IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
382 Commits 38 Branches 54 Tags
d32a2d63dec1af65603a0f8e117677dd37a2fd00
Commit Graph

382 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Anton Romanov
d32a2d63de Added Conda CentOS documentation 2020.4 (#1367) 
* Added Conda CentOS documentation 2020.4

* Added OS
 2020-09-01 13:17:00 +03:00
Mikhail Letavin
c8d07caf67 [IE CLDNN] Move iGPU to first position in GPU device map (#1829) 2020-08-20 13:46:23 +03:00
Mikhail Letavin
f855af885d [IE CLDNN] dp4a query that should work with new driver (#1768) 2020-08-14 15:38:24 +03:00
Denis Orlov
c880ecb78a Merge 2020.4.0.1 (#1764) 
* [GNA] Update GNA lib + propagate QoS timeout to the calling app (#1188)

* [GNA] Remove empty PWL (#1459)

* [GNA] Support timeout value set in Wait (#1499)

* [GNA] Bump GNA2 version to 1010 (#1510)

* [GNA] stored request id for completed sync infer request in order to get status later using wait() (#1458)

* stored request id for completed async infer request in order to get it's status later

* preserved status not started for multiple sequential calls to wait()

Co-authored-by: Denis Orlov <denis.orlov@intel.com>

* [GNA] Fix callbacks (#1607)

* [GNA] Bump GNA2 version to 1047 (#1614)

* merge documentation updates from 2020/4 branch (#1671)

* update system requirements (#1321)

* update release version in readme

* Doc Migration from Gitlab (#1289)

* Update FakeQuantize_1.md

* Update performance_benchmarks.md

* Updates graphs for FPGA

* Update performance_benchmarks.md

* Change DL Workbench structure (#1)

* Changed DL Workbench structure

* Update performance_benchmarks_faq.md

* Fixes in DL Workbench layout

* Fixes for CVS-31290

* [DL Workbench] Minor correction

* Fix for CVS-30955

* Added nGraph deprecation notice as requested by Zoe

* fix broken links in api doxy layouts

* Fixed POT TOC

* Update PAC_Configure.md

PAC DCP 1.2.1 install guide.

* Update inference_engine_intro.md

* Update opset.md

* Update VisionAcceleratorFPGA_Configure.md (#1378)

Updated from 2020.3 to 2020.4

Co-authored-by: domi2000 <domi2000@users.noreply.github.com>

* Updated documentation for 2020.4 (#1434)

* Updated documentation for 2020.4

* Updated Core::ReadNetwork documentation (#1178)

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
Co-authored-by: Nikolay Tyukaev <nikolay.tyukaev@intel.com>
Co-authored-by: domi2000 <domi2000@users.noreply.github.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>

* Documentation updates for 2020.4 (#1672) (#1729)

* Doc updates

* 2020.4 doc updates

* Removed </br> tag

* Minor fix

* Minor fixes

* Updated documentation for 2020.4 (#1434)

* Updated documentation for 2020.4

* Updated Core::ReadNetwork documentation (#1178)

* Fixed docs

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>

Co-authored-by: Pavel Rodionov <pavel.rodionov@intel.com>
Co-authored-by: Eugene Smirnov <eugene.smirnov@intel.com>
Co-authored-by: Alexey Suhov <alexey.suhov@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
Co-authored-by: Nikolay Tyukaev <nikolay.tyukaev@intel.com>
Co-authored-by: domi2000 <domi2000@users.noreply.github.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
 2020-08-14 12:24:36 +03:00
Andrey Zaytsev
4fa0e8aad7 Fixes links for DL Streamer samples (#1767) 2020-08-13 18:46:43 +03:00
Andrey Zaytsev
cf8450e56f Update Model_Optimizer_FAQ.md (#1753) 2020-08-13 13:16:31 +03:00
Andrey Zaytsev
648c86ee9a Documentation updates for 2020.4 (#1672) 
* Doc updates

* 2020.4 doc updates

* Removed </br> tag

* Minor fix

* Minor fixes

* Updated documentation for 2020.4 (#1434)

* Updated documentation for 2020.4

* Updated Core::ReadNetwork documentation (#1178)

* Fixed docs

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
 2020-08-07 15:29:18 +03:00
Ilya Lavrenov
b75ce14c21 Removed legacy include from plugin api (#1651) 2020-08-06 11:34:24 +03:00
Ilya Lavrenov
a9fe3c44d1 Minimized ie_paralle.hpp include in plugin api (#1650) 2020-08-06 11:25:12 +03:00
Ilya Lavrenov
8efed7cdca Updated documentation for 2020.4 (#1434) 
* Updated documentation for 2020.4

* Updated Core::ReadNetwork documentation (#1178)

* Fixed docs

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
 2020-07-23 14:17:15 +03:00
Nikolay Tyukaev
a9c6e7269f Update VisionAcceleratorFPGA_Configure.md (#1378) 
Updated from 2020.3 to 2020.4

