Commit Graph

80 Commits

Author SHA1 Message Date
Maxim Vafin 0b3ff5edc2
Add MO support for MVN-6 (#3772)
* Add MO support for MVN-6

* Apply review feedback

* Apply review feedback

* Enable MVN-6 decomposition

* Fix shape_infer issue

* Fix MVN6 decomposition

* Fix build

* Fix tests

* Small fix

* Add MVN-6 reader test

* Apply feedback

* Apply review feedback

* Fix onnx test failure
2021-02-02 17:45:56 +03:00
Mateusz Bencer b90f908c58
Enable Bersquad-10 in ONNX CI (#3889) 2021-01-27 10:22:16 +01:00
Bartosz Sledz 247606baf6
Add support for nonconstant optional NMS-5 inputs (#3640) 2021-01-26 14:41:28 +01:00
Gorokhov Dmitriy d58b4c65c8
[CPU] Plugin migration on oneDNN (v1.6) (#3725) 2021-01-26 16:31:10 +03:00
Nikolay Shchegolev 245bc33e8a
[CPU] GatherElements implementation. (#3860) 2021-01-26 09:53:20 +03:00
Jan Iwaszkiewicz 647104f602
[nGraph][ONNX] WA for currently unsupported precisions (#3964) 2021-01-25 13:08:15 +01:00
Mateusz Bencer 4d98d7ceee
ONNX tests mismatch error (#3836) 2021-01-18 12:39:32 +01:00
Bartosz Sledz 928201bee4
Add support for ONNX Operator ReduceSum v13 and revise other Reduce operators (#3605) 2021-01-18 10:47:40 +01:00
Mateusz Tabaka 20b9d390e1
[ONNX] don't hardcode broadcast shape in Mul, Add, Sub, Div (opset <= 6) operators (#3679) 2021-01-14 11:24:37 +01:00
Tomasz Dołbniak 303c549791
nGraph copyright update for 2021 (#3832) 2021-01-13 16:43:04 +03:00
Bartosz Sledz f6c2f3cc16
Change failing test ticket number (#3677) 2021-01-12 07:10:48 +03:00
Yury Gaydaychuk 9069781659
CPU implementation for ROIAlign (#3579) 2021-01-11 12:04:45 +03:00
Gorokhov Dmitriy 37b6e75730
[CPU] Fixed Divide operation support for I32 precision (#3721)
* [CPU] Fixed Divide operation support for I32 precision
2020-12-28 19:18:19 +03:00
Rafal Blaczkowski eac33e1b0e
OpenVino ONNX CI update (#3750)
* Enlarge timeouts for OpenVino ONNX CI

* Enlarge a lot timeouts

* Update processing script
2020-12-28 11:03:38 +03:00
Rafal Blaczkowski 6d45a9c041
ONNX CI improvement (#3673)
* Improve corner-case resistance

* small improvements
2020-12-25 07:46:55 +03:00
Mateusz Tabaka a8022cdbc8
Enable TinyYolo v3 in CI (#3651) 2020-12-23 12:25:54 +01:00
Mateusz Tabaka 4f14e842c1
Update ONNX models to latest master (#3658)
* Update ONNX models to 00d95ba9e5758fd0bc5e6978033fabc4f2a95e61

That version fixes yolov4 and roberta models

* remove yolov4 post processing

* remove model directory before unpacking
2020-12-22 08:04:32 +03:00
Mateusz Bencer 0b05653d7a
Resolved problems with ssd_resnet34_mlperf_opset10 (#3487)
* Resolved problems with ssd_resnet34_1200

