IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
5,904 Commits 38 Branches 54 Tags 1.1 GiB
c4ce6c5430
Commit Graph

5904 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Indira Salyahova
0644aaa947
[POT] Add new special metrics in aa (#9251) 
* Update utils.py

* Update utils.py
 2021-12-17 12:05:27 +03:00
Maxim Andronov
04dc16f861
[CPU] General fixes for dynamic shapes. Part 2 (#8871) 2021-12-17 11:12:07 +03:00
Min, Byungil
94c3731b50
[GPU] support multiple sum post-op of onednn kernel (#9221) 
+ Applied WA for multiple sum post-ops of nednn kernel

Signed-off-by: Min, Byungil <byungil.min@intel.com>
 2021-12-17 10:43:21 +03:00
Sergey Lyubimtsev
b41cb57773
Fix build issue for openvino wheel package on Windows (#9265) 
* Fix build issue for openvino wheel package on Windows

* fix env
 2021-12-17 10:42:21 +03:00
Ivan Tikhonov
dbd2b5dc08
ONNX/IR/Common FrontEnds Refactoring (#9174) 
* Refactor ONNX,IR,Common FrontEnds

* Rename frontends dir to frontend

* Rename frontend_manager, frontend_defs -> manager, defs; move Place, InputModel to src for Paddle FE

* remove exports for ir/input_model

* fix unit tests

* Fix unit tests

* revert ONNX_API/IR_API defines

* move manager.hpp to frontend dir

* delete common folder; rename defs to visibility; fix includes

* revert local changes

* codestyle

* fix build: set correct includes

* fix includes

* fix build; resolve review comments

* fix install paths

* correct installation folder for onnx_import

* use IE_THROW in ir frontend
 2021-12-17 08:05:30 +03:00
Mikhail Nosov
4fea4024b4
Overwrite 'model' layout with preprocessing when layout is already set (#9258) 2021-12-17 00:55:47 +03:00
Alexander Zhogov
d421bc6c4f
Azure CI: Fix "access denied" issue with certutil on Windows CC (#9269) 2021-12-16 22:09:26 +03:00
Yury Gaydaychuk
58f0c75b91
[CPU] RoiAlign: case of integer tensor handled (#8069) 2021-12-16 22:02:09 +03:00
Ekaterina Aidova
012e513f75
update POT submodule (#8740) 
* update POT submodule

* update tests
 2021-12-16 19:05:36 +03:00
Alexander Zhogov
0668ea0779
Azure CI: Fix "access denied" issue with certutil on Windows (#9262) 
* Azure CI: Fix "access denied" issue with certutil on Windows

* Use Invoke-WebRequest for GitHub
 2021-12-16 18:54:08 +03:00
Steve Yoo
bd2e3de295
Create LSTMCell-1 (#9073) 2021-12-16 17:48:10 +03:00
Vladislav Volkov
6ddc47a7ef
[CPU] Convert precisions on inputs/outputs (#8805) 2021-12-16 16:58:19 +03:00
Sergey Shlyapnikov
2514c0ef38
[GPU] Add gemm_tiled_opt i8/u8 output support (#9202) 2021-12-16 15:20:28 +03:00
Alexander Zhogov
d10e8005c0
Revert "Fix build issue for openvino wheel package on Windows (#9231)" (#9260) 
This reverts commit 460a6634fd.
 2021-12-16 14:33:56 +03:00
Vitaliy Urusovskij
2db19e6bf7
Fix c4146 warning: unary minus operator on unsigned type (#9153) 2021-12-16 13:13:05 +03:00
Sergey Lyubimtsev
460a6634fd
Fix build issue for openvino wheel package on Windows (#9231) 
* fix build issue for openvino wheel package on Windows

* revert ngraph_libs
 2021-12-16 13:01:03 +03:00
Anton Chetverikov
fa05743e01
[MO]Handle new format of fp16 irs in croupconv pass (#8921) 
* Handle new format of fp16 irs in croupconv pass

* Update condition check

* Make check more explicit
 2021-12-16 11:20:50 +03:00
Yuan Hu
4dab2662aa
[Auto plugin] add KEY_NETWORK_PRIORITY (#8146) 
* add KEY_NETWORK_PRIORITY

