[OV20] Reference implementation for NV12toRGB and NV12toBGR operations by nosovmik · Pull Request #7601 · openvinotoolkit/openvino

nosovmik · 2021-09-22T15:15:36Z

Details:

Reference implementation for NV12toRGB and NV12toBGR operations
No preprocessing code, just new operations with tests

Tests:

ngraph: visitor + type_prop
template plugin: reference implementation
inference-engine: shared tests for plugins
cpu plugin: compare with ref implementation tests

Tickets:

62174

ngraph/core/include/ngraph/ops.hpp

ilya-lavrenov · 2021-09-22T15:42:30Z

BTW, can we also tests to compare with old G-API preprocessing?
It's a kind of compatibility tests:

create pipeline with new preprocessing and perform inference
configure CNNNetwork to accept NV12Blob and performance inference on the same data
the result should be the same. It will guarantee that users migrated from old preprocessing to new one will have the same experience

Probably, it can be done separatelly.

...tests/functional/plugin/cpu/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp

Tests: - ngraph: visitor + type_prop - template plugin: reference implementation - inference-engine: shared tests for plugins - cpu plugin: compare with ref implementation tests

ngraph/core/include/openvino/op/nv12_to_bgr.hpp

Added appropriate shape inference tests Added error test for >2 inputs Fixed failed CI tests

+ Try to fix Ninja build

ngraph/core/include/ngraph/op/nv12_to_rgb.hpp

ngraph/core/reference/include/ngraph/runtime/reference/convert_color_nv12.hpp

# Conflicts: # ngraph/core/src/preprocess/preprocess_steps_impl.cpp

ilya-lavrenov · 2021-09-28T09:54:27Z

@jane-intel @ilyachur @ArtemySkrebkov-intel please, have a look

docs/template_plugin/tests/functional/op_reference/convert_color_nv12.cpp

...nctional/shared_test_classes/include/shared_test_classes/single_layer/convert_color_nv12.hpp

ngraph/core/include/openvino/op/util/convert_color_nv12_base.hpp

ngraph/core/include/openvino/op/nv12_to_rgb.hpp

ilyachur · 2021-09-29T03:57:48Z

ngraph/core/src/op/util/convert_color_nv12_base.cpp

+}
+
+bool ov::op::util::ConvertColorNV12Base::is_type_supported(const ov::element::Type& type) const {
+    return type.is_dynamic() || type.is_real() || type == ov::element::u8;


Why don't we support integer types?

I checked this case with @jane-intel while reviewing 'operation specification'. My original proposal was to support only u8 & fp32, and it was updated to 'u8 or any supported floating point type'. See PR #7595

BTW, OpenCV usually supports u8, u16, f32

@jane-intel can you please comment on this? User can do 'convert_element_type' if needed, but I'm also ok to update just approved specification and update to 'u8 + any_float + any_number_16bit_or_bigger'

I was convinced that we could decode NV12 only to the list of types we listed in the spec. but if there is another use case -- then let's all them to spec and here also

Currently specification states "u8 or any supported floating-point type." - here is checked exactly this (+ dynamic type for evaluation on inference stage)

Observed issue with shuffling Y pixels on little-endian systems, added tests

ngraph/core/src/op/nv12_to_rgb.cpp

e-nugmanova · 2021-09-30T13:00:41Z

ngraph/core/src/op/util/convert_color_nv12_base.cpp

+}
+
+bool ov::op::util::ConvertColorNV12Base::is_type_supported(const ov::element::Type& type) const {
+    return type.is_dynamic() || type.is_real() || type == ov::element::u8;


I was convinced that we could decode NV12 only to the list of types we listed in the spec. but if there is another use case -- then let's all them to spec and here also

e-nugmanova · 2021-09-30T13:01:30Z

ngraph/core/src/op/util/convert_color_nv12_base.cpp

+        }
+        // Set shape based on UV shape, if Y are dynamic
+        if (shape_uv.rank().is_static()) {
+            if (out_shape[N_DIM].is_dynamic()) {


why do we need to check that?

If batch for Y is not defined, but batch for UV is defined - then use batch value from UV

we should use ngraph::Dimension::merge

ilya-lavrenov · 2021-09-30T13:34:21Z

@nosovmik we decided to merge. Let's fix @jane-intel 's remarks in PR with preprocessing step itself.

