Commit Graph

7852 Commits

Author SHA1 Message Date
Roman Lyamin
31e3c11291
[GPU] Use int64_t type for axis in CumSum (#12306) 2022-07-28 09:16:21 +04:00
Roman Lyamin
5e52d519ea
[GPU] Align TopK parameters with ngraph (#12278) 2022-07-28 09:15:41 +04:00
Maxim Vafin
25b0013b8f
[MO] Fix broken port numbering for Constant operations (#12318)
* Restore inputs order in IR Reader

* Fix broken port numbering for Constant operations

Co-authored-by: Chetverikov <anton.chetverikov@intel.com>
2022-07-27 21:57:33 +02:00
Roman Kazantsev
4176608f0b
[TF FE] Fix conversion of NetVLAD model (#12328)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-07-27 22:47:36 +04:00
River Li
0ef4ccb86f
[CC]Fix CC issue for transformation (#12292)
* Revert "Fixed 3 naming issue"

This reverts commit a92d3cfff5.

* Revert "Fix CC issues for transformation and snippets"

This reverts commit d08a3f5aac.

* Fix NGRAPH_PASS_CALLBACK issue to make it can work

* Fix matcher name missing issue
2022-07-27 16:17:53 +04:00
Taylor Yeonbok Lee
361ca2078d
[GPU] Fix get_default_params & choose_impl not to dependent on program_node (#12239)
* Getting rid of dependency from get_default_param for typed_program_node

* Fix bug

* Enable two pathes to call choose_impl / does_possible_impl_exists / does_an_impl_exists to be able to use given layout

* Replaced impl factory API to get kernel_impl_param's pointer

* Update for recently added primitives

* Add and apply optional_layout

* fix kernel_param_impl to be handled as unique_ptr

* Applied review comments

* Fix rebase conflict

* Fix CI error
2022-07-27 14:36:53 +04:00
Ilya Lavrenov
101e1ea5ad
simple Windows installer POC (#12308)
* Fixes for cases when TBB_DIR env var is set

* Don't use make in build_samples.sh script

* First version of Windows installer

* WIndows NSIS installer
2022-07-27 14:04:22 +04:00
Sun Xiaoxia
1dd13e2cf6
Xiaoxia/onetbb old version (#12303)
* support oneTBB old version

* fix oneTBB version mismatch issues

* fix clang issue

* add 'tbb' path to setupvars.sh and OpenVINOConfig.cmake.in

* Update scripts/setupvars/setupvars.sh

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Shen, Wanglei <wanglei.shen@intel.com>
2022-07-27 16:49:53 +08:00
Szymon Irzabek
761a6d10d0
[GNA] Add missing support for batch normalization with weights broadcasting. Add unit tests. (#12301) 2022-07-27 12:14:09 +04:00
almilosz
d7cf585485
[PyOV] Test refactoring (#12248) 2022-07-27 08:44:10 +02:00
Ilya Churaev
4df5a104f3
Investigate GNA tests (#12267)
* Test commit

* Revert "Disable loading of v7 reader for new IR versions (#12252)"

This reverts commit cb6ca7bb89.

* Revert "Test commit"

This reverts commit 977b83f2ba.
2022-07-27 09:26:13 +04:00
Ilya Lavrenov
14e8e3259d
Fixed build_samples.sh not to call setupvars.sh for Debian package case (#12309) 2022-07-26 23:17:41 +04:00
Sebastian Golebiewski
6227123d21
Porting to master - update -readme for CPP and Python benchmark (#12245)
Porting #11961
2022-07-26 14:12:08 +02:00
Chenhu Wang
7d5fbebe27
[DOC] [CPU] Proofreading for grammatical and stylistic corrections (#12288) 2022-07-26 16:11:32 +04:00
Roman Lyamin
e2da32721b
[GPU] Use int64_t type for axis in softmax (#12287) 2022-07-26 13:21:43 +04:00
Pawel Raasz
72509ec041
Add const fold check in operators instead pass (#12189)
* Add const fold check in operators instead pass
- refactor constant fold pass to using ov instead of ngraph
- add constant_folding_is_disabled overload for raw pointer

