IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,563 Commits 38 Branches 54 Tags
4021e144b53d9d9708a856f667d9847cdecabcfa
Commit Graph

959 Commits

Author SHA1 Message Date
Zoran Zomborat
4021e144b5 [IE] Add RTTI macro to ReshapeFullyConnectedFusion ngrap pass (#2837) 2020-10-29 07:33:55 +03:00
Evgenya Stepyreva
347e1206d5 setBatchSize: getting rid of ConstantFolding (#2842) 
* setBatchSize: getting rid of setBatchSize

* Trigger CI

* Feedback adressed

* Trigger CI

* f -> specialized_function
 2020-10-28 22:49:12 +03:00
Evgenya Stepyreva
13a9ba6a2b [ SSR ] Transpose->MatMul (#2525) 
* [ SSR ] Reshape->Softmax->Reshape

* Call DepthToSpaceFusion during SmartReshape

* rtti

* remove softmax wa
 2020-10-28 20:06:42 +03:00
Bartosz Sochacki
9b4f499930 Extended test infrastructure to call per plugin configure function before running a test. The function allows to pass plugin specific configuration (#2731) 2020-10-28 14:57:46 +03:00
Vladislav Vinogradov
50645befb7 [IE][CMAKE] Fix build issues with custom configuration (#2851) 
* FASTER build enabled
* MYRIAD plugin disabled
 2020-10-28 12:20:26 +03:00
Irina Efode
1689634574 [IE TESTS][IE MKLDNN] Disable CtcLoss SLT due to sporadic failures (#2852) 2020-10-28 12:00:11 +03:00
Gladilov, Gleb
18f7e4f4f0 [IE][VPU]: Improves myriad plugin API (#2816) 
LoadNetwork takes network argument by constant reference.
Myriad plugin implementation applies transformations to
given network in order to get compiled model.
Transformations take network argument by non-constant
reference, so at some point of time network copy must be
acquired. ICNNNetwork is neither copyable nor movable, so
the only way to get network copy is using special utility
returning std::shared_ptr.

Myriad plugin does not expose any ownership strategy,
so prefers to take network argument by simple reference.
Plugin also requires nGraph -> CNN conversion during
LoadNetwork implementation. Conversion utilities returns
std::shared_ptr, which makes plugin to use workaround for
lifetime of converted object (to have 2 "pointers" to
network: raw pointer to input network and smart pointer to
converted network). Such workarounds make code more
error-prone, because using wrong pointer to semantically
the same object may lead to unexpected results.

To overcome these issues API has been changed in a way to
make interfaces more clear (do not expose ownership strategy
or mutability) and get rid of unnecessary workarounds.

Signed-off-by: Gladilov, Gleb <gleb.gladilov@intel.com>
 2020-10-28 11:14:14 +03:00
Gleb Kazantaev
91afa14901 Add dynamic shape checks for legacy transformations (#2783) 
* Added dynamic shape checks for ConvertInterpolate pass

* Added dynamic checks for ConvertLRNToLegacy pass

* Added dynamic checks for ConvertMatMul* pass

* Added dynamic checks for ConvertPadToLegacy pass

* Updated TileIE; added dynamic checks to ConvertTileToLegacy pass

* Added dynamic checks to FCBiasFusion pass

* Added dynamic checks to Reshape1DOps pass

* Added dynamic checks to ReshapeFCFusion pass

* Added dynamic checks to ReshapeFC pass

* Updaed Reshape1DConvolution pattern
 2020-10-28 10:36:16 +03:00
Vladimir Paramuzov
c7661078d9 [IE CLDNN] Removed unused DO gpu impl (#2809) 2020-10-28 09:24:22 +03:00
Gorokhov Dmitriy
abb8817cf6 [CPU] Generic JIT Eltwise implementation (#1464) 2020-10-28 09:16:28 +03:00
Mateusz Tabaka
186e00fa2a Remove obsoleted v0::Product op (#2860) 2020-10-28 07:12:52 +03:00
Maksim Doronin
07fbf93a0d [IE][VPU]: Implement HSwish layer with tests (#2775) 
* Implement HSwish layer with tests
* Disable HSwish decomposition by a predicate
* Update vpu firmware
 2020-10-28 00:38:10 +03:00
Andrey Kamaev
a6520995fe MSVC warnings fix (#2620) 
* Fix MSVC build warnings in Ngraph

* Fix MSVC build warnings in transformations library

* Fix MSVC build warnings in core,legacy,preprocessing

* Fix MSVC build warnings in XLink

* Fix MSVC build warnings in Myriad plugin
 2020-10-27 12:24:57 +03:00
Monica-elena Burger
314ec2df72 [IE][VPU]: Config key to disable weights analysis pass (#2714) 
* Add config key to disable weights analysis pass in graph transformer
 2020-10-27 11:52:18 +03:00
Polina Brzezinskaya
0040d47b00 [IE][VPU]: Bidirectional mode for broadcast on vpu (#2627) 
* Support for bidirectional broadcast mode
 2020-10-27 11:49:35 +03:00
Roman Lyamin
77365bcb4c [IE CLDNN] Added Round-5 operation (#2838) 2020-10-27 10:56:15 +03:00
Mikhail Ryzhov
dc52ec7880 [Samples] Python: added support of onnx models (#2782) 
* [Samples] Python: added support of onnx models

* [Docs] Python: added support of onnx models

Updated documentation
 2020-10-27 10:23:25 +03:00
Jozef Daniecki
c6fc247f99 Add nGraph function serialization. (#2579) 
* Add nGraph function serialization.

