IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
12,768 Commits 38 Branches 54 Tags 1.1 GiB
9ecbcf1135
Commit Graph

12768 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Oleksii Khovan
9ecbcf1135 [GPU] ScatterElementsUpdate-12 (#19254) 
* GPU primitive and kernel changes to support ScatterElementsUpdate-12

* Add single-layer test for ScatterElementsUpdate-12

* Unit tests:
  - fix formats test - add separate data type for indices;
  - add tests for Reduction.
 2023-11-23 14:41:10 +01:00
Tomasz Jankowski
96aafcb661 [Ref] Drop legacy API (#20006) 
* Drop legacy API - CoordinateTransform

* Refactor AvgPool ref

* Fix zero padding indices ceil rounding

* Transpose 3D reshaped kernels

* Reuse max_pool v8 ref in v1

* Change ref::slice params validation

* Fix wrong alloc in max_pool ref

* Drop legacy from TopK

* Fix mvn ref

* Deprecate unused

* Drop ngraph from TopK op

* Remove deprecated

* Use OPENVINO_ASSERT

* Replace headers paths

* Replace headers paths

* Add missing include

* Address review comments

* Clean up

* Remove unused and duplicated code
 2023-11-23 14:41:10 +01:00
Ilya Lavrenov
7493342d28 Removed Azure pipelines migrated to GHA (#20245) 2023-11-23 14:41:10 +01:00
Irina Efode
e3846fedee [CONFORMANCE][SUBGRAPHS DUMPER] Rework subgraphs_dumper graphs extraction algo feedback by plugins (#19669) 
* [CONFORMANCE][SUBGRAPHS DUMPER] Change repeat pattern extractor to avoid duplications and reduce graphs size

* Small change

* temporary

* merge

* try to handle large models

* Fixes + tests

* Remove extra

* Exclude models after const folding in case dynamic modesl

* shapes to meta

* Fix tests

* Fix test + is_subgraph

* Fix issue with default output

* change hashing

* Check memory

* Hash algo

* correct modelsize check

* Log large models

* tmp disable fused_names extractor

* add device for fused_names

* remove extra

* fix vuild

* Disable fused_names extractor
 2023-11-23 14:41:10 +01:00
Irina Efode
e10febe0fb [CONFORMANCE][CMAKE] Add SubgraphsDumper lib (#20053) 2023-11-23 14:41:09 +01:00
Ivan Tikhonov
e0fc364538 Model builders refactoring: rename dirs, targets, file names (#19885) 
* Model builders refactoring

* Apply review comments

* resolve review commets: update cmake target names

* fix build: use correct headers

* fix headers

* fix build

* fix docs
 2023-11-23 14:41:03 +01:00
Piotr Krzemiński
bddd25a5a7 [Ref][Core][Opset13] Add Multinomial Operation (#19655) 
* [Ref] Multinomial base file

* [Ref] Add core & reference implementation reusing other ops

* [Ref] Fix reference implementation, add missing parameters, add tests

* [Core] Add opset13, register multinomial, add shape inference

* [Ref][Core] Fix compile errors

* [Ref][Core] Clang fix

* [TEMPLATE] Remove bf16, f16, f64 types

* [TEMPLATE] Remove incorrect input types for 'input' parameter

* [Ref][Tests] Remove deleted test types

* [Ref] Fix & optimize  shape inference

* [PT FE] Apply suggestions from review

* [Template] Migrate to new API

* [Core] Add a clause for dynamic input in shape inference

* [Tests] Add missing type_prop test (?)

* Update multinomial_shape_inference.hpp

* Update multinomial.hpp

* [Ref] Fix build issues

* [Ref] Fix clang and style

* [Ref] Fix tests without replacement

* [Ref] Fix with_replacement sampling error

* [Ref] Remove debugging artifacts

* [Ref] Cast to 64-bit size for 32-bit systems

* Update multinomial.hpp

* [Ref] Add missing type_prop tests, add shape inference tests

* Update multinomial.cpp

* Update multinomial_shape_inference_test.cpp

* Update multinomial.cpp

* Update multinomial.hpp

* [Ref] Fix compilation errors from shape inference test

* [Ref] Fix compilation error of type_prop, apply recommendations from review

* [Ref] Add multiple shape inference tests

* [Ref] Change TEST to TEST_F, add more type_prop tests

* [Ref] Clang fixes

* [Ref] Fix shape inference tests with mismatching args

* [Ref] Fix remaining type_prop errors

* [Ref] Replace HostTensor with normal Tensor in shape inference tests

* Update opset.cpp

* [Ref] Possible fix for 'function empty' error

* [Ref] Add a cast to remove conversion warning

* [Ref] Add conformance test of Multinomial

* [Ref] Match style of conf test to the remaining tests

* Update single_op_graph.cpp
 2023-11-23 14:40:31 +01:00
Katarzyna Mitrus
05e75c3edd [Opset13][pyAPI] Python API opset13 init and NMSRotated-13 (#20204) 
* Opset13 init

