IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
13,616 Commits 38 Branches 54 Tags 1.1 GiB
e2e9d6056f
Commit Graph

13616 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Tomasz Jankowski
cf58a83094
[core] Migrate ScatterElementsUpdate operator to new API (#21212) 
* Remove redundant code

* Repalce HostTensor with ov::Tensor for v12

* Repalce HostTensor with ov::Tensor for v3

* Add Tensors count assertion

* Rename

* Revert axis normalization

* Don't duplicate the code
 2023-11-28 12:32:30 +04:00
Katarzyna Mitrus
37bac6ebcd
[Opset13][FP8][Spec] FakeConvert op specification (#21039) 
* FakeConvert spec init

* Add spec files to the opset docs

* Remove apply_scale attribute and update inputs description

* Experimental op notice

* Update short description

* Update detailed description.

* Add BF16 type to supported inputs

* Update  note about "Fake"

* Add more details

* Add formula of the operation
 2023-11-28 09:14:06 +01:00
Alexander Suslov
be5c755c32
migrate to new convert API (#21323) 2023-11-28 11:36:25 +04:00
Ilya Lavrenov
c241405c5e
Update docs (#21326) 2023-11-28 11:26:09 +04:00
Xuejun Zhai
441427abc8
[CPU Plugin][Func Test] Upgrade ConvWithZeroPointFuseSubgraphTest to API 2.0 (#21330) 
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-28 10:52:09 +04:00
Pawel Raasz
164d101295
[core]Refactor leftovers after migration to new API (#21304) 
* Refactor leftovers after migration to new API

* Restore output tensors count check
 2023-11-28 10:48:12 +04:00
Wanglei Shen
acecf31642
[CPU][ARM] Enable multi-stream execution (#21009) 2023-11-28 10:41:56 +04:00
Xuejun Zhai
9320fa7c86
[CPU Plugin][Func Test] Upgrade ConvConcatSubgraphTest to API 2.0 (#21301) 
* [CPU Plugin][Func Test] Upgrade ConvConcatSubgraphTest to API 2.0

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

* [CPU Plugin][Func Test] Upgrade ConvConcatSubgraphTest, remove ngraph namespace

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

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-28 10:39:29 +04:00
Pawel Raasz
53baeacc2e
[core]Remove deprecated function from Loop (#21299) 
* Migrate leftovers in Loop operator to new API
- use new version of `get_constant_from_source`
- migrate `is_rank_compatible_any_of` to dev API
- Improve rank compatibility checks

* Use new version of `is_rank_compatible_any_of`
instead deprecated to reduce bin-size

* Remove deprecated `is_rank_compatible_any_of`
 2023-11-28 10:37:15 +04:00
Roman Lyamin
01b4faf47f
[GPU] Enable CPU pinning for compilation tasks executor (#21261) 2023-11-28 09:40:00 +04:00
David Nam
f84d1c531a
[GPU] Fix constant dimension in case of node from if-op internal body (#21214) 
* [GPU] Fix constant dimension in case of node from if-op internal body

* Add a condition to restrict to case where allow_new_shape_infer is false

* Add a condition to restrict to case where allow_new_shape_infer is false

* Add functional test

* Add a condition to retrict to case where the program is inner program
 2023-11-27 15:11:07 -08:00
Artyom Anokhov
80feb465f6
[packaging] Fixed python component naming format for APT (#21321) 
* debian.cmake: Updated python naming format, added conflict versions for python-samples

* Updated naming format for RPM python comp as well
 2023-11-27 23:27:14 +04:00
Jan Iwaszkiewicz
bc78fd359e
[PyOV] Dynamic attributes for Python based operators (#21256) 2023-11-27 16:16:02 +01:00
Maciej Smyk
4804ff8b1e
[DOCS] Update of Sample Articles for master (#20957) 
* Sample Articles Update

* Update get_started_demos.md

* Update get_started_demos.md

* Update get_started_demos.md

* Update get_started_demos.md

* Update docs/articles_en/learn_openvino/openvino_samples/get_started_demos.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Update docs/articles_en/learn_openvino/openvino_samples/get_started_demos.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* Update docs/articles_en/learn_openvino/openvino_samples/get_started_demos.md

