IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
12,087 Commits 38 Branches 54 Tags
e2db808495c4f48af97aeff820fd1e2dcb2105a1
Commit Graph

12087 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Paul Youngsoo Ahn
e2db808495 [GPU] Fix multiple output issue in get_output_layout(#19186) (#19186) 2023-08-14 20:49:21 +00:00
Irina Efode
a0d1b91a78 [CONFORMANCE] Readability in model_utils (#19175) 2023-08-14 23:15:20 +04:00
Aleksandr Voron
e48b2dfc34 [CPU][ARM] Set FP16 inference precision by default for non-convolution networks on ARM (#19069) 2023-08-14 22:22:39 +04:00
Maxim Vafin
e49b2c05f1 [PT FE] Fix behavior of convert_partially method to align with new description (#19147) 
* [PT FE] Fix behaivior of convert_partially method to align with new description

* Simplify

* Do not add a message to exception of get_converted_model

* Update src/frontends/pytorch/src/frontend.cpp

* Supress normalize exception only when model is valid

* Create TranslateSession in own scope
 2023-08-14 16:56:06 +00:00
Mateusz Mikolajczyk
f1d61f72ac [PT FE] Add aten::tensor_split transformation (#19144) 
* Add aten::tensor_split

* Fix formating

* Reduce number of test cases

* fix requested changes
 2023-08-14 18:31:38 +02:00
Egor Duplenskii
680333b2db [CPU][ARM] Enable FP16 precision for CumSum node (#19176) 2023-08-14 15:22:43 +00:00
Roman Kazantsev
600c2d8283 [TF FE][TF Hub] Fix conversion of SavedModel with only numerical names operations (#19166) 
* [TF FE] Fix conversion of SavedModel with only numerical names operations

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

* Compare tensor names in the unit-test

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

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-08-14 14:10:53 +00:00
Ilya Lavrenov
1ffab2fe30 Added --single-version-externally-managed during python package build (#19177) 2023-08-14 17:45:23 +04:00
Piotr Krzemiński
e77070890a [PT FE] Fix Sporadic Quantized Ops Errors (#18962) 
* [PT FE] Fix sporadics with round & 0 zero_pt, 1.0 scale

* [PT FE] Change scale and round input in quantized cat tests

* [PT FE] Add rounding to conv & linear tests

* Update test_quantized_cat.py

* Update test_quantized_cat.py

* [PT FE] Replace randn with rand for consistency in convnd
 2023-08-14 15:41:36 +02:00
Ilya Lavrenov
2830b20d73 Removed 'wheel' upper bound in requirements.txt (#19170) 2023-08-14 17:40:25 +04:00
bstankix
6afe49decf [DOCS] Add state retention to design-tabs (#19179) 2023-08-14 13:37:52 +00:00
Maxim Vafin
b10b773f0c [PT FE] Support aten::randint and aten::index_put_ on mask (#19158) 
* [PT FE] Support aten::randint and aten::index_put_ on mask

* Fix code style
 2023-08-14 15:08:08 +02:00
Ilya Lavrenov
11610b2cc9 Added 'openvino_req_files' component for archives (#19174) 2023-08-14 16:58:08 +04:00
Anton Voronov
87f9b2bdf8 [CPU] Fixed checks in snippets_mark_skipped for MatMul weights (#19141) 2023-08-14 16:04:35 +04:00
Georgy Krivoruchko
46f428eeac [ONNX] Implemented cache for MMAP handles (#19130) 
* Implemented cache for MMAP handles

* Applied comments and fixed behavior when m_data_length==0

* Aligned data length calculation with no-MMAP implementation

* Removed unused code
 2023-08-14 15:56:59 +04:00
Maciej Smyk
e5c4350d92 [DOCS] Review release docs for master (#19152) 2023-08-14 13:40:34 +02:00
Sergey Shlyapnikov
86c4c6785d [GPU] Don't invalidate users after reorder insertion (#19137) 2023-08-14 14:16:54 +04:00
Maksim Kutakov
4996d1f034 TensorMemoryBlob: sync data handle on alloc call (#19149) 2023-08-14 13:22:11 +04:00
Evgeny Kotov
44a90dc874 TransposeSinking PRelu special slope fix input(1) (#19066) 
* fix + unit tests