Co-authored-by: domi2000 <domi2000@users.noreply.github.com>
 2020-07-18 12:51:10 +03:00
Nikolay Tyukaev
2f1283687b Doc Migration from Gitlab (#1289) 
* doc migration

* fix

* Update FakeQuantize_1.md

* Update performance_benchmarks.md

* Updates graphs for FPGA

* Update performance_benchmarks.md

* Change DL Workbench structure (#1)

* Changed DL Workbench structure

* Fixed tags

* fixes

* Update ie_docs.xml

* Update performance_benchmarks_faq.md

* Fixes in DL Workbench layout

* Fixes for CVS-31290

* [DL Workbench] Minor correction

* Fix for CVS-30955

* Added nGraph deprecation notice as requested by Zoe

* fix broken links in api doxy layouts

* CVS-31131 fixes

* Additional fixes

* Fixed POT TOC

* Update PAC_Configure.md

PAC DCP 1.2.1 install guide.

* Update inference_engine_intro.md

* fix broken link

* Update opset.md
 2020-07-16 15:24:27 +03:00
Alexey Suhov
023e7c2c3f update system requirements (#1321) 
* update system requirements

* update release version in readme
2020.4 		2020-07-14 20:25:39 +03:00
Alexey Suhov
34ddb70f7d fix build target name in demos for Windows (#1248) 2020-07-07 18:26:50 +03:00
Andrew Bakalin
21e092122f [VPU] WA for statis shape allocation (#1106) 2020-06-24 16:28:59 +03:00
Roman Kazantsev
92c1333653 Correct removing nodes from graph and add test for ConstToResult transform (#1083) 
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2020-06-24 15:39:08 +03:00
Roman Kazantsev
c26ec8b312 [IE] Preserve output data name after merging and update output data map (#1092) 
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2020-06-24 12:30:25 +03:00
Andrew Bakalin
32054ff180 [VPU] Support for originalLayersNames attribute in exec graph (#1073) 2020-06-23 12:19:15 +03:00
Ilya Churaev
7cff005ada Disable ref implementations (#951) 
* Add NGRAPH_EVALUATE_ENABLE flag and disable all reference implementations

* Enable some evaluate methods

* Added dynamic library with reference implementations

* Fixed tests

* Enabled unsqueeze  CF

* Removed nGraph test library

* Disable all nGraph tests to check

* Enable some reference implementations

* Added debug message

* EVALUATE true

* Revert "Disable all nGraph tests to check"

This reverts commit 38bca3ed3dfed029e892fe609ea7e48c5cfadb67.

* Enable some implementations

* Removed some TYPE_CASE reference implementations

* Fixed reshape

* Revert types for Broadcast and Add

* Disabled failing gpu_engine.user_context test

* Disabled failed nGraph tests

* Add u8 for non_zero

* Revert "Added debug message"

This reverts commit 4b9f4894f5ae9963426830ac5e5eb833af8847aa.

* Revert "Enable some reference implementations"

This reverts commit d2001a636df7504e0ad5abe5c98725ef0be07379.

Revert "Enabled unsqueeze  CF"

This reverts commit 814a8e52cb2b673446d24e54ed11af1dd3d80fad.

Revert "Enable some evaluate methods"

This reverts commit 73767b8942d857bf60317f29120c98c528344a04.

* Revert "Add NGRAPH_EVALUATE_ENABLE flag and disable all reference implementations"

This reverts commit cfaa7d7e7bf34b617f53a556d24fea2189372592.
 2020-06-23 12:17:40 +03:00
Ivan Tikhonov
06707cc53f Fix for Kaldi models with Memory layers and a batch more than 1 (#1025) 
* fix kaldi models with memory (batch > 1)

* 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 11:47:18 +03:00
Konrad Dobros
fff93d8f05 [IE CLDNN] Add work-around for 1d input to Gather (#1069) 2020-06-23 11:44:20 +03:00
Gladilov, Gleb
637ddd5dfb [IE][VPU]: Fixes klocwork issues (#1075) 2020-06-23 09:58:12 +03:00
Ivan Tikhonov
fa4c5e8e38 Fix ARM build: explicit type conversion (#1061) 
* fix arm build: explicit type conversion