* removed debug code

* Added correct handling onnx nodes from parent graph scope

* removed unnecessary include

* fixed calcution index to replace

* fixed LoopParentParametersUsedInBody test

* added set_friendly_name

* apply Unsqueeze for each concatenated Loop output

* added handling trip count with value max_int

* merge from upstream/master

* update xfail list

* added checking is trip_count is constant
2020-12-21 14:32:15 +03:00
Katarzyna Mitrus 6d89a96d9e
Ramove LSTM_Seq_lens model xfail declaration (#3635) 2020-12-17 16:20:01 +03:00
Rafal Blaczkowski be69a4de2f
Enable automatic update of ONNX Model Zoo for ONNX CI (#3511) 2020-12-17 14:12:47 +01:00
Mateusz Bencer 261cb6ecf8
Enable yolo v3 test, added post-processing step (#3510) 2020-12-16 16:52:08 +01:00
Tomasz Socha dbf855b320
[ONNX][Python][Tests] Update ONNX to onnx 1.8 (#3557) 2020-12-11 11:57:50 +01:00
Jan Iwaszkiewicz e1a7f7e5af
[nGraph][IE] Enable FP64 data type in IE and review nGraph Python tests (#2563) 2020-12-02 12:09:28 +01:00
Mateusz Bencer 5de9e0d3d0
Add calling validate_and_infer_types to onnx Loop (#3289) 2020-11-24 06:02:11 +03:00
Mateusz Tabaka 37f6c0caf9
Update xfail issue numbers for models that fail with AssertionError: … (#3246)
* Update xfail issue numbers for models that fail with AssertionError: zoo models results mismatch

* update xfail reason with model name
2020-11-23 06:39:35 +03:00
Mateusz Bencer aa622003a8
update tests status (#3186) 2020-11-18 13:32:59 +01:00
Mateusz Bencer 393779b227
Fix accuracy problem for YoloV3 (incorrect StridedSlice nop elimination) (#3179) 2020-11-17 18:12:01 +01:00
Gleb Kazantaev fc8df42e7e
Fix NMS5 dynamism issues (#3137)
* Fixed ConvertNMS5ToLegacy conversion pass to resolve dynamism as soon as possible; fixed output precision to avoid troubles during convert_precision pass

* Added NMS5ToLegacy conversion for cldnn plugin

* Fixed NMS3 copy method

* Updated NMS5ToLegacy pass to avoid convert precision issues

* Updated nGraph reader and Functional tests

* Removing odd CF call

* removed xfail for test that is expected to pass

* Fixed Convert operations friendly_name

* Removed NMS5ToLegacy from opset1_to_legacy conversion

* Update NMS5 layer tests

* Update NMS5 DSR tests
2020-11-17 18:34:05 +03:00
Jan Iwaszkiewicz cfe143fd33
[nGraph][ONNX] Rename xfails (#3061) 2020-11-17 10:34:33 +01:00
Ivan Tikhonov b45e1a25a5
LSTM/GRU/RNN Sequences : support for seq_lengths input (#2788)
* sequences to ti transformations, support for seq_lengths input, update reference implemetations, add new tests

* fix python api, update sequences to ti transformation

* fix sequences to ti transformation

* Update sequences to TI transformation: fix reverse sequence support

* update single layer tests, fix TI reference impl, fix Sequences to TI transformations

* ngraph code style

* fix build

* fix ngraph python api

* resolver review comments, refactoring

* Resolve review remarks

* delete xfail
2020-11-17 07:04:20 +03:00
Mateusz Tabaka 8f82589be0
Update tolerance values for ONNX model tests (#3131) 2020-11-16 15:23:20 +01:00
Bartosz Sledz 749d70bb63
Add ceil_mode for Max and Avg pooling (#2965) 2020-11-16 15:16:24 +01:00
Katarzyna Mitrus 8dbff709fb
ONNX LSTM fix get_shape error (#3033)
* ONNX LSTM get dimension only if required

* Test dynamic onnx lstm model import

* Enable LSTM_Seq_lens_unpacked_model import test

* Disable model zoo execution test "MSFT_opset9_LSTM_Seq_lens_unpacked"

* Add missed comma in xfail list

* Update error messages

* init xfail issue

* test zoo models import xfail issue

* Fix SEQ_LENGTH init

* Comments update

* Fix usage of v0::Add by overloaded operator
2020-11-13 17:31:29 +03:00
Ivan Tikhonov c309bb77d2
Reference implementations for Loop and TensorIterator ops (#2978)
* 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

* first debug version

* more tests

* missing test file

* removed not needed shapes from test data

* move test data to new folder

* shape infer tests

* Added execution 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

* more execution tests

* add a new constructor of Loop op, resolve review remarks

* execution tests

* synchro with current version

* handle scalars and more tests

* scalar test enabled

* loop reference impl

* bug fixes in tests, onnx importer part and in the ref implementation of the Loop op

