IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,222 Commits 38 Branches 54 Tags
86e39a6775fc47694cbbaf85d11cd83883d8ba5a
Commit Graph

1222 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Artyom Anokhov
86e39a6775 [Scripts] Fix setting PYTHONPATH logic (#2305) 
* setupvars.sh: Added logic for exporting path env in case if it not defined

* setupvars: Removed duplicated colon

* install_openvino_dependencies: Updated copyrights

setupvars.bat: Updated notification about incorrect Python version. Removed checking ICC2019
setupvars.sh: Removed logic with choosing higher version of installed Python. Added dynamic detecting python3 major and minor version for setting path. Add checking minimum required Python version(now 3.6)
 2020-09-17 16:41:46 +03:00
Tomasz Dołbniak
2645421df6 Clone a specific tag for pybind11 (#2296) 2020-09-16 23:04:42 +03:00
Zoe Cayetano
9b1961502b Update get_ov_update_message.py (#2286) 2020-09-16 20:33:39 +03:00
Vladimir Gavrilov
2023a7cd81 Fixes for Interpolate-4. (#2281) 2020-09-16 19:41:37 +03:00
Vladislav Volkov
105cd18d0b Fix for static PartialShape detection algorithm (#2177) 2020-09-16 18:09:07 +03:00
Maksim Doronin
92d19291c8 [IE][VPU]: KW fixes (#2186) 
* Some KW fixes
* Fix printTo in vpu ngraph transformations
 2020-09-16 18:08:55 +03:00
Vladislav Vinogradov
191e9f7f72 [IE][TESTS] Fix compareRawBuffers and compareBlobData methods (#2246) 
Use `<=` comparison instead of `<` with thresholds.
This allows to use `0` threshold for bit-exact comparison.
 2020-09-16 18:00:06 +03:00
Alexander Novak
126c2600bb Add VPUX configuration to compile_tool (#2248) 2020-09-16 17:59:17 +03:00
Alexey Suhov
b922800ae2 update OpenCV version to 4.5.0 (#2260) 2020-09-16 16:12:59 +03:00
Maxim Shevtsov
272b17f5d9 Reverting devicePriorities to be vector and respect the order, as opposed to the incorrect (recent?) refactoring that introduced the unordered_map that effectively ignores the priorities (#2251) 2020-09-16 16:12:40 +03:00
Evgeny Latkin
b89e7d69dd [IE][VPU]: update firmware 1381 (#2236) 2020-09-16 16:05:43 +03:00
Ilya Churaev
528e6f9328 Fixed KW warning and review issues (#2262) 2020-09-16 15:33:10 +03:00
Gorokhov Dmitriy
ebf009d1a1 Revert "[IE TESTS] dynavic batch for mvn layer (#1010)" (#2256) 
This reverts commit 2e3378c50f.
 2020-09-16 14:11:34 +03:00
Andrew Bakalin
d604a03ac0 [IE][VPU]: Fix K propagation through Reshape (2021.1) (#2180) 
* Fix K propagation through Reshape
* Add test cases
 2020-09-16 12:42:15 +03:00
Nikolay Shchegolev
e7e82b9eb7 Statically analyzed issues. (#2261) 2020-09-16 12:32:20 +03:00
Maxim Kurin
f5bd16990e [IE][VPU][OpenCL] 2021.1 release compiler (#2189) 2020-09-16 00:46:27 +03:00
Evgenya Stepyreva
488f2dd916 [DOC] Reshape feature (#2194) 2020-09-15 21:24:25 +03:00
Evgeny Talanin
79853baf28 Add exposing function signatures via Cython (#2244) 2020-09-15 20:19:57 +03:00
Svetlana Dolinina
6c5e0cfaa4 Duplicate PR 2167 for release branch: GatherTree description was extended and outdated link fixed (#2235) 
* add more alrifications to description

* move clarification to comment

* pseudo code become more accurate

* review changes
 2020-09-15 19:36:51 +03:00
Maksim Doronin
d239b2584c [IE][VPU]: Remove the second call of ngraph::CommonOptimizations (#2221) 
* Remove the second call of ngraph::CommonOptimizations in myriad plugin
* Reuse code with vpu ngraph transformations
 2020-09-15 17:08:46 +03:00
Roman Vyunov (Intel)
28a733b771 [IE][VPU]: Workaround to support parameter Beta for layer Swish (#2207) 
* Workaround to full support Swish layer. It is faster than native Swish for now.
 2020-09-15 14:44:38 +03:00
Ilya Churaev
7bba2a9542 Fixed output names for case with redundant ops before result (#2209) 2020-09-15 14:00:27 +03:00
Ilya Churaev
9b7e22f49a Fix QueryNetwork for networks with KSO (#2202) 
* Added a test to reproduce QueryNetwork with KSO

* Fixed QueryNetwork for networks with KSO

* Added additional test
 2020-09-15 14:00:09 +03:00
Ilya Churaev
a4dc5c89f3 some nGraph KW fixes (#2176) 
* Removed redundant methods

* Fixed KW for linux
 2020-09-15 13:59:42 +03:00
Ilya Churaev
fef1803a86 Extend error message (#2174) 2020-09-15 13:59:15 +03:00
Tomasz Dołbniak
e94393df10 FakeQuantize + Mul fusion (#2133) 
* FQ+Mul fusion transform skeleton

