IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
7,331 Commits 38 Branches 54 Tags 1.1 GiB
4da0941cd2
Commit Graph

7331 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Alexander Kozlov
4b4bd7399c
Fixed conflicts (#11332) 2022-03-30 16:10:03 +03:00
Anastasia Kuporosova
9fa5150d71
[Python API][Docs] Fix references for several classes (#11251) 2022-03-30 13:29:30 +03:00
Ilya Lavrenov
932f8bf767
Install 97-myriad-usbboot.rules to install_dependencies (#11301) 2022-03-30 13:03:42 +03:00
Ilya Churaev
17f8f7ec25
Fixed typo in exception message (#11322) 2022-03-30 12:45:09 +03:00
Vladimir Paramuzov
fccd5d4445
[GPU] ShapeOf op (#10983) 2022-03-30 12:27:04 +03:00
Ivan Novoselov
1beb7158d5
[Snippets] Develop Snippets test infrastructure (#10605) 2022-03-30 12:21:19 +03:00
Sergey Shlyapnikov
cd703580b6
[GPU] Host time optimizations for in order queue (#11255) 
* [GPU] Host time optimizations

* Fix failed fusings_gpu/permute_eltwise_loop.basic/* tests
 2022-03-30 10:53:53 +03:00
Ivan Tikhonov
f13b6252e9
Fix insertion of tensor names after UnrollTensorIterator transformation (#11276) 
* revert previous version of convert_seq_to_ti transformation

* try to check that outputs of TI are connected to Result nodes

* add unit tests

* fix codestyle

* fix Memory tests

* revert local change

* revert local change

* replace duplicated code with lambda
 2022-03-30 10:26:04 +03:00
Maxim Andronov
72f802f282
[CPU] Fix Parameter -> Result model for dynamic case (#10764) 2022-03-30 10:20:52 +03:00
Anton Pankratov
614a6a3457
[CPU] Graphs are created in compiled_model constructor (#10872) 2022-03-30 10:02:12 +03:00
Vladimir Gavrilov
e7b35c3b00
nGraph reference for the operation RDFT. (#11175) 
* Written nGraph reference for the operation RDFT.

* Used std::reverse() algorithm to simplify the function reverse_shape() from fft_common.cpp.

* Added assert into the function offset_from_coords_and_strides().

* Deleted redundant variable.

* Deleted redundant functions from the reference implementation of (I)DFT.

* Renamed the method reverse_shape() in fft_common.hpp.

* Code style fix.
 2022-03-30 09:38:05 +03:00
Alexander Zhogov
1386f52dd6
Azure CI: Disable Model Optimizer UT 2022-03-30 09:01:05 +03:00
Ilya Lavrenov
9f923ba39f
Install only proper GNA library files (#11243) 2022-03-30 08:58:31 +03:00
yanlan song
f6e5ec9684
return device infer request in passthrough mode (#11253) 
Signed-off-by: fishbell <bell.song@intel.com>
 2022-03-30 09:21:13 +08:00
Ilya Lavrenov
4145291e84
Added f16 tests for tensor (#11273) 2022-03-30 01:11:07 +03:00
Anton Chetverikov
5d719cbc7b
[MO] Remove _output_shape nodes attribute while loading TF meta graph (#11078) 
* Remove _output_shape attribute while loading meta_graph

* Update tools/mo/openvino/tools/mo/front/tf/loader.py

Simplify code

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>

* Add comment about the problem

Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
 2022-03-29 21:27:00 +03:00
Gleb Kazantaev
01b701349d
Move tensor utils to common utils (#11306) 2022-03-29 21:08:55 +03:00
Alina Kladieva
458378e9e7
Skip sporadic GPU canInferOnUserQueue test case (#11310) 2022-03-29 19:48:37 +03:00
Ilya Lavrenov
fb99fd1d2f
Try to remove MO install rules (#11208) 
Co-authored-by: Alexander Zhogov <alexander.zhogov@intel.com>
 2022-03-29 19:24:30 +03:00
Dmitrii Khurtin
4b0417018a
[GNA] Fixed clang 13 build issue (#11238) 2022-03-29 19:06:50 +03:00
Vitaliy Urusovskij
d261da4820
Replace get_os_name() with get_os_type() in get_lib_path() (#11300) 
In case of ubuntu system `get_os_name()` returns "ubuntu",
but `get_os_type()` returns "Linux" which is expected by tests
 2022-03-29 18:17:38 +03:00
Evgenya Stepyreva
ed030e113e
StridedSlice default shape inference (#11292) 2022-03-29 16:42:52 +03:00
Gleb Kazantaev
5b0a1fe7bb
Move FunctionsComparator to common utils (#11277) 
* Move FunctionsComparator to common utils

* Fix includes
 2022-03-29 14:51:17 +03:00
Jade Cho
070c47ec09
[GPU] fix a bug of onednn sum post-op (#11254) 
+ Add a unit test for this.
 2022-03-29 20:35:09 +09:00
Mikhail Letavin
23732417c5
[GPU] Propagate output flag to mutable_data deps to ensure correct event creation (#11021) (#11021) 2022-03-29 13:08:58 +03:00
Maxim Andronov
d764fe7d27
[CPU] Prohibit int8 desc convolution creation in case s8 precision on data input (#10730) 2022-03-29 09:44:06 +00:00
Gleb Kazantaev
866f006a83
Transformations Python API (#10971) 
* Keep changes

