Vladimir Gavrilov
b15a70caf7
Corrections in MO to fix performance drop in Interpolate-4 when mode=linear instead of linear_onnx ( #4488 )
...
* Written the transformation that replaces 'linear' mode of Interpolate-4 by 'linear_onnx' mode, when the input tensor rank is equal to 4.
* Fixed BOM-file.
* Fixed copyright year.
* Added message into assert.
* Small fix.
2021-02-27 08:49:47 +03:00
Alexey Suhov
5e43744001
Fix warnings with PDB override for RelWithDebInfo configuration ( #4520 )
2021-02-26 23:06:24 +03:00
hyunback kim
d72c20528e
[IE CLDNN] Fix reduce accumulate issue in unittest. ( #4448 )
2021-02-26 18:53:54 +03:00
Svetlana Dolinina
a1ef9498a3
fix unintended shape change ( #4510 )
2021-02-26 18:29:29 +03:00
Bartosz Sledz
b0043bb599
ONNX Slice operator support types dynamically ( #4507 )
2021-02-26 16:28:51 +01:00
Ewa Tusień
f88f81c6ba
OnnxBackendNodeModelTest XFAILs cleanup ( #4432 )
2021-02-26 15:34:24 +01:00
Katarzyna Mitrus
76fed9315e
Legacy LSTM/RNN/GRU tests clean up ( #4265 )
2021-02-26 14:27:18 +01:00
Ivan Tikhonov
7cf7e1b5fa
Reset Variable to dynamic state in revalidate_and_infer function of ReadValue op ( #4430 )
2021-02-26 14:01:29 +03:00
Alexey Varyzgin
67592d427e
Simd build issue in VS2017 ( #4496 )
...
* disable and cleanup interp and resample that is covered by interpolate
* Simd build issue in VS2017
Co-authored-by: chenhuwa <chenhu.wang@intel.com>
2021-02-26 12:24:13 +03:00
Maxim Vafin
c635b949cd
Improve axes input specification for MVN-6 ( #4491 )
...
* Improve axes input specification for MVN-6
* Apply feedback
2021-02-26 11:11:11 +03:00
Mikhail Ryzhov
2db51bb0d0
[Python] Fixed issues in runtime wheel ( #4359 )
...
* Added rpath for plugins
* Corrected dll pathes for PIP
* Fixed plugin install names
* Put libs to the sub-package
* Corrected libraries path according to the new location
* Added download and home page urls
2021-02-26 10:31:58 +03:00
Alexandra Sidorova
ab5d4aa3dc
[CPU] Fixed MVN-6 with negative axes decomposition ( #4494 )
...
* [CPU] Fixed MVN with negative axes
* Added tests
* Added tests with unordered axes case
2021-02-26 10:27:09 +03:00
Yegor Kruglov
f7b6ad710f
update output ports count depending on opset version ( #4439 )
2021-02-26 09:18:03 +03:00
Gleb Kazantaev
53a96f4a5a
Added default value for broadcast to SquearedDifference operation ( #4490 )
2021-02-26 07:44:08 +03:00
Andrey Somsikov
dcce0f549c
Add LeakSanitizer default suppressions list ( #4473 )
2021-02-26 06:32:42 +03:00
Maxim Andronov
cce3375d55
Revert "[CPU] Changed output blobs creation used output info ( #3796 )" ( #4492 )
...
This reverts commit a15246e1d0
2021-02-25 23:06:19 +03:00
Ilya Churaev
1458ba392e
Removed hardcoded shapes from LogSoftmax operation ( #4475 )
...
* Removed hardcoded shapes from LogSoftmax operation
* Added tests
* Fixed comments
2021-02-25 20:02:14 +03:00
Alexander Zhogov
c38e7a2986
Azure CI: Add verbose output for mount
2021-02-25 19:01:42 +03:00
Tomasz Dołbniak
24d2502f83
Check the inputs number before unsafe access ( #4480 )
2021-02-25 15:02:38 +01:00
Patryk Elszkowski
af712743ab
Comparison of InputDescription and OutputDescription in SubGraph ( #4123 )
...
