Mikołaj Życzyński
3ea1657e4f
[IE CLDNN] Activation with fused quantize bug fix ( #613 )
...
fixed bug connected with quantization fusing to activation
added scale and activation fusing support
added corresponding tests
2020-06-03 09:30:49 +03:00
Ilya Lavrenov
cdd31da1c7
Updated deprecated messages ( #715 )
2020-06-03 06:04:50 +03:00
Edward Shogulin
9f6fde9af2
[LPT] Output layers fix ( #677 )
2020-06-02 23:44:24 +03:00
Ilya Churaev
99a2423ec0
Enabled thread tests ( #717 )
2020-06-02 23:42:05 +03:00
Nikolay Shchegolev
4f6c976add
[CPU] EmbeddingBagOffsetsSum, EmbeddingBagPackedSum, EmbeddingSegmentsSum operations. ( #576 )
...
* [CPU] EmbeddingBagOffsetsSum, EmbeddingBagPackedSum, EmbeddingSegmentsSum operations.
* Performance fix
* Perf v2
* Code style
2020-06-02 21:56:17 +03:00
Anna Alberska
4c44ce9795
add PassManagerSettings & create more legible description for concat quantization exception and a test for it ( #563 )
2020-06-02 21:03:27 +03:00
Andrey Babushkin
6f69ba04c8
[Jenkinsfile] Add failFast parameter ( #721 )
...
It allows us to rebuild Jenkins build and wait until all stages are finished despite of some of them may fail
2020-06-02 20:22:25 +03:00
iimironov
a79cd75596
Imironov/cvs 31297 add yolov4 support ( #594 )
...
* Add transformation of softplus operation into log(1.0 + exp(x)).
2020-06-02 19:20:29 +03:00
Evgeny Latkin
b2816dc1ec
[IE][Myriad] Gather: add test case ( #644 )
2020-06-02 17:41:19 +03:00
Gleb Kazantaev
638c7b891c
Updated DeconvolutionIE to support dynamic shapes ( #671 )
...
* Updated DeconvolutionIE to support dynamic shapes
* Updated DeconvolutionIE to support output_shape input
* Updated ConvertConvolutions pass
2020-06-02 17:26:28 +03:00
Vladimir Paramuzov
cbe45b7d0a
[IE CLDNN] Fixed names mapping chain in runtime graph to respect original names ( #599 )
2020-06-02 17:25:41 +03:00
Vitaliy Urusovskij
1d179fdb39
Add parallel downloads to stress tests ( #678 )
2020-06-02 17:24:22 +03:00
Gleb Kazantaev
be3b4a3362
specificCreator for Transpose operation ( #713 )
...
* Updated Transpose node convertor; replaced get_vector with cast_vector
* Replaced NodeCreator with specificCreator
2020-06-02 17:15:36 +03:00
Andrey Somsikov
5776b66fb2
Enable Control Flow Guard for Windows binaries ( #714 )
...
Control Flow Guard is security option.
2020-06-02 16:46:23 +03:00
azhogov
8377c714aa
Revert "Add ittnotify from IntelSEAPI"
...
This reverts commit 0583b37a14
2020-06-02 12:52:14 +03:00
azhogov
f15096e101
Revert "Use ittnotify from thirdparty"
...
This reverts commit 3863656f44
2020-06-02 12:50:06 +03:00
Anton Chetverikov
265e3c7cba
Remove TopKnormalizer from MO IR Reader transformation_list ( #590 )
...
* Remove TopKnormalizer from transformation_list and added call of normalize_outputs to fix read/save of some models
2020-06-02 12:43:41 +03:00
Maksim Doronin
daaeaa5881
[IE VPU] Enable s32->u8 conversion ( #699 )
2020-06-02 12:20:06 +03:00
Evgeny Lazarev
278868b7a1
Align MO requirements files ( #710 )
2020-06-02 11:32:39 +03:00
Vladimir Paramuzov
dbdaaa93dd
[IE CLDNN] Quantized deeplabv3 optimizations ( #646 )
...
Enabled dilation for imad dw fsv16 kernel
Added argmax and mutable_data to fsv16 white list
Enabled byxf input for quantize scale_shift kernel
2020-06-02 09:17:39 +03:00
Somsikov, Andrey
3863656f44
Use ittnotify from thirdparty
...
VTune ittnotify lack of support aarch64. Switching to use ittnotify
in sources to support any target architecture.
