IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,022 Commits 38 Branches 54 Tags 1.1 GiB
e60331a232
Commit Graph

1022 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ivan Tikhonov
c74643f6b6
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
 2020-08-24 14:11:01 +03:00
Vladimir Paramuzov
2acf3f27e1
[IE CLDNN] Enabled tensor pitches in topk kernel for 0 input (#1898) 2020-08-24 13:03:39 +03:00
Lukasz Debski
0a5dfc62b2
[IE CLDNN] Forcing bfzyx format in MVN layer (#1903) 2020-08-24 13:03:21 +03:00
Mateusz Tabaka
d7db4974f3
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
 2020-08-24 12:26:15 +03:00
Vladimir Paramuzov
c8aa3a7f2b
[IE CLDNN] FP16 support for some quantized kernels (#1855) 2020-08-24 08:47:45 +03:00
Tomasz Dołbniak
d4567d5ab5
Linux clang compilation error fix (#1891) 2020-08-21 17:22:54 +03:00
Evgenya Stepyreva
80e09dfa3b
[ MO ] Change layout of Shape sub-graphs once (#1875) 
* [ MO ] Change layout of Shape sub-graphs once
 2020-08-21 16:27:02 +03:00
Tomasz Dołbniak
067d29a3f0
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
 2020-08-21 15:15:27 +03:00
Denis Orlov
3ae90cf258
[GNA] Additional checks (#1018) 2020-08-21 14:43:01 +03:00
Ilya Churaev
f009be66c2
Added detailed error messages for cases when network has dynamic shapes on the conversion moment (#1890) 2020-08-21 13:13:44 +03:00
Harald Rotuna
84028be544
Add method to classification_result for returning results (#1460) 2020-08-21 11:59:12 +03:00
Gleb Kazantaev
762cb8d6ab
Fix addOutput (#1888) 2020-08-21 05:51:42 +03:00
Alexander Zhogov
39dc48f92d
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*
 2020-08-20 20:53:01 +03:00
Ilya Churaev
3cb7454f67
Fixed error message for ONNX importer tests (#1880) 2020-08-20 18:46:34 +03:00
Anna Likholat
e35b23a9ff
[JAVA] Changed blob costructor (using cArray) in samples (#1863) 2020-08-20 18:45:14 +03:00
Ilya Lavrenov
5d328b94a6
Reuse make_executable_network in ImportNetwork (#1869) 
* Reuse make_executable_network for ImportNetwork

* make_executable_network returns ExecutableNetwork cpp wrapper
 2020-08-20 18:34:19 +03:00
Anton Potapov
d92cec16fc
Updating ADE version (#1877) 
- Fix gcc 9 build warnings
 2020-08-20 18:32:41 +03:00
Jedrzej Hajduczenia
1880958f8b
[IE CLDNN] Add 3d spatials support to conv & pool imad kernels and unblock any in/out feature sizes (#1693) 2020-08-20 14:54:54 +03:00
Evgeny Lazarev
94bfff2011
ONNX ScatterND MO support (#1813) 
* Added extractor for ONNX operation ScatterNDUpdate

* Updated list of supported operations for ONNX
 2020-08-20 13:57:22 +03:00
Roman Lyamin
3a9e160031
[IE TESTS] Added single layer tests HSwish (#1861) 2020-08-20 13:32:16 +03:00
Anton Dudchenko
de8bfae243
[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
 2020-08-20 12:56:12 +03:00
Evgenya Stepyreva
920bf23718
[ MO ] FloorDiv replacement (#1860) 
* [ MO ] FloorDiv replacement

* BOM file

* Review comments

* FloorDiv in SupportedFrameworkList.md
 2020-08-20 12:33:44 +03:00
Ewa Tusień
54b9b7ae6c
Remove Structural Attributes from Proposal op. (#1853) 2020-08-20 12:31:43 +03:00
Ilya Churaev
d25bb6314a
Deprecate nGraph v0 ops and builders (#1856) 
* Deprecate nGraph v0 ops

