Chen Xu
cba0892832
* [CPU] Extend Reduce node to support blocked layouts nC[d]hw8/16C ( #580 )
2020-09-07 15:35:11 +03:00
Mikołaj Życzyński
ab6d3a5227
[IE CLDNN] Grouped convolution kernel improvement ( #2063 )
2020-09-07 11:52:06 +03:00
Tomasz Socha
a5389010a9
Remove list of the supported ops by ONNX Importer ( #2061 )
2020-09-07 10:50:55 +02:00
Mikhail Letavin
75b4e193f7
[IE CLDNN] Fix the order of dimensions in reshapes inserted by Select primitive ( #2082 )
2020-09-07 11:49:56 +03:00
Evgeny Latkin
062a4e2900
VPU: update firmware version to 1354 ( #2087 )
2020-09-07 10:58:36 +03:00
iliya mironov
9939253fed
Refactored legacy code for mean_scale_values transformations ( #1936 )
...
* Remove move_to_preproc. Not actual.
* Updated documentation
2020-09-07 10:41:47 +03:00
Andrey Chekhonin
b683b5501d
[IE][VPU]: Fix behavior tests for MXpcie ( #1879 )
...
* Moved mem type patching under USB protocol switch
* Myriad beh tests fix
2020-09-07 10:38:07 +03:00
Vladislav Volkov
50c6f02a2e
Ngraph improvements ( #2058 )
2020-09-07 10:36:52 +03:00
Maxim Vafin
6730cab192
Move FakeOutput resolving to back phase ( #2033 )
2020-09-07 10:20:24 +03:00
Vladimir Paramuzov
51564f415c
[IE CLDNN] Fixed fsv16 lrn kernel with fp16 input ( #2086 )
2020-09-07 09:04:05 +03:00
Tomasz Dołbniak
0cd0c1a551
Handle Split axes as i64 ( #2079 )
2020-09-07 05:48:32 +03:00
Lukasz Debski
33c3aeb867
[IE CLDNN] Fixing blocked format opting for strided_slice ( #2073 )
2020-09-05 19:01:43 +03:00
Vladimir Paramuzov
4f5f91bd9c
[IE CLDNN] Disable unsupported blocked formats for softmax ( #2049 )
2020-09-05 10:11:18 +03:00
Mikołaj Życzyński
ad2ed5b480
[IE CLDNN] Reduce performance drop fix ( #2065 )
2020-09-05 10:11:00 +03:00
Konrad Dobros
b3e69f1f7d
[IE CLDNN] Enable bfyx fully_connected for large batches ( #1996 )
...
This change enables fully_connected to use bfyx format for large
batches, when optimized bf_tiled kernel best performance.
2020-09-04 22:22:46 +03:00
Maxim Vafin
18a49f9e7e
Fix fusing Multiply node with Convolution in case group != 1 ( #1882 )
...
* Fix fusing Multiply node with Convolution in case group != 1
* Add transformation test
* Do not fuse if not possible to reshape const
* Update fuse_linear_ops.py
2020-09-04 20:32:51 +03:00
Tomasz Dołbniak
51fa5ab8cb
Make pybind more verbose in debug on windows ( #2045 )
...
* Make pybind more verbose in debug on windows
* Remove the NDEBUG flag everywhere
* Code complexity reduction...
* Missing colon
* And now the missing empty line...
* Reusable functions
* Now the mood of the sentence was wrong...
* Free functions instead of methods
2020-09-04 19:03:33 +03:00
Jozef Daniecki
8e9b733534
HostTensor2Vector ( #2027 )
...
* Add host_tesnor_2_vector() implementation and unit tests. One reference OP refactored to use it.
* Ngraph assertion message refactored.
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
* Fix style.
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
2020-09-04 16:02:14 +03:00
Gorokhov Dmitriy
696091adea
[CPU] Disabled several non-valid static assertions ( #2055 )
2020-09-04 15:38:07 +03:00
Anton Potapov
74b77a4c97
[PP GAPI] - Generic precision conversion kernel ( #1897 )
...
- U16toF32 conversion kernel converted to more generic ConvDepth one
- U16 <-> F32 conversion only are supported for now
- kernel is not used in the preprocessing graph yet
- tests are extended
2020-09-04 15:24:36 +03:00
Ivan Tikhonov
2d606e35c5
Enable force shape inference in RNNSeqNormilize transformation ( #2069 )
2020-09-04 15:08:52 +03:00
Polina Brzezinskaya
7212ff5bb2
fix for typo in src/inference_engine/CMakeLists.txt ( #1988 )
2020-09-04 15:07:47 +03:00
Gladilov, Gleb
4ecdd19653
[IE][VPU]: Introduces annotations of stages memory types ( #1991 )
...