* draft - looks good, need merge with other branch
* apply suggestions from PR
* apply suggestions from PR
* add unit test - NotValidInputOrOutput
* rephraze equal for constant
* cleanup all TODOs
* Try to fix TI
* try to satisfy PR comments
* fix spelling
Co-authored-by: Patryk Elszkowski <patryk.elszkowki@intel.com>
2021-02-25 16:31:35 +03:00
Vladimir Paramuzov
8f4d2be537
[IE CLDNN] Enabled cpplint for cldnn and kernel selector ( #4478 )
2021-02-25 16:18:27 +03:00
Edward Shogulin
cec2f2fb9e
[LPT] integrated fixes for release 2021.3 ( #4460 )
...
* [LPT] denormal handling in AddTransformation
* [LPT] ReshapeTransformation: 4D->3D after Convolution fix
* [LPT] fuse eltwise to fq fix
* [LPT] fuse mul to fq: mul by zero handling
* [LPT] FuseConvertTransformation: convert with unexpected precision
* [LPT] Disable constant folding on weights during reshape
* [LPT] new Q/DQ weigths prerequisites
* [LPT] AddTransformation (swapMultiplyAndAdd) constant precision definition workaround
Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
2021-02-25 16:00:19 +03:00
iliya mironov
c8450fabb5
Disabled unit test for CTCGreedyDecoder with fp16 input data ( #4481 )
2021-02-25 15:35:17 +03:00
Anton Dudchenko
74fe55f6d0
[IE][VPU]: Add config option to disable asynchronous DMA on device ( #4421 )
...
* [IE][VPU] Add config option to disable asynchronous DMA on device
* Parse option
* Update firmware
2021-02-25 14:48:33 +03:00
Taylor Yeonbok Lee
564be86407
[IE CLDNN] Added a new permute kernel optimized with tiling ( #4424 )
2021-02-25 12:54:28 +03:00
Bartosz Sledz
6c98171e23
Fix output names for group of Strided Slices to Variadic Split optimization ( #4378 )
...
* Add tests which reproduces issue
* Fix Output Names in StridedSlice optimization
* Fix codestyle
* Add check if at least one StridedSlice has Result operation as a consumer
2021-02-25 12:53:46 +03:00
iliya mironov
799f34238e
Imironov/fix ctc greedy decoder pattern matcher ( #4441 )
...
* Fix puttern matcher condition
* Refactoring pattern matcher
* Update unit tests
2021-02-25 09:42:43 +03:00
Anton Pankratv
61422f97ac
Moved preprocessing macro tools to separate library ( #4464 )
2021-02-25 07:32:48 +03:00
Andrey Somsikov
0646219f3e
Translate app failures from cond comp tests ( #4393 )
2021-02-24 22:54:37 +03:00
Aleksandr Korolev
194de08cf3
[IE][VPU]: Remove legacy convert passes from Myriad Plugin ( #4022 )
...
* Replaced ie::NetPass::ConvertPrecision with ngraph::ConvertPrecision
* Fixed case with wrong behavior in merge_subsequent_dsr_operations.cpp
* Remove NGRAPH_RTTI from vpu/ngraph #49823
2021-02-24 22:37:45 +03:00
Andrey Dmitriev
c2f607745f
[GNA] Import/Export memory layer name ( #3252 )
...
* [GNA] Added import/export names of memory layer
Added test
Added fix
[GNA] Added import/export names of memory layer
Added fix
test build
centOS fix
* Added fix version
* [GNA] Added export/import scale factor for memory layer
* [GNA] Fix comments
2021-02-24 19:05:09 +03:00
Krzysztof Bruniecki
304c31d10e
[GNA] Enable Zero Padding ( #4252 )
...