* Update py API to use Opset13

* Add nms_rotated op to py API

* Add tests

* Add trailng comma

* Adjust blank spaces

* Add nms_rotated to init file

* Update tests

* Update style

* Adjust Optional keyword

* Update op docs with shapes

* Add Tensor rypes hints

* Update tests to import opset13
 2023-11-23 14:40:31 +01:00
Karol Blaszczak
40c9bca845 [DOCS] conan fix (#20216) 2023-11-23 14:40:31 +01:00
jmacekx
b461cbe581 [DOCS] add pyyaml to docs requirements (#20236) 2023-11-23 14:40:31 +01:00
Irina Efode
cb16e43831 [GHA][CONFORMANCE] Init gtest filter for parallel runner in case not used arg (#20234) 2023-11-23 14:40:31 +01:00
Nadezhda Ageeva
d0b8ce16ad Keep precision of inputs/outputs in SubgraphBaseTest::calculate_refs (#20227) 2023-11-23 14:40:30 +01:00
Ilya Churaev
6c5cde9b64 Moved ConstantResultTest to new API (#20224) 2023-11-23 14:40:30 +01:00
Alexandra Sidorova
edf84b5512 [CPU][Snippets] Fixed EnforcePrecision pass registration (#20051) 2023-11-23 14:40:30 +01:00
Tatiana Savina
5e1a140d71 [DOCS] Port doc conversion change (#20232) 
* [DOCS]  Fix conversion docs comments (#20144)

* fix comments

* more fixes

* fix missing part

* add ovc to img (#20192)
 2023-11-23 14:40:30 +01:00
Sebastian Golebiewski
c52ec6d0e3 Changing file structure of Operation Sets (#20225) 2023-11-23 14:40:30 +01:00
Sergey Shlyapnikov
19326fe52f [GPU] Fix runtime reorders optimization and add runtime memory dependencies (#20202) 2023-11-23 14:40:29 +01:00
Andrey Kashchikhin
38a6e5a2a2 [CI] [GHA] Introduce GHA Linux CUDA Pipeline (#19884) 
* add pipeline

* rm triggers

* address comments

* use uninteractive as env

* rm triggers

* rm unused testdata

* use better concurrency group

Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>

* use aks runner

* correct path

* provide path

* add missing cmake options; rm unnecessary dir creation

* use image from private docker

* split OV and plugin cmake & build; do not fail on warning for plugin build

* use different build_dir for nvidia plugin

* add missing options

* rm unnecessary options; add target for build

* Apply suggestions from code review

try fix for NVIDIA plugin

* Apply suggestions from code review

revert to default contrib repo, used ccache for CUDA files

---------

Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
 2023-11-23 14:40:29 +01:00
Mateusz Mikolajczyk
633019eae4 [Ref][Core][Opset13] BitwiseAnd, BitwiseOr and BitwiseXor core shell and reference (#20058) 
* Add Bitwise binary core and refs

* Add draft for tests

* Formatting, build issues and tests

* Fix tests

* Add reference tests

* Apply requested changes

* Add requested changes

* Rename

* uncomment test

* Update src/tests/functional/plugin/conformance/test_runner/op_conformance_runner/src/op_impl_check/single_op_graph.cpp

Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>

* change reference

---------

Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
 2023-11-23 14:40:29 +01:00
Vladimir Paramuzov
7e17e57db4 [GPU] Fix custom layer (#20220) 2023-11-23 14:40:29 +01:00
Ilya Lavrenov
92f949b92c Added python search path for Conda (#19929) 2023-11-23 14:40:29 +01:00
Sofya Balandina
b527170dd7 [apiConformance] Remove 1.0 api tests (#20185) 2023-11-23 14:40:28 +01:00
Ilya Lavrenov
f0b94e1c19 Explicitly set Python3_FIND_STRATEGY (#20215) 2023-11-23 14:40:28 +01:00
Edward Shogulin
93b0e867a8 [LPT] [NPU] Multiply support (#19859) 
* [LPT] [NPU] Multiply support

* [LPT] [NPU] Multiply support documentation

* 1) FakeQuantize support 2) refactoring

* [LPT] DisableCleanup attribute + cleanup transformations extension

* [LPT] DisableCleanup usage

* [LPT] Tests infrastructure support

* [LPT] infrastructure quick fix

* [LPT] Recurrent Cell Transformation fix

* refactoring & comment fixes
 2023-11-23 14:40:28 +01:00
Maciej Smyk
63e143d8dd [DOCS] Adding Conan distribution article to docs for master (#20205) 2023-11-23 14:40:28 +01:00
Sebastian Golebiewski
d84928034a Changing file structure of Operation Sets section (#20214) 2023-11-23 14:40:28 +01:00
Maciej Smyk
4d2a6b9fce Device Plugins Restructure (#20219) 2023-11-23 14:40:27 +01:00
Vladimir Paramuzov
a7026a2fcc [GPU] Use ov element type and float16 inside plugin (#20110) 2023-11-23 14:40:27 +01:00
Sebastian Golebiewski
c3c661f081 Changing file structure of POT Tool Examples section (#20213) 2023-11-23 14:40:27 +01:00
Sebastian Golebiewski
ad107866cf Changing file structure of POT tool section (#20208) 2023-11-23 14:40:27 +01:00
Oleg Pipikin
96c129e29a Refactor FakeQuantizeLayerTest, ExtractImagePatchesTest, GatherNDLayerTest, GatherTreeLayerTest (#20016) 
* Refactor FakeQuantizeLayerTest

