IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,518 Commits 38 Branches 54 Tags
e07ac53300ea054bb7251eddf7a69c412fb0474c
Commit Graph
2692 Commits
Author SHA1 Message Date
Edward ShogulinandIlya Lavrenov c3c26b4807 [LPT] Refactoring: PoC (#5226) 
* LPT fix for Windows

* LPT fix for Windows

* Remove inference_engine_transformations_EXPORTS

* [nGraph] Register new node in GraphRewrite

* [LPT] nGraph alignment

* [LPT] nGraph alignment: tests

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
 2021-07-19 16:48:20 +03:00
Patryk Elszkowski 0d9212683f FakeQuantize - reference implementation refactor (#6478) 
* new implementation of FakeQuantize

* move FakeQuantize backend test to fake_quantize.in.cpp

* enable some test for FakeQuantize

* Add support for PDPD broadcasting and some backend tests

* arm plugin expect less attributes in function call

* try to fix arm plugin build

* try to build arm plugin

* start changing backend test

* add check for attributes number in visitor test

* fix backend test after refactoring

* add default parameter value to runtime::reference::fake_quantize

* Revert "add default parameter value to runtime::reference::fake_quantize"

This reverts commit 9d2c00d967.

* add SLT for FakeQuantize

* remove fesetround

* change `v1` namesapce to `v0` in ref impl

* add FakeQuantize-1 to VERIFIED_OP_REFERENCES

* pass immutable reference to test functions
 2021-07-19 12:20:54 +03:00
Ivan Tikhonov 697c52abfe DeformableConv v8: reference implementation (#6514) 
* DeformableConv v8:reference implementation

* ngraph codestyle

* update reference iplementation

* Disable tests on GPU

* fix unit tests

* Update DeformConv single layer tests

* fix serialization tests
 2021-07-19 06:15:34 +03:00
Ilya Lavrenov bc36425381 Added suggest-override flag (#6631) 2021-07-16 18:55:05 +03:00
Vladimir Paramuzov 22fddb4315 [GPU] Fixed matmul handling for some shapes (#6642) 2021-07-16 17:05:52 +03:00
Katarzyna Mitrus fa8f45b7f2 GRN - reference revision and tests (#6629) 
* Add GRN shared single layer test instance for CPU

* Remove GRN backend tests from fused_op.in

* Init GRN new template reference tests

* Add more bias values to GRN single layer tests

* Add more GRN template reference test cases

* Remove unused parameter from GrnParams

* Refactor GRN template referene tests and add more types

* Add anonymous namespace

* Add bf16 type to cpu single layer tests

* Add Serialization test

* Add GRN to revised ops
 2021-07-16 14:47:13 +03:00
Evgeny Kotov c64b809e87 GNA convert matmul to pointwise convolution transformation unit tests (#6524) 
* ConvertMatmulToPointWiseConvolutionTest first test

* add ConvertMatmulToPointWiseConvolutionFqTest

* use general functions to create test subgraphs

* use general funstion to append node; add ConvertMatmulWithBiasToPointWiseConvolutionTest

* add ConvertMatmulWithBiasToPointWiseConvolutionFqTest

* use decorator instead of bool function arguments

* remove unused functions

* cleanup

* add ConvertMatmulWithFqToPointWiseConvolutionTest

* add ConvertMatmulWithFqToPointWiseConvolutionFqTest

* add ConvertMatmulWithFqToPointWiseConvolutionTestNoAddNode

* remove debug

* add ConvertMatmulToPointWiseConvolutionTestInputRank3

* use TEST_P for ConvertMatmulToPointWiseConvolution tests

* use testing::values fixture instead of multiple tests

* cleanup

* use combine tests for invalid inputs

* code style cleanup

* fix unique_ptr build under Windows

* code review fixes: function template params

* code review fixes: remove duplicated test entry

* fix function arguments alignments
 2021-07-16 10:39:42 +03:00
Evgeny Kotov f48ea5d1cc GNA add ReorderActivationAndPooling transformation unit tests (#6469) 
* refactoring code using testing::Combine

* add unnamed namespace to prevent duplicate symbols

* add unnamed namespace to prevent duplicate symbols

* fix createActivation -> createActivationFactory

* code review fixes: align function arguments

* fix centos7 build
 2021-07-16 10:30:38 +03:00
Ilya Lavrenovandmbencer 1621c66ad8 Static protobuf for FEs (#6588) 
* protobuf static + mixed editor and importer

* merged onnx common

* remove ngraph_test_util to onnx_importer and onnx

* styles applied

* Revert "remove ngraph_test_util to onnx_importer and onnx".

