Commit Graph

509 Commits

Author SHA1 Message Date
Andrew Bakalin
36fd61f2c9
[VPU] Fix eltwise broadcast (#1001)
* [VPU][Tests] Extend eltwise test cases

* [VPU] Fix Myriad2

* [VPU] Update firmware

* [VPU] Review fixes

* [VPU] Update old deprecated tests
2020-06-23 15:03:50 +03:00
Katarzyna Mitrus
5a2df9ebe7
[ONNX importer] Add support for Usample-8 and Upsample-9 (#967) 2020-06-23 13:11:46 +02:00
Roman Kazantsev
5ad1bf643d
Correct removing nodes from graph and add test for ConstToResult transform (#1084)
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2020-06-23 13:49:14 +03:00
Ilya Lavrenov
a3a368da64
CMAKE: cross-compilation for ia32 (#1074) 2020-06-23 12:35:17 +03:00
Irina Efode
d20246d2f1
[IE TESTS] Add Squeeze single layer test (#985)
* [IE TESTS] Add Squeeze single layer test

* [IE TESTS] Add Unsqueeze test

* Fix some comments
2020-06-23 10:05:28 +03:00
Evgenya Stepyreva
543cccc8cf
[ DTS ] MatMul (#974)
* [ DTS ] MatMul

* [ TESTS ] Dynamic MatMul inference test disabled
2020-06-23 09:58:03 +03:00
Konrad Dobros
9592be6d22
[IE CLDNN] Add work-around for 1d input to Gather (#1070) 2020-06-23 09:40:15 +03:00
Evgenya Stepyreva
f40338ff4b
[ MO ] Hard-coded Interpolate followed by concat reshape-ability fixing (#818) 2020-06-23 08:27:27 +03:00
Ivan Tikhonov
3490b985dd
Fix for Kaldi models with a batch of more than 1 (#1012)
* Fix kaldi models (batch > 1)

* ngraph codestyle

* fix ngraph to ie conversion

* Added comment

* apply review comments

* Added test for the case using the SetBatchSize function when ReadValue op is in the network

* Check status code instead of message

* Use new ngraph api
2020-06-23 08:22:12 +03:00
Ivan Tikhonov
b5be90a886
Fix Android ARM build (#1032)
* fix arm build: size_t -> uint64_t

* apply static_cast

* fix dynamic_to_static_shape_binary_elementwise.cpp file

* add static_cast in prior_box.cpp
2020-06-22 23:37:08 +03:00
Maxim Vafin
9276334144
Cherry-pick fix OneHot transformation for Bert Squad opset 10 (#1068)
* Fix OneHot transformation for Bert Squad opset 10

* Add transformation for squeezing depth for OneHot
2020-06-22 20:42:02 +03:00
Denis Orlov
85b8bdcfa6
[GNA] Initialize a local variable (#1067) 2020-06-22 18:49:38 +03:00
Pavel Rodionov
d9489d1f5d
[GNA] Support export model with multiple inputs/outputs and Permute layer (#775) 2020-06-22 18:00:29 +03:00
Vladimir Paramuzov
0ec07b2c3b
[IE CLDNN] fsv4 to fsv16 conv (#1030) 2020-06-22 17:09:39 +03:00
Alexander Chaiko
a5270192d0
[IE CLDNN] WA to inconsistency between input and const 1d tensors for concat (#1063) 2020-06-22 17:02:23 +03:00
dmitrygo
f075b98f20 [CPU] Fixed issue with unsupported reorder case for groupped convolutions 2020-06-22 16:31:01 +03:00
Andrey Somsikov
52a42624e9
Add memcheck runner script (#1031)
Script executes measurement isolated with gtest-parallel,
handles database uploading and reports generation.
2020-06-22 16:23:09 +03:00
Anton Romanov
81046cacf4
Fix samples build script (#819) 2020-06-22 16:12:02 +03:00
Kamil Magierski
f675848680
Fix cases then const blob precision is not FP32/FP16 (#1020)
Co-authored-by: kmagiers <kmagiers@intel.com>
2020-06-22 15:46:01 +03:00
Adam Osewski
491e5e9fbb
[Py] Ngraph Py API TensorIterator (#718) 2020-06-22 11:40:58 +02:00
Evgeny Lazarev
970b1301b5
Cleanup IR v7 from the MO (#1008)
* Removed back phase transformations related to IRv7

* Fixed setting value for the input port using the 'set_value' method

* Removed front and middle phase transformations related to IRv7

* Cleanup the rest of the Model Optimizer transformations from IRv7 specific transformations

* Final cleanup of the deprecated IR v7 related code

* Removed 'blobs_as_input' usage in the Model Optimizer.

