Commit Graph

27 Commits

Author SHA1 Message Date
Ilya Churaev 748780e392
Supports tensor names with delimiter (#4085)
* Supports tensor names with delimiter

* Fixed comments

* Allow to use different delimiters
2021-02-04 06:38:05 +03:00
Edward Shogulin f57f1fafc7
[LPT] Q/DQ support integration (#3575)
* [ MO ] New INT weights form

	Ticket #34096

	FQ = Quantize -> Dequantize =
	= FQ` -> Convert(int8) -> Convert(src_dtype) -> FQ =
	= Constant(int8) -> Convert(src_dtype) -> FQ =
	= Constant(int8) -> Convert(src_dtype) -> Subtract(zero_point) -> Multiply(scale)

* [LPT] Q/DQ representation support

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
2021-02-03 17:05:34 +03:00
Nikolay Shchegolev 8d7c9de090
[CPU] Enable MVN-6 operation. (#3400) 2021-02-03 16:49:37 +03:00
Patryk Elszkowski 3ad1360f5f
Compare function - compare attributes - unit test (#4092)
* Enable node attributes comparing in SLT

* Add values of compared values to error message

* Switch from op version to set

* Test for Constant node

* Compare clamp min max attribute tests

* try to fix CentOS build

* use HasSubstr matcher from gMock

* add more tests

* Add DummyConstan op to check if validation handle different types

* use new Function comparison API

* Add test for unsupported type

Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
2021-02-03 15:24:25 +03:00
Nikolay Shchegolev 4d9a030ff2
[CPU] Enable CTCGreedyDecoderSeqLen. (#3890) 2021-02-03 12:36:41 +03:00
Ilya Churaev 2ebae7cf30
Introduce the Broker API to map original framework names to OV (#3800)
* Added tests

* Fixed tests

* Added tests to check addOutput method

* Added support of port names in the IR

* Update copyrights

* Deprecate tensor name

* Fixed comments

* Enabled functional tests for GPU, GNA and Myriad

* Fixed get_tensor().get_names()

* Added unit test to check tensor names

* Fixed code style

* Skip add output test for GNA

* Added serialization support

* Added PythonAPI

* Fixed tests

* Fixed tests

* Fixed typo

* Try to disable GNA test

* Fixed tests

* Removed unused variables

* Fixed tests

* Update documentation

* Fixed comment
2021-01-29 06:28:31 +03:00
Yury Gaydaychuk a1422a49d7
[CPU] PSROIPooling node enhancements (#3851)
- bf support for PSROIPooling
- nhwc, blocking formats support
- code refactor & performance improvements
- cpu specific tests
2021-01-28 11:55:54 +03:00
Nikolay Shchegolev 245bc33e8a
[CPU] GatherElements implementation. (#3860) 2021-01-26 09:53:20 +03:00
Irina Efode aa775cc0a1
[IE TESTS] Remove TEST_P(Range... from lib with shared_classes (#3999) 2021-01-25 14:45:05 +03:00
Bartek Szmelczynski cdb9edddfc
Missing attr seriazliation (#3920)
* add override method for int since attribute keep_top_k from detection_output requires it

* remove if statement to prevent gtest tests duplicate names for avg_pool

* add single layer tests for seriazliation for AvgPool, PriorBoxClustered and DetectionOutput operators

* add apropiate styling of the code
2021-01-25 08:42:22 +03:00
Ilya Lavrenov 9cfe909e1e
Unused variables (#3963)
* Added -Wused-variable flag

* Fixes for clang compiler

* Removed wrong -Wno-error from protobuf compilation

* More fixes
2021-01-22 17:41:15 +03:00
Irina Efode a3234593db
[IE TESTS] Fix passrate in report (#3904)
* [IE TESTS] Fix passrate in report

* add skip
2021-01-21 11:05:10 +03:00
Vladislav Vinogradov bad4e97d9b
Extend and fix input/output precisions support in functional tests (#3933)
* Use actual blobs type to get nGraph element type,
  when generating inputs and calculating reference results.
  It will allow to run tests with `undefined` preset and
  use real type, returned from the device to generate and process input.
  It also fixes the case with several inputs with different type.
* Extend `convertOutputPrecision` function to fully support
  conversions from/to fp16/bf16 types.
  The device might return blobs in that formats, so they need to be
  supported by the testing framework.
2021-01-20 20:08:33 +03:00
Andrey Sokolov db5cd6751d
[IE][VPU][Tests]: Fix ROIPooling test (#3705)
* fix initialization bug of spatial_scale in tests (affected input generating)
* fix input generating for bilinear ROI Pooling
* correct parameters for myriad tests:
    * myriad plugin does not support batch for this layer;
    * decrease threshold since myriad uses fp16 calculations
2021-01-20 14:17:19 +03:00
Szymon Durawa 4f5230bb03
Visitor api ti serialization (#3777)
* Add on_adapter(Function) for serialization.

* Add port_map and back_edges serialization.

* Add 2  unit tests for TI serialization.

* Convert lambda expression into function pointer.

