IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
5,012 Commits 38 Branches 54 Tags 1.1 GiB
0c1efd8e7a
Commit Graph

5012 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
myshevts
0c1efd8e7a increasing the timeout to test the ssd_* models perf (timeout?) issues 2021-10-27 16:08:15 +03:00
myshevts
69160fd282 code style 2021-10-26 16:51:03 +03:00
Roman Lyamin
5125c66179 [IE CLDNN] Disable bs_fs_yx_bsv16_fsv16 format for int8 convolution 2021-10-26 16:49:29 +03:00
myshevts
4ddf63ab5f moved the bacthed request statring ( along with input copies) to the dedicated thread 2021-10-25 18:09:12 +03:00
myshevts
74040fed95 fix the pre-mature timeout restaring via waiting for batch1 requests completion 2021-10-25 17:30:50 +03:00
myshevts
7560a9319e allowing the auto-batching only with tput hint to let more conventional tests pass 2021-10-21 19:04:28 +03:00
myshevts
e11c6cb0ad accomodate the config per device-id, after rebase to the latest master 2021-10-21 13:43:26 +03:00
myshevts
0de3055825 inputs outputs copies, works with AUTO and demo now 2021-10-21 10:45:48 +03:00
myshevts
294e202a05 explicit _completionTasks,reverting BA to use the timeout 2021-10-21 10:45:47 +03:00
myshevts
8cae121764 quick-n-dirty timeout impl 2021-10-21 10:45:46 +03:00
myshevts
3d2cd5fb71 stub pipeline task to comunicate the readiness rather than promise/future 2021-10-21 10:45:45 +03:00
myshevts
c5c18f9eac testing which models perform badly due to kernels and NOT (batched) footprint 2021-10-21 10:45:44 +03:00
myshevts
26359812e4 code style 2021-10-21 10:45:44 +03:00
myshevts
1c98dbe244 quick-n-dirty batch footpint vs device total mem 2021-10-21 10:45:43 +03:00
myshevts
776624ff2a WIP:moving the auto-batching to the icore to let the MULT/AUTO support that, ALLOW_AUTO_BATCHING as a conventional config key. still fials hot device swap 2021-10-21 10:45:42 +03:00
myshevts
ac21d71321 experimenting with DG1 on the batch size selection, also collecting the mem footprint 2021-10-21 10:45:41 +03:00
myshevts
e7b743ac33 changes from rebasing to the latest master 2021-10-21 10:45:40 +03:00
myshevts
f27f922e19 eearly experiments with model mem footprint 2021-10-21 10:45:39 +03:00
myshevts
f1b8e586ac replaying modified version of actual batch selection 2021-10-21 10:45:38 +03:00
myshevts
29449f1cf0 applying/accomodating the API changes after rebase to the master 2021-10-21 10:45:38 +03:00
myshevts
9357d3fd3d auto-batching POC squashed (all commits from auto-batch-2021.3 branch) 
(cherry picked from commit d7742f2c747bc514a126cc9a4d5b99f0ff5cbbc7)
 2021-10-21 10:45:37 +03:00
Gleb Kazantaev
f8439eeed8
Update Transformations tests to check tensor and node names (#8100) 
* Check tensor names in pass tests

* Update Transformations tests to check tensor and node names

* Check input node names; default TENSOR_NAMES comparison; fix transformations to keep node names
 2021-10-21 10:41:37 +03:00
Vladislav Golubev
243efa465e
[Transformations] FCTransformations: leftovers (#8062) 2021-10-21 10:38:14 +03:00
Mingyu Kim
cb26462288
Reshape activation zero points tensor to one element tensor. (#8105) 
Co-authored-by: Jade Cho <jade.cho@intel.com>
 2021-10-21 16:26:49 +09:00
Dawid Kożykowski
64340ec2fc
[ONNX] ConvInteger (#8042) 2021-10-21 08:58:20 +02:00
David Nam
e9777a6da0
Migrate range1,4 to template plugin test (#8023) 
* Migrate range1,4 to template plugin test

* Fix cpplint issue

* Return NULL in default case in range test

* Fix cpplint error
 2021-10-21 09:27:56 +03:00
David Nam
f80005f513
Migrate arithmetic2 to template plugin test (#8053) 2021-10-21 09:27:06 +03:00
Luwei Zhou
c2512f8dc5
[shape_infer]Implement ExperimentalDetectronDetectionOutput shape infer. (#7903) 
* Implement ExperimentalDetectronDetectionOutput shape infer.

Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>

* Update on the review comments.

* Update based on review
 2021-10-21 09:15:16 +03:00
Ilya Churaev
83fe59bd3e
Moved SO Loader to util library (#8017) 
* Moved SO Loader to util library

* Removed redundant headers

* Fixed code style

* Fixed build

* Fixed templateFuncTests

* Removed SharedObjectLoader from util library
 2021-10-21 06:47:48 +03:00
Ilya Churaev
0f3c10c810
Infer request api (#7962) 
* Introduce new API

* Fixed comments

* Fixed code style

* Introduce some new API

* Fixed code style

* Reverted names

* Exend OVExecNetwork tests

* Changed executable network API

* Fixed tests

* Fixed comments

* Fixed style

* More tests

* Applied changes

* Fixed windows build

* Fixed typo

* Fixed some tests

* Fixed code style

* Fixed pre-proc tests

* Fixed documentation comments

* Added more comments

* Fixed code style

* Remove friend

* Removed find tensor API from internal classes

* Avoid old API in new constructors

* Fixed CPU tests

* Fixed comments

* Fixed template tests

* Extended test cases

* Revert data creation

* Fixed GNA and GPU plugins

* Fixed comments

* Fixed GNA tests

* Try to fix tests for GPU

* Fixed GNA tests

* Fixed GNA

* Try to fix Myriad tests

* Removed check to see an exception message

* Fixed HETERO import

* Reverted mkl-dnn submodule

* Fixed clang-format

Co-authored-by: y <ilya.lavrenov@intel.com>
 2021-10-20 22:08:55 +03:00
Ivan Tikhonov
a9b773e4b2
[TF FE] Port Transpose Sinking transformation (#8043) 
* TransposeSinking transformation

* Enable TransposeSinking

* apply codestyle

* Add unit tests
 2021-10-20 20:31:32 +03:00
Yuan Hu
3a909a7f5f
replace AUTO_DEVICE_LIST with MULTI_DEVICE_PRIORITY in test cases (#7932) 
* replace AUTO_DEVICE_LIST with MULTI_DEVICE_PRIORITY in test case

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

* remove KEY_AUTO_DEVICE_LIST

Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
 2021-10-20 19:44:58 +03:00
David Nam
eb7d7e4413
Migrate arithmetic1 to template plugin test (#8052) 
* Migrate arithmetic1 to template plugin test

* Remove backend tests of arithmetic1
 2021-10-20 19:16:51 +03:00
Ivan Tikhonov
5cd63f47e5
Fix TI Serialization for IR 11 (#7977) 
* Fix TI Serialization for IR 11

* Enable TI Serialize tests with IR10
 2021-10-20 16:30:22 +03:00
Ilya Sharikov
028d78a90f
Update paths to OMZ tools (#8072) 2021-10-20 14:39:28 +03:00
Mikhail Nosov
e976a221f5
[OV2.0 Preprocessing] NV12 ref implementation fixes + tests with legacy CNNNetwork (#7985) 
* NV12 Ref impl: Align with Legacy NV12 conversion
Little-endian tricks are completely not needed finally

Basic tests of OV20 preprocessing vs Legacy preprocessing:
- Mean/Scale
- Resize (Linear vs Bilinear)
- NV12 color conversion

* Register Template plugin in legacy core before CNNNetwork compliance test
NV12: round to nearest integer for 'u8' mode
Fix preprocess-reference NV12 tests (swap U & V)

