IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
10,564 Commits 38 Branches 54 Tags
c2a90f4c01bc2b97ecacc5d6ad423f5e66041130
Commit Graph
10564 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Irina Efode c2a90f4c01 [CONFORMANCE] Fix error with import sigkill (#16884) 2023-04-12 18:21:57 +04:00
Wang Wangwang c2c2143f45 clean AB property from virtual plugin and core global config (#16877) 
* Benchmark_app set ov::hint::allow_auto_batching through compile_model

* Remove the process about allow_auto_batching in set_property of core

* Remove allow_auto_batching and auto_batch_timeout property from AUTO plugin

* Reserve the info logs and add API to check auto_batching

* Update test case, rm AB property test from core config tests

* Update some API in AUTO plugin config
 2023-04-12 17:37:57 +04:00
Tomasz Dołbniak fb49228fec Pillow modes in the preprocessor's resize mechanism (#16601) 2023-04-12 15:30:42 +02:00
Sofya Balandina ed5148b75f [apiConformance] Refactor io_tensor tests (#16348) 2023-04-12 17:22:01 +04:00
Vladimir Paramuzov 7d4496bb12 [GPU] Remove unused constants from the graph (#16873) 2023-04-12 16:52:26 +04:00
Mateusz Bencer e737e18b02 [ONNX FE] Fix Squeeze v1 (#16865) 2023-04-12 14:33:49 +02:00
Sergey Shlyapnikov 997f60f1c3 [GPU] Fix shape_of shape inference optimization (#16863) 2023-04-12 15:44:34 +04:00
Mateusz Tabaka bdd79fe931 CompressQuantizeWeights - use f32 precision when computing scale and zero point (#16794) 
Ticket: 101825
 2023-04-12 12:42:39 +02:00
Szymon Irzabek 496fe7a7db [GNA] Extend unsupported concat detection to include cascaded concat with convolution (#16756) 2023-04-12 12:19:42 +02:00
Przemyslaw Wysocki 69d6ef33fc [PyOV] Align and bump numpy, further tidy up requirements (#16652) 
* Align numpy

* Simplify the rest

* Minor change

* Minor change

* Restart CI

* Update paddle reqs
 2023-04-12 13:14:38 +04:00
Marcin Kusmierski b755d17090 [GNA] Fix plugin crash when infinite loop discovered. (#16770) 2023-04-12 10:00:52 +02:00
Maxim VafinandRoman Kazantsev 23c90aecea Add support for opset10 and opset11 in MO IR Reader (#16742) 
* Add support for opset10 and opset11 in MO IR Reader

* Fix unique

* Refactor tests

* Fix Unique shape infer

* Update tests

* Apply suggestions from code review

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Apply review feedback

* Fix BOM tests

* Update tools/mo/unit_tests/mo/utils/ir_reader/ops_test.py

* Improve error log

* Fix test fails when using pytest

* Add changes forgotten in last commit

* Fix error message

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2023-04-12 11:35:52 +04:00
Ivan Tikhonov 132dceb146 Delete redandant node copies in TSSqueeze, TSUnsqueeze and TSReduction transformations (#16753) 
* Delete redandant node copies in TSSqueeze, TSUnsqueeze and TSReduction transformations, add new tests

* codestyle

* codestyle
 2023-04-12 11:30:48 +04:00
Bo Liu 4bb9222c6e fix Paddle unit tests unexpected exceptions and seg fault issue (#16808) 
* fix Paddle unit tests unexpected exceptions and seg fault issue