Will be fixed in next PR

* Temporary disable sporadically failed test * Looks like skip test config didn't skip the test

commit 950c40d9261279824f9ae2a7b712c0ac84546f47 Merge: 249364e16 5eaf02972 Author: Efode, Irina <irina.efode@intel.com> Date: Thu Oct 7 22:27:46 2021 +0300 Merge remote-tracking branch 'upstream/master' into plugin commit 249364e1663bf773a21e72d0d8d625a115cb0f08 Author: Efode, Irina <irina.efode@intel.com> Date: Thu Oct 7 22:26:27 2021 +0300 ov separating commit 5eaf0297234323a8fd9171af128061f8ace5baea Author: Andrey Somsikov <andrey.somsikov@intel.com> Date: Thu Oct 7 22:00:39 2021 +0300 Fix coverity linux pipeline (#7879) Exclude python, contrib, and samples from the build. Clean up unnecessary dependencies installation. Publish artifacts. commit ec126c6252aa39a6c63ddf124350a92687396771 Author: Ilya Lavrenov <ilya.lavrenov@intel.com> Date: Thu Oct 7 18:59:24 2021 +0300 old / new API precisions conversions, old_api_map applying (#7853) * Enabled support of IR v11 in IR frontend * Enabled serialization to v11 * Added indexes for Inputs/Outputs * Fixed typo * Fixed code style * Fixed deserialization tests * FIxed typo * Avoid changes in the original serialized function * Split IRv7 and IRv10 code * Added preprocessing steps to read network * Added preprocessing for new API for IR v10 * clang-format * Updates for compiler flags * Reverted some changes * Fixed TI tests * Removed version from the function and indexes from parameters/results * Restore function version * Clone function rt info * Removed v11 version * Added serialization of old API map in ngraph. * Changed order type to int64_t. * Fixed uint64_t error, added comments. * Apply suggestions from code review Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com> * Read old_api_map * Added tests with undefined type and empty order. * Fixed reprocessing * Updated gitignore * Updated serialize / deserialize tests * Added set, get and has methods. * Fix in tests. * Applied old_api_map tests * Fixed empty convert_layout * Allow Layout from empty string * Fixed clang-format * Export FEM::load_by_model * Apply suggestions from code review Co-authored-by: Ilya Churaev <ilyachur@gmail.com> * Made inline methods, changed to shared_ptr. * Small fix. * Moved methods to header file. * Small fix. * Applied post-processing * Fixed review comments Co-authored-by: Ilya Churaev <ilya.churaev@intel.com> Co-authored-by: Anastasia Popova <anastasia.popova@intel.com> Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com> Co-authored-by: Ilya Churaev <ilyachur@gmail.com> commit 05cd830de5b8ffdd0cea6ef667095868eaa2fb2f Author: Eugeny Volosenkov <eugeny.volosenkov@intel.com> Date: Thu Oct 7 18:40:57 2021 +0300 Move eval tests to template tests (#7132) * Add If implementation with reference * fix test * fix comments * Fix validate_and_INFER_TYPES * rewrite tests for dynamic cases * Fix ci failed * add comentaries for validate_and_infer_types * fix api * Added ngraph checks and delete copied op from opset8 * code style fix * fix code style * add checkers to reference * add has_evaluate * fix eval * Fix code style * fix code style * Add template plugin tests * fix code style * delete boolean * fix IfParams * Fix comments * intermediate commit * delete eval test * add common header * Fix codestyle * fix set_invariant_input/set_body_output * fix code_style * fix codestyle * delete validate_and_infer_types from type prop tests * delete comments commit 465304a10877755b58eb37d1436a86bd6bfd8e31 Author: Egor Duplensky <egor.duplenskii@intel.com> Date: Thu Oct 7 18:32:09 2021 +0300 [CPU] Remove get_friendly_name WA (#7589) The ngraph issue has been fixed. WA is not needed anymore. commit bdc8208dd3d35e519f9475ed99ba829921f3fe16 Author: Anton Dudchenko <anton.dudchenko@intel.com> Date: Thu Oct 7 15:57:13 2021 +0300 [IE][VPU] Update FW (#7499) Update FW with revert changes for 256MB commit 36f09f186a924cd0be478094ee6e014c7f37eef0 Merge: f4e6f4477 cfe18d289 Author: Efode, Irina <irina.efode@intel.com> Date: Thu Oct 7 15:54:03 2021 +0300 Merge remote-tracking branch 'upstream/master' into plugin commit f4e6f4477787aefe847dcf6bd869ea4dffc3bfb2 