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* adding python code

* applying suggested changes

* Apply suggestions from code review

* Update docs/articles_en/learn_openvino/openvino_samples/get_started_demos.md

* Update docs/articles_en/learn_openvino/openvino_samples/get_started_demos.md

* Update docs/articles_en/learn_openvino/openvino_samples/get_started_demos.md

* Update docs/articles_en/learn_openvino/openvino_samples/get_started_demos.md

* Update get_started_demos.md

* fix notes

* fix synching of tabs

---------

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
Co-authored-by: sgolebiewski-intel <sebastianx.golebiewski@intel.com>
 2023-11-27 16:15:31 +01:00
Sun Xiaoxia
0bdd658317
Remove legacy threading code (#21279) 
* remove legacy threading code

* fix code style
 2023-11-27 18:45:34 +04:00
Alina Kladieva
d722e42052
[GHA] Smart CI for more pipelines (#21307) 
* Add Smart CI for more pipelines. Refactor logic for workflow skip

Since different workflows may have different requirements for skipping them, I suggest to move these requirements to parameters instead of hardcoding them

* Use patterns for skipping pipeline for conformance-only

* Remove path filters for Android

* Return mistakenly deleted param

* Propagate params to Python script

* Add missing outputs mapping

* Return push trigger

* Skip CC CPU func when CPU is not affected

* Fix variable name
 2023-11-27 18:43:54 +04:00
Andrey Kashchikhin
ca4c276072
[CI] [GHA] Increase precommit timeouts for TF Hub jobs (#21308) 
* increase timeouts

* add more
 2023-11-27 18:41:11 +04:00
Ivan Tikhonov
57d794c810
ConvertPrecision transformation: handle Assign, ReadValue and Variable (#21266) 
* ConvertPresicion transformation: handle Assign, ReadValue and Variable

* revert debug code

* use correct commit for onednn_gpu

* codestyle
 2023-11-27 18:34:31 +04:00
Oleg Pipikin
eaa3098920
Refactor ConvReshapeAct (#21219) 2023-11-27 14:33:03 +00:00
Karol Blaszczak
558e713043
[DOCS] fixes lts disclaimer master 2023-11-27 14:58:10 +01:00
Vitaliy Urusovskij
6dd448d9cc
Fix COPY_INSTEAD_OF_MOVE and AUTO_CAUSES_COPY (#21267) 
* Fix `AUTO_CAUSES_COPY` for hetero compiled_model

* Fix `COPY_INSTEAD_OF_MOVE`

* Fix `AUTO_CAUSES_COPY` in template comp_model
 2023-11-27 16:31:32 +04:00
Mateusz Tabaka
b027766b0a
Stop constantfold_subgraph on nonconstfoldable ShapeOf (#21171) 
* Stop constantfold_subgraph on nonconstfoldable ShapeOf

Ticket: CVS-124628

* pass tensor to Constant constructor

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
 2023-11-27 12:30:54 +01:00
River Li
b02ddc5831
[CPU] API 2.0 migration for cpu plugin properties (#20022) 2023-11-27 15:02:41 +04:00
River Li
45d6aa2171
[CPU Tests] migrate FuseTransposeAndReorderTest to API 2.0 (#21297) 2023-11-27 10:18:23 +00:00
Vladislav Golubev
598da6e5c0
[Transformations] Leftovers: FuseU4WeightsAndZeroPoint transformation (#20709) 
* util::visit_constant_path

* ConvertU4WeightsZeroPointToScalar: avoid unnecessary insert

* Review comments applied

* codestyle fix
 2023-11-27 10:38:05 +01:00
Vladislav Golubev
c50bd2b55f
[Snippets] MHA tests: bf16 inputs generation restored (#21250) 2023-11-27 13:20:05 +04:00
Sungeun Kim
1a235ffe79
get layout from get_output_layout in primitive_inst (#21294) 2023-11-27 13:02:02 +04:00
Maxim Vafin
e52f922d35
[PT FE] Unify hub tests, add marks for timm models (#21283) 
* Unify hub tests, add marks for timm models

* Fix hf tests
 2023-11-27 12:22:13 +04:00
Xuejun Zhai
4fdbb2d4e8
Xuejun/snippet remove inference engine (#21293) 
* [CPU Plugin][Snippet] remove InferenceEngine, replace with ov

