IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
11,816 Commits 38 Branches 54 Tags
458125e15859ac568a207c72d309f2cd0973fa29
Commit Graph
11816 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Maciej Smyk 458125e158 [DOCS] Link fix for Get Started for master (#18798) 
* Update get_started.md

* Update get_started.md
 2023-07-26 12:25:52 +02:00
Katarzyna Mitrus 7629d0b9cf [ShapeInference] Additional check for the shape of DetectionOutput input (#18675) 
* Additional check for DetectionOutput input shape

* Tests

* Update test description

* Update error message and check type

* Use OV_EXPECT_THROW
 2023-07-26 12:24:56 +02:00
Mikhail Ryzhov 962bfa6545 [GNA] Fixed Transpose replacement with Gather (#18624) 2023-07-26 11:46:00 +02:00
Sergey Shlyapnikov 7f917446c2 [GPU] Force ov::enable_profiling if OV_GPU_DumpProfilingData debug option is used (#18687) 2023-07-26 13:32:30 +04:00
Ilya Churaev 18505b99b7 Removed core member remapped devices and use proxy config instead (#18791) 2023-07-26 08:20:43 +00:00
Luwei Zhou 3228522b53 [CPU] Fix legacy zero point issue (#18399) 2023-07-26 11:56:35 +04:00
Jakub Nowicki 53efed1571 Gna plugin more meaningful memory dump (#18119) 
* added display of sum of memory usage per operation block and per memory type in GNA dump file

* fixed some clang format issues

* forgot to save file - missing clang fix

* changes according to review - added counting memory usage per layer and names changes

* clang changes

* changes according to review

* clang fixes
 2023-07-26 09:50:11 +02:00
Zhang Yi 1c0c929231 [CPU] MLAS backend integration (#17885) 
- currently enabled only for FP32 FullyConnected node on x86 CPUs
 2023-07-26 07:40:34 +00:00
Nadezhda Ageeva 97b4b13074 Adds ov::internal::exclusive_async_requests in ov::internal::supported_properties (#18746) 
* Adds ov::internal::exclusive_async_requests into ov::internal::supported_properties

* Update HETERO tests for ov::internal::exclusive_async_requests
 2023-07-26 09:43:21 +04:00
Evgeny Kotov 4d3601ac11 fix (#18762) 2023-07-26 08:36:30 +04:00
Ilya Churaev 7767af3529 Fixed proxy plugin initialization with internal names (#18783) 2023-07-25 22:14:42 +04:00
Pawel Raasz 5a4cf4c8b6 Review ReorgYolo class for shape inference aspects (#18633) 
* Add static shape adapter
- Adapters holds CPU dimension which can be reference to it or vector
- Add ov::optional for holding optional result from shape inference
- Add new `infer` function in `IStaticShapeInfer`

* Temporary support of StaticShape

* Minor corrections in ShapeInferenceTA

* Migrate shape_infer to new interface version

* Replace StaticShape by adapter implementation

* Replace IShapeInferCommon by IStaticShapeInfer

* Correct code formatting

* Fix build issues

* NodeValidationFailure::create for StaticShapeRef

* Review ReorgYolo op for shape inference
- Check partial shape and label propagation
- Check shape_infer implementation
- Update tests for static and dynamic shapes

* Change dim::is_valid to dim::is_empty
 2023-07-25 18:51:17 +02:00
Nadezhda Ageeva e2c3d0fe73 Disable hetero tests on linux_debian (#18781) 2023-07-25 17:14:26 +04:00
bstankix 3c1c3e6768 [DOCS] Update newsletter and carousel (#18776) 
* Add preloader to newsletter pup-up

* Add scroll nav to banner carousel
 2023-07-25 12:11:47 +00:00
Katarzyna Mitrus 26d53eb1da [GroupNormalization-12] Reference implementation update to minimize fp16 error (#18760) 
* Update mean calculation in group_normalization ref

* Update tests

* Update using namespaces
 2023-07-25 13:07:15 +02:00
Evgenya Stepyreva 6be083d37e SharedOpOptimization (#18622) 
* SharedOpOptimization

* PR Comments adressed

* Misprint

* Removed unnecessary mode_ref

* Fixed memcmp and modified tests accordingly

* Style

* Comment from Sergey resolved

* Optimize operations in groups

* Removed Transpose fusion per agreement with Dmitry

* Style

* Resolved unnecessary looping of the graph
 2023-07-25 15:00:44 +04:00
Ilya Churaev d3fdc761f6 Try to fix get_data() and lto (#18766) 
* Try to fix get_data() and lto