Author: Efode, Irina <irina.efode@intel.com> Date: Thu Oct 7 15:18:51 2021 +0300 fix nms commit cfe18d289cbc4a390ff9406cab435838445caf47 Author: Bartek Szmelczynski <bartosz.szmelczynski@intel.com> Date: Thu Oct 7 13:40:15 2021 +0200 Scatter update ref impl revision (#7476) * add template tests for scatter_update * rm CT from ref impl * fix namings * minor code refactor * fix style * change ref impl * add lambda func * new tests * remove CT from reference implementation, add template tests * fix cpu IE * refactor template tests * split template tests commit 126943800ec5606a7668dc20d70e298c1f142566 Author: Mateusz Tabaka <mateusz.tabaka@intel.com> Date: Thu Oct 7 11:28:27 2021 +0200 Add support for ONNX op "com.microsoft.EmbedLayerNormalization" (#7837) commit f856ac02039c03bcd6415e699a6ca8bebf529292 Author: Dmitrii Khurtin <dmitrii.khurtin@intel.com> Date: Thu Oct 7 12:25:18 2021 +0300 [GNA] Added ConcatAlignFilter support for Accuracy Aware mode (#7834) * Added ConcatAlignFilter support for Accuracy Aware mode * fails after reviewing and added tests * moved the test to gna/scale_factors_tests; added comments to test commit 6f43b8d0af1f2f1094abc16fb19df1c10867dde6 Author: Dmitrii Khurtin <dmitrii.khurtin@intel.com> Date: Thu Oct 7 12:18:22 2021 +0300 [GNA] Fixed failed to inserting reshape around MatMul (#7833) * Fixed failed to inserting reshape around MatMul. * remove unnecessary * added comments commit d11ff041303d2a77c861a9bb88a1dbb45ce01a99 Author: Alina Kladieva <alina.kladieva@intel.com> Date: Thu Oct 7 12:09:22 2021 +0300 Update skip_tests_config.cpp (#7874) commit 055479c4fa255437972c97e0f47b32cfd1027352 Merge: 9ac894183 4c80b110d Author: Efode, Irina <irina.efode@intel.com> Date: Thu Oct 7 12:05:22 2021 +0300 Merge remote-tracking branch 'upstream/master' into plugin commit 4c80b110d087a6c73f36538b39387199f2466f1e Author: Yury Gaydaychuk <yury.gaydaychuk@intel.com> Date: Thu Oct 7 11:31:08 2021 +0300 [CPU] Deformable convolution improvements (#7168) * jit impl. optimized * reviewed * reviewed commit 94d5d819613b89511f2034f414538429ee35f1b6 Author: Ilya Znamenskiy <ilya.znamenskiy@intel.com> Date: Thu Oct 7 10:30:07 2021 +0300 [GPU] Quantize scale shift opt optimizations (#7770) commit 623117fe2454d27577716301831e28335ed5097b Author: Anastasia Popova <anastasia.popova@intel.com> Date: Wed Oct 6 23:15:45 2021 +0300 Serialization of old API map in nGraph. (#7840) * Added serialization of old API map in ngraph. * Changed order type to int64_t. * Fixed uint64_t error, added comments. * Apply suggestions from code review Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com> * Added tests with undefined type and empty order. * Added set, get and has methods. * Fix in tests. * Apply suggestions from code review Co-authored-by: Ilya Churaev <ilyachur@gmail.com> * Made inline methods, changed to shared_ptr. * Small fix. * Moved methods to header file. * Small fix. Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com> Co-authored-by: Ilya Churaev <ilyachur@gmail.com> commit e20cefb62044f10cb96349adfce5973be77d5114 Author: Mikhail Nosov <mikhail.nosov@intel.com> Date: Wed Oct 6 21:17:10 2021 +0300 PrePostProcessor.output() - first implementation of post-processing (#7866) * PrePostProcessor.output() - first implementation of post-processing Supported convert_layout, convert_element_type and custom operations * Fix review comments * Added test for pre and post processing together Fix clang-format * Move 'validate_and_infer_types' before post-processing commit 9ac89418381491353a46c3b8086928f3febe5910 Author: Efode, Irina <irina.efode@intel.com> Date: Wed Oct 6 20:17:35 2021 +0300 fix inference chaining commit d0383a21acfc69d75425237706959aacd35d8eab Merge: ed60bfe34 a4788989f Author: Efode, Irina <irina.efode@intel.com> Date: Wed Oct 6 19:40:42 2021 +0300 Merge remote-tracking branch 'upstream/master' into plugin commit a4788989f2bd18fba232c081dd1a593a901ae493 Author: Dawid Kożykowski <dawid.kozykowski@intel.com> Date: Wed Oct 6 17:16:58 2021 +0200 disable failing test (#7872) commit cddfeda4dd805b981d7a4d7395ae06fad3d6a571 Author: Dawid