* FQ+Mul fusion transform tests prep

* Basic UT for the transform

* Basic implementation of the transform

* Parametrized UTs for FQMul transform

* Parametrization of FQ+Mul UTs

* Make sure that the shapes of constants match

* Check if the mul constant matches FQ data

* CentOs compilation error fix

* PR feedback and adjusted tests

* NHWC layout of the mul constant

* UT: FQ output limits 4D

* Redundant CF pass removed

* Rewrite the graph in a different way

* Shape checking infrastructure skeleton

* Handle some negative cases

* Check the rt info in the fusion test

* Fuse all Mul nodes detected after FQ node

* Dont cast the original FQ node

* Dont throw if CF fails in new output range calculation

* More UTs

* Accept any type of input to FQ in the transformation

* Test the fusion when all FQ inputs are non-const

* Fusion test when only one output limit is const
 2020-09-15 11:33:35 +03:00
Artyom Anokhov
2e4f46e1fd [Scripts] Fixing issue with exporting path-like env when it undef (#2164) 
* setupvars.sh: Added logic for exporting path env in case if it not defined

* setupvars: Removed duplicated colon

* Kept quotes where they were

* setupvars: updated copyrights
 2020-09-14 19:49:42 +03:00
Edward Shogulin
177906b99a [LPT] Copy constant with several outputs before blob update (#2197) 
* [LPT] Copy constant implementation

* [LPT] the same Constant ops as FQ interval boundaries
 2020-09-14 18:32:37 +03:00
Anna Alberska
6d38488462 [GNA] fix scale factor calculation for unfused bias after fc (2021.1) (#2195) 
* [GNA] fix scale factor calculation for unfused bias after fc

* change check

* add test

* apply requested changes

* cpplint fix

* apply test changes

* modify model for test to match ::op::
 2020-09-14 17:30:12 +03:00
Kamil Magierski
db5aa551af LSTMCell test [GNA] LSTMCell fix for GNA (#2216) 2020-09-14 17:29:45 +03:00
Denis Orlov
6d90eedbd2 [GNA] Safety fixes (#2193) 2020-09-14 12:10:25 +03:00
Sergey Shlyapnikov
a91e256d27 [IE CLDNN] Memory allocation optimizations (#2178) 2020-09-11 15:55:46 +03:00
Sergey Shlyapnikov
bdd0247362 [IE CLDNN] Fix stack-use-after-scope issue (#2150) 2020-09-10 18:59:15 +03:00
Gleb Kazantaev
18abd6cfd7 Updated ConvertPrecision pass not to make extra copy of Constant data (#2108) 2020-09-10 17:11:10 +03:00
Kate Generalova
6c3f7fd654 [samples] remove unused ngraph (#2156) 2020-09-10 16:04:13 +03:00
Nikita Kudriavtsev
62c7ca9698 [IE Myriad][#38489] Reduce test scope for Swish layer (#2163) 2020-09-10 15:47:20 +03:00
Alexey Fadeev
5c4f918db2 Fixed differences between glib versions (#2153) 2020-09-10 15:11:08 +03:00
Anton Dudchenko
c7633e7016 [IE][VPU]: Support ngraph::Function in VPU QueryNetwork (#1929) 
* Support ngraph::Function in VPU QueryNetwork
 2020-09-10 14:49:19 +03:00
Nikita Kudriavtsev
ef2581d5c6 [IE Myriad][IE Tests] Activation layer's constants parametrization. (#2071) 
CI passed: https://gitlab-icv.inn.intel.com/inference-engine/product-configs/merge_requests/870
 2020-09-10 12:56:21 +03:00
Kate Generalova
d4d460101d fix #38545 remove CPU network layer check for py samples (#2145) 2020-09-10 12:44:13 +03:00
Mateusz Tabaka
926be83568 Add support for custom onnx operators: DetectionOutput, Normalize and… (#2064) 2020-09-10 11:27:12 +02:00
Maxim Kurin
362080b5be [IE][VPU][Custom CL]: Fix binary convolution3x3 3d transaction (#2144) 
* Fix binary_convolution3x3.cl kernel & test
 2020-09-10 11:55:32 +03:00
Ilya Znamenskiy
3797a28e65 [IE CLDNN] Fully connected MMAD kernel optimizations (#2115) 2020-09-10 08:56:04 +03:00
Nikolay Shchegolev
5403003d02 [CPU] statically analyzed issues. (#2139) 2020-09-10 08:35:32 +03:00
Anton Voronov
0e34b392ee [CPU] Supported depthwise 6d, 7d, ..., added test (#971) 2020-09-10 08:33:38 +03:00
Ilya Churaev
27ca6be728 Fixed addOutput behavior for experimental ops (#2138) 2020-09-10 06:14:11 +03:00
Gorokhov Dmitriy
d78fd196e8 [CPU] Fixed quantization post op memory leak (#2101) 2020-09-09 18:59:37 +03:00
Maxim Andronov
b3829c58a8 [CPU] add const and precision check quantize ranges (#2074) 2020-09-09 18:57:58 +03:00
Evgenya Stepyreva
3af3e459c3 [ IE ] ExperimentalDetectron shape infer fix (#2143) 2020-09-09 18:25:53 +03:00
Anna Likholat
53c03db307 [JAVA] Code style check added (#1984) 2020-09-09 17:49:23 +03:00