Commit Graph
8291 Commits
Author SHA1 Message Date
Irina Efode 3f14ec7fcb Fix relative path in conformance runner script (#13418) 2022-10-13 12:50:49 +04:00
Zhang Yi 7d5e0abcaa [CPU]add interaction op with FP32 & BF16 support (#12351) 2022-10-13 11:59:48 +04:00
Luwei Zhou 61acc4a08b [CPU] Add conv per-tensor input zero point. (#12270)
- Enable per-tensor zp on AVX512_VNNI and AVX512_AMX ISA to use BRGCONV kernel.
- Fix brgconv should not be disabled correctly in some INT8 model which has binary postops
- Merge optimization of convolution attribute PR to lower down the load network time latency
- Only enable conv/group conv S8 input on AMX. Non-AMX same with 2022.1 LPT input precision config.
2022-10-13 10:07:11 +04:00
hyunback kim 383ec09d85 [GPU] Fix endless loop issue in onednn optimization post-opt (#13413)
* [GPU] Fix endless loop issue in onednn optimization post-opt
* Reproduced in yolo_v5s.int8
* Add OV_GPU_DisableOnednnOptPostOps in debug_configuration
2022-10-13 14:47:03 +09:00
Ilya Churaev 01d332eb59 Added initial documentation version for Inference component (#13439) 2022-10-13 08:38:32 +04:00
Karol BlaszczakandAlina Kladieva 22bfd50b5f DOCS-https-change-for-notebook-repository (#13426)
Porting https://github.com/openvinotoolkit/openvino/pull/13145 to master

Co-authored-by: Alina Kladieva <alina.kladieva@intel.com>
2022-10-13 07:18:35 +04:00
Maciej Smyk 39abc5368d DOCS: Port to master - NNCF Fix (#13283)
Port from #13215
2022-10-12 17:06:37 +02:00
Przemyslaw Wysocki b36fc446a3 [PyOV] Update docs with Python 3.10 (#13243) 2022-10-12 15:52:41 +02:00
Mikhail Ryzhov a197c814f8 renamed unit tests in azure ci (#13450) 2022-10-12 17:04:23 +04:00
Sebastian GolebiewskiandMaciej Smyk 60099a19bd DOCS: Fixing formatting in Samples - port to master (#13128)
* DOCS: Fixing formatting in Samples - porting to master

Porting
https://github.com/openvinotoolkit/openvino/pull/13085

Fixing incorrectly numbered lists and indentation of code blocks.

* Update get_started_demos.md

Co-authored-by: Maciej Smyk <maciejx.smyk@intel.com>
2022-10-12 14:16:02 +02:00
Karol Blaszczak 7f75da93ed DOCS-benchmarks table update (#13436) 2022-10-12 12:39:13 +02:00
Oleg PipikinandIlya Churaev 11579530b7 Add IR frontend tests (#13178)
* Add IR frontend tests

* Fix comments

* Add tests

* Fix comments 1

* Fix comments 2

* fix comments 3

* fix code style

* Fix comments 4

* Fix comments 5

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
2022-10-12 13:31:58 +04:00
Irina Efode 07aabf27bc The same Conformance IR name version by version (#13329)
* Initial version

* Add ports info

* Checks

* add dynamic
2022-10-12 11:46:01 +03:00
Ilya Lavrenov c2911adf94 Conda-forge fixes (#13392) 2022-10-12 12:16:13 +04:00
Mikhail RyzhovandAdam Tumialis ea3ac0d335 [GNA] Rename and move to new place gnaFuncTests, gnaUnitTests (#13280)
* [GNA] Move tests to plugin dir

* reverted temporary fix

* Added linux specific compiler flags

Co-authored-by: Adam Tumialis <adam.tumialis@intel.com>
2022-10-12 09:33:42 +02:00
Haiqi Pan c0c4c41241 Correct the GPU number that triggers the CPU removal in CTPUT (#13225) 2022-10-12 15:00:04 +08:00
Katarzyna Mitrus 844b0a2682 [shape_infer] Shape inference function for GRU/AUGRUSequence operations (#12982)
* shape_infer function for gru_sequence