* Turn of execption throwing on failed visitation.

* CNNNetworkNgrapImpl serialize also support fallback to v7 serialization.

* Add error message for legacy IR not implemented case.

* Store tests models in files.

* Add tests with multiple layers.

* Style aligned to IE rules.

* Add visit_attributes to ExecutionNode.

* Layer version XML atribute implementation.

* Fix opset atribute creation for ExecutionGraph. Refactoring.

* Add missing header.

* Move opset collecting to private scope.

* Add missing header.

* Add test wit multiple oututs. Fix found issues: constant name, result
outputs.

* Move serialization to transformation library.

* Add versioning to serialization transformation.

* Add functional tests with ONNX importer path.

* Add nodes unique name checking and correction.

* Add checks for unsuported cases: dynamic shapes & GenericIE node

* General refactoring.

* Add comment describing type name translations.

* Add serialization deterministicity tests.

It's needed to ensure that subsequent calls to serialize() on the same function are giving the same results.

* Serialization in CNNNetworkNGraphImpl::serialize executed via pass::Manager.

Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>

* NGRAPH_CHECK messages refactored.

* Performance and const correctness refactoring.

* Style formatting applied.

* Code simplifaction.

* Serialize transformation documentation refactoring.

* Changed compare_function() to throw on functions with multiple outputs.

Before this check was implemented with assert which means it was working
only in debug builds. Now it is working also in release build.

* Adjust tests to new compare_functions() behaviour.

* Replace cmakes add_definitions with more modern target_compile_definitions

Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
 2020-10-27 06:57:48 +03:00
Alexander Peskov
6e5a4714ac Make MVN behaviour deterministic (#2458) 
* Change default parallel reduce alg into deternimistic way

Signed-off-by: Alexander Peskov <alexander.peskov@intel.com>

* Introduce ie::parallel_for semantic with group_id parameter

Signed-off-by: Alexander Peskov <alexander.peskov@intel.com>

* [CPU] Make MVN behaviour deterministic

Signed-off-by: Alexander Peskov <alexander.peskov@intel.com>
 2020-10-26 21:01:38 +03:00
Evgenya Stepyreva
40a4ae3cfa [SSR] Transformation mimicking oldSetBatchSize logic (#2597) 
* [SSR] Transformation mimicking oldSetBatchSize logic

* Self-review

* gkazanta comments adressed

* support for opset1::Proposal and  opset4::Proposal. Use of pattern predicates

* Constant Folding during setBatchSize

* StridedSlice->Squeeze resolver

* SR tests added

* Squeeze->StridedSlice

* Comments

* getting rid of folding

* comment

* sq->ss transformation

* Revert "sq->ss transformation"

This reverts commit 9731b1cf52.

* Revert "comment"

This reverts commit a57b4f863e.

* Revert "getting rid of folding"

This reverts commit 85405dab0a.
 2020-10-26 20:51:59 +03:00
Jedrzej Hajduczenia
8884791362 [IE CLDNN] Improve LO rules for expected FQ format (#2790) 2020-10-26 20:36:00 +03:00
Ivan Tikhonov
735c8747b5 Loop operation: IE IR Reader update (#2766) 
* ie_ir_reader update, Loop implementation update

* fix ie ir reader
 2020-10-26 19:30:14 +03:00
Alexandra Sidorova
de686fce39 [CPU] Added operation HSigmoid-5 (#2005) 2020-10-26 18:42:30 +03:00
Edward Shogulin
5007cba70a [LPT] bfloat enabling fix (#2819) 2020-10-26 16:02:11 +03:00
Mikhail Ryzhov
0267cbd286 Fixed ngraph sample logical errors (#2600) 
* Fixed ngrapth sample logical errors

- added batch size, because sample accepts several images
- set label file as optional
 2020-10-26 15:36:49 +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
Aleksandr Korolev
d34dc7e206 [IE][VPU]: Add runtime precision info in MYRIAD plugin (#2535) 
* Add runtime precision info in MYRIAD plugin
 2020-10-26 11:32:43 +03:00
Evgeny Latkin
77ba9acada [IE][VPU][Myriad]: Mish layer optimization (#2648) 
* Myriad: new firmware version 1426
 2020-10-26 10:50:37 +03:00
Vladimir Paramuzov
c722f6a05a [IE CLDNN] Fixed fusing config for fsv16 eltw kernel (#2807) 2020-10-26 09:03:00 +03:00
Tomasz Dołbniak
6c341df85a ONNX models validation tweak and test (#2798) 
* Test checking the current ONNX ir_version support