* Fixed build

* Added deprecated defines to fix windows
 2020-08-20 12:27:14 +03:00
Evgenya Stepyreva
802d605bff
[ 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
 2020-08-20 12:06:45 +03:00
Pavel Rodionov
6d7f2f03ec
Revert "[GNA] Remove old GNA1 from Cmake scripts (#1686)" (#1864) 
This reverts commit ffe8599c30.
 2020-08-20 10:59:21 +03:00
Artyom Anokhov
f57d6124e9
install_NEO_OCL_driver.sh: Added downloading driver functionality after removal NEO from the package (#1872) 2020-08-19 22:21:34 +03:00
Evgeny Lazarev
8a6b3b6d89
Restore change of i64 parameters to i32 (#1866) 2020-08-19 20:18:04 +03:00
Ewa Tusień
a8e611f90b
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.
 2020-08-19 17:55:20 +02:00
Gleb Kazantaev
301d6b50e3
Moved AlgebraicSimplification and NopElimination passes to IE (#1859) 
* Moved AlgebraicSimplification and NopElimination passes to IE

* Fixed headerfiles
 2020-08-19 18:55:11 +03:00
Vladimir Paramuzov
016c696869
[IE CLDNN] Enable fsv16 format for all quantized models (#1791) 2020-08-19 16:19:42 +03:00
Vladislav Vinogradov
fa8d07aebe
[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.
 2020-08-19 16:05:00 +03:00
Evgeny Latkin
831711d01a
re-enable the myriadMultipleGraphsTests_nightly (#1836) 
* re-enable the myriadMultipleGraphsTests_nightly

* refresh version of Myriad firmware
 2020-08-19 16:03:37 +03:00
Anna Alberska
a2b71aef56
[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
 2020-08-19 16:03:18 +03:00
Jedrzej Hajduczenia
fb885873ea
[IE CLDNN] Fix vector iterators incompatibility issue in prepare_primitive_fusing (#1842) 2020-08-19 15:51:24 +03:00
Gleb Kazantaev
939fc2f21b
Fixed addOutput (#1844) 
* Fixed addOutput

* Added tests; removed addOutput second call
 2020-08-19 14:57:28 +03:00
Vladimir Paramuzov
5c02f8d250
[IE CLDNN] Mixed precision scale support (#1848) 2020-08-19 14:17:45 +03:00
Evgeny Lazarev
ff7f4c61f3
Removed MO conversion of i64 inputs to i32 (#1835) 2020-08-19 13:58:57 +03:00
Anton Chetverikov
4925485c14
ExtractImagePatches MO implementation and nGraph transformation (#739) 2020-08-19 13:23:41 +03:00
Yegor Kruglov
b3e7cc55a6
[ MO ] Random Uniform Replacer (#1814) 2020-08-19 12:32:16 +03:00
Ilya Lavrenov
8b98f20480
LoadNetwork interface: executable network is returned as return value (#1840) 
* LoadNetwork interface

* Added reference to SOPointer to returned ExecutablNetwork

* Fixed test
 2020-08-19 11:44:29 +03:00
Edward Shogulin
819bd9bd82
[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>
 2020-08-19 11:36:48 +03:00
Vladimir Paramuzov
29873d2338
[IE CLDNN] Use fsv4 instead of af32 layout for imad case (#1784) 2020-08-19 10:10:55 +03:00
Ilya Churaev
6ab61c1f7b
Fixed path for pad reference impl (#1846) 2020-08-19 09:41:59 +03:00
Sergey Nesterov
ff04f33636
[IE CLDNN] added fusing support for ref and b_fs_yx_fsv16 implementations (#1692) 2020-08-19 09:18:00 +03:00
Katarzyna Mitrus
ceb8a25c94
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
 2020-08-19 08:04:00 +03:00
Maxim Vafin
6b04eca3c2
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
 2020-08-19 07:58:41 +03:00
Ivan Tikhonov
c5ca8f5b51
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>
 2020-08-19 07:09:32 +03:00
Ilya Lavrenov
618c6f7f23
Return serialization to IR v7 under conditional compilation (#1820) 2020-08-19 06:53:17 +03:00
Ilya Churaev
f613f618f1
Fixed set/get batch size logic for scalar inputs (#1837) 2020-08-19 06:37:04 +03:00