* Add single layer test for tensor iterator.

* Add limitation for file name length during serialization.

* Add file name length limitation for Serialize().

* Add WA for LSTMCell v0 in serialize class, new test class for TI serialization with dynamic weights, add bin path to SerializationParams, replace call to ngfunction_2_irv10 with visitor.on_attribute().

* Remove hacks for TI from ngfunction_2_irv10(), validate buffers in port_map.

* Changed year in new added test files.

* Add check for version of LSTMv0 WA, add assert for model read from file.

* Remove append_copy for xml Function, changed comparison for LSTMvo WA.

* Update second WA for LSTMCell v0 with version check.

* Remove find_child when searching for port_map and back_edges.
2021-01-19 15:26:29 +03:00
Gorokhov Dmitriy 2bfc941cf1
[CPU] Runtime precision for execution graph (#3886) 2021-01-19 11:25:28 +03:00
Alexander Perepelkin f5085d3216
Enable calculation of reference data without prior run of infer request (#3856) 2021-01-18 12:12:07 +03:00
Liubov Batanina 3a21c99b48
Replaced size_t with int64_t (#3744) 2021-01-16 00:39:01 +03:00
Gabriele Galiero Casay a555908858
Develop Bucketize Reference Implementation (#3693)
* Bucketize: Revise op class and add type_prop unit tests

* Bucketize: Develop reference implementation

* Bucketize: Add unit tests

* Bucketize: Add single layer test and cpu instantiation

* Bucketize: Add unit test with empty buckets for INTERPRETER

* Bucketize: Typo in buckets element type check

* Bucketize: Add custom generated inputs in single layer test class

* Bucketize: Use random_device to generate seed for data blob

* Bucketize: Remove unsupported f64 precision

* Bucketize: Add function description

* Bucketize: Remove randomness of inputs generation by using static seed

* Bucketize: Support different precisions for data and bucket inputs

* Bucketize: Refactor type_prop tests and improve backend unit test coverage
2021-01-15 17:51:58 +03:00
Bartosz Lesniewski 2e09cd653a
Attributes have different values in MO and NGraph IRs (#3793)
* regionyolo do_softmax attribute

* add serialization single layer tests for normalizel2 and reshape

* add prelu sslt, change letter size in op name to align with MO

* add shufflechanels sslt, add workaround to serialize the op with proper opset number

* add broadcast sslt, change attribute string representations to lowercase

* add pad sslt, change attribute string representations to lowercase

* Unify sslt name prefixes

* add prelu name translation for serialization

* change expected type of regionyolo do_softmax attribute to bool

* transform autobcast type attr to lowercase, add unit test, add special opset mapping in serialization

* style fix

* fix indentation

* fix indentation 2

* Possibility of different opset assignment for different op versions

* Update header dates in  modified files

* Match special opset to type_info_t instead of a string

* Adjust the comment to match the code
2021-01-15 07:17:12 +03:00
Elizaveta Lobanova 36edd1fb38
[GNA] Fix handling of permutes around convolution for a case with 1 channel (#3481)
Fix of concat scale factors calculation causing infinite loop during memory layer requantization

Fix of copy layer unsupported batch size
2021-01-13 16:12:19 +03:00
Andrew Bakalin 24237863b2
[IE][VPU][TESTS]: Gather: support outer padding for indices (#3665)
* Update firmware
* Add the test case from the network
* Disable fp32 case, because in this case the network has output Convert which receives non-inner stride in its input which is not supported now.
* Support FP16 comparator.
2021-01-12 13:56:52 +03:00
Alexander Perepelkin dedd5a51e8
Allow multiple output shapes testing (#3728) 2020-12-25 17:37:16 +03:00
Yury Gaydaychuk 6d320d7162
convert to bf is to be inserted only after non-const layer (#3597) 2020-12-24 10:20:44 +03:00
Patryk Elszkowski 2bc18c27aa
Constant attr to visitor (#3540)
* Add new path for constant in IR serializer.

* Apply suggestion from review.

* Unique name for temporary test file

* Switch from static to constant member function - GetTestName

* Ensure bin path is not empty.

* Compare Constants op by string values converted to float.

* Add path validation.

Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
2020-12-23 16:14:26 +03:00
Vladimir Paramuzov 241b0faea1
[IE CLDNN] NGraph integration into cldnn plugin (#2506)
Co-authored-by: Roman Lyamin <roman.lyamin@intel.com>
Co-authored-by: Mikhail Letavin <mikhail.letavin@intel.com>
2020-12-23 13:35:44 +03:00
Irina Efode 602f8f2e08
[IE TESTS] Move SLT classes to `SharedTestClasses` lib & add serialization functionality to the common class (#3431)
* [IE TESTS] Changing functional test utils structure

* Example

* Remove extra

* Apply comments

* fixes

* [IE TESTS] Change the structure

* Continue

* step 3

* [IE TESTS] Complete transition single layer test classes

* [IE TESTS] Transition Subgraph

* Fix subgraph namespaces

* fix

* Apply comments

* latm fix
2020-12-15 22:32:00 +03:00