* Moves splitLargeKernelConv tests to unit tests
Originally, file with tests has been placed in a wrong place
so it was not integrated into any testing application.
Now it is a part of unit tests on VPU.
Test itself has been disabled due to issue with NCE unit usage
described in #-33366
* Introduces pass I/O memory types annotation of stages
It is useful to see where inputs and outputs are located in
performance report for analysing possible issues.
* Introduces endsWith and tuple2Vector utilities
endsWith checks if source has suffix equals to second
argument. tuple2Vector converts tuple of arbitrary size
containing the same type to vector. It could be useful
working with gtest parameter generators that have
std::tuple as return type.
* Introduces unit tests on annotating stages memory types
* Introduces missing format placeholders
* Makes memory types annotation optional
Enables private option "enableMemoryTypesAnnotation" which
disabled by default. Disabling annotation by default allows
avoid issues with tests which rely on stages names.
Signed-off-by: Gladilov, Gleb <gleb.gladilov@intel.com>
2020-09-04 14:33:10 +03:00
Kamil Magierski
9df59284bc
[GNA] Fix Activation output size not matching convolution if padded. ( #1980 )
...
* Fix Activation output size not matching convolution if padded.
* Fix input padding handling in Convolution
* fix static bug
* Use correct value for feature rotation.
* [GNA] Fix regression
* Added tests
* Added tests
2020-09-04 13:23:00 +03:00
Piotr Rozen
b27ce4b04d
Fixed speech demo compilation issue on 2021.1 and models are updated to IRv10 ( #2029 )
2020-09-04 12:25:45 +03:00
Nikita Kudriavtsev
4b348500d4
[IE][VPU]: Reduce XLink log level in AOTBehaviorTests ( #2044 )
2020-09-04 11:59:51 +03:00
Vladimir Paramuzov
214b25c49d
[IE CLDNN] Fix performance degradation for brain-tumor-segmentation-0002 ( #2038 )
...
JIRA: 37933
Co-authored-by: Egor Churaev <egor.churaev@intel.com>
2020-09-04 11:54:59 +03:00
Nikita Kudriavtsev
35357f686d
[IE][VPU]: Fix for Swish layer ( #2034 )
...
* Fix Swish layer serialization.
* Added shared test for Swish
* Firmware update 1326 -> 1349
2020-09-04 11:52:13 +03:00
iliya mironov
0c1b2f836b
Add Mish with SoftPlus transformation ( #1815 )
...
* Add Mish with SoftPlus transformation
* Refactoring accrding code review
* Add softplus to mish pass registration
* Add checks customer count for SoftPlus and Tanh ops
2020-09-04 11:07:37 +03:00
Anton Pankratv
8017ac03ea
Hetero plugin dump dot file using ngraph pass ( #2042 )
...
* Hetero plugin dump dot file using ngraph pass
* Removed unused code
* Fixed color Index
* reverted prcision forwarding
2020-09-04 10:55:40 +03:00
Alexey Varyzgin
4c87427818
[CPU][BF16] bf16 for Gemm or MatMul was enabled ( #1920 )
2020-09-04 10:04:02 +03:00
Chenhu Wang
479e13e713
[CPU] Interpolate operation implementation ( #1465 )
2020-09-04 09:54:05 +03:00
Jedrzej Hajduczenia
021941bf03
[IE CLDNN] Fix i8 regression on single-image-super-resolution-1032 ( #1990 )
2020-09-04 09:20:16 +03:00
Ivan Tikhonov
2f5a28d44f
LSTMCell/Sequence v1, reference implementations and decompose transformations for LSTM/GRU/RNN Cells ( #2000 )
...
* validate_and_infer_types() implementation
* input parameter validation for LSTM, GRU and RNN
* style-check applied
* Add LSTMSequence dynamic shape validation and test props for RNNCell, GRUCell, LSTMCell and LSTMSequence.
* recurrent_sequence.hpp moved to ngraph/core/include/ngraph/op/util/
* style check applied
* removed unused variable from LSTMSequence::validate_and_infer_types
* Add missing newline mark at the end of file.
* Add supression macro for FusedOp deprecation.
* Add element type initialization
* transpose,rnn cell reference implementations
* Apply PR review remarks
* reference implementations for cells op, single layer tests, align lstm cell/sequence according to the spec
* lstm/gru/rnn cell decompostion transformations
* ngraph codestyle
* clean up
* ngraph code style
* change inheritance of Cells, fix build
* fix build
* fix build again
* remove Peepholes from LSTMSeq, fix copy_runtime_info in transformations
* Rewrite tests to use gtest exception assertions.