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* use uniqueName instead of fulldieviceName

use lamba instead of macro

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* test draft

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix compile issue

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* add test config

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* add origin select test

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* perf Counter as seperate member

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* add null device test case for select device

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix cache test failed issue

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* use a function to register priority

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* add const

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* add some comments

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* initialize AutoContext in define

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* use lock guard

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* change get() to wait()

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* add unregister in load failed

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* add const on unique name

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix compile issue

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* add test for ParseMetaDevices and fix logic issue

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* change key name to AUTO_NETWORK_PRIORITY

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix compile issue caused by API change in master

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix key incorrect test in ci

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* go back to origin set config code

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix mock test issue after Parameter changed to Any

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix macos compile issue

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* remove question comments

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* remove duplicate config

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* update test case

from the hello_query_device
CPU
   FULL_DEVICE_NAME : Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz
GPU
  FULL_DEVICE_NAME : Intel(R) Gen9 HD Graphics (iGPU)
MYRIAD.3.1-ma2480
  FULL_DEVICE_NAME : Intel Movidius Myriad X VPU
MYRIAD.3.2-ma2480
  FULL_DEVICE_NAME : Intel Movidius Myriad X VPU

currently GetMetric("MYRIAD","FULL_DEVICE_NAME")
will thrown No KEY_DEVICE_ID

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* only GPU use the fullDeviceName

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix rebase issue

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* change directory after ie test moved

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>

* fix winodws compile unit test issue

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
 2021-12-16 10:48:04 +03:00
Roman Lyamin
2068d5838b
[GPU] Add I420toRGB/I420toBGR operations (#9204) 2021-12-16 10:27:27 +03:00
Alexandra Sidorova
58be795970
[CPU] Added BF16 support for CumSum as well (#9030) 2021-12-16 10:24:57 +03:00
Maxim Andronov
d5f84ad783
[CPU] Deconvolution dynamism support (#8512) 2021-12-16 09:53:14 +03:00
Indira Salyahova
ea3f34c351
Temporary revert test layout (#9242) 
* Update test_image_loading.py

* Update test_image_loading.py
 2021-12-16 08:51:24 +03:00
Ilya Churaev
9b71a5fb70
Fixed python tests (#9238) 2021-12-16 07:52:59 +03:00
Mateusz Tabaka
40f668140e
Fix compilation error in template_plugin tests (#9248) 2021-12-16 01:52:26 +03:00
Irina Efode
d1e54d9961
[IE TESTS] Fix filters in report (#9232) 2021-12-15 23:43:24 +03:00
Dawid Kożykowski
0b9158c2b8
Extend ONNX FE for operation Softmax-8 (#9189) 2021-12-15 21:40:43 +01:00
Andrey Noskov
b643294300
[GNA] Added import/export test (#8769) 
* [GNA] Added import/export test
   - still need fixes

* Fixed inputs and const vals

* Parametrized input shape for import base test

* Deleted commented code

* Fixed input shape in test

* Fixed SF for import
 2021-12-15 23:39:31 +03:00
Mateusz Tabaka
38bbc30a29
[ONNX] Fix memleak caused by shared_ptr cyclic dependency (#9236) 
ONNXFrameworkNode had it own copy of shared_ptr<Graph> so in convert phase,
it can be used to produce real ngraph nodes (by graph->make_ng_nodes(..)).
But Graph also keeps ONNXFrameworkNodes in its cache and in consequence
its own shared_ptr, which is causing a dependency cycle.