Kożykowski <dawid.kozykowski@intel.com> Date: Wed Oct 6 16:53:20 2021 +0200 disable matmul integer ie tests (#7870) commit 606fdc2ec56b3a93f2f83dc9de4181e930dc3dc5 Author: Paul Youngsoo Ahn <paul.y.ahn@intel.com> Date: Wed Oct 6 15:29:14 2021 +0300 [IE] Add new API to return the number of logical cores (#7688) (#7688) - Add functional tests commit f57dc05c664d73b2fb6d85916297678e53a1fc78 Author: Mikhail Nosov <mikhail.nosov@intel.com> Date: Wed Oct 6 15:22:05 2021 +0300 [OV20] Convert NV12 to RGB operation + preprocessing (#7508) * # Conflicts: # docs/template_plugin/tests/functional/op_reference/convert_color_nv12.cpp # inference-engine/tests/functional/plugin/cpu/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp # inference-engine/tests/functional/shared_test_classes/include/shared_test_classes/single_layer/convert_color_nv12.hpp # inference-engine/tests/functional/shared_test_classes/src/single_layer/convert_color_nv12.cpp # ngraph/core/include/openvino/core/preprocess/input_tensor_info.hpp # ngraph/core/include/openvino/core/preprocess/preprocess_steps.hpp # ngraph/core/include/openvino/op/nv12_to_bgr.hpp # ngraph/core/include/openvino/op/nv12_to_rgb.hpp # ngraph/core/src/op/nv12_to_bgr.cpp # ngraph/core/src/op/nv12_to_rgb.cpp # ngraph/core/src/preprocess/pre_post_process.cpp # ngraph/core/src/preprocess/preprocess_steps_impl.hpp # ngraph/test/CMakeLists.txt * Added more test to cover 100% of code Allow convert element type for 'multi-plane' color format * Inherit tensor names for 'convert_color' * Clang * Fix tests * Disable 'int8' preprocessing resize test * Fix review comments * Add more restrictions and tests for planes sub-names * 1) Added check for uniqueness of tensor names generated for nodes Raise error if user's plane sub-name conflicts with some node in a function 2) Added exception safety to preprocess build. Before, when input #2 fail, only one preprocess will be applied to function and it will be corrupted Exception guard will restore function to original state if exception occurs * Fix clang-format commit 659daf610f1cb31848c88f42c5c27d8bd5f0b6f1 Author: Dawid Kożykowski <dawid.kozykowski@intel.com> Date: Wed Oct 6 13:53:47 2021 +0200 [ONNX] MatMulInteger (#7825) commit 9add27fd742f076d52fa9b6d081e9141b4c32533 Author: Andrey Sapozhnikov <andrey.sapozhnikov@intel.com> Date: Wed Oct 6 14:44:09 2021 +0300 [GNA] Adding missed ifdef's (#7167) * Added missed ifdef * Moved ifdef's to avoid unused variables and unclosed scopes * lower string number for ifdefs commit 11516bb2b2732755132b954afa48bdfd05c7872b Author: Krzysztof Bruniecki <krzysztof.bruniecki@intel.com> Date: Wed Oct 6 13:34:59 2021 +0200 [GNA] Remove WA for undefined reference in GCC (#7842) commit 80e0bed855a9f90addcaf49251e760faadc59a9c Author: Ilya Churaev <ilya.churaev@intel.com> Date: Wed Oct 6 14:17:27 2021 +0300 Remove ngraph from new API (#7838) commit cd675a56a4934340a31b99bf01f04ead00b59e2a Author: Liu Bo <bo4.liu@intel.com> Date: Wed Oct 6 17:46:00 2021 +0800 Paddle Op conversion for SSD-MobileNetV3: exp, stack (#7547) * Paddle Op conversion for SSD-MobileNetV3: exp, stack * apply review comments * remove fp64 type check of exp * use default_opset * add axis check * apply review comments commit f83cf4b76586e39fa87d29a89c3d72a6b1c30729 Author: Liu Bo <bo4.liu@intel.com> Date: Wed Oct 6 17:43:24 2021 +0800 [FrontEnd]Paddle_Op_Conversion_prior_box (#7639) * Paddle_Op_Conversion_prior_box * use default_opset * apply review comments * const type variables modification commit 5ef3472bee89661a5b58da6c43fe846e38eceeb7 Author: Gleb Kazantaev <gleb.kazantaev@intel.com> Date: Wed Oct 6 12:40:26 2021 +0300 Fix FrameworkNodeAttr Deserialization (#7854) commit faeeedf14143ef7c87f8c7199c3e0f7d9a5477c0 Author: Egor Duplensky <egor.duplenskii@intel.com> Date: Wed Oct 6 11:58:46 2021 +0300 [CPU] [DEBUG_CAPS] Execute all the nodes to have debug info available (#7809) Otherwise Reshape / Output / etc nodes are missed in verbose log And blobs from Output nodes are node dumped commit 17dc82a00a381da3051b7e3960984cb7e747909b Author: Ilya Znamenskiy <ilya.znamenskiy@intel.com> Date: Wed Oct 6 11:44:49 