* resolve tests issues
* ngraph codestyle
* add missed files
* fix typeprop tests
* fix lstm sequence checks
* fix arm build
* fix arm again
* delete unnecessary file
* add convert weghts format function, enable lstm test, resolve review comments
* add ngraph builders
* ngraph codestyle
* fix unit tests
* revert transpose reference implementation
* revert LSTM Cell v0, add LSTMCell v1, update transformation lstm_cell_to_cell_ie
* v1 version of LSTMCell op
* LSTMSequence v1 operation, exclude LSTMSeq from opset4
* fix python api tests
* resolve review comments, tests for decomposition transformations, switch lstm cell to opset4 in mo
Co-authored-by: Szymon Durawa <szymon.durawa@intel.com>
2020-09-04 09:04:36 +03:00
Ilya Churaev
28eed7708e
Removed builders from public API ( #2059 )
...
* Removed builders from public API
* Fixed build
2020-09-04 06:06:43 +03:00
Vitaliy Urusovskij
0b61a7568f
First time to inference POC ( #1964 )
2020-09-03 22:08:37 +03:00
Vladimir Gavrilov
e6a36123db
Reverted conversion of Resize-10 to Interpolate-4 in ONNX Importer. ( #2048 )
...
* Reverted conversion of Resize-10 to Interpolate-4. Now Resize with opset version < 11 generates Interpolate-1 again.
* Corrected tests.
2020-09-03 19:34:35 +03:00
Evgeny Latkin
e97100581e
[IE][VPU]: allocate maximum shaves for mish activation ( #1995 )
...
* Mish activation calculation costs more time than memory copy, so
allocate more shaves mish activation.
Co-authored-by: Jiang, Renzhi <renzhi.jiang@intel.com>
2020-09-03 19:22:56 +03:00
Ilya Znamenskiy
e862c3b720
[IE CLDNN] Fix result storing in leftover's branch ( #2050 )
2020-09-03 18:47:32 +03:00
Vladimir Paramuzov
b976782c70
[IE CLDNN] Fallback to FP16 for non-quantized layers in quantized FP16+INT8 IR ( #941 )
2020-09-03 17:41:29 +03:00
Dmitry Kurtaev
37a7bbc08c
[IE][VPU][Watchdog]: Reduce CPU usage for idle VPU ( #2030 )
2020-09-03 16:49:48 +03:00
Anna Khakimova
efad27d68c
AVX2/AVX512 32FC1 Resize ( #1788 )
2020-09-03 16:22:43 +03:00
Evgeny Lazarev
f60b46f3d4
Fixed visitor for Interpolate-1 and Interpolate-4 ( #2051 )
...
* Fixed visitor for Interpolate-1 and Interpolate-4
* Code style fix
* Remove unnecessary changes
* Fixed compilation on Linux for Atttribute visitor of vector<size_t>
* Added unit test for IE IR Reader for Interpolate-4
* Updated unit test for IR Reader for Interpolate-4
* Updated unit test
2020-09-03 16:00:46 +03:00
Anastasia Kuporosova
d9e9abcf50
[Python Tools] Replace use of layers in cross-check-tools ( #1803 )
2020-09-03 15:40:32 +03:00
iliya mironov
5a376477a9
Fix version print ( #2022 )
...
* Fix version print
2020-09-03 15:39:02 +03:00
Dmitry S
f57fae9f73
fixed python & glib vers differences ( #2057 )
2020-09-03 15:10:17 +03:00
Ilya Churaev
6f83889886
Fixed a case with empty order in transpose op ( #2043 )
...
* Fixed a case with empty order in transpose op
* Fixed comments
* Fixed transpose tests
* Fixed tests
2020-09-03 14:50:01 +03:00
Pavel Rodionov
166ec394bd
[GNA] Move old headers ( #2002 )
2020-09-03 14:42:30 +03:00
Andrey Dmitriev
6b2ac800aa
[GNA] Fixed case of unconnected output of split layer ( #1344 )
...
[GNA] Fixed case of unconnected output of split layer
[GNA] Fixed case of unconnected output of split layer
test
[GNA] Fixed case of unconnected output of split layer
fixed
2020-09-03 13:23:58 +03:00
Gleb Kazantaev
1f79a4054b
Fix ConvBiasFusion pass for some rare cases ( #2032 )
...
* Extended ConvMultiplyFusion tests with bias fusion
* Updated ConvBiasFusion with precise constant validation
* Fix ConBiasFusion tests
* Updated eltwise fusion tests
* Changed test parameters
2020-09-03 11:15:50 +03:00