This change removes shared_ptr<Graph> from ONNXFrameworkNode class
and moves it to decoded function runtime info, so Graph is in a single
place now and its lifetime ends when decoded function is destroyed.
 2021-12-15 21:24:35 +01:00
Steve Yoo
d9ecb108f1 Create Einsum-7 (#8982) 2021-12-15 21:46:10 +03:00
Steve Yoo
93698483b5
Migrate ExtractImagePatches-3 (#8981) 2021-12-15 21:45:18 +03:00
Steve Yoo
2619269496
Create TopK-3 (#9106) 2021-12-15 21:42:24 +03:00
Ilya Lavrenov
e6d08aef5b
Don't use EXCLUDE_FROM_ALL with samples targets (#9237) 2021-12-15 21:21:46 +03:00
Vladimir Dudnik
aa457268d4
[IE Samples] make coverity happy (#9203) 
* make coverity happy

* apply code style
 2021-12-15 17:58:06 +03:00
Ilya Churaev
9aedece398
Fixed cpu tests location (#9224) 2021-12-15 14:32:43 +03:00
Sergey Shlyapnikov
1177d2b282
[GPU] Change FQ output for first Convolution (#9200) 
* update onednn_gpu

* [GPU] Add bs_fs_yx_bsv8_fsv4 format

Co-authored-by: Kim,SungEun <sungeun.kim@intel.com>
 2021-12-15 13:15:13 +03:00
Ilya Znamenskiy
b492b59136
[GPU] Fix for conv/deconv weights calculated in runtime (#8952) 2021-12-15 12:17:13 +03:00
Indira Salyahova
2f07b98251
[POT] Support layout in pot (#9060) 
* support layout pot

* pylint
 2021-12-15 09:12:54 +00:00
Zhang Yi
4fba88d29a
Yi3/shape inference 3rd batch (#8611) 2021-12-15 10:23:19 +03:00
Ilya Churaev
e8d5cf43d0
Move ie tests (#9161) 
* Moved inference engine tests

* Fixed cmake

* Fixed paths

* Try to fix build

* Try to fix fluid tests

* Try to fix CI

* One more fix

* New issue

* Additional fix

* Disable Wall for tests

* Fixed old unit tests

* Revert "Disable Wall for tests"

This reverts commit 8b6e058f59.

* Fixed some tests

* Fixed master build

* Fix build

* Fixed some warning

* Fixed merge conflicts

* Try to fix LTO
 2021-12-15 08:50:56 +03:00
Mateusz Tabaka
0e4c50e24d
[MO] Move reverse input channels before mean/scale (#9182) 2021-12-15 00:41:21 +03:00
Egor Duplensky
3f6a026ae9
[CPU] Enable matmul deconv bin postops (#8009) 2021-12-14 19:44:38 +03:00
Irina Efode
2b9c4a7f42
[IE TESTS] Fix run of behavior GPU plugin config tests (#9178) 
* [IE TESTS] Fix run of behavior GPU plugin config tests

* Return extra removed

* remove extra lines
 2021-12-14 18:09:34 +03:00
Anastasia Popova
3cb27715e2
Partial shape serialization MO (#8927) 
* Support of partial shape in MO.

* Added partial shapes serialization in MO.

* Removed breckets.

* Fixed parameter extender in IR reader.

* Removed wrong changes.

* Added checks, added tests.

* Updated help.

* Fixed import.
 2021-12-14 17:59:19 +03:00
Tomasz Dołbniak
eab49eec8b
Backward compatible bindings for the Node class (#9193) 2021-12-14 15:33:39 +01:00
Yegor Kruglov
5c0b125554
Softmax-8 python API (#9057) 
* added ngraph api for softmax-8

* Updated comments
 2021-12-14 16:25:23 +03:00
Ilya Lavrenov
a64d694ded
Fixed ARM Android build (#9205) 2021-12-14 14:15:44 +03:00
Sungeun Kim
bf3046e3a0
[GPU] Integration Prelu fusing (#8958) 
* [GPU] Add new data format: os_is_yx_osa2_isa8_osv8_isv2

* fusing prelu

- add onednn_post_op_type::binary_relu

* update onednn_gpu
 2021-12-14 20:09:50 +09:00
Ilya Churaev
7ac9a8f88e
Enable ov core unit tests for cpu gpu devices (#9188) 2021-12-14 10:40:56 +01:00
Katarzyna Mitrus
3efe5b312e
[ONNX] Tests manifest and xfails cleanup (#9133) 2021-12-14 12:40:02 +03:00
Pavel Zamelin
a023c588ba
Fix parseArgMap for layer names with : (#8826) 2021-12-14 12:36:14 +03:00