aug 2020 14:16:58 +0000 (17:16 +0300)]
Enable eager execution while TensorFlow 2 model is loaded (#1945)
Anton Pankratv [Wed, 26 Aug 2020 13:38:41 +0000 (16:38 +0300)]
Fixed threading configuration parameters (#1919)
* Fixed threading parameters
* Updated documentation
* Fix for macos
* Fix doc
Vladimir Paramuzov [Wed, 26 Aug 2020 13:15:02 +0000 (16:15 +0300)]
[IE CLDNN] int8 output support in fsv16 dw conv (#1886)
Kamil Magierski [Wed, 26 Aug 2020 13:09:19 +0000 (15:09 +0200)]
Disable CanConvertFromAOTtoSueModel test (#1949)
Anton Pankratv [Wed, 26 Aug 2020 12:33:37 +0000 (15:33 +0300)]
Query network should return all supported layers (#1845)
* Query network should return all supported layers
* Added other plugins. Fixed hetero and multi
* IRv7 test use legacy impl
Maksim Kutakov [Wed, 26 Aug 2020 12:13:32 +0000 (15:13 +0300)]
[IE TESTS] Add Reverse Seq single layer test (#1933)
* [IE TESTS] Add Reverse Seq single layer test
* Added spaces for better readability.
Sergey Shlyapnikov [Wed, 26 Aug 2020 12:12:55 +0000 (15:12 +0300)]
[IE CLDNN] Weights reorders optimization (#1542)
* [IE CLDNN] Fix incorrect (g)_is_os_(z)yx_isv16_osv16 layout name
* [IE CLDNN] Constant blobs copying improvements
* [IE CLDNN] Weights reorders optimization
Kamil Magierski [Wed, 26 Aug 2020 10:43:43 +0000 (12:43 +0200)]
[GNA] Aligning GNA2 and GNA Unit testing (#952)
Co-authored-by: kmagiers <kmagiers@intel.com>
Mateusz Tabaka [Wed, 26 Aug 2020 08:51:51 +0000 (10:51 +0200)]
Introduce Quantize-Dequantize to FakeQuantize transformation (#1849)
* Introduce Quantize-Dequantize to FakeQuantize transformation
* Revert changes in DequantizeLinear
* apply code format
* Changes after review:
- description for transformation
- remove NGRAPH_CHECK and move some checks from callback to predicates in pattern
- check if out_low/high are broadcastable for FQ's first input
- fix params to copy_runtime_info
* Add type_matches and type_matches_any predicates
* Use get_single_value
* Changes after review:
- add brief description of transformation
- use get_pattern_value_map instead of get_pattern_map
- change opset1 to opset4
- fix params to copy_runtime_info
* Check result of dynamic_pointer_cast
Gleb Kazantaev [Wed, 26 Aug 2020 08:31:40 +0000 (11:31 +0300)]
Fixed Precision Conversion for GenericIE operation type (#1917)
* Fixed Precision Conversion for GenericIE operation type
* changed logic for setting output type in GenericIE
Wenzeng Chen [Wed, 26 Aug 2020 07:38:58 +0000 (15:38 +0800)]
[IE][VPU]: Fix NCE hang due to input dimensions exceed HW limitation (#1636)
* Fixed NCE hang due to input dimensions exceed HW limitation
* Added convolution test for big input dimensions
Signed-off-by: wenzengc <wenzeng.chen@intel.com>
Vladislav Volkov [Wed, 26 Aug 2020 05:38:29 +0000 (08:38 +0300)]
Improvements for MKLDNN Input node execution (#1913)
Gleb Kazantaev [Wed, 26 Aug 2020 03:28:03 +0000 (06:28 +0300)]
Removed WA with adding fake output for VariadicSplit operation (#1938)
Evgenya Stepyreva [Tue, 25 Aug 2020 17:30:41 +0000 (20:30 +0300)]
[ MO ] Fix for remove_op_node_with_data_node (#1934)
Pavel Rodionov [Tue, 25 Aug 2020 16:59:01 +0000 (19:59 +0300)]
[GNA] Remove profiler (#1931)
Anton Chetverikov [Tue, 25 Aug 2020 16:36:39 +0000 (19:36 +0300)]
SoftPlus operation implementation (#1365)
Ivan Tikhonov [Tue, 25 Aug 2020 16:23:09 +0000 (19:23 +0300)]
Common specific creator for ops to be converted to ie ops (#1928)
* Add common specific creator for ops to be converted to ie ops
* fix cpu func tests
* Add macro for specific creators
Maxim Vafin [Tue, 25 Aug 2020 15:43:43 +0000 (18:43 +0300)]
Fix output name collision for incorrect ONNX models (#1930)
Mateusz Tabaka [Tue, 25 Aug 2020 14:12:55 +0000 (16:12 +0200)]
Adjust tolerance values in ModelImportRunner to the ones onnxruntime … (#1894)
Evgeny Lazarev [Tue, 25 Aug 2020 13:39:34 +0000 (16:39 +0300)]
Fixed order of transformation to convert the TF OD API SSD models (#1887)
* Fixed order of transformation to convert the TF OD API SSD models
* Refactored the sub-graph modification for the TF OD API models related to Squeeze/Reshape after SSD heads
Liubov Batanina [Tue, 25 Aug 2020 13:28:05 +0000 (16:28 +0300)]
Added BatchNormInference tests (#1927)
Ilya Lavrenov [Tue, 25 Aug 2020 13:00:09 +0000 (16:00 +0300)]
Deprecated migration to Core guide (#1910)
Maksim Doronin [Tue, 25 Aug 2020 08:43:24 +0000 (11:43 +0300)]
[IE][VPU]: Update firmware (#1915)
* Firmware update contains changed conditions for removing inner dimension with length 1 in Permute kernel
Maksim Doronin [Tue, 25 Aug 2020 08:42:23 +0000 (11:42 +0300)]
[IE][VPU]: Fix KW issues on Linux (#1916)
* nullptr dereference fixed in Concat and Reduce stages in Graph Transformer
* missed parameters in asserts in StridedSlice stage was added
Edward Shogulin [Tue, 25 Aug 2020 07:43:33 +0000 (10:43 +0300)]
[LPT] BLOCKED layout ignoring (#1873)
* [LPT] BLOCKED layout ignoring
* [LPT] Permute transformation tests
* [LPT] Tests rework
Alexandra Sidorova [Tue, 25 Aug 2020 07:19:06 +0000 (10:19 +0300)]
[CPU] Added H-Swish activation (#1445)
Adam Osewski [Tue, 25 Aug 2020 03:12:39 +0000 (05:12 +0200)]
Reference implementation for ScatterUpdate (#1678)
* Reference implementation for ScatterUpdate and use of it in evaluate.
* Review comments. Clarify comments.
* Update file directory.
* Replace scatter_update reference implementation in ngraph/core/reference/
* Remove template code from ScatterUpdate reference implementation
* Apply review requests
Co-authored-by: mitruska <katarzyna.mitrus@intel.com>
Edward Shogulin [Mon, 24 Aug 2020 17:09:01 +0000 (20:09 +0300)]
[LPT] GemmTransformation usage fix (#1899)
Tomasz Dołbniak [Mon, 24 Aug 2020 16:03:01 +0000 (18:03 +0200)]
v0::Pad operator removal (#1912)
* v0::Pad operator removal
* Obsolete test removal
Pavel Rodionov [Mon, 24 Aug 2020 15:20:31 +0000 (18:20 +0300)]
[GNA] Change GNA library version to 1047.1 (#1867)
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