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

* [CPU Plugin][Snippet] remove ngraph namespace

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

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-27 12:00:58 +04:00
Anastasia Kuporosova
815980f290
[PyOV] Replace legacy assert (#21268) 
* [PyOV] Replace legacy assert

* codestyle

* apply comments

* Update src/bindings/python/src/pyopenvino/graph/dict_attribute_visitor.cpp
 2023-11-27 11:51:01 +04:00
Mateusz Mikolajczyk
ed061d5179
[Opset13][FP8] FakeConvert-13 input validation improvements (#21226) 
* Improve shape type infer for FakeConvert-13

* Fix formatting

* Formatting + missing test

* Implement requested changes

* Improve type merge

* Fix formatting

* Add requested type_prop tests

* Implement requested changes

* Fix formatting

* Implement requested changes

* Use template type
 2023-11-27 07:38:08 +00:00
Chenhu Wang
6b898fc8d9
[CPU] Interpolate extend to rank 3 input support (#21003) 2023-11-27 07:32:18 +00:00
Ekaterina Aidova
eaae00c2ca
[PT FE]: support aten::empty_like (#21258) 
* [PT FE]: support aten::empty_like

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

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

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
 2023-11-27 07:15:19 +00:00
Ekaterina Aidova
a5d53aeaef
[PT FE]: fix for aten::index_put_ if values.r > indices.r (#21255) 
* [PT FE]: fix for aten::index_put_ if values.r > indicies.r

* add more complex test case
 2023-11-27 07:01:16 +00:00
Roman Kazantsev
9421f4cf2d
[TF FE] Speed up compilation - part 5 (#21288) 
* [TF FE] Speed up compilation - part 5

Avoid usage of heavy opsetX header

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

* Complete constant.hpp template methods for string Tensor

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

* Revert "Complete constant.hpp template methods for string Tensor"

This reverts commit 8f86ab2e7b.

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-11-27 10:51:18 +04:00
River Li
a6463c1ac6
[Core]lstm test api20 (#21031) 
* [Core] lstm api fix

* Fix LSTMCell failure issues

* Solve GNA failures

* Update for comments

* Minor update

* Use new ov::test::utils::makeEltwise

---------

Co-authored-by: Durandin, Pavel <pavel.durandin@intel.com>
 2023-11-27 10:25:58 +04:00
Xuejun Zhai
058001eb84
[Coverity Scan Issue] fix cs issues in scaled_attn.cpp (#21270) 
* [Coverity Scan Issue] fix cs issues in scaled_attn.cpp

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

* Fix review comments

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

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-27 10:25:02 +04:00
Wanglei Shen
72cb4e4820
add additional checks for bad cache information in VM (#21059) 
* add additional checks for bad cache information in VM

* update implementation
 2023-11-27 07:51:44 +08:00
Luo Cheng
91660b1c05
[CPU] Fix ScaledDotProductAttension accuracy problem (#21217) 2023-11-26 14:47:04 +04:00
Pavel Esir
493a338ad2
resolve TODO in efficient compression: return hashing compression back (#21141) 
* turn on compression by searching duplicate blobs (by hash) for fp16

* style-fix

* apply comments

* added multimap

* style fix
 2023-11-25 08:35:35 +00:00
Tomasz Jankowski
8231d57c38
[core] Migrate ScatterNDUpdate operator to new API (#21231) 
* Drop legacy stuff

* Repalce HostTensor with ov::Tensor
 2023-11-25 11:33:28 +04:00
Roman Kazantsev
9f87f72ca6
[TF FE] Speed up compilation - part 4 (#21269) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-11-25 01:06:20 +04:00
Evgeny Kotov
965313ba0b
[TF Hub][Perf Tests]Implement performance tests in precommit to compare read_model and convert_model paths (#21023) 
* begin