* Reuse gru sequence shape infer for augru shape infer

* link ov_shape_inference in transformations

* Move attention input validation to shape_infer

* Update gru_sequence type prop tests

* type prop tests update

* gru_sequence shape_infer tests

* Update merged dimensions init

* Enable GRUSequence shape_infer in cpu

* Comments update

* Align error messages

* Change constexpr int to size_t in tests

* Apply types refactor

* Remobe set_input_is_relevant_to_shape from gru/augru_sequence

* Style apply

* revert constexpr for result_et

* Uninitialize valid_num_directions variable
2022-10-12 10:35:54 +04:00
Pawel Raasz 988ed3b2f1 Remove deprecated util functions (#13417)
* Remove deprecated and not used functions:
- ngraph::is_valid_permutation
- ngraph::apply_permutation

* Use not blocking assertion in transpose test,
type prop
2022-10-12 10:23:26 +04:00
Pawel Raasz 660b309235 Extract and move transpose evaluate bounds tests (#13428)
* Extract and move transpose evaluate bounds tests

* Apply clang-format
2022-10-12 06:41:02 +02:00
Ivan Tikhonov 8a9890dbf1 [TF FE] Support DynamicStitch operation (#13408)
* Delete unneccessary changes

* codestyle

* skip dynamic stitch layer tests for legacy frontend

* apply review comments

* fix unit tests, apply review comments
2022-10-12 08:04:19 +04:00
Wang, Yang 6bd099917a [AUTO plugin] Enable benchmark setting performance hint with none value to hardware device through AUTO/MULTI plugin (#13063)
* Set 'UNDEFINED' as the performancehint default value. Update benchmark app to pass performance hint with none value to MULTI/AUTO plugin.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Using 'UNDEFINED' as the default value of hint in AUTO/MULTI plugin.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Adding a flag instead of adding a default value of hint to check if user configures the performance hint to AUTO/MULTI plugin.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update benchmark python version.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
2022-10-12 10:03:17 +08:00
yanlan song 37a0afa330 disable binder related tests (#13399)
Signed-off-by: fishbell <bell.song@intel.com>

Signed-off-by: fishbell <bell.song@intel.com>
2022-10-12 04:12:42 +03:00
Ekaterina Aidova d6694e4820 [OMZ]: update submodule to minimize ac dependencies (#13416) 2022-10-11 19:56:58 +04:00
Liubov Talamanova 968bd6c96b Fix bug with unknown node type (#13406) 2022-10-11 19:05:54 +04:00
Evgenya Stepyreva abd58eef5c Group Convolution: prevent dyn input shape from making weights dynamic via ShapeOf (#13374)
* GroupConvolution: prevent dynamic input shape to make weights dynamic via ShapeOf

* Minor fix to get rid of deprecation warnings
2022-10-11 18:48:11 +04:00
Ruslan Nugmanov 37dbcdac3f Adds fixture for tf2 layer tests to run them with new FE (#13403)
* Adds fixture for TF new FE

* fixes imports
2022-10-11 17:25:05 +04:00
Roman Lyamin 9c6ad77852 [GPU] FullyConnected dynamic (#13015)
* [GPU] FullyConnected dynamic

* [GPU] Fix FC OneDNN usage
2022-10-11 16:51:18 +04:00
Oleksandr Zhydkov 2d4d80a444 [GPU] Add support class agnostic box regression for experimental detectron … (#13003)
* add support class agnostic box regression for experimental detectron detection output

* add test
2022-10-11 21:31:47 +09:00
Oleksii Khovan 66b5f9acf2 [GPU] GenerateProposals-9 (#11994)
* add static_output attribute to enable GPU implementation of GenerateProposals.
This change may be reverted when dynamic shapes support will be implemented
in GPU plugin.

* - add GPU single layer test;
- add normalized attribute to SLT.

* add GPU primitive for GenerateProposals

* add kernel for GenerateProposals

* add unit test for GenerateProposals

* add blocked layouts support

* tidy up

* support blocked layouts also for 2nd and 3d outputs

* Transformation to deal with dynamic output in GPU
  - revert changes in GenerateProposals interface and shape inferenece;
  - add transformation;
  - custom compare method in single-layer test.

* address review comments

* fix after rebase

* fix after rebase

* review comment: added nms_eta to testcase name generation

* - added input types combination to functional tests;
- fix float16 comparison.