* Remove Reshape from skip const inferences
in legacy graph transformer

* Const fold test for modified operators
2022-07-26 11:12:23 +02:00
Yuan Xu
04cbe34801
Update error message on pypi.org (#12243)
* Add Overview page

* Revert "Add Overview page"

* fix references

* update links

* update the wording to be more clear

* add the error message about Visual studio back

* update links to static html links of 2022.2

* port changes to master

* update description
2022-07-26 06:33:07 +00:00
Roman Kazantsev
914d79b7e6
[TF FE] Implement LinSpace and BatchMatMul translators (#12271)
* [TF FE] Implement LinSpace and BatchMatMul translators

It helps to convert STN model (from e2e testing) using TensorFlow frontend

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

* Fix BatchMatMul translator

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

* Fix LinSpace operation translator

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

* Apply code-review feedback

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

* Apply code-style rules

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

* Apply code style rules

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-07-26 01:31:37 +03:00
Evgenya Stepyreva
00d34c5f1d
Remove Interpolate Transposes as it does nothing (#12205) 2022-07-25 19:26:55 +00:00
Mateusz Tabaka
270051ebce
[CPU] Add RDFT and IRDFT operators (#12099)
* [CPU] Add RDFT and IRDFT operators

Tickets: 79178 and 79192

Co-authored-by: Mateusz Bencer <mateusz.bencer@intel.com>
2022-07-25 19:23:27 +02:00
Irina Efode
862aebce71
Update summarize.py (#12175) 2022-07-25 15:34:28 +03:00
Vladimir Paramuzov
87b73b4508
[GPU] Get rid of direct layout::size field usages (#12172)
* [GPU] Get rid of direct layout::size field usages to simplify further replacement

* [GPU] Enabled -Wall and resolved compiler complaints
2022-07-25 16:31:01 +04:00
Ilya Lavrenov
36df7f51ae
Fixes for cases when TBB_DIR env var is set (#12266)
* Fixes for cases when TBB_DIR env var is set

* Don't use make in build_samples.sh script
2022-07-24 15:13:00 +04:00
Ilya Churaev
cb6ca7bb89
Disable loading of v7 reader for new IR versions (#12252)
* Disable loading of v7 reader for new IR versions

* Try to fix CI

* Fixed PDPD frontend

* Fixed error message creation
2022-07-22 23:34:04 +04:00
Ilya Lavrenov
926a87e7eb
Install user provided TBB as well (#12260) 2022-07-22 22:36:58 +04:00
Ilya Churaev
811a483acb
Fixed newAPI for case if core was removed (#12207)
* Fixed newAPI for case if core was removed

* Fixed code style

* Fixed typo

* Use new API by default

* Create core with template plugin

* Added doxygen comment
2022-07-22 16:46:08 +03:00
Roman Kazantsev
23e513d679
[MO] Fix Mul fusion with dynamic dimension (#12253)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-07-22 14:01:42 +04:00
Xiping Yan
9519461453
Move GNU build flag to "cmake/developer_package/compile_flags/sdl.cmake" (#12143)
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
2022-07-22 10:13:13 +04:00
Ilya Lavrenov
564b25a71f
Fixed WIndows backslash paths (#12250) 2022-07-22 01:34:46 +03:00
Konstantin Beluchenko
ed65d199bb
[GPU] ROIAlign v9 support (#11899)
* ROIAlign v9 support

* Code changes after review1

* Code changes after review2

* fix of single layer test for Windows

* Since PR #12043 we don't need strong include order of primitive_base.hpp and
impls/implementation map.hpp anymore

* Code changes after review3

* Code changes after review4
2022-07-21 11:52:32 +02:00
Roman Kazantsev
598975fb63
[TF FE] Handle optional attributes for Convolutional operations (#12230)
* [TF FE] Handle optional attributes for Convolutional operations