2021 +0300 [GPU] Num threads per eu update (#7823) commit b5499f6573878332b27ac80f693b804dc28bd853 Author: Andrey Somsikov <andrey.somsikov@intel.com> Date: Wed Oct 6 10:39:18 2021 +0300 Fix coverity_linux Azure pipeline error (#7857) commit 3455dd973f44e718fa71b60df98059764c9c12b9 Author: Egor Duplensky <egor.duplenskii@intel.com> Date: Wed Oct 6 09:57:57 2021 +0300 [CPU] Replace sgemm with MatMul primitive (#6785) commit d29648164aecaf3f6f6090854ba442565bc6203b Author: Jade Cho <jade.cho@intel.com> Date: Wed Oct 6 12:38:54 2021 +0900 [GPU] Merge activation_ref kernel update. (#7767) + Support b_fs_yx_fsv32, bs_fs_yx_bsv32_fsv32 and bs_fs_yx_bsv32_fsv16 format. commit dffe4a4251913c3dd692695ddb485b7e37ca9be8 Author: Ivan Tikhonov <ivan.tikhonov@intel.com> Date: Tue Oct 5 18:45:17 2021 +0300 If-8 operation: Serializer and Reader parts (#7545) * added ir reader * add serializer * fix code style * fix code style * fix code style * fix codestyle * update IR reader for IF op * move Function comparator to ngraph tests utils, update unit tests * update tests * cleanup * update unit tests * fix build issue * ngraph codestyle * Apply suggestions from code review Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com> Co-authored-by: Eugeny Volosenkov <eugeny.volosenkov@intel.com> Co-authored-by: Gleb Kazantaev <gleb.nnstu@gmail.com> commit 275d4838c5bd6de89957f69f3f877473f2169637 Author: Andrey Somsikov <andrey.somsikov@intel.com> Date: Tue Oct 5 17:43:10 2021 +0300 Add coverity pipeline (#7828) * Add pipeline for OSS coverity scan * Intercept and submit the build to coverity * Remove tests * Remove test dependencies installation commit 58e8893a2693913f47e1746fdf52fba2e89f070d Author: Mikhail Letavin <mikhail.letavin@intel.com> Date: Tue Oct 5 16:04:42 2021 +0300 [GPU] Separate async pipeline into explicit stages (#7197) commit a56d81345d308a4bd6c78778525a583923812225 Author: Anton Chetverikov <Anton.Chetverikov@intel.com> Date: Tue Oct 5 15:07:44 2021 +0300 [MO] IR Reader meta_info using update (#7133) * Initial change to allow saving graphto IR without meta_info * Update saving and restoring functions, add more comments * Add unit tests for define_data_type() function * Fix wrong name * Update condition * Update meta_data checks * Update data_type restoretion and missed outpurt ports handling * Update and add new test * Update comments * Remove commented code * Rename function * Update temporary Result operations processing * Remove define_data_type function * Move node_normalize_output function to Op class methods * Update comments * Update comments commit cdb3e1776324a0fe500cfc2767876cea21a46b0b Author: Anastasia Kuporosova <anastasia.kuporosova@intel.com> Date: Tue Oct 5 13:55:54 2021 +0300 [New Python API] Add new python API based on pybind11 (#7752) * Mk/ov pybind poc (#48) * Move _pyngraph module to ngraph.pyngraph * Stub for IECore and IENetwork classes * Additional API classes * passing test, extended functions and added blob * worksave * [POC Python API] Add IECore methods * [POC Python API] Add iecore tests * ienetwork * ienet, input_info, dataptr * irequest and exeecnet * adapted benchmark * Move _pyngraph module to ngraph.pyngraph * Stub for IECore and IENetwork classes * Additional API classes * passing test, extended functions and added blob * worksave * [POC Python API] Add IECore methods * [POC Python API] Add iecore tests * ienetwork * ienet, input_info, dataptr * irequest and exeecnet * adapted benchmark * Added suport for InputInfo bindings * Add Blob support for different types * fix typo * Fixed InputInfo maps * Add keys() to inputs maps * add uint8 blob * return read_network as it should be * return read_network as it should be * fix blob buffer * remove const input_info files and fix codestyle * add mode parameter in benchmark app * return _pyngraph * delete benchmark copy * return pyngraph as in master * fix benchmark working * add comment with api which need to implement * remove unnecessary code from benchmark * remove hardcoded path from setup.py * Rename vars in setup.py * working wheel * fix wheel building * Revert "working wheel" This reverts