* Model stream rewinding in ONNX reader only

* Fix for CentOS
 2020-10-26 06:35:20 +03:00
Mateusz Tabaka
4d2674962d Remove obsoleted v0::Broadcast and BroadcastLike operators (#2779) 
* Remove obsoleted v0::Broadcast and BroadcastLike operators

* remove NGRAPH_DEPRECATED marks from autobroadcast functions

* restore NGRAPH_SUPPRESS_DEPRECATED_START in autobroadcast.cpp
 2020-10-26 06:32:49 +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
Jedrzej Hajduczenia
7bd8391aba [IE CLDNN] Fix narrowing conversion error on VS2017 (#2804) 2020-10-24 00:57:30 +03:00
Alexey Suhov
2087b39cb4 Add OpenCV for CentOS 8 and RHEL 8 to dependencies.cmake (#2806) 2020-10-23 23:58:33 +03:00
Mikhail Ryzhov
dea5f43c9a Added onnx support for C samples (#2747) 
* ngraph python sample

This sample demonstrates how to execute an inference using ngraph::Function to create a network
- added sample
- added readme
- added lenet weights

* Added onnx support for C samples

* Revert "ngraph python sample"

This reverts commit 8033292dc3.

* Added onnx support for C samples

Fixed codestyle mistake

* Removed optional code

Co-authored-by: Alexander Zhogov <alexander.zhogov@intel.com>
 2020-10-23 21:47:01 +03:00
Vladislav Vinogradov
d846969a1c [IE] Fix UNITY build (#2799) 2020-10-23 19:21:02 +03:00
Gleb Kazantaev
33371ca1ac Added dynamic check for convertFunctionToCNNNetwork functoin (#2797) 
* Keep changes

* Added dynamic check for convertFunctionToCNNNetwork

* Fixed test
 2020-10-23 18:17:26 +03:00
Anton Chetverikov
c020fd3e7e Remove ExtractImagePatchesToReorgYolo transformation (#2687) 
Co-authored-by: Anton Chetverikov <anton.chetverikov@.intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
 2020-10-23 17:32:54 +03:00
Andrew Bakalin
cab7a77cba [IE][VPU][GT][DTS]: Update MyriadPlugin to work with dynamic NMS-5 (#2698) 
* [VPU][GT][NGraph] Get rid of DynamicNMS and transformation
* [VPU][NGraph] Update DTS for NMS
* [VPU][NGraph] Update StaticShapeNMS to be inherrited from NMS-5
* [VPU][GT] Update StaticShapeNMS stage to work with updated NGraph op
* [VPU][Tests] Update tests
* [VPU][GT] Fix StaticShapeNMS to be inherited from NonMaxSuppressionIE3
* [VPU][GT] Remove unused NonMaxSuppression
 2020-10-23 17:04:36 +03:00
Gleb Kazantaev
c4e0b74fb1 Add dynamic shape checks to nGraph transformations (#2735) 
* Added dynamic shape checks for BatchNormDecompositoin pass

* Added dynamic shapes checks for FQTranspose fusion pass

* Added patter::has_static_rank predicate

* Added dynamic shapes checks for BroadcastToTiles pass

* Fixed BN inputs order

* Add dynamic shape checks for DepthToSpace/SpaceToDepth passes

* Added dynamic check for ReduceToPooling pass

* Updated BN transformation

* Fix PR comments

* size_t to int64_t

* Updated reduce to pooling pattern
 2020-10-23 15:39:47 +03:00
Alexey Ershov
8c97127aa7 [IE][VPU]: Proposal: Implemented support for optional 2nd output (scores) (#2762) 
* Proposal stage: added support for optional 2nd output
* firmware updated
 2020-10-23 15:19:20 +03:00
Krzysztof Bruniecki
9c78a4855a Remove CNN GNA1/2 compatibility enforcement when other GNA device detected (#2745) 2020-10-23 13:30:16 +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
Egor Churaev
ca95240c91 [IE CLDNN] Fix linear_onnx Interpolate selection (#2769) 2020-10-23 13:16:47 +03:00
Tomasz Dołbniak
f1444b33e7 ONNX Reader supportModel() implementation (#2744) 2020-10-23 12:13:04 +02:00
iliya mironov
0a59be6f1e 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
 2020-10-23 12:35:56 +03:00
Mikołaj Życzyński
6b02cd380f [IE CLDNN] Fix padding in reduce fsv16 kernel (#2787) 2020-10-23 10:16:21 +03:00
Roman Donchenko
ba3fc7fb8a Fix spelling errors in the API and bindings (#2781) 2020-10-23 09:17:03 +03:00
Ilya Lavrenov
258c51bd1f 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
 2020-10-23 08:54:48 +03:00