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

* Apply code-style rules

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-07-21 09:30:13 +02:00
Marcin Kusmierski
3eafa653f3
[GNA] Fix accuracy degradation in compact mode (#12150) 2022-07-20 12:53:45 +02:00
Nadezhda Ageeva
fdae2eb8e3
[GNA] Fixed convolutions with shared transpose and un-fuse-able activations after Convolution filter (Renew PR11373) (#12152)
* Commits from PR11373:
Fixed handling of transpose after convolution
[GNA] Fixed calculation of dimensions for ConvolutionFilter and PWL primitives
[GNA] Fixed coverity error and failed tests

* Apply comments

* Update src/plugins/intel_gna/gna_graph_compiler.cpp

Co-authored-by: Marcin Kusmierski <marcin.kusmierski@intel.com>

* Update src/plugins/intel_gna/gna_graph_compiler.cpp

Co-authored-by: Marcin Kusmierski <marcin.kusmierski@intel.com>

* Rollback names

* Separate test data

* Move coverity issue to separate request

Co-authored-by: Elizaveta Lobanova <elizaveta.lobanova@intel.com>
Co-authored-by: Marcin Kusmierski <marcin.kusmierski@intel.com>
2022-07-20 14:50:07 +04:00
Egor Duplenskii
3cec746a64
[CPU] Explicitly enable DNNL_VERBOSE only in case of CPU_DEBUG_CAPS (#12108) 2022-07-20 14:08:24 +04:00
Chen Xu
ee9127e10e
[CPU] Fixed heap sort bug regarding heapifying (#12221) 2022-07-20 13:14:08 +04:00
Roman Kazantsev
c332a162ff
[MO] Fix TopK partial shape inference with dynamic K (#12212)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-07-20 09:16:24 +02:00
River Li
9a3c969cb7
Restore FEM to be static instance (#12219)
* Restore FEM to be static instance

* Restore frontend manager in ie_read_network.cpp
2022-07-20 08:09:31 +03:00
Ilya Lavrenov
00fe7be00f
Use system pugixml where it's possible (#12218) 2022-07-20 08:53:17 +04:00
Chenhu Wang
43b3fff708
[DOC][CPU] Denormals optimization doc (#12127) 2022-07-20 04:35:45 +03:00
Jan Iwaszkiewicz
06019c442f
[PyOV][DOCS] Python API contribution and developer guide (#12145)
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2022-07-19 16:25:58 +02:00
Irina Efode
5ea8186888
[IE TESTS][CONFORMANCE] Fix OpImplCheck Precision (#12148) 2022-07-19 12:35:12 +04:00
Artur Kulikowski
6a795936b2
ONNX: Pass name to the InputEdge (#12177) 2022-07-19 08:52:54 +02:00
Xiping Yan
6966af3ced
Xp/benchmark app ocl (#12112)
* Add some tip description about enable OpenCL for benchmark_app.

Signed-off-by: xipingya <xiping.yan@intel.com>

* Export doesn't work, we need to add -Dopencl_root_hints=[PATH]/OpenCL-CLHPP/include to cmake command.

Signed-off-by: xipingya <xiping.yan@intel.com>

Co-authored-by: Chen Peter <peter.chen@intel.com>
2022-07-19 14:43:59 +08:00
Ilya Lavrenov
3c0b17f108
Debian packages: base version (#11387) 2022-07-19 09:07:26 +03:00
Ilya Lavrenov
6307fdc77b
Fixes for system libraries pugixml, tbb (#12206)
* Fixes for system libraries pugixml, tbb

* Added more dependencies for core
2022-07-19 08:52:06 +04:00
Evgenya Stepyreva
1535be3c16
TI repetative shape inference (#12178) 2022-07-18 18:47:15 +03:00
Jade Cho
7b03520395
Check memory allocation size of network graph (#11911)
+ Add exception handling for out of resource
2022-07-18 20:39:21 +09:00
Sungeun Kim
3bd475ad26
[GPU] integrate persistent caching for onednn (#12094)
* integrate persistant caching for onednn
* add api to save/load binary file.
2022-07-18 20:13:46 +09:00
Katarzyna Mitrus
4e379d63eb
Update opset.md with opset9 (#12169) 2022-07-18 11:01:45 +02:00
Tomasz Dołbniak
cc3ec0c50a
Update of naming of the last operators in the graph (#12139) 2022-07-18 07:34:14 +02:00