2020-06-01 20:53:39 +03:00
Somsikov, Andrey
0583b37a14
Add ittnotify from IntelSEAPI
...
Adding ittnotify component of https://github.com/intel/IntelSEAPI
commit 88a56e0ecd162667c7afd2ee9969221d62a32509 (HEAD -> master, origin/master, origin/HEAD)
Merge: 6d743e1 809062a
Author: Alex <alexander.a.raud@intel.com>
Date: Wed Jul 10 15:06:46 2019 -0700
2020-06-01 20:53:39 +03:00
Andrew Bakalin
d48e0ef5a6
[VPU][NGraph] Reuse NonZero evaluate in StaticShapeNonZero ( #658 )
...
* [VPU][NGraph] Reuse NonZero evaluate in StaticShapeNonZero
* [VPU][Tests] Adopt old tests to work with reverted indices
* [VPU] Update firmware
2020-06-01 18:57:06 +03:00
Katya
41ed6f0891
[IE Python API] fix TensorDesc test file name ( #701 )
2020-06-01 15:58:05 +03:00
Maksim Doronin
69e3af4c99
[IE VPU] OutShapeOfReshape per-layer tests ( #631 )
...
* [IE VPU] OutShapeOfReshape per-layer tests
* [IE VPU] Update firmware
* [IE VPU] OutShapeOfReshape: get rid of code duplication
2020-06-01 14:51:04 +03:00
Piotr Rozen
935b48b978
Added speech recognition demo package for centOS ( #682 )
2020-06-01 14:41:45 +03:00
Vladislav Vinogradov
88264b895a
[IE] Fix build error ( #703 )
...
Missing changes in transformation library due to IE API dependency removal.
2020-06-01 13:09:23 +03:00
Mikhail Letavin
65f62945dd
[IE CLDNN] Free up first copy of weights/biases that were transferred to USM device memory ( #561 )
2020-06-01 12:01:28 +03:00
Roman Kazantsev
004f414b89
Fix SparseWeightedSum transform for Wide and Deep ( #698 )
...
WhereDecomposition transform is applied to Where operation in for-garbage sub-graph remained after SparseWeightedSum transform.
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2020-06-01 11:48:06 +03:00
Jedrzej Hajduczenia
4001d0d99f
[IE CLDNN] Prefer bf(wz)yx format for reshape ( #691 )
...
Performance improvement for icnet-camvid model
2020-06-01 10:38:33 +03:00
Ilya Churaev
d970d0494e
Removed dependency on Inference Engine from transformation library ( #680 )
...
* Removed dependency on Inference Engine from transformation library
* Change transformations export macro
* Fixed comments
2020-06-01 10:31:31 +03:00
Ivan Tikhonov
cd01ccd449
Reshape-Permute-Reshape pattern to DepthToSpace layer transformation ( #601 )
...
* implemented depth_to_space transformation
* renaming
* added functional tests, fixed mistakes in implementation of the transformation
* disable ConvertSpaceToDepth/ConvertDepthToSpace transformation for CPU plugin, enable DepthToSpaceFusion for CPU plugin only, add specific creators
* fix wrong include
* fix for functional tests: set transformation callback
* revert callback calls for CPU plugin
* move functions to .cpp file
* Apply review comments
* Apply additional review comments
* fix cast to bool type
2020-06-01 09:24:16 +03:00
Ewa Tusień
b4893945c7
[ONNX] Add Range op to ONNX importer ( #548 )
...
* Added Range op to ONNX importer.
* Disable tests for IE.
2020-06-01 05:59:39 +03:00
emmanuelattia-philips
7ec63cafe3
Ie capi callback with explicit calling convention ( #697 )
...
* Added explicit calling convention to CAPI callback
* Fixed typo spacing
* Renamed INFERENCE_ENGINE_CALLBACK to INFERENCE_ENGINE_C_API_CALLBAC to make the macro really specific to the C API
2020-05-31 23:19:37 +03:00
Gladilov, Gleb
3bf7a69df1
[IE][VPU]: Faster-RCNN fixes on myriad plugin side ( #665 )
...
* [IE][VPU]: Fixes deallocation data for cases of CMX allocator run
The final loop tries to deallocate data objects that keep shape values for
other data objects that're outputs of a model. But the case when allocator
takes only CMX data into consideration was not handled and since allocation
could not happen, it lead to fail on deallocation of a data object that has
not been allocated.
