Maxim Andronov
9ac542c455
[CPU] Restore legacy SetBlob and GetBlob to API 1.0 version ( #10094 )
2022-02-14 15:35:13 +03:00
Daniil Lyakhov
56be1a5438
Change User Transformations applying order in MO ( #10241 )
...
* Fix user transformation order in mo
* Move user transformation behind FP16 compression
* Move user transformation call before fp16 compression
2022-02-14 15:06:09 +03:00
Tomasz Dołbniak
a9b6eaf5c0
Multiple ONNX opset imports handling ( #10332 )
2022-02-14 12:59:41 +01:00
Dmitry Pigasin
9b1e4b801b
Add -layout option ( #10272 )
2022-02-14 14:47:10 +03:00
Nikolay Shchegolev
3cb7592607
[CPU] Gather node. Support case with batchDims == indicesRank. ( #10170 )
2022-02-14 14:44:10 +03:00
Gorokhov Dmitriy
be4464ca2b
[CPU] Migrated legacy post ops mechanism on runtime data pointers ( #9938 )
2022-02-14 14:17:45 +03:00
Jan Iwaszkiewicz
9e89ee2478
[PYTHON] New Python docs and refactor/improvements ( #10032 )
2022-02-14 10:24:33 +01:00
Irina Efode
7ff5f5ea70
[IE TESTS][IE CONFORMANCE] Move Read_ir tests to Conformance ( #10300 )
2022-02-14 12:15:37 +03:00
hyunback kim
c5b26bc10c
[GPU] Support deconv double blocked format for b=32 ( #10164 )
...
* [GPU] Support batch32 deconv onednn
onednn rls-v2.6-pc2 support deconv batch32,
so remove the batch size limitation.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Update to merge duplicated checking onednn condidton in deconv.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Update to use is_node_for_onednn func in get_preferred_impl_type
Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-02-14 17:39:26 +09:00
Anastasia Kuporosova
931f4c077d
[Python API] Update python test installation ( #10283 )
2022-02-14 11:24:29 +03:00
Anton Pankratov
be8e15c180
fix HETERO with branching without splits ( #10325 )
...
* Default value of streams in ba is AUTO
* Fixed hetero cases with branches
* Fixed format
2022-02-14 10:36:41 +03:00
Roman Lyamin
d13e04a693
[GPU] convolution_kernel_bfyx_1x1_opt fix ( #10338 )
2022-02-14 10:32:19 +03:00
Maksim Derbasov
bb0d82f724
Fix warnings ( #10278 )
2022-02-14 07:48:41 +03:00
Mikhail Nosov
d85715f991
Remove dynamism from API 1.0 ( #10167 )
...
* Refresh the PR
* Added check for dynamic inputs to LoadNetwork/QueryNetwork
* Fix review comment
* Added 'validation' callback to 'load network from file'
* Fix MockICore
* Added null-pointer check
2022-02-13 20:41:14 +03:00
Ilya Lavrenov
ba19551b13
Fixed typo ( #10313 )
2022-02-13 16:20:41 +03:00
Anastasia Popova
ac2e639ff8
Added telemetry to modules names list. ( #10295 )
2022-02-13 10:28:17 +03:00
Ilya Lavrenov
80a901e103
Add TF FE to OpenVINO package ( #10314 )
...
* Add TF FE to OpenVINO package
* Add double install for TF FE
2022-02-12 23:42:12 +03:00
Indira Salyahova
ea00eae922
[POT] Fix for measuring input shape when inference model with batch greater 1 in FBC ( #10063 )
...
* fix: diffrent batch shape in prediction and target in ac
* add calculate metric in engine True
* resolve conflicts
2022-02-12 19:12:58 +03:00
Nikita Malinin
8e43987cd7
[POT] Update IEEngine for SW API support ( #10304 )
...
* Update IEEngine for SW API support
* Change Engine for GNA sample
* Change stacks into reshape
2022-02-12 18:57:35 +03:00
Indira Salyahova
976a20cedf
[POT] Update input pattern ( #10220 )
...