* applied remarks

* handle unsupported cases

* rewrite unit tests

* update INTERPRETER manifest

* is_termination_condition_always_true simplification

* [TEST] update python models tests

* review remarks

* added xfail to tiny_yolov3

* missing model test

* revert test data

* fixed numbers of failing tests

* fixed failed test description

* fix test message

* fix xfail test

* reference implementation for ngraph::function

* update loop reference implementation

* Refactor loop reference implementation

* ngraph codestyle

* Refactoring

* Submodule update

* Skip check for Reduce ops in mkl for scalar cases, support for yolov3

* fix ngraph reader tests

* revert ceiling op, renaming

* Add allias(Ceiling) for Ceil op in mkl

* delete xfails

* fix build

* single layer tests for tensor iterarator

* Refactor TensorIterator and Loop ref impls

* revert dynamic tensor creation, disable some dynamic test cases

* fix warning

* Resolve review remarks

* revert Predefined values in Loop tests

Co-authored-by: Mateusz Bencer <mateusz.bencer@intel.com>
2020-11-10 15:49:59 +03:00
Mateusz Bencer 0baad0696c
[ONNX Importer] Resolved problem with incorrect opset version set in subgraph (#2959) 2020-11-10 09:57:06 +01:00
Andrew Bakalin 8d4f8c4edd
[ONNX] Return NMS-5 generation (#3003)
* [ONNX] Return NMS-5 generation

* Disable failed models
2020-11-10 09:45:14 +03:00
Rafal Blaczkowski 935ac543ac
Update ONNX models preprocessing script (#2936)
* Update onnx zoo models

* Update xfail list

* Update xfails
2020-11-05 12:40:48 +03:00
Rafal Blaczkowski fbf7cc70ab
Update xfails (#2979) 2020-11-05 10:12:51 +03:00
Tomasz Socha 7c6794344c
[ONNX][PyTests] Fix result datatype missmatch (#2596) 2020-11-04 12:19:40 +01:00
Michał Karzyński 23188e1b04
Expand ONNX functions to sub-graphs before import (#2733)
Co-authored-by: Bartosz Sledz <bartosz.sledz@intel.com>
2020-11-04 10:48:34 +01:00
Alexandra Sidorova 5596c7c841
[CPU] Added eltwise Round-5 (#2347) 2020-11-02 18:44:50 +03:00
Alexander Peskov 6fe05ecda7 Unmark passed ONNX test
Signed-off-by: Alexander Peskov <alexander.peskov@intel.com>
2020-11-02 12:37:48 +03:00
Nikolay Shchegolev 50408defba
[CPU] Enable GatherND tests in ONNX. (#2904) 2020-10-29 22:53:26 +03:00
Maxim Andronov fdbfab8546
[CPU] Add tests for SetBlob + I64 (#2402) 2020-10-29 11:34:29 +03:00
Mateusz Bencer 53b865eb58
ONNX Loop (#2847)
* 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

* first debug version

* more tests

* missing test file

* removed not needed shapes from test data

* move test data to new folder

* shape infer tests

* Added execution 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

* more execution tests

* add a new constructor of Loop op, resolve review remarks

* execution tests

* synchro with current version

* handle scalars and more tests

* scalar test enabled

* loop reference impl

* bug fixes in tests, onnx importer part and in the ref implementation of the Loop op

* applied remarks

* handle unsupported cases

* rewrite unit tests

* update INTERPRETER manifest

* is_termination_condition_always_true simplification

* [TEST] update python models tests

* review remarks

* added xfail to tiny_yolov3

* missing model test

* revert test data

* fixed numbers of failing tests

* fixed failed test description

* fix test message

* fix xfail test

* zoo models tests clean-up

* missing comma

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
2020-10-29 09:51:51 +03:00
Gorokhov Dmitriy abb8817cf6
[CPU] Generic JIT Eltwise implementation (#1464) 2020-10-28 09:16:28 +03:00
Tomasz Dołbniak d5cd8673f4
Fix the model downloader script (#2784) 2020-10-23 09:58:12 +03:00
Jan Iwaszkiewicz 77794535ab
[ONNX] WA for I64 images (#2411) 2020-10-22 14:06:23 +02:00
Mateusz Tabaka d901bbfce3
Use MVN in GroupNorm/InstanceNorm in ONNX importer (#2711)
* Use MVN in GroupNorm/InstanceNorm in ONNX importer

* Remove mosaic_8 model from xfail list
2020-10-21 13:48:53 +03:00
Tomasz Dołbniak 3688ff4c51
Use LogSoftmax-5 in the onnx_importer (#2602) 2020-10-21 10:50:16 +02:00