commit 11d03a1833cf11276bcfc232c30c95c9a7f269b6. * fix tests * Added async infer * pass by ref * add ccompiler to requirements * fix blob creation and view * replace abscent method with working code in benchmark * fix building * worksave * worksave queue * no-deadlock async infer * add lock handle in waitAll * fix building issues with includes * update of setup and cmakelist * fix setup.py way of building * add new methods for ie_core * add ienetwork methods: serizlize and getfunction * add methods for exec net and infer request class * remove ccompiler from requirements * remove set from cmake * Update Blob class with precisions * Rewrite test_write_numpy_scalar_int64 * Generic Blob casting in infer queue * implementation of preprocess_info * update license * add set_blob method * worksave * added template for setblob * Added blob convert in infer request * move blob casting to common namespace * add_outputs method * work with func from pyopenvino * add user_id to callbacks * remove hardcoded root dir * refactor code and comments * [Python API] use parametrize in blob tests * move common functions to conftest file * Add tests for blob * Update test_blob and test_network * add parametrize in blob tests * blob refactoring * Fix sync in InferQueue and add default callbacks * patch for protobuf cmake * blob refactoring * rename convert_to_blob to cast_to_blob * rename to cast_to_blob in infer queue * add missing cast_to_blob * remove boost * change license * undo in cmake * fix building * [IE PYTHON API POC] Add fixed InferQueue and modification in async part of benchmark * Add read_network(model,blob) * Add blob_from_file helper * Add read from Path * Add tests * Add read_network from bytes * Error throwing in Common IE functions * Cleaning samples * Changes in ConstInputInfoWrapper class * Add StatusCode to callback function for InferRequest * Add random image generation and model path getting * Move example model to examples path * Adapt sync and async examples to new helpers * Return request info containing StatusCode and ID from InferQueue for top idle request. * Update benchmark app to use new API with request info * Update examples to use two different approaches to InferQueue * reset new line * Add is_ready() to InferQueue * fix building * remove benchmark * temporary add separate flag for building poc * refactoring * Remove GIL acquire in default callback and latencies * Adapt benchmark to Core() * Codestyle * fix building * [Python API] Move ngraph python api to the new destination * fix building tests * fix code-style checks * building in azure * fix building wheels * apply fixes * new structure * fix building * Add support for InferRequest::Cancel in pyopenvino * fixes remove gil release add async infer after cancel * remove extra files * remove examples and benchmark * fix code style * fix building * fix tests * merge inits from old and new api * fix azure ci * fix setup.py * fix setup.py building * try to fix mac Co-authored-by: Michal Karzynski <michal.karzynski@intel.com> Co-authored-by: jiwaszki <jan.iwaszkiewicz@intel.com> Co-authored-by: anastasia.kuporosova <akuporos@akuporos.inn.intel.com> Co-authored-by: Alexey Lebedev <alexey.lebedev@intel.com> Co-authored-by: Mateusz Tabaka <mateusz.tabaka@intel.com> * Fix comments * fix comments: cmakelist * fix building on arm * permission for merge script * permission for merge script Co-authored-by: Michal Karzynski <michal.karzynski@intel.com> Co-authored-by: jiwaszki <jan.iwaszkiewicz@intel.com> Co-authored-by: anastasia.kuporosova <akuporos@akuporos.inn.intel.com> Co-authored-by: Alexey Lebedev <alexey.lebedev@intel.com> Co-authored-by: Mateusz Tabaka <mateusz.tabaka@intel.com> commit 3859990b1b9e9e4003e12d59f3fee7ae76f0bdfe Author: Ilya Churaev <ilya.churaev@intel.com> Date: Tue Oct 5 13:09:59 2021 +0300 Introduce IR v11 (#7787) * Enabled support of IR v11 in IR frontend * Enabled serialization to v11 * Added indexes for Inputs/Outputs * Fixed typo * Fixed code style * Fixed deserialization tests * FIxed typo * Avoid changes in the original serialized function * Fixed TI tests * Removed version from