* Added test
 2023-07-25 14:09:21 +04:00
Anastasiia Pnevskaia 5aad9ee652 Used share_memory param in tf.Graph decoder. (#18747) 2023-07-25 11:16:17 +02:00
Nadezhda AgeevaandVitaliy Urusovskij be02d1a3c9 [HETERO] Implement get_runtime_model function (#18586) 
* [HETERO] Implement get_runtime_model function

* [HETERO] Adds unit tests

Update src/plugins/hetero/tests/unit/properties_tests.cpp

Co-authored-by: Vitaliy Urusovskij <vitaliy.urusovskij@intel.com>

* Temporarily disable GA

---------

Co-authored-by: Vitaliy Urusovskij <vitaliy.urusovskij@intel.com>
 2023-07-25 12:30:04 +04:00
Ilya Lavrenov 5792bba6d1 Disabled multi_isa in ARM CPU plugin (#18737) 2023-07-25 11:48:54 +04:00
yanlan song ff3399a87a enable auto handle GPU.invalid_index case (#18658) 
* let auto handle GPU.valid_index case

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

* resolve merge conflict

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

* add suppress macro

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

* revert changes

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

* update case

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

---------

Signed-off-by: fishbell <bell.song@intel.com>
 2023-07-25 15:31:53 +08:00
Andrei Gorbachev 02ebdcbb8f [Coverity] fix uninitialized scalar field (#18751) 
* fix Uninitialized scalar variable

* fix CVS-116194

* a few fix

* fix Uninitialized scalar variable

* fix CVS-116194

* a few fix

* rm dead code
 2023-07-25 10:57:28 +04:00
Maciej Smyk 393b3b1545 background fix for images (#18756) 2023-07-25 08:45:06 +02:00
cecilia peng 7fbd3a7ebf [CPU] Zero-copy optimizations for model outputs (#18476) 
- Implement zero-copy output between plugin graph and infer request, thus eliminate memory copy overhead and optimize performance
- Implement double buffer for InferRequest outputs
 2023-07-25 10:33:48 +04:00
Wang KaiandIlya Churaev fdfafbb7d2 removing redundant statement in ov::descriptor::Tensor::Tensor (#18098) 
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
 2023-07-25 07:55:42 +02:00
Ilya Churaev e7cd113a47 Add to_string() method to ov::element::Type (#18697) 
* Add to_string() method to ov::element::Type

* Fixed Python legacy API

* Fixed typo
 2023-07-25 09:22:16 +04:00
Ilya Churaev 29ca4b99c5 Add property to configure internal name under the proxy plugin (#18727) 2023-07-25 09:22:02 +04:00
Katarzyna Mitrus 99557e3356 Enable ScatterElementsUpdate test for reduction mean (#18682) 
* Enable scatter elements test for reduction mean

* Remove remaining comment
 2023-07-25 06:45:05 +02:00
Xuejun Zhai 5efdbf57ad [AUTO BATCH PLUGIN] fix review comments (#18660) 
* [AUTO BATCH PLUGIN] fix review comments

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

* [AUTO BATCH PLUGIN] fix review comments

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

* [AUTO BATCH PLUGIN] add get property ov::device::properties & ov::auto_batch_timeout

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

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-07-25 07:19:04 +04:00
Wang, YangandChen Peter 1be4b21905 [AUTO] Set property optimal_number_of_infer_requests to hw device with default value (#17848) 
* Query the property optimal_number_of_infer_requests from plugin first if plugin supported.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Query the property ov::optimal_number_of_infer_request of actual device first and use it as the result of AutoExecutableNetwork property.

* Updated.

* Updated.

* Update.

* Update.

---------

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
 2023-07-25 10:05:18 +08:00
Wang, YangandChen Peter 85f514788e [AUTO] Clean up the logic of AUTO device priorities (#18557) 
* Update selection logic for 3rd part devices within AUTO plugin.

* Remove MYRAID from AUTO test case.

* Update.

* Update.

* Update.

