IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
12,184 Commits 38 Branches 54 Tags 1.1 GiB
6d3726024d
Commit Graph

12184 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Sebastian Golebiewski
6d3726024d
[DOCS] Updating Supported Model Formats article (#18495) 
* supported_model_formats

* add-method

* apply-commits-18214

Applying commits from:
https://github.com/openvinotoolkit/openvino/pull/18214

* Update docs/MO_DG/prepare_model/convert_model/supported_model_formats.md

* Update docs/MO_DG/prepare_model/convert_model/supported_model_formats.md

* Update docs/MO_DG/prepare_model/convert_model/supported_model_formats.md

* Update docs/MO_DG/prepare_model/convert_model/supported_model_formats.md

* Update docs/MO_DG/prepare_model/convert_model/supported_model_formats.md

* Update supported_model_formats.md

* Update docs/MO_DG/prepare_model/convert_model/supported_model_formats.md

* Update docs/MO_DG/prepare_model/convert_model/supported_model_formats.md

* review-suggestions

* Update supported_model_formats.md
 2023-08-23 18:26:07 +02:00
Maksim Kutakov
6a628f7056
[CPU] Fix deconvolution default primitive search algo (#19261) 
* Fix deconvolution default primitive search

* Add dedicated test
 2023-08-23 16:58:38 +02:00
Maksim Kutakov
c6a02b76be
[CPU] Fix convolution plus sum layout alignment (#19279) 2023-08-23 16:29:26 +04:00
Vladislav Golubev
982d0f43c4
[CPU] Optimal number of streams calculation moved after LPT (#19313) 2023-08-23 16:28:42 +04:00
Marcin Kusmierski
25e89a754d
[GNA] Fix memory leak in insert_copy_layer.cpp (#19266) 
* Added cleanup transformation for inert copy layer transforamtions
 2023-08-23 13:11:16 +01:00
Anton Voronov
59d58b2296
[CPU][ONEDNN] jit_uni_dw_conv_row_f32: fixed post ops start index (#19126) 2023-08-23 15:52:09 +04:00
Ilya Churaev
bc868a8873
Enable clang format for itt headers (#19326) 2023-08-23 15:13:59 +04:00
Ilya Churaev
dcfb6bb042
Remove some legacy headers from inference component (#19325) 
* Remove some legacy headers from inference component

* Fixed code style
 2023-08-23 15:13:30 +04:00
Mustafa Cavus
aa53394c07
TorchFX bugfix missing core object in get_device() (#19255) 2023-08-23 14:42:38 +04:00
Vladimir Paramuzov
3b2e263879
[GPU] Fix reshape optimization (#19270) 2023-08-23 10:25:04 +00:00
Ekaterina Aidova
80b8b6fff1
[PT FE]: allow example input list with single tensor (#19308) 2023-08-23 12:08:39 +04:00
Ivan Tikhonov
128ec5452e
Transformations API 2.0: replace ngraph headers and namespaces with openvino (#19304) 
* switch to OV headers and namespaces

* resolve review comments

* fix precomp header

* refactoring, add missing include
 2023-08-23 11:45:34 +04:00
Oleg Pipikin
7aa51d6775
Remove makeParams (#19306) 2023-08-23 11:39:05 +04:00
Evgeny Kotov
f4cc3bf7d3
add callback check (#18397) 
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
 2023-08-23 11:01:11 +04:00
Xuejun Zhai
50214511e7
Avoid creating new threads when converting legacy inference request to API 2.0 (#19342) 
* Fix error in CVS-115961, caused by wrapper covert 1.0 req to 2.0 req create 2 more threads

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Eable the test of compareAutoBatchingToSingleBatch with batch size 4 & num req 64, after fix issue 115961