* fix after rebase

* use vector for input ids

* fix after rebase
2022-10-11 21:10:32 +09:00
Ilya Churaev b2e35592f7 Fixed comments after PR 13366 (#13389) 2022-10-11 13:07:18 +04:00
Ilya Churaev f58dc8f7c5 Fixed mac build generation (#13415) 2022-10-11 06:45:06 +00:00
Alina Kladieva 067537f6d0 Show ccache stats in linux_coverity (#13382) 2022-10-11 08:25:19 +04:00
Ilya Lavrenov 54eede2e6a Enabled clang-format for offline_transformations (#13410) 2022-10-11 07:56:30 +04:00
Tomasz Dołbniak b00796324c Unique-10 operator specification (#13361) 2022-10-10 20:06:21 +03:00
Georgy Krivoruchko 28954a82d9 Subgraphs Dumper fixes (#13356)
* Fixed exception in case more than one output

* Fixed a loosing an operations in case of constant inputs
2022-10-10 18:38:15 +03:00
Roman Kazantsev 589c95ec19 [TF FE] Support DynamicPartition operation (#13363)
* [TF FE] Support DynamicPartition operation

Add support for DynamicPartition operation and validate it with the layer tests

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Add implementation

* Rescale partition indices to provide stable sorting

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-10-10 17:52:55 +04:00
Pawel Raasz b4ad7033c9 Opset 1 transpose shape inference review (#12937)
* Test to interval shape propagated by transpose

* Test to propagate labels by transpose

* Add template transpose shape inference

* Fixes to transpose shape inference

* Update names for shapes:
input -> input_shape
order -> order_shape

* Not fill output shape for dynamic range

* Add constexpr to SeqGen and Between comparator

* Correct StaticShape creation in test

* Tests check partial value propagate in arg input

* Add evaluate upper, lower, label to transpose
- add test

* Add common methods for inference and evaluate

* Move helpers to shape_inference

* Move transpose attribute to transpose op

* Fix include in transpose operator

* Correct label generation and type

* Fix null conversion

* Use uint64_t for labels tensor

* Fix compare labels

* Use order length as output rank

* Update transpose transformation test

* Move helpers to validation_util

* Correct test assertion for expected shape

* Transpose evaluate use common function
for output calculation

* Remove redundant helpers from transpose test
2022-10-10 16:18:52 +04:00
Wang, YangandRiver Li 457f606812 [AUTO] fix Performance inefficiencies issue (#13273)
* fix Performance inefficiencies issue caused by previous PR.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: River Li <river.li@intel.com>
2022-10-10 08:42:43 +00:00
Asthestarsfalllandcecilia peng 94ef65f0bd add paddle elementwise mod op (#12370)
Co-authored-by: cecilia peng <cecilia.peng@intel.com>
2022-10-10 11:03:09 +03:00
Vladislav Golubev 372fe475c9 [LPT] Removed legacy limitations on dequantization propagation for several transformations (#13048) 2022-10-10 10:58:23 +04:00
OlehKravchyshyn e8c8ad19f4 [GPU] eye-like operation (#11937)
* eye-like operation

single layer tests
unit tests

* [GPU] adjust eye implementation to the current GPU operation design
2022-10-10 11:29:40 +09:00
Ruslan Nugmanov 80b6086bab Adds TF2 layer tests witn new FE in precommit (#13311)
* marks tf2 keras tests as precommit for new FE

* adds tf2 layers tests for new FE in precommit

* removes redundant tabulations

* review changes

* fix field name

* fix syntax error

* removes failing tests

* removes failed test

* removes failed test
2022-10-08 16:40:34 +03:00
Orest Chura 1e5ff24834 Fix openvino_mock_py_frontend target compilation (missing openvino::runtime dependency) (#13393) 2022-10-08 11:17:51 +04:00
Ilya ChuraevandIlya Lavrenov a8abfa221b Fixed small comments after enabling warning as error (#13364)
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-10-07 19:40:26 +04:00
Ilya ChuraevandTatiana Savina 767944cc46 Changed structure of core components and fixed links (#13366)
* Changed structure and fixed links

* Exclude README.md from CI check

* Update README.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update README.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update src/README.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update src/README.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update src/README.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Fixed links

* Update src/frontends/README.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update src/frontends/README.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update src/plugins/README.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2022-10-07 19:04:55 +04:00
Roman Kazantsev f5febef8a6 [TF FE] Support SegmentSum operation (#13354)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-10-07 17:01:14 +03:00
Irina Efode cdb486d838 [CONFORMANCE] Fix Summary (#13358) 2022-10-07 14:40:05 +04:00
Jade Cho 36f28e5618 [GPU] Convert AvgPool to Reduce for onednn (#13037) 2022-10-07 18:25:47 +09:00
Ilya Lavrenov c83ad806d9 Enabled LTO for OSX (#13266) 2022-10-07 12:09:44 +04:00
Roman Kazantsev 227f9ae5af [CI, Azure] Fix linux-arm64 (#13368)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-10-07 10:15:49 +04:00