Signed-off-by: Gladilov, Gleb <gleb.gladilov@intel.com>
* [IE][VPU]: Fixes allocator with work on data to shape edges
Since there is new relationship between data objects: some
data objects may contain shape of other data object - allocator
must properly respect that. The thing is if 2 data objects are
connected in such a way, they represent unite entity (dynamic
data object) and should have the same lifetime.
Signed-off-by: Gladilov, Gleb <gleb.gladilov@intel.com>
2020-05-31 13:17:36 +03:00
emmanuelattia-philips
bad5bb30a3
Added ie_core_read_network_from_memory to the C API ie_bridge. ( #674 )
...
* * Added ie_core_read_network_from_memory to the C ie_bridge.
* Added size argument for xml_content, fixed const correctness of the weight_blob, fixed unit test
* * Removed debug message
* Changed variables names from model_xxx to weights_xxx to be more consistent with the argument name of the tested function.
* Added a description for xml_content_size in ie_core_read_network_from_memory.
* * xml_content is now passed as uint8_t
* reading function factorized in the unit-test
2020-05-31 02:25:39 +03:00
Ilya Lavrenov
3d42871523
Added dependency on ONNX reader ( #693 )
2020-05-30 15:15:20 +03:00
Denis Orlov
9af51a165f
[GNA] Workaround support for callbacks ( #591 )
2020-05-30 00:43:42 +03:00
Edward Shogulin
e2729b87f3
[LPT] Convolution regression tests ( #543 )
...
* [LPT] Base test infrastructure extending & Convolution test
* [LPT] LPT test infrastructure refactoring
2020-05-29 22:56:58 +03:00
Anastasia Kuporosova
3ef1a26174
[IE TOOLS] Use input_info in python benchmark app ( #660 )
2020-05-29 21:28:17 +03:00
Anastasia Kuporosova
cbad43f3a5
[Python API] Fix PreProcessInfo tests ( #690 )
2020-05-29 21:20:16 +03:00
Vladimir Gavrilov
3a24eb6a62
MO fails generating IR from XLNET model due to a bug in the transformation ConvertGroupedStridedSlice ( #625 )
...
* Small fix in the transformation ConvertGroupedStridedSlice. Now VariadicSplit is generated only in the case when node has at least 2 output nodes.
* Added unittests for the case when there is only one StridedSlice.
2020-05-29 21:01:09 +03:00
Ilya Churaev
963f55a189
Fixed CODEOWNERS paths ( #684 )
2020-05-29 20:57:32 +03:00
Vladimir Paramuzov
f7052a107d
[IE CLDNN] Optimized FQ kernel in fsv16 layout ( #573 )
...
- Optimized FQ kernel in fsv16 layout. Enabled scaleshift transform for FP16 precision
- Disabled activation_opt kernel with fused ops in some cases
2020-05-29 20:10:30 +03:00
Evgenya Stepyreva
6cfa77223e
[ nG ] Added F16 folding support ( #686 )
2020-05-29 19:09:01 +03:00
Ilya Churaev
11bd4f8a42
Do not use ONNX reader if ONNX importer was disabled ( #683 )
2020-05-29 17:46:40 +03:00
Anna Khakimova
be3b711972
Pre-processing(GAPI): AVX2/AVX512 implementation of 3C/4C Resize via universal intrinsics. ( #612 )
2020-05-29 15:44:12 +03:00
Ilya Lavrenov
011128cb54
Python: Fixed installation rules to install additional .so files generated from .pyx ( #676 )
2020-05-29 14:45:59 +03:00
Katarzyna Mitrus
5f8f9ec108
[nGraph] Reorder nGraph LSTMSequence inputs and outputs dimensions ( #560 )
...
* Reorder nGraph LSTMSequence input/outpt dimensions
* Update nGraph pythonAPI for LSTMSequence
* Reorder axes in ONNX importer LSTM
* Tests update
* Fix clang warning
* Use opset3 namespace
* Style apply
* Tests update
* Use opset1 namespace
* Remove usage of GetOutputElement in ONNX importer LSTM
* Remove opset0 header
* Use Node::output()
2020-05-29 14:29:18 +03:00
Ivan Tikhonov
a4f13ae9fe
fix constant folding of Concat op ( #675 )
2020-05-29 14:09:20 +03:00