* Decreased default threshold and use random distribution for inputs generation

* Added tests RefImpl vs OpenCV - NV12 color conversion
Added CPU accuracy tests + nightly (including all RGB color combinations)

* Fix build issue after rebase

* Remove test code

* Fix comments
Disable OpenCV tests on CI (some machines can't load opencv_imgproc during test)
 2021-10-20 13:39:46 +03:00
Anton Voronov
8280a1a045
[CPU] cleanup after oneDNN v2.3 migration (#7933) 2021-10-20 13:23:25 +03:00
Pavel Esir
9f64f77a3c
[MO] allow zero size dimensions in Slice output (#7791) 
* allow zero size dimensions in Slice output

* updated comments regarding 0-size dimensions
 2021-10-20 13:16:06 +03:00
Maxim Andronov
21090f47b2
[CPU] Reshape, Squeeze, Unsqueeze dynamic done (#7831) 2021-10-20 12:33:29 +03:00
Victor Kuznetsov
5628a51c1f
timeout changes (#8067) 2021-10-20 12:02:39 +03:00
Maxim Andronov
984fda6305
[CPU] Select dynamic done (#7818) 2021-10-20 11:38:48 +03:00
Wilson Seok
11ddd731b7
Migrate ngraph backend test/group convolution (#8089) 
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now

* update repo

* add op reference test of group_convolution and group_convolution_backpropdata

* update reference test of group_convolution/group_convolution_backpropdata and remove their ngraph backend test
 2021-10-20 11:20:11 +03:00
Wilson Seok
132ae33de0
Migrate ngraph backend test/deformable convolution (#8045) 
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now

* update repo

* add initial version of op reference test of deformable convolution

* update reference test

* update reference test 2

* update deformable_convolution referencet est

* add deformable_convolution_opset8 op reference test

* update skip_test_config.cpp

* remove backend test and add visitor api test

* merge test code of deformable_convolution v1 and v8 in a single file

* merge deformable_convolition_opset8 of visitor api test into single file
 2021-10-20 11:19:19 +03:00
Jan Iwaszkiewicz
17914d516a
[ONNX] QLinearMatMul (#7418) 
* Add qlinear_matmul files

* Extend matmul helpers

* register op in bridge

* Add test for 2d

* newlines at end of files

* Codestyle changes

* Re-use of nodes inputs

* Remove xfails

* Register as set1

* reshape inputs as scalars

* remove fixed xfail issue residues

* update changes to fit the newest master

Co-authored-by: dkozykowski <dawid.kozykowski@intel.com>
 2021-10-20 11:02:14 +03:00
Gleb Kazantaev
88f56669e2
Remove Provenance tags (#8101) 2021-10-20 10:28:58 +03:00
Ilya Lavrenov
4f203b9a2e
Fixed ENABLE_NCC_STYLE condition (#8092) 2021-10-20 09:01:59 +03:00
Kelvin Choi
c454e414bb
[GPU] Add unittests for fusing reorder bfyx to fsv32 (#8080) 
Signed-off-by: Kelvin Choi <kelvin.choi@intel.com>
 2021-10-20 13:57:18 +09:00
Mingyu Kim
a1c77879d5
[GPU] Select impl_type after layout propagation (#8054) 
pooling layout is not chosen initially in reorder_inputs.
In that case, cldnn pooling is chosen instead of onednn.
 2021-10-20 12:19:46 +09:00
hyunback kim
6a63cc1936
[GPU] Apply fusing/reshape changes into master. (#8002) 
* [GPU] Apply fusing/reshape code into master.

Merge prepare_primitive_fusing, handle_reshape into master.

Signed-off-by: hyunback <hyunback.kim@intel.com>

* Apply code-review.

Signed-off-by: hyunback <hyunback.kim@intel.com>

* Apply code-review

Signed-off-by: hyunback <hyunback.kim@intel.com>
 2021-10-20 09:08:39 +09:00
Roman Lyamin
03424849fb
[GPU] Add separate config for each device (#7421) 2021-10-19 16:51:38 +03:00