* Update special_patterns.py
* Update IgnoredPatterns.md
2022-02-12 18:56:41 +03:00
Vladislav Volkov
78281fef74
[CPU] [Ngraph] Fix of memory leak in PassBase::get_name and leak in jit_avx2_1x1_convolution_with_dw_conv_fwd_t kernel ( #10199 )
2022-02-12 15:48:49 +03:00
Maksim Kutakov
451453c4ce
[CPU] Fixes for CpuBlockedMemoryDesc constructor and reorder availability checks ( #10299 )
2022-02-12 15:29:55 +03:00
Alexander Zhogov
e49370c008
Azure CI: Enable tests on Mac again
2022-02-12 14:22:37 +03:00
Alexander Zhogov
74475e216d
Azure CI: Add ccache on Mac ( #10290 )
...
* Azure CI: Add ccache on Mac
* Temp OFF
* disable tests
2022-02-12 11:52:07 +03:00
Ivan Tikhonov
9989db5ae0
Rename frontend extension files ( #10257 )
...
* Delete _extension suffix in file names; add extension.hpp header to include all extensions
* add extension.hpp file to include all extensions
* codestyle
2022-02-12 09:19:20 +03:00
Maxim Shevtsov
e3cc4833f4
Auto batch smart reshape strict testing (once we moved to dim tracking) ( #10253 )
...
* fixed perf-counters
* explicit auto-batching params that should guarantee the auto-batching is triggered ( to avoid fallback to no-batching when the selected batch1 size is just 1)
* makeConvPoolReluNoReshapes and using that whenever applicable to gaurantee the auto-batching is required (not important for things like plugin/executable-network config tests, but important for the inference-requests)
* getDefaultNGraphFunctionForTheDevice moved to the ov_behavior_test_utils.hpp
2022-02-12 02:00:34 +03:00
Pavel Esir
653ed4a34c
[MO] use revision hashes to compare IE & MO versions ( #10230 )
...
* fixed version comparison: for comparsion extracted hashes are used
* shortened 7 -> 11 to match the current version fromat from nightly
* corrected regex, added comparing by minimal hash len
2022-02-12 00:13:48 +03:00
Anton Pankratov
897e2acd91
Default value of streams in ba is AUTO ( #10305 )
2022-02-12 00:09:31 +03:00
Roman Lyamin
7b288d125a
[GPU] Gather fusion tests fix ( #10308 )
2022-02-11 20:57:44 +03:00
Aleksandr Korolev
c2a9036482
[VPU] Fix performance hint ( #10309 )
2022-02-11 19:39:00 +03:00
guozhong wang
14c1e98e8c
Guozhong/check format ( #10184 )
...
* remove formatTimeMilli from time_utils.cpp
* add traceCallStacks test case
* add traceCallStacks test case in format_test.cpp
* add param:"test" to function TraceCallStacks()
* catch the exception of checkFormat
* add space for try catch
* rollback time_utils.cpp time_utils.hpp and log_utils_format_test.cpp
* modify testcase for log.hpp
* modify testcase from format_s to format_s_d_ld_u_lu2
2022-02-11 19:10:13 +03:00
Yuan Hu
7abd61f867
[AUTOPLUGIN] OV config 2.0 support ( #10191 )
...
* add support for LOG_LEVEL and supported_properties
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix compile error
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add test case for log_level and full_name
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* update to ov 2.0
Signed-off-by: fishbell <bell.song@intel.com>
* fix benchmark_app faild for AUTO:GPU, GPU
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add case
Signed-off-by: fishbell <bell.song@intel.com>
* refine logic
Signed-off-by: fishbell <bell.song@intel.com>
* add test cases
Signed-off-by: fishbell <bell.song@intel.com>
* add more cases
Signed-off-by: fishbell <bell.song@intel.com>
* fix redifinition
Signed-off-by: fishbell <bell.song@intel.com>
* cpu plugin only in cpu tests
Signed-off-by: fishbell <bell.song@intel.com>
* typo in parameter
Signed-off-by: fishbell <bell.song@intel.com>
* use _core directly
Signed-off-by: fishbell <bell.song@intel.com>
* fix multi case failure
Signed-off-by: fishbell <bell.song@intel.com>
Co-authored-by: fishbell <bell.song@intel.com>
2022-02-11 23:39:09 +08:00
Ivan Novoselov
cc602ac6fd
[Snippets] Convert Load/Store to slarar versions if shape ends with 1 ( #10292 )
2022-02-11 17:27:32 +03:00
Liubov Talamanova
4d61600077
[POT] Fix cascade model names ( #10112 )
2022-02-11 15:54:41 +03:00
Victor Kuznetsov
bcd192e882
Revert changes with single-image-super-resolution-1032 - memcheck precommit ( #10271 )
2022-02-11 20:30:09 +08:00
Anton Pankratov
f36d3303d2
Added callback capturing notes ( #10256 )
...