* code review fixes

* code review fix: IsSpecialPRelu use only partial shape
 2023-08-14 12:45:54 +04:00
Ilya Lavrenov
aebf1edec7 Fixed build without protobuf-lite (#19164) 2023-08-14 11:57:35 +04:00
Egor Duplenskii
f09d2e2666 [CPU][ARM] Perf fixes for FP16 precision (#18973) 2023-08-14 09:22:03 +04:00
Mingyu Kim
4e96b6ba9d [GPU] Do not select onednn format for asymmetric weight (#19140) 
OneDNN does not support asymmetric weight.
 2023-08-14 12:59:07 +09:00
Roman Kazantsev
329abd8864 [TF FE][TF Hub] Support UnsortedSegmentSum operation (#19165) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-08-13 17:49:38 +00:00
Ilya Lavrenov
6067ab17ba Aligned target and files (libraries) names (#19161) 2023-08-13 11:31:44 +04:00
Wanglei Shen
0368474c8a fix manually setting Pcore+Ecore manually when model prefers Pcore only (#19160) 2023-08-12 18:19:02 +08:00
Oleg Pipikin
5379068610 Fix fill_tensor_random for real values: (#19095) 2023-08-11 20:26:17 +00:00
Roman Kazantsev
545c5bbde1 [TF FE][TF Hub] Support FakeQuantWithMinMaxArgs operation (#19154) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-08-11 16:58:35 +00:00
Zlobin Vladimir
396a899b75 benhcmark_app: fix -api sync -i multiple images (#19142) 
The Python version uses `app_inputs_info` to represent different input configurations, but the C++ version extends that use case and uses `app_inputs_info` to represent different input images as well. That means that the assumption that if `app_input_info.size() > 1`, then input shape is dynamic, doesn’t always hold for C++

Ticket 117673
 2023-08-11 19:09:48 +04:00
Fang Xu
e33de35063 [CPU] Add max_threads_per_core setting into StreamExecutor (#18857) 2023.1.0.dev20230811 2023-08-11 14:12:38 +00:00
Sergey Lyalin
edc8015a65 Fixed description for convert_partially (#19133) 
* Update src/frontends/common/include/openvino/frontend/frontend.hpp

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

* Better and correct description of convert_partially (normalize or not normalize)

* Update src/frontends/common/include/openvino/frontend/frontend.hpp

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
 2023-08-11 17:29:56 +04:00
Sebastian Golebiewski
260273932a remove-howto (#19139) 2023-08-11 14:01:22 +02:00
Ekaterina Aidova
9fd8a13fe6 [PT FE] aten::concat (#19101) 
* [PT FE] aten::concat

* Update src/frontends/pytorch/src/op/cat.cpp

* add out

* fix tests
 2023-08-11 15:49:18 +04:00
Wanglei Shen
a957764362 block SOC Ecore to be used in multi-threading on Windows (#18910) 2023-08-11 15:23:29 +04:00
Anastasiia Pnevskaia
6bf75f569c Fix of tensor names loosing for cf=True flag in MOC transformations. (#19014) 
* Added shape and type infer for result nodes in MOC transformations.

* Clang format.

* Added validate_nodes_and_infer_types() pass at the end of MOC pipeline.

* Clang format.

* Added test.