* fixes

* measure time and compare

* fix bug + update precommint models

* cleanup

* add wget to install requirements; add to linux.yml

* fixes + improvements

* output results to html

* remove unneeded code

* fix

* code review fixes

* store downloaded models in cache

* use 1000 runs

* use model paths from tf-hub tests

* use tf hub api to download instead of wget; measure some time stats

* small fixes

* remove unneeded files

* use own list of models

* remove uneeded if

* remove unstable models

* remove unstable models

* fix requirements

* code review fixes

* Update .github/workflows/linux.yml

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

* fix round_num function

* remove unstable network

* Update tests/model_hub_tests/models_hub_common/test_performance_model.py

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

* code review fixes

* build fix

* code review fixes

* code review fixes

* code review fixes

* Update tests/model_hub_tests/models_hub_common/test_performance_model.py

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

* Update tests/model_hub_tests/performance_tests/test_tf_hub_perfomance_model.py

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

* Update tests/model_hub_tests/performance_tests/test_tf_hub_perfomance_model.py

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

* Update tests/model_hub_tests/models_hub_common/test_performance_model.py

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

* code review fixes: use autoflake

* remove unneeded tensorflow_text

* Update .github/workflows/linux.yml

* Update linux.yml

Added TensorFlow_Hub_Performance_Models_Tests to final status check

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
 2023-11-24 18:13:44 +04:00
Ilya Lavrenov
e087ed083c
Revert "the proxy device with id should be also a proxy device. (#21248)" (#21271) 
This reverts commit c491381a0d.
 2023-11-24 17:49:37 +04:00
Andrzej Kopytko
758524978b
[DOCS] tabs styling (#21272) 2023-11-24 13:11:50 +01:00
Maxim Vafin
fe6ae4fbdd
[PT FE] Get input dtype for aten::sum from graph (#21262) 2023-11-24 15:45:42 +04:00
Georgy Krivoruchko
71836a959d
[TFLite] Moved tests to a separate file 2023-11-24 13:20:10 +04:00
Georgy Krivoruchko
a8e9989383
[CMAKE] Keep frontend's folder structure for Visual Studio (#21222) 2023-11-24 13:16:10 +04:00
Xuejun Zhai
807b77c38e
[Func Test] Upgrade func test of QuantizedConvolutionBatchNorm related to 2.0 (#21053) 
* [Func Test] Upgrade func test of QuantizedConvolutionBatchNorm related to 2.0

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

* [Func Test] fix QuantizedConvolutionBatchNorm test error, caused by error input

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

* [Func Test] fix format issue

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

* [Func Test] Fix errors

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

* [Func Test] Fix format issue

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

* [Func Test] Fix TransformationTestsF test error

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

* [Func Test] Fix test error

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

* [Func Test] Fix review comments

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

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-24 13:07:15 +04:00
Katarzyna Mitrus
63e7e2dd3e
[Opset13][FP8] FakeConvert evaluate and reference impl (#21034) 
* FakeConvert op init

* Update dest types names

* Update op hpp

* Update opset ops number

* Init type_prop tests

* Add attributes tests

* Add op check test

* Update namespace in fc cpp

* Update getters

* Refactor static member

* Make destination_type lower case

* Update type in test

* Move get_valid_types out of class

* Update ops number in opset

* Evaluate init

* Init poc evaluate

* Update types name

* Style update

* FakeConvert eval tests

* Add support for FP16 input

* Remove unused functions

* Use const auto and constexpr

* Create fake_convert reference file and move ref functions

* FakeConvert eval and reference update

* Remove unused is_normal variable

* Add bf16 tests

* Update construtor in tests

* adjust convert helper name

* Update comments

* Make func params as constexpr

* Update types

* Non scalar scale shape tests

* Use autobrodacast_select

* Use single autobroadcast_select

* Check scale_shape size

* Add var to keep scale_shift lambda

* Use lamda only for autobroadcast

* More checks for per channel scale

* Remove union half_t

* Change template to fp16 type for emulate

* Use f8e4m3_min_val as constexpr

* Update unsigned short to uint16_t

* Minor style refactor

* Minor comments update

* Update fake_convert_details namespace to func

* Update apply_conversion return type

* Add doxygen text

* Update supported type assert

* Remove duplicated tests

* Update namespace move to cpp

* Fill init with zeroes instead of reserve

* Use add div mul sub reference for applying scale

* Use autobroadcast_select for applying scale

* Bring back opt broacast cases

* Reuse scale_shift as func

* Adjust s and o var names

* Update multiplication in loop tu accumulate
 2023-11-24 09:54:19 +01:00