IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,537 Commits 38 Branches 54 Tags
77365bcb4c337394c10f0cb79a5f28ec506b00f6
Commit Graph

184 Commits

Author SHA1 Message Date
Roman Lyamin
77365bcb4c [IE CLDNN] Added Round-5 operation (#2838) 2020-10-27 10:56:15 +03:00
Ilya Lavrenov
166ab89b95 Reorganize LPT: (#2803) 
- inference_engine_lp_transformations keep ngraph LPT
- inference_engine_lp_transformations_legacy keep old CNNLayer based LPT
 2020-10-26 14:10:17 +03:00
Patryk Elszkowski
5036b12544 enable reference implementation in CTCGreedyDecoder single layer test (#2680) 
* enable reference implementation for CTCGreedyDecoder single layer tests

* update unit test to have blnak_index

* remove merge_repeated disable flag for CPU test because CPU impl always
merge

* add CTCGreedyDecoder single layer tests for CPU

* changes to match xPU implementations

* apply reviewers suggestions

Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
 2020-10-26 13:34:50 +03:00
Vladimir Paramuzov
980bbd172a [IE CLDNN] Enabled more functional tests and added several fixes into ops implementations (#2763) 2020-10-24 23:38:13 +03:00
Edward Shogulin
c2271da637 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>
 2020-10-23 13:22:55 +03:00
Andrew Bakalin
3dfec639f0 [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
 2020-10-22 15:04:53 +03:00
Ilya Churaev
e364271cf6 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
 2020-10-22 13:22:38 +03:00
Irina Efode
a2e49469b5 Cleanup single_layer_tests (#2716) 2020-10-20 14:31:59 +03:00
Anton Potapov
8715b60d88 [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
 2020-10-19 12:35:59 +03:00
Ivan Tikhonov
84b5fc51dc [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
 2020-10-19 06:53:46 +03:00
Roman Lyamin
cc569d2254 [IE CLDNN] Added HSigmoid operation (#2700) 2020-10-18 20:47:22 +03:00
Kamil Magierski
95d7c29628 [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
 2020-10-16 13:23:32 +03:00
Gabriele Galiero Casay
c9b16a79f5 Reference Implementation for RegionYolo operator (#2474) 2020-10-15 22:30:12 +02:00
Katarzyna Mitrus
fadd16ce89 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
 2020-10-15 13:42:21 +03:00
Gleb Kazantaev
94eacc6544 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
 2020-10-14 10:58:01 +03:00
Nikita Kudriavtsev
5ce622f4f4 [IE Myriad] Fix layer tests for logical_and (#2622) 2020-10-12 16:37:31 +03:00
Alexander Perepelkin
a1b8a11000 Allow to specify both in/out precision, add in/out layout in tests (#2516) 
* test definitions

* CPU plugin shared tests

* CPU plugin custom tests

* GNA plugin shared tests

* GPU plugin shared tests

* MYR plugin shared tests

* TML plugin shared tests
 2020-10-11 11:05:55 +03:00
Liubov Batanina
7f78dd797e [IE Tests] Added NormalizeL2 tests (#2327) 
* Added NormalizeL2 tests

* Added NormalizeL2 reference

* Add nGraph tests

* Fix tests

* Added NormalizeL2 builder
 2020-10-08 07:23:25 +03:00
Kamil Magierski
4c1ae9b339 [GNA] Issue 39975 - cascade concat fix (#2486) 
* concat input not used fix rough implementation

* [GNA] Cascade concat input not assigned fix

* reduce copying in recursive function

* [GNA] Aligned cascade concat test
 2020-10-06 11:01:19 +03:00
Kamil Magierski
0e62e5e17f [GNA] FIX CopyLayerPass for concat parent cases (#2485) 
* [GNA] fix cases when layer output is used in both memory and concat parent layer

* coma fixes

* Issue-36189 CopyLayerPass for concat parent cases fix test

* Fix test for CPU

* Remove test for GPU
 2020-10-06 11:00:38 +03:00
Kamil Magierski
8abdc32676 [GNA] Fix LSTM Cell channel C being 0 on output (#1174) 
* [GNA] get output before activation test

[GNA] SubstituteScaleShiftBroadCastPass fix for cases when there are multiple scaleshifts as an output from the layer