* Removed function '_fuse_add' from the Model Optimizer since it is not used anymore.

* Removed 'keep_in_IR' node attribute for FakeQuantize ops in the MO

* Disabled failing gpu_engine.user_context test
2020-06-22 11:52:00 +03:00
Ilya Lavrenov
c75920ee69
Remove some stuff from legacy library (#1043) 2020-06-22 11:35:44 +03:00
Edward Shogulin
fbec64d2d2
[LPT] BERT with specific biases support & improvement (cherry-pick to master) (#1021)
* [LPT] BERT with biases support

* [LPT] Gemm biases and quantization

* [CPU] Fixed FullyConnected + Depthwise node fusing

* [LPT] FullyConnected 3D: symmetric quantization support

* [LPT] FullyConnected 3D: symmetric quantization support fix

* [CPU] Fixed FullyConnected + Depthwise fusing initialization

Co-authored-by: dmitrygo <dmitry.gorokhov@intel.com>
2020-06-20 19:06:26 +03:00
Marcin Sielski
22328d49be
Fix build issue (#923)
* Fix build issue

Why:

* Enable to build OpenVINO.

This change addresses the need by:

* Adding include directories,
* Removing IE::inference_engine_c_api dependency.

* Remove IE::inference_engine_nn_builder reference.

Why:

* Enable to build OpenVINO.

This change addresses the need by:

* Removing  IE::inference_engine_nn_builder dependency.

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2020-06-19 22:06:30 +03:00
Konrad Dobros
2a1a92d31a
[IE CLDNN] Fix activation implementation for fsv16 format (#1037)
For b_fs_yx_fsv16 format in reference kernel features for dispatch are
rounded to multiple of 16. This change adds correct check in kernel to
return work-items that are inside this dispatch padding.
Previously those work-items could corrupt memory expected to be filled
with 0s, and for parametrized activation due to bounds checking with
modulo operator they could have been corrupting actual layer output.

Issue: CVS-27672
2020-06-19 21:41:08 +03:00
Ilya Lavrenov
0b2827e027
Moved plugin to hidden folder (#999) 2020-06-19 21:04:12 +03:00
Ilya Lavrenov
79ff221957
Removed VPU option (#1027) 2020-06-19 20:55:53 +03:00
Vitaliy Urusovskij
3417004e6d
Add memcheck comparison script (#935)
Add compare_memcheck_2_runs.py compares two runs.
Add handling of broken files for `parse_memcheck_log`
2020-06-19 15:56:32 +03:00
Ilya Lavrenov
e8aed763d2
Removed Int8 normalizer and statistics (#919)
* Removed Int8 normalizer and statistics

* Removed statistics handling from tests utils

* Fixed tests compilation with statistics
2020-06-19 15:10:21 +03:00
Andrey Sokolov
4cfc4243e9
[IE VPU] use optimized ReduceMean instead of GlobalPooling (#629) 2020-06-19 14:48:53 +03:00
Ilya Lavrenov
bf3f799927
Removed shape infer extension (#917) 2020-06-19 14:48:26 +03:00
Andrey Zaytsev
d67371617a
Added opset docs (#992) 2020-06-19 14:39:57 +03:00
Maksim Doronin
a5e5af068f
[IE VPU] Evaluate DSR (#770)
* [IE VPU] Add evaluate method to DSR