---------

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
 2023-07-25 10:03:14 +08:00
Andrew Kwangwoong Park dfb1493f2f [GPU] Update ReorgYolo to use nGraph shape inference (#18663) 
* Update ReorgYolo to use ngraph shape infer

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add dynamic TCs for ov_gpu_func_tests

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Add shape infer TCs for ov_gpu_unit_tests

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Apply comments

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Fix clang-format

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Fix conflict

Signed-off-by: Andrew Park <andrew.park@intel.com>

---------

Signed-off-by: Andrew Park <andrew.park@intel.com>
 2023-07-25 02:47:27 +02:00
Taylor Yeonbok Lee ce729761d6 Add new debug config "DisableRuntimeBufferFusing" (#18726) 2023-07-24 23:56:21 +02:00
Irina Efode f70ef8be5b [CONFORMANCE] Extend Graph Cache by repeats in models (#18602) 
* Add Repeat extractor

* fix build
 2023-07-24 23:24:15 +02:00
Oleg Pipikin bf4a2a462a Refactor common_test_utils (#18693) 
* Refactor common_test_utils

* Apply comments
 2023-07-24 21:23:42 +02:00
Sergey Shlyapnikov 42237bcbdb [GPU] Optimize update_shape synchronization for OOOQ and prohibit memory reuse for shape_of-subgraph nodes (#18742) 2023-07-24 11:34:19 -07:00
Paul Youngsoo Ahn 080ae32a8b [GPU] Fix cl kernel build error (#18513) 
* [GPU] Fix cl kernel build error(#18513)

* [GPU] Rollback cl kernel code change and add type converions to activatino function)

* [GPU] Use output data type instead of unit type in MakeActivationJitConstants

* [GPU] remove unused code and add comments
- add unit test
 2023-07-24 10:45:02 -07:00
Ekaterina Aidova 016eb43741 [PT FE]: fix issues with squeeze producing dynamic rank (#18748) 
* [PT FE]: fix issues with squeeze producing dynamic rank

* Update test_squeeze.py

* Update test_squeeze.py

* Update test_slice.py

* Apply suggestions from code review
 2023-07-24 20:10:20 +04:00
Ilya Lavrenov de2675c381 Added cpack calls in python tools (#18754) 2023-07-24 19:55:07 +04:00
Ilya Lavrenov afc563cfc6 Changed the component for conda-forge downloads stat (#18755) 2023-07-24 18:49:13 +04:00
Evgeny KotovandIvan Tikhonov 6ecbdaea08 fix TSGatherForward transformation (#18537) 
* add comment

* rewrite new_order generation code

* add unit tests

* code review fix

* fix windows build

* code review fixes

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
 2023-07-24 14:18:22 +00:00
Pawel Raasz 5eab1be682 Migrate shape infers to new IStaticShapeInfer API (#18579) 
* Add static shape adapter
- Adapters holds CPU dimension which can be reference to it or vector
- Add ov::optional for holding optional result from shape inference
- Add new `infer` function in `IStaticShapeInfer`

* Temporary support of StaticShape

* Minor corrections in ShapeInferenceTA

* Migrate shape_infer to new interface version

* Replace StaticShape by adapter implementation

* Replace IShapeInferCommon by IStaticShapeInfer

* Correct code formatting

* Fix build issues

* NodeValidationFailure::create for StaticShapeRef
 2023-07-24 15:59:18 +02:00
Mang Guo ec8fe6353a Allow weight sharing across NUMA nodes inside one socket (#17989) 
* Allow weight sharing across NUMA nodes inside one socket

* Fix comments

* Add WA for MacOS
 2023-07-24 20:49:46 +08:00
Ilya Lavrenov 86c68fffe4 Removed Intel Myriad headers from new API (#18736) 
* Removed Intel Myriad from new API

* Renamed GPU unit tests
 2023-07-24 16:20:08 +04:00
Irina Efode 1d3dec9e99 [CONFORMANCE] Extend Graph Cache by Fused names based extractor (#18601) 
* Add fused names based subgraph extractor

* fix test build
 2023-07-24 13:52:00 +02:00
Maxim Vafin bc734dfaaa [PT FE] Enable quantized conv and linear tests (#18723) 2023-07-24 13:33:11 +02:00
bstankix 7e1d8283f2 Update newsletter with filtered form fields (#18740) 2023-07-24 13:23:00 +02:00
Karol Blaszczak bfe3faca1e [DOCS] conformance update (#18732) 
conformance table
fix Add in ONNX layers
 2023-07-24 11:43:33 +02:00
Egor Duplenskii 5833f32c22 [CPU][ARM] Fix perf issues of oneDNN 3.2 migration (#18589) 2023-07-24 13:01:59 +04:00
Mateusz Bencer 24c428326a Align mmap offset with page size for Linux (#18678) 
* Align mmap offset with page size for Linux

* removed aligned_size

* reverted aligned_size + added proper unit test
 2023-07-24 12:53:33 +04:00