[GNA] Generalize Fix where LSTMCell output was zero due to being fused into activation

[GNA] Fix LSTMCell being zero on channel C if being output layer

* linux build fix
 2020-10-06 10:59:03 +03:00
Anton Pankratv
b21d0fe978 Removed similar behaviour tests (#2528) 2020-10-05 12:21:03 +03:00
Andrey Dmitriev
949e23d0e8 [GNA]specific execution order for delayer copy layer (#2117) 
[GNA]specific execution order for delayer copy layer + Test
 2020-10-01 15:09:53 +03:00
Mikhail Kozlov
6ae332b072 Fix virtual class inheritance for single layer test detection output (#2472) 2020-10-01 14:34:04 +03:00
Egor Churaev
a05333217c Support operation Interpolate-4 in OpenVINO (#1596) 
JIRA: 26973
 2020-10-01 11:41:51 +03:00
Vladislav Vinogradov
d28a5d6c4f [CMAKE] Introduce FASTER_BUILD experimental feature (#2438) 
It uses CMake 3.16 built-in utilities to speed up build time:

* Unity builds
* Precompiled headers

The feature is controlled via `ENABLE_FASTER_BUILD` CMake option (disabled by default).
The option avaialble only on CMake >= 3.16.
The feature is enabled per-target via `ie_faster_build` function.

Some observations:

* Don't have actual numbers for compile time, but subjectively can see
  speed up locally with VS 2019.
* Unity builds gives much more effect, but has some restriction on source files,
  so are not used everywhere.
 2020-09-28 18:53:11 +03:00
Andrey Markelov
63fbe78d76 Fix tile layer test header (#2315) 2020-09-28 17:13:49 +03:00
Anton Pankratv
c8233b7b7c Fixed canStartSeveralAsyncInsideCompletionCallbackWithSafeDtor (#2404) 2020-09-28 11:08:34 +03:00
Anton Pankratv
863a7bd663 Holder test thread safe for all (#2425) 2020-09-25 21:12:24 +03:00
Andrew Bakalin
03d184726a [IE][VPU]: Supports I32 for some eltwise precisions + tests (#2364) 2020-09-25 18:29:34 +03:00
Aleksandr Korolev
eda9498b79 [IE][VPU]: Reduce tests execution time (#2378) 
* [IE][VPU]: Reduce tests execution time

* [IE TESTS] Remove 'ConfigurePlugin()' from 'memory_LSTMCell.hpp'

* [IE VPU TESTS] Myriad conv layer tests was changed

Co-authored-by: Maksim Doronin <maksim.doronin@intel.com>
Co-authored-by: kora6 <kora6@github.com>
 2020-09-25 14:24:12 +03:00
Liubov Batanina
f8a17a1317 Changed pad data type (#2354) 2020-09-23 13:10:58 +03:00
Kamil Magierski
9fca26b21e [GNA] LSTMCell fixes (#2080) 2020-09-22 18:13:28 +03:00
Eugene Smirnov
f0b10bf071 [GNA] fake quantize single layer tests for GNA plugin (#2060) 
* fake quantize single layer test for GNA plugin

* implemented fakequantize for fp32 case as an activation function

* added proper seed randomisation within single test run

* [GNA] [FAKEQUANTIZE] fixed ref-fp32 implementation on GNA to use nearbyint instead of roundf

* [GNA] [FAKEQUANTIZE] restored random seed

* [GNA][FAKEQUANTIZE] disabled 4d and integer tests for FakeQuantize

* [GNA][FAKEQUANTIZE]updated ngraph FakeQuantize builder to accept seed

* [GNA][FAKEQUANTIZE]aligned FP calculations order on GNA with reference ngraph - this however gives more error

* [CPU]build of FakeQuantise tests restored

* [TESTS][FAKEQUANTIZE] ignore extra inferRequests for disabled tests

* [GNA] Fixed legacy unit test failuers appeared due to extra check for possible segfault in import frames

* [GNA] adopted fuse multiple identities for FakeQunatize layer

* [GNA]fp32 runtime code review
 2020-09-21 14:22:14 +03:00
Alexander Perepelkin
c13ec24e1e Specify in and out precisions separately, add layouts for convolution (#2211) 
* Specify in and out precisions separately, add layouts for convolution