* Added callback capturing notes
* fixed spelling
2022-02-11 14:51:32 +03:00
Sergey Shlyapnikov
03566b4e4d
[GPU] Fix outputs blobs allocation for U16/I16 data types ( #10180 )
...
* [GPU] Fix outputs blobs allocation for U16/I16 data types
* [GPU] Add U32, U64, FP64 data types support; add information about legacy fused activations to .info file
* Update auto_batch.cpp
fixed u64 inputs for the auto-batching
Co-authored-by: Maxim Shevtsov <maxim.y.shevtsov@intel.com>
2022-02-11 14:08:36 +03:00
Nikita Demashov
20d2633af0
removed defaultPrecisions as global variable and added as field in Params class ( #9185 )
...
fix canConvolutionBeTransformed arguments
fix isAsymmetricOnWeights in GPU plugin
added defaultPrecisions in TestTransformationParams
set new default attribute precisions
try to set const default precisions in network_helper.cpp
apply precision_set
[LPT] Default precisions
rebase
remove extra const
used defaultPrecision in tests
fixed SimpleLowPrecisionTransformer default argument
fixed AttributeParameters default argument
added defaultPrecisions in functions
fix assign_and_read_value_transformation tests
fixed wrong defaultPrecisions definition
fixed ConcatWithNeighborsWithConvolutionTransformation tests
remove getDefaultPrecisions
rebase
remove getDefaultPrecisions from gpu plugin
remove getDefaultPrecisions from lpt_mkldnn_plugin.cpp
use predefined member
update mkldnn_plugin.cpp & lpt_mkldnn_plugin.cpp
resolved conversations
make all lambda captures by ref
2022-02-11 13:41:03 +03:00
tgubanova-lohika
04c1b9760c
[GPU] Implement ExperimentalDetectronTopKROIs operation ( #10208 )
2022-02-11 13:32:49 +03:00
Vladimir Paramuzov
dc1e9aa9bd
[GPU] 6d broadcast support ( #10280 )
2022-02-11 13:29:09 +03:00
Vladimir Paramuzov
013b5f5b5f
[GPU] Added cl batched headers post-processing ( #10093 )
2022-02-11 13:26:22 +03:00
Nikita Malinin
d758a21d6e
Update gna_sample with API 2.0 features ( #10236 )
2022-02-11 13:23:02 +03:00
Alexey Lebedev
31501a7992
Fix random ( #10240 )
2022-02-11 13:06:07 +03:00
Mateusz Tabaka
6e1bc49862
Update xfail reason for ssd mobilenet models ( #10287 )
2022-02-11 10:34:42 +01:00
Nikolay Tyukaev
f03590d245
fix edit on github for pot and ovsa ( #10285 )
2022-02-11 12:13:12 +03:00
Mikhail Nosov
5535fdefa9
Fix coverity scan issues ( #10266 )
...
* Fix coverity scan issues
For virtual 'noexcept' functions everything that can throw exception shall be handled inside function
* Remove 'noexcept'
2022-02-11 10:44:57 +03:00
Tomasz Dołbniak
c186449735
Do not process null nodes in JSON analysis ( #10269 )
2022-02-11 08:42:25 +01:00
Mang Guo
8bbabf8720
[CPU] Get interpolate scales input during interpolate node init if the input is Constant. ( #10229 )
2022-02-11 10:27:50 +03:00
Maxim Andronov
cf805b17b9
[CPU] Support legacy dynamic batch via dynamic shapes ( #9646 )
2022-02-11 10:17:58 +03:00
Min, Byungil
281e38bd83
Use onednn reorder for newly added format ( #10273 )
...
+ Added new format to onednn optimized format list
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-02-11 15:58:11 +09:00