* Use explicit conversion in prior_box_ie.cpp
 2020-06-22 23:37:54 +03:00
Maxim Vafin
c9fc6f0531 Fix OneHot transformation for Bert Squad opset 10 (#954) 
* Add transformation for squeezing depth input for ONNX OneHot operation because from some TF models it has shape [1] instead of []
 2020-06-22 18:58:07 +03:00
Denis Orlov
c9eb6ae62b [GNA] Initialize a local variable (#1066) 2020-06-22 18:49:22 +03:00
Alexander Chaiko
eef56ca80c [IE CLDNN] WA to 1d input for concat (#1040) 2020-06-22 15:25:17 +03:00
Gorokhov Dmitriy
36f1c00e02 [CPU] Fixed issue with unsupported reorder case for groupped convolutions (#893) 2020-06-22 14:06:53 +03:00
Konrad Dobros
5c43765011 [IE CLDNN] Fix activation implementation for fsv16 format (#1038) 
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
 2020-06-22 09:17:00 +03:00
Ilya Lavrenov
bbfc9bbc14 Deprecated IGNORE_IR_STATISTIC VPU option (#1028) 2020-06-20 10:38:47 +03:00
Pavel Rodionov
9c607528ef [GNA] Support export model with multiple inputs/outputs and Permute layer (#1024) 2020-06-19 18:06:38 +03:00
Denis Orlov
ae9e0510f0 [GNA] Additional checks (#998) 2020-06-19 13:14:32 +03:00
Edward Shogulin
76af547c17 [LPT] BERT with specific biases support & improvement (#968) 
* [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>
 2020-06-19 13:14:20 +03:00
Kamil Magierski
5e97a3123f Fix cases then const blob precision is not FP32/FP16 (#1000) 
Co-authored-by: kmagiers <kmagiers@intel.com>
 2020-06-19 13:13:19 +03:00
Andrey Dmitriev
532dec140b [GNA] fix permute 0_2_1 (#993) 2020-06-19 10:20:55 +03:00
Vladimir Paramuzov
c41c6294f9 [IE CLDNN] Fix strided slice (#953) 2020-06-19 08:23:25 +03:00
Gorokhov Dmitriy
3bbe88e659 [IE Common][WA] Skipped const folding for Convolution layer (#1002) 2020-06-19 01:25:20 +03:00
Maxim Andronov
2f3d5f68cd [CPU] fix one dims scale shift (#983) 2020-06-18 14:21:07 +03:00
Evgeny Talanin
843f81a1cc [IE TESTS] disable Some myriad tests on Win (#763) (#988) 
* [IE TESTS] disable Some myriad tests on Windisable Some myriad tests on Win

* Skip test with todo

Co-authored-by: Irina Efode <irina.efode@intel.com>
 2020-06-18 13:57:21 +03:00
Pavel Esir
c596707a09 fixed some typos in MO help (#979) 2020-06-18 11:02:28 +03:00
Konrad Dobros
cf60baf2f0 [IE CLDNN] Fix gather dimensions calculation (#960) 2020-06-18 00:31:17 +03:00
Nikita Kudriavtsev
aeb70036d7 [IE Myriad] Remove Myriad 2 from supported devices in XLink (#978) 2020-06-17 17:47:55 +03:00
Daria Mityagina
dea04dae8c [IE Myriad] - WrapInLoop fix: if data has consumer's input inside subgraph - replace them (#958) 2020-06-17 17:27:17 +03:00
Ilya Churaev
14b44803ba Fixed cpack information, removed some links (#975) 2020-06-17 17:17:10 +03:00
Andrey Dmitriev
06286f2aae [GNA] Added fix multiple output with one go to memory and test (#888) 
[GNA] Added fix multiple output with one go to memory and test

[GNA] Added fix multiple output with one go to memory and test

[GNA] Added fix multiple output with one go to memory and test

Added multi output

Update gna_pass_manager.cpp

test

[GNA] Added fix multiple output with one go to memory and test

[GNA] Added fix multiple output with one go to memory and test

[GNA] Added fix multiple output with one go to memory and test

Added multi output

Update gna_pass_manager.cpp

test

tests

[GNA] Added fix multiple output with one go to memory and test

[GNA] Added fix multiple output with one go to memory and test

Added multi output

Update gna_pass_manager.cpp

test

tests

Added pass

Test

test

tests_2

return old
 2020-06-17 11:23:56 +03:00
Ilya Churaev
97e5fc4bae Use creators only for default opsets (#932) 2020-06-16 12:25:06 +03:00
Alexey Tarakanov
47218284b2 Support fp16 networks for releases_2020_4 (#936) 2020-06-16 10:31:57 +03:00
Andrey Dmitriev
6079a35b81 [GNA] Added test for ScaleShift and fixed power layer with non-zero shift (#922) 
* [GNA] Added test ScaleShift and fixed power layer with non zero shift

added tests

[GNA] Added test ScaleShift and fixed power layer with non zero shift

* Test Assert

* rebuild
 2020-06-16 00:32:28 +03:00
Roman Kazantsev
4f4352f301 Fix preserving names of output layers after TopK NGraph transformation (#928) 
* Fix preserving names of output layers after TopK NGraph transformation (#843)

* Fix preserving names of output layers after TopK NGraph transformation

It helps to infer semantic-segmentation-adas-0001 model. See CVS-31977.

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix a test for TopK

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix TopK NGraph transformation and its test

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Disable smoke_LoadNetworkAccuracy due to sporadic failure

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2020-06-15 20:57:45 +03:00
Anastasia Kuporosova
a67d74c41f [Python API] Fix long inference (#897) 2020-06-15 16:21:41 +03:00
Ivan Tikhonov
26c563132d Revert prior box constant folding (#906) 
* Revert "Const folding and reference implementation for PriorBox(Clustered) ops (#785)"

This reverts commit 9fc818478a.

* apply codestyle for ngraph part
 2020-06-15 12:38:27 +03:00