* test ngraph_test_util dependencies

* Fixed static protobuf

* Next

* Fixes

* Fixed cross-compilation

* Don't export / install onnx_proto

* Fixed Windows

* Fixed opencl headers

* Fix

* Added exclude-all for exe as well

* Fixed code style

* Try without LTO

* LTO off only for onnx importer

Co-authored-by: mbencer <mateusz.bencer@intel.com>
 2021-07-16 07:25:40 +03:00
Patryk Elszkowski 2a15e3e79c add DepthToSpace to VERIFIED_OP_REFERENCES (#6655) 2021-07-15 20:13:36 +03:00
Evgeny Kotov cd3d48f98f GNA add SplitConvolution transformation unit tests (#6460) 
* add SplitConvolution tranformation tests

* fix SplitConvolution transformation copying runtime info

* fix test names

* code review refactoring

* code review refactoring: add node general function

* code review refactoring: FakeQuantize node general function

* code review refactoring: graph output concatenation

* code review refactoring: coding style cleanup

* use clone function instead of creating reference function code duplicate

* use decorator for main tests

* rewrite all with decorators

* fix make_unique for Windows build

* code style fixes

* code review fixes: fix auto& -> &&

* code review fixes: fix template functions defenitions
 2021-07-15 17:37:31 +03:00
Vladimir Paramuzov 788e76722f [GPU] Impls refactoring (#6603) 2021-07-15 12:05:34 +03:00
George Zlobin 7be2b782ba [IE][VPU]: PLATFORM configuration option hotfix (#6643) 2021-07-15 11:40:42 +03:00
Katarzyna Mitrus ebb3c8518c ShuffleChannels - add to revised ops (#6624) 
* Update opset in attributes test

* Update attributes test input shape

* Add to revised ops
 2021-07-15 08:55:29 +03:00
Bartosz Lesniewski c14edd4134 Revise PriorBoxClustered Op (#6525) 
* Move type prop tests to separate file, add cases with exceptions thrown

* Add visitor test, add step to pbc attributes

* SLT for CPU, adjust GPU and SSLT to serve the step attr

* Add backend test

* Fix variance issue, verify by SLT

* Formatting fix

* Add another backend testcase

* Add PriorBoxClustered to trusted ops list

* Add step attr description, remove obsolete comments from ref impl

* Test multiple step values in SLT
 2021-07-15 07:27:51 +03:00
Alexandra Sidorova 864b3ba62f [CPU][IE TESTS] Added Gather-7 I8 test support (#6225) 2021-07-14 22:24:33 +03:00
Egor Duplensky 3617a7e520 [CPU] Graph's RemoveEdge refactoring (#6221) 
- Move RemoveEdge from graph optimizer to graph
- Remove extra removeEdge lambdas
 2021-07-14 22:24:07 +03:00
Szymon Irzabek 34c20ad9a8 Add fake quantize support for convolution padding (#6577) 
* [GNA] Add fake quantize support for convolution padding

Combine seven ngraph matcher passes into two.
Remove max pool size checking.
Add ngraph reference tests for subgraphs which were processed by POT.
Fix remaining issues with Max Pooling output calculations.
Add setting of default compile target based on execution target.

* [GNA] Remove redundant subgraph matcher

* [GNA] Remove redundant subgraph matcher
 2021-07-14 16:29:10 +03:00
Anton Voronov ae25f5f581 [CPU] gemm inner product - memory access fix (#6072) 2021-07-14 16:09:41 +03:00
Vladimir Paramuzov cbad1b2539 [GPU] Moved memory pool to network (#6599) 2021-07-14 14:17:55 +03:00
Dmitry Pigasin 1cfe27ae1f [IE Samples Docs] Add rows with model download and conversion (#6626) 
* Add information about model preparation