* Align convolution layer tests instantiations with updated definition

* Align convolution layer tests instantiations with updated definition for template plugin

* net, in, out prcs

Co-authored-by: Mikhail Treskin <mikhail.treskin@intel.com>
 2020-09-21 13:03:01 +03:00
Liubov Batanina
6839ef7699 Add TopK tests (#2165) 2020-09-21 11:37:22 +03:00
Ivan Tikhonov
1b7dfc6e4c Fix bidirectional mode in reference implementations of GRU/LSTM/RNN Sequences (#2264) 
* fix bidirectional case in references of sequences ops, enable decomposition of bidirectional cases in CommonOptimizations

* introduce new opset5, include GRU/RNN/LSTM Sequences to opset5

* Revert "introduce new opset5, include GRU/RNN/LSTM Sequences to opset5"

This reverts commit 73c22a11db.
 2020-09-18 10:14:01 +03:00
Irina Efode
12abb2eb49 [IE TESTS] CoreThreading_LoadNetwork tests were disabled for GPU plugin (#2245) 2020-09-16 16:46:02 +03:00
Gorokhov Dmitriy
83e96891ca Revert "[IE TESTS] dynavic batch for mvn layer (#1010)" (#2257) 
This reverts commit 2e3378c50f.
 2020-09-16 14:11:48 +03:00
Anton Potapov
d590144545 [PP GAPI] Addded tests to cover exisiting precision conversions done by (#1976) 
some plugins

- added shared parameterized tests
- instantiated for template plugin
- instantiated for cpu plugin
- fixed CPU plugin to properly handle U16 input
- fixed CPU reverse_sequence primitive to alolw input/oputput tensors to
be in FP32 only
- updated ngraph test_simple_computation_on_ndarrays to not expect
failure on U16 input
 2020-09-16 12:41:14 +03:00
Anna Alberska
3ecee2ce49 [GNA] fix scale factor calculation for unfused bias after fc (#2097) 
* [GNA] fix scale factor calculation for unfused bias after fc

* change check

* add test

* apply requested changes

* cpplint fix

* apply test changes

* modify model for test to match ::op::
 2020-09-15 16:04:06 +03:00
Ilya Churaev
1bae5504ca Fixed query network for networks with KSO (#2201) 
* Added a test to reproduce QueryNetwork with KSO

* Fixed QueryNetwork for networks with KSO

* Added additional test
 2020-09-15 14:02:15 +03:00
Edward Shogulin
ac2370b420 [LPT] Copy constant with several outputs before blob update (cherry-pick to master) (#2198) 
* [LPT] Copy constant implementation

* [LPT] the same Constant ops as FQ interval boundaries
 2020-09-15 09:18:58 +03:00
Nikita Kudriavtsev
ef2581d5c6 [IE Myriad][IE Tests] Activation layer's constants parametrization. (#2071) 
CI passed: https://gitlab-icv.inn.intel.com/inference-engine/product-configs/merge_requests/870
 2020-09-10 12:56:21 +03:00
Anton Voronov
0e34b392ee [CPU] Supported depthwise 6d, 7d, ..., added test (#971) 2020-09-10 08:33:38 +03:00
Bartosz Sochacki
8b87e1a477 [GNA] Fix for concat layer with >2 inputs (#1475) 
* Fix for concat layer with more than 2 inputs

Signed-off-by: Bartosz Sochacki <bartosz.sochacki@intel.com>

* Fixed check if affine is used for crop layer

Signed-off-by: Bartosz Sochacki <bartosz.sochacki@intel.com>

* code cleanup for fix affine layer check

Signed-off-by: Bartosz Sochacki <bartosz.sochacki@intel.com>

* added test for concat layer with multiple inputs

* simplified test to use less number of layers

* fixed code style

* fixed coding style

* addressed review comments and one more issue that appeared during testing

* fixed code style errors

* scale factor propagation for concat layer with multiple inputs

* fix for a case when all inputs to concat are activation layers

* fix for linux compilation - C++14 is not enabled and fails on lambda with auto parameters

* corrected current year in headers in concat multi input tests

* fixes for code review issues raised by Denis Orlov

* enabled integer mode computation in GNA concat multi input test

* removed 1 space per review comment

* a fix to fail when not all scale factors are equal

* added GNA_DEVICE_MODE config to concat multi input test

* corrected searching for a next input to concat layer

* changed selection of 2nd candidate for source quant value

* code style fix - else and brackets should be in the same line

* small code improvement

* fix for mixing line endings

* addressed with endless requantization loop and fixed failing tests
 2020-09-09 14:55:07 +03:00
Alexander Peskov
ad74204402 [TEST] One more ReduceSUM func test 
Special test case with input values which cannot be correctly processed via
decomposition with int AVG pool layer.