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-08-23 10:25:47 +04:00
Alexandra Sidorova
27bf0f9e1e
[Snippets] Fixed memory leak in LinearIR (#19316) 2023-08-23 09:18:04 +04:00
Maxim Vafin
4882ccde03
[PT FE] Fix issue when FakeQuantize is not inserted after regular operations (#19314) 2023-08-22 17:18:23 +02:00
Karol Blaszczak
6eee51a6ef
[DOCS] including NPU documents (#19340) 2023-08-22 17:17:37 +02:00
Pratham Ingawale
9a76daf94b
generator to pytest (#19298) 
* trying with pytest

* update as per suggested

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2023-08-22 17:42:56 +04:00
Sebastian Golebiewski
6cd70af7c2
update-notebooks (#19337) 2023-08-22 15:37:37 +02:00
Oleg Pipikin
de65abc6b3
Remove WA for vpu repo with CommonTestUtils namespace (#19275) 2023-08-22 13:03:45 +00:00
Zhang Yi
7e724565b5
[CPU] Use parallel_nt_static for MLAS threading (#19297) 2023-08-22 10:38:07 +00:00
Sergey Shlyapnikov
7df8d1ca2d
[GPU] Add per iteration performance profiling mode (#18637) 2023-08-22 12:37:36 +02:00
Surya Siddharth Pemmaraju
acbac2f560
Added openvino torch backend import statement in init files (#19208) 
* Added openvino torch backend import statement in init files

* Added openvino/torch folder for simplyfing the import

* Removed imports from all the other init.py files

* Fixed flake8 issues

* Removed requirements.txt

* Removed redundant functions
 2023-08-22 14:24:53 +04:00
Irina Efode
551cb7ab1a
[CONFORMANCE] Extend conformance runner to use in GA with expected_failures filelist (#19285) 
* [CONFORMANCE] Extend conformance runner to use in GA with expected_failures filelist

* fix

* exclude failed tests from run in case without update

* Small refactoring
 2023-08-22 13:32:34 +04:00
Sofya Balandina
0cc3044764
Add attr info to rename_conformance_ir hash (#19277) 2023-08-22 13:30:24 +04:00
Sebastian Golebiewski
4703196f5c
link-to-frontend (#19178) 2023-08-22 11:21:56 +02:00
Zhang Yi
53c47aaa91
[CPU]Fix mlas threadpool of MlasExecuteThreaded (#19292) 2023-08-22 12:49:38 +04:00
Sebastian Golebiewski
20bf7aec13
[DOCS] Update tutorials for master (#19307) 
* update-160823

* fixes

* fix-toc-headings

* fix-headings

* fix

* fix-headings

* fix

* fix-headings

* fixes

* Update 220-cross-lingual-books-alignment-with-output.rst

* fixes

* fix

* fix-toc-headings

* fix-headings

* fix toc

* fix toc

* fix toc

* add-missing-301-nncf

* Update 301-tensorflow-training-openvino-nncf-with-output.rst

* fix toc

* fixes
 2023-08-21 16:47:14 +02:00
Wanglei Shen
7c273dc2c5
fix SDL issue (CID 1518459) (#19287) 2023-08-21 20:24:59 +08:00
Pavel Esir
90f6500871
[tests] switch layer tests to FP16 on pre-commit (#19090) 
* switch to FP16 on layer tests on precommit; add Pytorch layer tests for precision sensitive subgraph

* remove redundant changes

* moved precision sensitive tests into test_mo_convert_pytorch.py

* remove redundant dumping

* skip layer tests with chaotic output

* add copy() to avoid side effects
 2023-08-21 16:03:47 +04:00
Roman Kazantsev
5539d052b0
[JAX][TF Hub][TF FE] Introduce JAX layer tests and support of XLA operations (#19269) 
* [JAX][TF Hub][TF FE] Introduce JAX layer tests and support of XLA operations

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

* Fix JAX layer tests infa

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

* Extend run for JAX layer tests

* Use ovc convert_model

* Fix translator and extend layer test cases

* Exclude jax testing on Windows

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-08-21 16:01:48 +04:00
Ilya Churaev
cbe744b717
Introduce model reader which works only with new API (#19077) 
* Introduce model reader which works only with new API