* Add the missed file extension for the onnx model

* [c] Add information about model preparation

* [cpp] Add information about model preparation

* Update the string about model converter

* Specify a model name at steps 1 and 2 of the running example
 2021-07-14 12:07:34 +03:00
Evgenya Stepyreva 3710c0ee58 Optimize ShapeOf sub-graphs (#6627) 
1. Include shape sub-graphs optimization in the model optimizer nGraph pipeline
2. Extend shape sub-graph optimizations with useless Concat and useless Gather optimization
 2021-07-13 18:31:41 +03:00
George Zlobin 3d13424e42 [IE][VPU]: Completion of Configuration options refactoring in VPU plugins (#6176) 
* [IE][VPU]: Refactors PROTOCOL configuration option

* [IE][VPU]: Refactors POWER_CONFIG configuration option

* [IE][VPU]: Refactors HW_OPTIMIZATION configuration option

* [IE][VPU]: Refactors HW_EXTRA_SPLIT configuration option

* [IE][VPU]: Refactors HW_BLACK_LIST configuration option

* [IE][VPU]: Refactors TILING_CMX_LIMIT_KB configuration option

* [IE][VPU]: Refactors WATCHDOG_INTERVAL configuration option

* [IE][VPU]: Refactors PRINT_RECEIVE_TENSOR_TIME configuration option

* [IE][VPU]: Refactors PERF_REPORT_MODE configuration option

* [IE][VPU]: Refactors PERF_COUNT configuration option

* [IE][VPU]: Refactors PACK_DATA_IN_CMX configuration option

* [IE][VPU]: Refactors NUMBER_OF_SHAVES configuration option

* [IE][VPU]: Refactors NUM_EXECUTORS configuration option

* [IE][VPU]: Refactors NUM_CMX_SLICES configuration option

* [IE][VPU]: Refactors HW_POOL_CONV_MERGE configuration option

* [IE][VPU]: Refactors TENSOR_STRIDES configuration option

* [IE][VPU]: Refactors INJECT_SW_OPS configuration option

* [IE][VPU]: Refactors IGNORE_UNKNOWN_LAYERS configuration option

* [IE][VPU]: Remove HW_WHITE_LIST configuration option

* [IE][VPU]: Refactors HW_DILATION configuration option

* [IE][VPU]: Refactors FORCE_PURE_TENSOR_ITERATOR configuration option

* [IE][VPU]: Remove FORCE_DEPRECATED_CNN_CONVERSION configuration option

* [IE][VPU]: Refactors EXCLUSIVE_ASYNC_REQUESTS configuration option

* [IE][VPU]: Refactors ENABLE_WEIGHTS_ANALYSIS configuration option

* [IE][VPU]: Refactors ENABLE_TENSOR_ITERATOR_UNROLLING configuration option

* [IE][VPU]: Refactors ENABLE_REPL_WITH_SCRELU configuration option

* [IE][VPU]: Remove ENABLE_REPLACE_WITH_REDUCE_MEAN configuration option

* [IE][VPU]: Refactors ENABLE_PERMUTE_MERGING configuration option

* [IE][VPU]: Refactors ENABLE_MEMORY_TYPES_ANNOTATION configuration options

* [IE][VPU]: Refactors DUMP_INTERNAL_GRAPH_FILE_NAME configuration options

* [IE][VPU]: Refactors DUMP_ALL_PASSES_DIRECTORY configuration options

* [IE][VPU]: Refactors DUMP_ALL_PASSES configuration options

* [IE][VPU]: Refactors DISABLE_REORDER configuration option

* [IE][VPU]: Refactors DISABLE_CONVERT_STAGES configuration option

* [IE][VPU]: Refactors DEVICE_ID configuration option

* [IE][VPU]: Refactors DEVICE_CONNECT_TIMEOUT configuration option

* [IE][VPU]: Refactors DETECT_NETWORK_BATCH configuration option

* [IE][VPU]: Refactors CUSTOM_LAYERS configuration option

* [IE][VPU]: Refactors MEMORY_TYPE configuration option

* [IE][VPU]: Refactors FORCE_RESET configuration option

* [IE][VPU]: Refactors PLATFORM configuration options

* [IE][VPU]: Remove PLUGIN_LOG_FILE_PATH configuration options

* [IE][VPU]: Remove COMPILER_LOG_FILE_PATH configuration options

* [IE][VPU]: Refactors CHECK_PREPROCESSING_INSIDE_MODEL configuration option

* [IE][VPU]: Refactors ENABLE_EARLY_ELTWISE_RELU_FUSION configuration option

* [IE][VPU]: Refactors ENABLE_CUSTOM_RESHAPE_PARAM configuration option

* [IE][VPU]: Refactors NONE_LAYERS configuration option

* [IE][VPU]: Remove INPUT_SCALE and INPUT_BIAS configuration option

* [IE][VPU]: Refactors ENABLE_ASYNC_DMA configuration options

* [IE][VPU]: Delete old configuration API
 2021-07-13 16:58:25 +03:00
Evgeny Kotov a3868698e6 GNA add SwapInputMatMul transformation unit tests (#6458) 
* - add SwapInputMatMul transformation unit tests
- fix SwapInputMatMul matcher pattern