* Clang format.
 2023-08-11 15:19:07 +04:00
Gorokhov Dmitriy
2bdb7bd23e [CPU] FullyConnected acceleration with 8bit weights decompression on SPR (#19111) 2023-08-11 14:14:32 +04:00
Przemyslaw Wysocki
45a60639af [PyOV] Add sympy dependency for torchvision preprocessor tests (#19112) 2023-08-11 12:03:59 +02:00
Ilya Lavrenov
a251346031 [CPU] Give different output name for dnnl (#19136) 
* Give different output name for dnnl

* Apply suggestions from code review

added prefix to library name
 2023-08-11 13:54:44 +04:00
Ilya Lavrenov
cc5ab26a95 Remove explicit CRT options from MLAS (#19115) 2023-08-11 13:03:12 +04:00
Maxim Vafin
cc08b0091e [PT FE] Remove torch strides compensation (#19129) 2023-08-11 10:46:04 +02:00
Mingyu Kim
c1c4c4cd51 [GPU] Onednn version update to latest 3.2 (#19135) 2023-08-11 17:41:41 +09:00
Anton Voronov
2a3132941c [FIX][CPU] Convert CF: added convert childs number check (#19022) 
* [FIX][CPU] Convert CF: added convert childs number check

* code style fix

* WIP: [CPU][TESTS] Convert CF: Added subgraph test with two outputs for Convert node

* MatMulDecompressConvertTest refactoring + instances fixes

* removed KeepConstAndDecompressionForMatMul pass and added cpu callback for KeepConstAndDecompression

* MatMulDecompressConvertTest2: added graphs and small problem description

* small review fix
 2023-08-11 12:10:00 +04:00
Yuan Hu
85609d4881 [Core] fix Memory Leak caused by create/inference request consequently in separate thread (#18868) 
* try to fix memory issue

Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>

* save code

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix life cycle issue

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* update comment and save stream of master thread in tbb ThreadLocal

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* update

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* not save the main stream in tbb

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* remote test code and update comment

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix mistaken modify

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix format issue

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* add test

Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>

* improve test

Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>

* fix the test

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* remote unused code

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* update the comment of the code

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix format issue

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* revert test case

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

---------

Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
 2023-08-11 11:53:07 +04:00
Ilya Lavrenov
0a32ec0e76 Fixed compilation with 32 bits (#19100) 2023-08-11 11:49:48 +04:00
Sun Xiaoxia
0ed1749ad9 [CPU] Removed socket id=-1 workaround on macOS (#18779) 2023-08-11 10:38:21 +04:00
Wanglei Shen
2ed5e50bd1 [CPU] Update stream info for mixing MAIN_CORE_PROC and HYPER_THREADING_PROC (#18863) 2023-08-11 10:31:31 +04:00
Wanglei Shen
c62ad1add8 Support Win7 in cpu information parser (#19109) 2023-08-11 09:54:13 +04:00
Anastasiia Pnevskaia
59872ee072 Removed InputCutInfo, disabled input cut in OVC. (#18927) 
* Fixed output_model logic.

* Removed InputCutInfo, disabled input cut in ovc.

* Disabled output cut, added tests for setting shapes or types for not all inputs.

* Returned support of numpy type.

* Separated MO and OVC python API tests.

* Small corrections.

* Added output dir test, exceptions test.

* Tests fixed.

* Corrected extension param description.

* Corrected input description, minor code corrections.
 2023-08-10 23:47:27 +04:00
Maxim Vafin
5f71679fb9 [PT FE] Use weight share switch in frontend (#18993) 
* [PT FE] Use weight share switch in frontend

* Return static for function

* Update src/bindings/python/src/openvino/frontend/pytorch/ts_decoder.py

* Fix issue with quantized constants

* Add tests for shared
 2023-08-10 19:28:38 +00:00
Anastasiia Pnevskaia
726abefbaa Update reminder message in MO and OVC. (#19132) 
* Updated reminder.

* Updated reminder.
 2023-08-10 19:14:13 +00:00
Shuangji Yang
8e103bcf39 fix bug on conversion of gather to sequeeze (#19012) 
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
 2023-08-10 22:25:41 +04:00