* Fix GNA compilation

* Removed old code

* Fixed Windows build

* Remove legacy headers from core_impl

* Fixed caching tests if plugin on legacy API call ReadNetwork
 2023-08-21 15:42:36 +04:00
Roman Kazantsev
19ff7fba3d
[TF FE] Fix support of CTCLoss and add tests to pre-commit (#19291) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-08-21 14:26:36 +04:00
Wanglei Shen
61fcf3855a
fix SDL issue (CID 1518457) (#19289) 
* fix SDL issue (CID 1518457)

* update for comments
 2023-08-21 17:43:09 +08:00
Maxim Vafin
d55e45f677
[PT FE] Support non boolean inputs for __or__ and __and__ operations (#19268) 
* [PT FE] Support non boolean inputs for __or__ and __and__ operations

* Add test for __or__
 2023-08-21 10:55:30 +02:00
Zlobin Vladimir
3813b0bc55
classification_sample_async: state that the samples support NCHW model layout only (#19259) 
Ticket 107409
 2023-08-21 09:02:29 +04:00
Karol Blaszczak
601cfadabf
Update prerelease_information.md (#19282) 2023-08-18 20:00:54 +02:00
Karol Blaszczak
3e6a3eee6d
[DOCS] contributing guidelines (#19218) 
changes to the contribution guide
 2023-08-18 17:59:31 +02:00
Karol Blaszczak
7635f89141
[DOCS] pre-releasenotes 23.1 Aug port master (#19273) 2023-08-18 17:58:01 +02:00
Vladimir Paramuzov
526d76c81f
[GPU] New headers and namespaces in some parts (#19229) 2023-08-18 15:57:15 +04:00
Anton Voronov
4f29e60742
FIxed is_on_constant_path() using in all places (#19239) 
* Fixed matmul weights check in snippets_mark_skipped

* fix

* ConvertMatMulToFC: is_on_constant_path fix

* [TESTS] added SplitMatMulConcat subgraph test

* MarkDequantizationSubgraph: is_on_constant_path fix
 2023-08-18 14:01:07 +04:00
Roman Kazantsev
24ddf1b274
[TF FE] Use regular Convolution in case dynamic input channels (#19253) 
* [TF FE] Use regular Convolution in case dynamic input channels

This solution is aligned with the legacy frontend but it has limitation.
This is a temporal solution until the core obtains ShapeOf evaluator.

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

* Remove unused variable from the test

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

* Fix unit-test

* Update mo unit-test

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-08-18 13:39:59 +04:00
Vitaliy Urusovskij
ef33c2b3fd
Fix uninit members in default GroupNormalization() (#19244) 2023-08-18 12:16:55 +04:00
Irina Efode
e9fdf0cac4
[CONFORMANCE] Add progress bar to Subgraphs Dumper (#19235) 2023-08-18 11:59:22 +04:00
Ivan Tikhonov
dc6f04f475
Handle unspecified type in wrap_tensor function; unit tests (#19220) 2023-08-18 10:25:09 +04:00
Ivan Tikhonov
20bb450af2
Fix TransposeSinking when the data input is broadcasted (#19233) 2023-08-18 10:23:59 +04:00
Georgy Krivoruchko
e4bed7a31c
[ONNX] Fixed issue with missing sort when wstring path (#19250) 
* Fixed issue with missing sort when wstring path

* Fixed CI linux builds
 2023-08-18 01:24:59 +04:00
Anastasia Kuporosova
f51f0c7a6a
try to remove redandant functions (#18761) 
* try to remove redandant functions

* remove redundant imports

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-08-17 16:11:39 +00:00
Edward Shogulin
318009f8d5
[LPT] MoveFakeQuantize: Q/DQ pattern identification generalization (#18945) 
* [LPT] MoveFakeQuantize Q/D pattern dequantization generalization

* [LPT] MoveFakeQuantize Q/D pattern dequantization generalization: quantize op convert
 2023-08-17 17:07:51 +01:00