the function and indexes from parameters/results * Restore function version * Clone function rt info * Removed v11 version commit 617a0b0b470b40b96f7debc4ab6f8f04de1a8a25 Author: Alexey Varyzgin <alexey.varyzgin@intel.com> Date: Tue Oct 5 13:09:52 2021 +0300 [CPU] Shared weights for RNN node (#7522) commit d89b14625995bf3eb7a0e821305202379a86f0c7 Author: Jade Cho <jade.cho@intel.com> Date: Tue Oct 5 16:22:33 2021 +0900 [GPU] Merge mvn kernel updates (#7736) * [GPU] Merge mvn kernel updates + Support bs_fs_yx_bsv32_fsv32 format for i8 and u8 dtype. + Support bs_fs_yx_bfv32_fsv16 format for fp16 dtype. * [GPU] Fix a bug of resample kernel selector. * [GPU] fix a build error of mvn unit tests commit c6b98d5e9bcfa3504379569f4ea433c24f5e23be Author: Alexander Zhogov <alexander.zhogov@intel.com> Date: Tue Oct 5 09:41:01 2021 +0300 CODEOWNERS: Remove openvino-admins from scripts commit acb6aa01ab97484e222ce77051c3015a546ab313 Author: Ilya Lavrenov <ilya.lavrenov@intel.com> Date: Tue Oct 5 04:26:01 2021 +0300 Added reporting of unresolved symbols for plugins (#7810) * Added reporting of unresolved symbols for plugins * Added HDDL dependency * Removed cross-compilation if * Revert "Removed cross-compilation if" This reverts commit da644a3afe541836cacf501830ff634d88011479. commit 21c70f8eb55ca4b51e5331b77787577ff5250155 Author: hyunback kim <hyunback.kim@intel.com> Date: Tue Oct 5 09:16:32 2021 +0900 concatenation_onednn migration (#7756) - update concatenation_onednn - add unit test using onednn concat Signed-off-by: hyunback <hyunback.kim@intel.com> commit bd2b346c6286e6488ff98eb5d6d82cfcea1f69fb Author: Irina Efode <irina.efode@intel.com> Date: Tue Oct 5 02:40:21 2021 +0300 [IE Tests] Aplly some comments for dynamic shapes (#7829) * [IE Tests] Aplly some comments for dynamic shapes * fix tss * fix postfix * remove cout * Fix crash * fix ci commit f762751968c94f82492cefaa49f37616341826d2 Author: Ilya Lavrenov <ilya.lavrenov@intel.com> Date: Tue Oct 5 01:06:10 2021 +0300 Deprecated dynamism in old IE API (#7812) commit a1ee7dca491c050880c00a70ecc2de4960b7123e Author: Svetlana Dolinina <svetlana.a.dolinina@intel.com> Date: Mon Oct 4 15:39:28 2021 +0300 fix error for model with lstm_nonlin without UseDropout attribute (#7730) * fix error for model with lstm_nonlin without UseDropout attribute * remove extra line * added dropoutmaskcomponent in doc as supported commit 0bebd53b4a2a4a25c498f50a62bb7cccf7dc8e7a Author: Ilya Lavrenov <ilya.lavrenov@intel.com> Date: Mon Oct 4 14:51:14 2021 +0300 Inference chaining: static and dynamic cases (#7776) * Fixed precisions conversion in new API * Added tests * Fixed old IR cases * Disable FP16 * Fixed regex for CentoOS * Refactored tests to use new API * Temp * Fixed tests * Moved smart reshape related sources to ngraph * Added tests for invalid names * Moved reshape to tensor_names * clang-format * Fixed CC build * Removed IEConv, IEDeconv from primitives pririty * Added tests for Inference chaining * Fixed dynamic chaining for template plugin * Added test for 2 conflicting names for the single parameter * Removed invalid test * Added more tests for dynamism * Fixed clang-format * Fixed macosx compilation * Some simplifications commit 996b15ccf256d1a310bc7566827ae66ef2a74492 Author: Irina Efode <irina.efode@intel.com> Date: Mon Oct 4 14:34:50 2021 +0300 [IE TEST] Enable support of Dynamic shapes in IE TEST infra with examples (#7718) * Squashed commit of the following: commit 69d82175a815a8073b96cae0ee551852d32ae802 Merge: 4c5eb0f8f 068d31511 Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Sep 28 19:07:37 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit 4c5eb0f8f476e1bf0cba71d871a93c9138a0d6cb Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Sep 28 19:06:16 2021 +0900 Build all (Multiple target shape inputs removed) commit dd3d17c85f09c7074cf0ab98654420d0aad1ba49 Merge: 0870cc6cc 1d3df63d6 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 20:29:47 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit 0870cc6cc17b47dc259352bb76fd75edbb7edafa Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 20:23:27 2021 +0900 While