* Update tests

* Keep changes

* Cleanup

* Add predicates support; new pattern ops; new tests

* support for public passes; added tests

* Fix compilation warning

* Fix code style

* Added docstrings; code cleanup

* Update python API tests

* Fix build on Windows

* Revert back pass registration logic

* Fix flake8 errors

* Update docstrings; fix utils.hpp

* Cleanup

* Cleanup

* Fix flake errors

* Fix mypy

* Skip mypy for passes
 2022-03-29 11:41:23 +03:00
Bo Liu
02c60c76ab
Paddle FasterRCNN Ops Conversion: greater_than, less_than, gather, floor (#9657) 
* Paddle FasterRCNN Ops Conversion: greater_than, less_than, gather, floor

* Apply suggestions from code review

* fix 'gather' testcase failure issue on CI

* implement 'axis' input for 'Gather' Op conversion with testcase comment;use common function for all elementwise Ops
 2022-03-29 16:20:37 +08:00
Alexey Lebedev
8f88889876
[docs] python snippets for devices master (#11176) 
* Update CPU docs

* update GPU docs

* update with sphinxtab

* Fix docs

* Add preprocessig snippet

* Fix path

Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
 2022-03-29 11:01:53 +03:00
Anton Pankratov
bc9f140bb4
Fixed element type destruction in global scope (#11211) 
* Fixed element type destruction in global scope

* Fixed mispirint
 2022-03-29 10:21:41 +03:00
Nikolay Tyukaev
8aa98ce0d5
fix wildcard sphinxdirective (#11264) 2022-03-28 20:56:56 +03:00
Nikolay Tyukaev
da9596bade
cvs-80083 (#11281) 2022-03-28 20:53:21 +03:00
Dmitry Belyakin
30ec7366bb
[OMZ]: update submodule (#11279) 2022-03-28 19:48:53 +03:00
Dmitrii Khurtin
a925ec6a29
changed symlink order of libgna (#11267) 2022-03-28 19:48:08 +03:00
Ilya Lavrenov
19d0e5ba52
CMAKE: IE_VERSION => OpenVINO_VERSION (#11242) 
* IE_VERSION => OpenVINO_VERSION

* Reverted installation of python unconditionally
 2022-03-28 19:32:21 +03:00
Karol Blaszczak
8b591c141e
Update installing-openvino-overview.md (#11271) 2022-03-28 15:15:32 +00:00
Dmitry Belyakin
27741d316e
[OMZ]: update submodule (#11239) 
* [OMZ]: update submodule

* bump omz ver
 2022-03-28 15:45:35 +03:00
Valentin Dymchishin
52937967bb
Add dynamism in memory tests (API 2) (#10589) 2022-03-28 12:51:53 +03:00
Irina Efode
76e2f2697f
[CONFORMANCE] Fix run of Conformance tests (#11225) 2022-03-28 12:29:27 +03:00
Ilya Churaev
10698abc29
Revert vpu custom kernel master (#11228) 
* Added original VPU custom kernel doc

* Moved to new API

* Added links from introduction

* Fixed intro
 2022-03-28 12:18:29 +03:00
RavirajSitaram
30884a8161
Fix -Winfinite-recursion error reported by compiler (#11247) 
Signed-off-by: Raviraj P Sitaram <raviraj.p.sitaram@intel.com>
 2022-03-28 11:54:11 +03:00
Nikolay Tyukaev
aded1a2c70
a bunch of doc fixes (#11230) (#11237) 2022-03-25 20:22:43 +03:00
Evgenya Stepyreva
2d7f46b95a
Update Divide_1.md (#11232) 2022-03-25 15:41:55 +00:00
Helena Kloosterman
05f97f2bb5
Update two paragraphs in performance hints docs (#11223) 2022-03-25 16:07:46 +03:00
Ilya Churaev
4dc0d6e711
Fixed comments after #11155 (#11202) 
* Fixed comments after #11155

* Add information about plugin option
 2022-03-25 16:02:18 +03:00
Smirnov Grigorii
a2705b1fed
f64 to f32 and 0.0. to 0.1 (#11127) 2022-03-25 15:10:23 +03:00
Andrey Somsikov
3442e90144
Fix setupvars.bat patching (#11160) 
* Fix setupvars.bat patching

setupvars.bat shoudl not be patched for regular Debug and Release
configurations.

* Use SRTEQUAL for cmake string comparison
 2022-03-25 14:15:04 +03:00
Eddy Kim
200026f28b
Missing backslashes right after mo (#11216) 2022-03-25 13:39:33 +03:00
Nikita Malinin
5e3e8d6084
[POT] Update POT with the ResultRenaming flag (#10989) 
* Update POT with the ResultRenaming flag

* Update flag

* Update gold
 2022-03-25 13:22:20 +03:00
Mikhail Nosov
8bfde58fd9
[Core] Improve performance for 'ov::Model::add_output' (#11052) 
* Improve performance for 'ov::Model::add_output'

On first call of `add_output(tensor_name)` all available tensor names are cached.
Next calls take nodes from cache which significantly reduces complexity.
Cache is invalidated if topological cache is not valid or cache points to incorrect output (no tensor name of this node anymore)

The same caching is done for 'add_output(op_name, output_index)'

Tests:
- Verifies that adding outputs to all nodes has linear complexity O(N), not O(N^2)
- Verifies cache invalidation scenarios

* Fix python tests

* Update topological cache after add_output(Output<Node>) by adding result to the end of cached ops

* Add 'm_shared_rt_info' to 'result node just for consistency (there is actually no scenario which may fail due to absence of this info for Result

* Added test cases to verify that names cache should be cleared on refresh of 'get_ordered_ops'
 2022-03-25 12:17:41 +03:00