* [GNA] Enable Zero Padding
Fix CNN2D stride order
Draft pooling
* Implement CNN2D FP32 mode in GNAPlugin
* Move padding flag to Policy
* Remove inactive output rotation code from CNN2D graph compiler routine (review)
* Add ConvReluSequence tests to gnaFuncTest as DISABLED
2021-02-24 19:03:40 +03:00
Konstantin Satunin
584185f854
Added badge for overall branch state
...
One badge for all checks: including GitHub actions, Azure DevOps, Jenkins
2021-02-24 18:19:01 +03:00
Konstantin Satunin
294987b235
Fixed badge for Public CI
2021-02-24 18:14:07 +03:00
Pavel Esir
162bdde251
[MO][TF] Fixed TFSliceToSlice conversion error on Win ( #4367 )
...
* [MO][TF] Fixed TFSliceToSlice conversion error on Win, replaced int32_max with ShapeOf, minor correction in comments
* review apply: added create_op_with_const_inputs
* review apply: renamed variables, updated typehints for int64_array, float_array, float32_array
* renamed to correct_ends
* returned back check_op_attrs=True
2021-02-24 16:34:43 +03:00
Victor Kuznetsov
7ba9723242
[Stress] Add precision field to MemCheck configs ( #4362 )
2021-02-24 14:56:09 +03:00
Tomasz Dołbniak
4d9ede42ca
Floats comparison implementation in IE_Engines ( #4342 )
2021-02-24 12:10:00 +01:00
Evgeny Lazarev
5fa1e2140e
Temporary disable telemetry ( #4449 )
2021-02-24 13:27:10 +03:00
Svetlana Dolinina
5ee00a989f
add string constants '0'/'1' to bool normalizer ( #4402 )
...
* add string constants '0'/'1' to bool normalizer
* fix bug
2021-02-24 13:17:32 +03:00
Gladilov, Gleb
abe59efec9
[IE][VPU]: Enables Clamp for batch extraction ( #4442 )
...
Signed-off-by: Gladilov, Gleb <gleb.gladilov@intel.com>
2021-02-24 13:04:00 +03:00
Roman Vyunov (Intel)
a576fb6f39
[IE][VPU] Pad layer: enabling of 3D support ( #4351 )
...
* Enabling of 3D support for Pad layer
* Added tests to new test infrastructure
2021-02-24 12:14:39 +03:00
Ilya Lavrenov
ea2bbb29c5
Enabled SSE42 on ia32 by default ( #4437 )
2021-02-24 11:25:41 +03:00
Sergey Shlyapnikov
71c50c2249
[IE CLDNN] Fix to handle reshape on graph optimization stage ( #4405 )
2021-02-24 11:12:59 +03:00
Maxim Andronov
a15246e1d0
[CPU] Changed output blobs creation used output info ( #3796 )
2021-02-24 10:31:52 +03:00
Jade Cho
54a7ecb725
[IE CLDNN] Optimize reduce fsv16 primitive when out_x=out_y=1 ( #4261 )
2021-02-24 10:25:36 +03:00
Evgeny Lazarev
7420bb6cb0
Fix pad op with int input ( #4438 )
...
* Added operation ConvertLike to the MO
* Fixed transformations with Pad which insert Const with pad value of incorrect type
* Added constant folding to ConvertLike operation
* Fixed unit tests for Pad transformations to include ConverLike operations
* Update copyright year
* nGraph code style fix
* Added OV_ITT_SCOPED_TASK for ConvertLike constant folding
2021-02-24 09:56:36 +03:00
Jozef Daniecki
4d9797c1fe
Fix U1 type constant comparison in compare_functions(). ( #4461 )
2021-02-24 09:37:36 +03:00
Ivan Tikhonov
afded195ba
delete unnecessary check in validate function of TI ( #4415 )
2021-02-24 07:13:47 +03:00
dependabot[bot]
a6989bb047
Bump tox from 3.21.4 to 3.22.0 in /ngraph/python ( #4452 )
2021-02-22 17:03:23 +01:00
Konstantin Satunin
0682d773ca
Unique locations for pdb files ( #4446 )
2021-02-22 11:41:03 +03:00