Signed-off-by: Alexander Peskov <alexander.peskov@intel.com>
 2020-09-09 12:41:31 +03:00
Andrey Dmitriev
8e6d9470bb [GNA] Handling input orientation (#1851) 
Added test

Add fix
 2020-09-08 10:46:10 +03:00
Ivan Tikhonov
063c7ef6b9 GRU/RNN/LSTM sequence ops, reference implementations, single layer tests (#1594) 
* gru/rnn sequences

* update gru/rnn sequences ops, add unit tests

* enable sequence transformations for cpu plugin

* ngraph codestyle

* update tensor iterator to rnn/gru/lstm sequence transformations, add unit tests

* ngraph codestyle

* add visitors for ngraph ie ops, fix a bug with incorrect axis, fix ngraph to ngraph ie conversion

* update GRUSequence/GRUSequenceIE according to plugin format

* fix ngraph ie implementations according to plugins restricrictions

* fix naming issue

* adapt unit tests to accordance to new changes

* strict checks, additional unit tests

* add descriptions for transformations, fix unit tests

* enable ti to sequnece and unroll transformations in plugins for testing

* disable tensor iterator ngraph reader tests

* delete unnecessary cmake file

* fix includes

* clean up, resolve review comments

* move ti to sequence transformation to ti folder

* validate_and_infer_types() implementation

* input parameter validation for LSTM, GRU and RNN

* style-check applied

* Add LSTMSequence dynamic shape validation and test props for RNNCell, GRUCell, LSTMCell and LSTMSequence.

* recurrent_sequence.hpp moved to ngraph/core/include/ngraph/op/util/

* style check applied

* removed unused variable from LSTMSequence::validate_and_infer_types

* Add missing newline mark at the end of file.

* Add supression macro for FusedOp deprecation.

* Add element type initialization

* transpose,rnn cell reference implementations

* Apply PR review remarks

* reference implementations for cells op, single layer tests, align lstm cell/sequence according to the spec

* lstm/gru/rnn cell decompostion transformations

* ngraph codestyle

* clean up

* ngraph code style

* change inheritance of Cells, fix build

* fix build

* fix build again

* remove Peepholes from LSTMSeq, fix copy_runtime_info in transformations

* Rewrite tests to use gtest exception assertions.

* resolve tests issues

* ngraph codestyle

* add missed files

* fix typeprop tests

* fix lstm sequence checks

* fix arm build

* fix arm again

* delete unnecessary file

* add convert weghts format function, enable lstm test, resolve review comments

* add ngraph builders

* ngraph codestyle

* fix unit tests

* revert transpose reference implementation

* move ti to sequences transformation to another branch, resolve review comments

* resolve review comments

* revert fix in ie_layer_validators

* revert LSTM Cell v0, add LSTMCell v1, update transformation lstm_cell_to_cell_ie

* v1 version of LSTMCell op

* LSTMSequence v1 operation, exclude LSTMSeq from opset4

* fix python api tests

* resolve review comments, tests for decomposition transformations, switch lstm cell to opset4 in mo

* references impl for RNN/GRU/LSTM Sequences, single layer tests, bidirectional transformation

* fix unit tests

* process dynamic ranks of rnn/gru/lstm ops

* remove sequences specifications from opset4

* resolve review comments

* fix validate_and_infer_types of GRU/RNN sequences

Co-authored-by: Szymon Durawa <szymon.durawa@intel.com>
 2020-09-08 10:31:44 +03:00
Edward Shogulin
dc8bbd930f [LPT] Multiinput with one parent and FQ with three Constant (#2066) 
* [LPT] FakeQuantize with three constants

* [LPT] Dequantization ops on thw inputs with one parent
 2020-09-07 20:31:45 +03:00