* code review fixes: remove unused piece of code

* use clone function instead of creating reference function code duplicate
 2021-07-13 16:54:56 +03:00
Evgeny Kotov b29ee60202 - add InsertTransposeAfterConvOrPool tranformation tests (#6462) 
- fix InsertTransposeAfterConvOrPool transformation copying runtime info
 2021-07-13 16:54:44 +03:00
Andrew Kwangwoong Park 2edb0e05cc [IE CLDNN] Add common comparator for ngraph reference and cldnn detection output primitive (#6530) 
- Add common comparator for sort function to be aligned with others(cldnn/mkldnn DO primitive)

Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>

Apply clang-format to do ngraph reference code

Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>

Apply code review

Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
 2021-07-13 14:52:45 +03:00
Vladimir Paramuzov 3e8c8c1025 [GPU] Simplified cldnn cmake (#6606) 2021-07-12 17:06:00 +03:00
Katarzyna Mitrus b7cc01b8e2 NormalizeL2 - reference implementation revision (#6349) 
* Update SLT to generate input with 0 and eps sensitive treshold

* Fix normalize_l2 reference to enable empty axes case

* Simplify empty axes case

* Moved backend tests from fused_op

* Update SLT treshold

* Enable SLT for empty axes case

* More single layer tests

* Backend tests refactor

* Add helper function to for normalize_l2 backend tests

* Rewrite NormalizeL2 backend tests to use test case and common helper function

* Update layer tests

* Cleanup unit-tests manifest

* Add more backend tests

* Update comments

* Fix applying eps in MKLDNN normalize

* Add 5D tests

* Backend tests refactor

* Remove duplicated tests

* Upate IE tests manifest

* Add 5D SLT

* SLT cleanup

* Update skipped SLT for CPU

* Add NormalizeL2 to verified ops

* Skip GPU SLT for empty axes case

* Update SLT epsilon values

* Revert mkldnn_normalize changes

* Update tests and issue nubmers

* Remove reudndant axes copy from reference
 2021-07-12 16:28:24 +03:00
Ilya Churaev 811f4c5ae9 Template reference tests (#6456) 
* Added convert tests

* Moved convert tests to template plugin

* Fixed build

* Fixed comments

* Fixed templateFuncTests

* Fixed review comments

* Added dynamic registration of template plugin

* Fixed functional tests

* Fixed behavior tests

* Added ticket

* Try to avoid fails
 2021-07-12 14:24:36 +03:00
Mateusz Tabaka 1a5bd8a510 [ONNX] Split importing model to two phases: decode and convert (#6326) 2021-07-12 12:13:25 +02:00
Ivan Tikhonov 434fcec53c DeformableConvolution v8: MO and IR reader (#6532) 
* ModulatedDeformableConvolution extractor

* Update MO to generate DeformableConv opset8

* clean up

* ir reader tests

* fix bilinear_interpolation_pad attribute

* update BOM file

* fix BOM file

* delete unnecessary tests

* resolve review comments

* fix e2e test

* fix e2e test

* resolve review comments

* add comment
 2021-07-12 08:09:41 +03:00
Paul Youngsoo Ahn 60651fe8f5 [GPU] Parallelize node.choose_impl in compile_graph (#6261) 2021-07-12 07:58:29 +03:00
Sergey Lyubimtsev b893eae9e7 Fix for missed OMZ public models in openvino-dev package (#6568) 
* Fix for missed OMZ public models in openvino-dev package

* fix linter issues
 2021-07-09 15:27:56 +03:00
Vladislav Golubev 2ff5d1fab1 [LPT] Plugin tests: added the ability to add test-cases with dynamic shapes (#6436) 2021-07-09 14:55:20 +03:00
Ilya Lavrenov 8b456cb9b4 Moved element_type() to MemoryBlob (#6549) 
* Moved element_type() to MemoryBlob