* Refactor ExtractImagePatchesTest

* Refactor GatherNDLayerTest

* Refactor GatherTreeLayerTest

* Apply comments

* Apply comments

---------

Co-authored-by: Pavel Durandin <pavel.durandin@intel.com>
 2023-11-23 14:40:27 +01:00
Maxim Vafin
7a6c5d0d41 [PT FE] Add support for aten::numpy_T and aten::feature_dropout (#20136) 
* Add support for aten::numpy_t and aten::feature_dropout

* Update tests/layer_tests/pytorch_tests/test_transpose.py

Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>

---------

Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
 2023-11-23 14:40:26 +01:00
Sebastian Golebiewski
08bc3b2d7c Changing file structure of Post-Training Optimization Tool section (#20207) 2023-11-23 14:40:26 +01:00
Pawel Raasz
75a939c9ba [core]Api 2.0/migrate Subtract op to new API (#20108) 
* Migrate Subtract to new API

* Sync has_evaluate precision with evaluate
 2023-11-23 14:40:26 +01:00
Maciej Smyk
bf8ba706f0 Deployment guide restructure (#20201) 2023-11-23 14:40:26 +01:00
Maciej Smyk
5a0f3b5373 model-preparation-restructured (#20186) 2023-11-23 14:40:26 +01:00
Maciej Smyk
4992f780da Model Optimization Guide Restructure (#20188) 2023-11-23 14:40:25 +01:00
Maciej Smyk
63cd040b90 Running Inference Restructure (#20195) 2023-11-23 14:40:25 +01:00
Sebastian Golebiewski
1813e3a9a2 [DOCS] Changing file structure of Apache MXNet Caffe and Kaldi section (#20200) 
* Changing file structure of Apache MXNet Caffe and Kaldi section

* Update
 2023-11-23 14:40:25 +01:00
Sebastian Golebiewski
27528f4b5e Changing file structure of OpenVINO API 2.0 transition section (#20199) 2023-11-23 14:40:25 +01:00
Sebastian Golebiewski
b53efd3fdc Changing file structure of Legacy Model Optimizer Extensibility section (#20198) 2023-11-23 14:40:25 +01:00
Ilya Lavrenov
c06e359536 Disable pkg-config search on Android via CMAKE_DISABLE_FIND_PACKAGE_PkgConfig (#20179) 2023-11-23 14:40:24 +01:00
Ilya Churaev
159518f325 Remove HostTensor from ov namespace (#20168) 
* Remove HostTensor from ov namespace

* Fixed build
 2023-11-23 14:40:24 +01:00
Anastasia Kuporosova
df9fa10312 [PyOV][Docs] Update docs with new way of using properties (#20116) 2023-11-23 14:40:24 +01:00
Przemyslaw Wysocki
64b6de4c43 Add field for JIRA ticket in Good First Issue template (#20187) 
* Add gfi

* Minor change

* Fix linter

* fix typo

* Fix typo'

* Add new field

* Minor change
 2023-11-23 14:40:24 +01:00
Andrey Kashchikhin
07a27b5bc6 [CI] [GHA] Transfer Linux ONNX Runtime to AKS runners (#20157) 
* transition to aks runners

* correct name

* incorporate onnxruntime into linux pipeline

* add missing python installation

* install build dependencies

* add path

* rm unused

* mv stage

* correct dir

* use 16-core for onnxruntime job

* rm obsolete

* rm logs

* rm unnecessary step

* rm unnecessary dir creation
 2023-11-23 14:40:24 +01:00
Alina Kladieva
7a48410e78 [build_samples_msvc] Exit properly on error (#20191) 2023-11-23 14:40:23 +01:00
Taylor Yeonbok Lee
0f06dc760f [GPU] Fix gpu memory handling (#19930) 
* [GPU] Added more debug print for prepare input/output
Skip enqueuemempcy for zero count tensor

* Fix mem alloc limitation

* Simplify memory check condition

* Fix not to wait for null event

* Additional fixes
- apply review comments (disable 0 size memcpy for other mem types) && return user event instead of nullptr
- fixd get_max_memory to return cpu memory instead of global memorysize (Because in windows, max_global_memory returns shared gpu memory instead of physical memory size)

* Fixed functest failure
 2023-11-23 14:40:23 +01:00
Sebastian Golebiewski
e64af9ee72 Changing file structure of Model Conversion Tutorials in Documenation section (#20193) 2023-11-23 14:40:23 +01:00
Sebastian Golebiewski
0424c36737 Changing file structure of Supported Model Formats section (#20189) 2023-11-23 14:40:23 +01:00