* parse confine from reqfile to keep algin with other requirements

* Apply suggestions from code review

* Apply suggestions from code review
 2023-04-12 11:13:25 +04:00
Karol Blaszczak 4b16c7554e [DOCS] minor fixes for front_ext and pre-notes (#16866) 2023-04-12 07:55:34 +02:00
Roman Lyamin f8aacf3b19 [GPU] Small fix for gather_nonzero (#16858) 2023-04-12 09:15:49 +04:00
Steve Yoo 0312d8cf1b Skip asymmetric compensation if its type is not data, and add its unittests (#16494) 2023-04-11 20:16:25 -07:00
Roman Lyamin 2312ec79a2 [GPU] Skip failing lstm tests (#16868) 2023-04-12 02:10:42 +02:00
Edward Shogulin 586dd4fb0a [Snippets] BF16 enforce in snippets (#16587) 2023-04-12 01:12:17 +02:00
Anastasia Kuporosova 31aa35b646 [PyOv] remove commented functions without implementation (#16864) 2023-04-12 01:07:29 +04:00
Przemyslaw Wysocki ea213f687a Fix regex (#16850) 2023-04-12 01:06:54 +04:00
Wang, Yang 3740ba9226 [IE Sample] incorrect nstreams retrieved from plugin (#16849) 
* Retrieve the ov::num_streams through compiledModel rather than through plugin.

* Update python version.
 2023-04-12 01:06:20 +04:00
Ivan Tikhonov 920900fbda Delete the redundant check in convert method of TF FrontEnd class (#16846) 
* remove a check in convert method

* delete unused variables and comment

* leave only one pass::Manager in normalize method
 2023-04-12 01:05:16 +04:00
Ilya Churaev 4a43753e02 Enable some tests for Template plugin (#16832) 
* Remove the skip of template plugin tests

* Enable some skipped tests for template plugin

* Added cancel callback, collect per-layer statistic, fixed tests

* Fixed template tests

* Rename internal API terminate to cancel

* Fixed windows tests

* Fixed logic with performance counters
 2023-04-12 01:02:28 +04:00
Ian Hunter 209db8a29b Update ie_common.h (#16860) 2023-04-12 00:52:02 +04:00
Andrew Kwangwoong Park 63b16baa7e [GPU] Fix strided slice clamped negative begin with negative stride (#16843) 
Signed-off-by: Andrew Park <andrew.park@intel.com>
 2023-04-11 11:52:22 -07:00
Roman Kazantsev 9e89b6c5f6 [TF FE] Support NonMaxSuppression with named outputs (#16835) 
* [TF FE] Support NonMaxSuppression with named outputs

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

* Simplify the test for NMS named outputs

* Share a script for test model generation

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-04-11 19:14:59 +02:00
Taylor Yeonbok Lee 7513e9dee1 [GPU] Applied w/a to resolve softmax accuracy issue (#16818) 
* Applied w/a to resolve softmax accuracy issue
The original impl resulted in accuracy issue if leftover is not aligned with subgroup size.
(e.g., for shape [1024, 306] where the lws = 32, itemsNum = 9, leftover = 18, subgroup size = 16)
In such a case, the result got wrong if subgroup block read/write is used.
As a w/a, not to use subgroup block read/write if leftover is not aligned with nsubgroup size.
However we can come up with better itenNum size / lefover handling in the follot bwing up work.

* Fix build error & minor revise

* Fix condition
 2023-04-11 10:01:22 -07:00
Mateusz Tabaka 4fbd094cba BroadcastConstRangeReplacement - skip unsqueeze if Broadcast input is 1D (#16851) 
Ticket: 106636
 2023-04-11 17:59:03 +02:00
Vladislav Golubev 98afdc848a [LPT] ConvolutionTransformation: support for a new per channel dequantization representation (#16687) 
* [LPT][TESTS] GrConv: added test cases with per channel dq on weights and without reshape

* FoldFQ: don't transform FQ with quantization by several dimensions

* ConvolutionTransformation: supported GrConv with per channel dq on weights and without reshape

* fold_reshape: refactoring
 2023-04-11 14:07:23 +02:00
Vladislav Golubev 296c2d6603 [Transforamtions] NonZero horizontal fusion: review leftovers (#16639) 
* Review comments applied

* codestyle

* review comments applied
 2023-04-11 15:42:43 +04:00
Ekaterina Aidova ca2265395d [PT FE]: fix aten::mean behaviour for provided dtype (#16790) 2023-04-11 14:29:29 +04:00
Ekaterina Aidova d41663694c [PT FE]: aten::gather (#16784) 
* [PT FE]: aten::gather

* add detach and sign
 2023-04-11 14:28:05 +04:00
Ekaterina Aidova d407bc1b3b [PT FE] fix invalid reshape shape after aten::index (#16821) 
* [PT FE] fix invalid reshape shape after aten::index