* [IE VPU] Enable DSR_Reshape tests

* [IE VPU] Improvements in DSR op

* [IE VPU] Fix typo in copyBlobAccordingUpperBound

* [IE VPU] Support dynamic inputs

* [IE VPU] Use dynamic inputs in tests

* [IE VPU] Improve conditions in propogateDynamism pass

* [IE VPU] Fix Myriad2 tests via dosabling reorder

* [IE VPU] make error message more explicit

* [IE VPU] Fix Win compilation: std::stoi in <string>

* [IE VPU] Improve data transferring to work with ND tensors

* [IE VPU] Avoid ODR in myriad common test utils

* [IE VPU] Split code in propagate dynamism into separate methods

* [IE VPU] Simplify conditions in DSR parsing

* [IE VPU] Emplace data in initialStages when remove stage order
2020-06-19 13:22:31 +03:00
Gorokhov Dmitriy
61821983bf
[IE Common][WA] Skipped const folding for Convolution layer (#1005) 2020-06-19 13:03:21 +03:00
Andrey Dmitriev
29701de86b
[GNA] fix permute 0_2_1 (#991) 2020-06-19 10:21:04 +03:00
Andrey Somsikov
cdab868cbc
fix: inference-engine/ie_bridges/python/requirements.txt to reduce vulnerabilities (#1006)
The following vulnerabilities are fixed by pinning transitive dependencies:
- https://snyk.io/vuln/SNYK-PYTHON-NUMPY-73513

Co-authored-by: snyk-bot <snyk-bot@snyk.io>
2020-06-19 01:27:32 +03:00
Vladimir Paramuzov
ba8226fcb4
[IE CLDNN] Fix strided slice (#950) 2020-06-18 19:55:17 +03:00
Alexander Zhogov
6ca5cc1fe2
Azure CI: Add gtest-parallel on Lin & Mac (#980) 2020-06-18 19:20:03 +03:00
Jedrzej Hajduczenia
491173e01e
[IE CLDNN] Add pooling b_fs_yx_fsv16 int8 (#565) 2020-06-18 16:40:52 +03:00
Mikhail Treskin
438c69411a
Adding new layer tests to validation (#848)
* Add transpose, gather and reduce ops layer tests

* Fix skipping of Reduce Logical tests

* Fix compilation error with icl
2020-06-18 14:31:16 +03:00
Maxim Andronov
fafc6a485d
[CPU] fix one dims scale shift (#989) 2020-06-18 14:21:23 +03:00
Nikolay Shchegolev
26ae52b461
[Common] Static analysed issues. Part II. (#881) 2020-06-18 13:59:26 +03:00
Nikita Kudriavtsev
fbf062c46b
Changes: (#982)
- Named structures in bmp.h to avoid MSFT compiler error
- Fix for non-void function with missing return statement to avoid Intel compiler error
- Enabled "smoke_ExportUsingFileNameImportFromStreamNoThrowWithDeviceName" test
- Fix for MvncTest
2020-06-18 13:49:20 +03:00
Evgenya Stepyreva
bb44f17a06
[ DTS ] Reduces (#940) 2020-06-18 11:36:07 +03:00
Evgenya Stepyreva
88cccee0b7
[ DYN NMS ] Static & Dynamic ops; DTS transformation; VPU tests (#884) 2020-06-18 00:16:20 +03:00
Evgeny Lazarev
356e40c988
Relaxed MO requirements for "protobuf" package (#864)
Co-authored-by: Evgeny Lazarev <elazarev.nnov@gmail.com>
2020-06-17 18:31:23 +03:00
Pavel Esir
00f0247b4e
fixed some typos in MO help (#972) 2020-06-17 18:27:37 +03:00
Evgenya Stepyreva
a32d9662c2
[ DTS ] Exp, Softmax, Greater (#926)
- Dynamic to Static transformation enabled for Exp, Softmax, Greater
- Logic Elementwises default ctor sets autobroadcasting according to spec
2020-06-17 18:20:08 +03:00
Ilya Churaev
e0cf66b31a
Fixed cpack information, removed some links (#976) 2020-06-17 17:17:32 +03:00
Konrad Dobros
ccbbdcf80d
[IE CLDNN] Fix gather dimensions calculation (#959) 2020-06-17 15:07:18 +03:00