* Updated indentation in documentation

* Added more fixes for precisions

* Fixed documentation for new serialize methods
 2021-07-09 14:09:02 +03:00
Anna Khakimova fb6b5a8275 Pre-processing: Resize area kernels dispatching refactoring. (#6515) 
* * Resize area refactoring

* * Applied comments.
 2021-07-09 13:00:56 +03:00
Mingyu Kim 0d775269ea [GPU] Debug config improvement (#6575) 2021-07-09 12:23:16 +03:00
Anna Likholat 98148539b3 serialize to memory (#6485) 2021-07-09 09:52:40 +03:00
Gleb Kazantaev 2a970a56d3 Enable common optimizations on MO (#6245) 
* Enable common optimizations on MO

* Added tensor name tracking; updated tests

* Disable DilatedConvolution transform

* Fix TopK3 transformation

* Codestyle fix

* Update tensor name logic

* Fix scatter nd shape inference for dynamic shape

* Update FrameworkNode to propagate dynamic output shape

* Enable HSwish in MO that is missing in nGrpah

* Cleanup MO and IE code

* Fix review comments

* Fix unit test
 2021-07-09 00:38:07 +03:00
Taylor Yeonbok Lee 5d6fa64621 [IE CLDNN] Improve bfyx convolution performance for shallow output ch (#6399) 2021-07-08 12:25:16 +03:00
Szymon Irzabek afe60b3263 Gna padding tests (#6541) 
* [GNA] Use built in ngraph padding calculation

* [GNA] Use less channels for tests

* [GNA] Rename tests file

* [GNA] Add ngraph reference tests and some minor fixes in the transformation itself

* [GNA] Add invalid ngraph reference tests

* [GNA] Align brace style

* [GNA] Remove unnecessary condition
 2021-07-08 11:49:07 +03:00
Szymon Durawa baef88c8fb Cosh revise. (#6516) 2021-07-08 09:03:59 +03:00
Gabriele Galiero Casay a4fef45e0c Enable lower input rank for BatchToSpace operation by fallback (#6553) 
* Enable lower input rank for BatchToSpace operation by fallback

* Added conditions to check valid data input rank for evaluate and has_evaluate methods
 2021-07-08 07:47:01 +03:00
Tingqian Li 340583fa35 Tq/revise asinh (#6498) 
* update spec

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* use RTTI macro

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* fix op scope typo

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* simplify evaluate template function

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* override validate_and_infer_types() to align with spec

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* Add visitor API test

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* Add type_prop test

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* Add SLT asinh test in cpu/gpu plugin

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* change `T` in the spec to *T*

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* refector spec according to Cos

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* Support element type of integral

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* Add new cpp files into CMakeLists.txt

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>
 2021-07-08 07:18:09 +03:00
Ilya Lavrenov 35d9bd0f63 Removed NGRAPH_PYTHON_BUILD_ENABLE (#6556) 2021-07-07 21:23:36 +03:00
Evgenya Stepyreva e9011a9536 ShapeOf Sub-Graphs Simplification (#6308) 
* ShapeOf Sub-Graphs Simplification

* Removed graph visualization

* Review comment

* comments resolved
 2021-07-07 18:12:14 +03:00
Andrey Sapozhnikov 86b97e0a74 [GNA] Functional test returned to the skip list due to instability (#6492) 2021-07-07 15:50:55 +03:00
Krzysztof Bruniecki b48404cdf2 Gna split align convert to conv filter (#6347) 
* Make unaligned split based on Conv instead of Affine

* Dump Gna2Tensor.Data pointer for debugging

* Apply suggestions from code review

* Reuse conv helpers

* Cleanup CNN fields

* Disable weights reducer on ConvolutionFilter
 2021-07-07 15:27:00 +03:00
Ivan TikhonovandGleb Kazantaev 85a5e9beb0 Deformable Convolution v8: transformations (#6533) 
* add DeformableConv8to1 transformation

* update deformable conv v8 to v1 transformation

* Update inference-engine/src/transformations/src/transformations/op_conversions/convert_deformable_conv_v8_to_v1.cpp

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

Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com>
 2021-07-07 08:52:38 +03:00
Ding Zhang 32897aba57 Fix deformable_convolution (#6393) 
* Fix deformable_convolution

* Fix unused-variable

* Change a test case

* Change tests back and add single test case
 2021-07-06 19:52:37 +03:00