* support aten::index_select
 2023-04-11 12:41:59 +03:00
Eddy Kim f6ee6e92f8 [GPU] fixed loop serialization logic for multi-stream execution (#16838) 
* fixed loop serialization logic for multi-stream execution

* fixed the multistream unit test
 2023-04-11 12:40:37 +04:00
Roman Kazantsev f991f92f8c [TF FE] Test ResourceGather operation and fix debug caps (#16819) 
* [TF FE] Test ResourceGather operation and fix debug caps

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

* Fix test generation script

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-04-11 11:33:32 +04:00
yanlan song 527c2dad2a query capacity before popping (#16828) 
* query capacity before popping

Signed-off-by: fishbell <bell.song@intel.com>

* refine

Signed-off-by: fishbell <bell.song@intel.com>

---------

Signed-off-by: fishbell <bell.song@intel.com>
 2023-04-11 11:25:29 +04:00
Mingyu Kim 615177ae09 [GPU] Update onednn version to latest v3.1 (#16848) 2023-04-11 15:05:35 +09:00
Roman Lyamin 234fe92931 [GPU] MVN 1d dynamic batch case fix (#16826) 2023-04-11 09:42:51 +04:00
Oleg Pipikin efc647a512 [Snippets][CPU] Fix cycle dependency check in snippets tokenizer (#16760) 2023-04-10 22:36:29 +04:00
Ilya Churaev 81821f3dbb Remove vopset typo (#16833) 
* Remove vopset typo

* remove ::
 2023-04-10 19:50:06 +04:00
Ilya Lavrenov f1d6725477 Removed legacy src files from inference library (#16839) 2023-04-10 19:26:09 +04:00
dependabot[bot] 81af7f52cb Bump pytest from 7.2.0 to 7.3.0 in /src/bindings/python (#16830) 
Bumps [pytest](https://github.com/pytest-dev/pytest) from 7.2.0 to 7.3.0.
- [Release notes](https://github.com/pytest-dev/pytest/releases)
- [Changelog](https://github.com/pytest-dev/pytest/blob/main/CHANGELOG.rst)
- [Commits](https://github.com/pytest-dev/pytest/compare/7.2.0...7.3.0)

---
updated-dependencies:
- dependency-name: pytest
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2023-04-10 16:50:12 +04:00
Ilya Lavrenov feb08c408f Return benchmark_tool to openvino-dev wheel (#16834) 2023-04-10 16:34:51 +04:00
Ilya Lavrenov 023dc1fa3d Remove warnings during cython call (#16831) 2023-04-10 16:28:15 +04:00
Roman Kazantsev f36ee94b4b [TF FE] Correct SpaceToBatch layer test (#16823) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-04-10 14:41:02 +04:00
Evgenya Stepyreva bc7a121a20 Removes legacy transformations from CNNNetworkNGraphImpl::reshape (#15853) 
* Removes legacy transformations from CNNNetworkNGraphImpl::reshape

* Removes legacy transformations from CNNNetworkNGraphImpl::reshape

* 6 more models propagate shape more precise

* Removes legacy includes

* Fix invalidation

* Test change

* win fix

* Ilyas suggestion

* Unary ops -- removed shape relying on the output of the op, used shapes from the input tensor instead

* Code clean up

* Equal: bounds evaluation

* Equal: bounds evaluation

* Restrict TypeRelaxed from partial_value propagation

* TypeRelaxed: propagate lower/upper bounds

* Remove debug prints

* fix build

* GPU shape inference problem fixed

* Generate Proposals: better dynamic shape propagation

* Style
 2023-04-10 12:36:56 +02:00
Ilya Churaev b921bf2e29 Remove redundant copy of ov::Any in has_rt_info method (#16802) 
* Remove redundant copy

* Fixed Python segfault and avoid a copy of ov::Any
 2023-04-10 13:56:35 +04:00
Sergey Shlyapnikov 2075dcb7c3 [GPU] Fix Interpolate assert (#16806) 2023-04-10 12:29:01 +04:00
Sofya Balandina ed50d3782c [apiConformance] Define mandatory scope for infer requiest tests (#16418) 2023-04-10 12:27:20 +04:00