working on applying multiple target shapes to templateFuncTests, still failed commit e73a9741deff84a5849e87c54b14637cfbcc93c5 Merge: 20ea316b0 3bf34b116 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 16:54:16 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit 20ea316b0d06d82aeafd9d85e129f5310b28fc86 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 16:52:39 2021 +0900 Apply Eltwise stype input shape to cpuFuncTests commit 080228297247e494b968177681f23599de3687d6 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 14:59:00 2021 +0900 Apply Eltwise input shape to templateFuncTests Modify GenerateInputs() to use functionRefs commit 25c399d922a50262590eed6da939a73b69f6041b Merge: ab476a9ba b3050c268 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 24 14:45:01 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit ab476a9ba36ffa5d5b9703eab4c9bce3c8b7649f Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 24 14:44:23 2021 +0900 Add functionRefs for PrePostProcessTest commit 451ce9096deecb051404130a9e4cff3a9b6963b1 Merge: 5710141cd 846c9c91f Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 24 12:20:34 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit 5710141cd8a89ada4f5cf289c53559479b7dde6e Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 24 12:16:06 2021 +0900 templateFuncTests * Remove StaticShape and add DynamicShape to make existing test cases static default * Fix typos cpuFuncTests * Add functionRefs to each case commit c3b87f098d439e6e4fd5f96e64a2ab473ce218c0 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 23 12:51:40 2021 +0900 Fix to use ngraph::clone_function() commit fa7e87b1469be04cad6e41c08df95d9f87d21dee Merge: a8890950d d7dfce209 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 23 10:47:15 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit a8890950d315027a89b7a6c189b5851d1c334085 Merge: ceb802d97 5847b35ed Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 16 19:24:08 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit ceb802d9781c3305eb9751bdbe5c90eb96b614df Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 16 19:24:00 2021 +0900 templateFuncTest runs except multiple input shape cases commit 8adbaba71d877ed74be023fcb6c5f0c0f7ab3793 Merge: d11e3e917 f44369ce4 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 15:30:48 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit d11e3e917e5fb83c23cb4e80a59c792059006fb3 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 15:30:27 2021 +0900 ConvolutionLayerTest for dynamic shape case (Test only) commit d8eaf21acd7c7682c39820b0263bf456c6299a80 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 14:41:38 2021 +0900 ConvolutionLayerTest for dynamic shape case commit fe57d0faa6562cfa902c4456814c2f0883b6bbce Merge: 39a691ab9 7a392253d Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 09:59:44 2021 +0900 Merge branch 'master' into sy/ilyachur/draft_dynamic_plugin_rebased commit 7a392253d7e59f9b742ef6f136ee4689e2bce658 Merge: b8966457b 021639a04 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 09:59:01 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 39a691ab9533503871697eee36158d252b70420e Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 09:55:38 2021 +0900 Remove redundant line commit 109cafeffea18d2d374ae72e0d630d51e601e9af Merge: 0245e05cc b8966457b Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 9 10:25:36 2021 +0900 Merge branch 'master' into sy/ilyachur/draft_dynamic_plugin_rebased commit b8966457b9236a1397255209ee963362f4ce0456 Merge: 904384fee 1c1401b06 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 9 10:24:37 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 0245e05cc852cda081d273cb2ea71eacdb3438f4 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 9 10:18:54 2021 +0900 Remove comments used for indivisual testing Change unproper function names Remove unnecessary template<> commit 0854f07291abc4cf2e3d223103533e8e9fdc30ef Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 3 13:31:22 2021 +0900 ConvolutionLayerTest and SoftMaxLayerTest on template_plugin for dynamic shapes rebased commit 904384fee3c86b6e3f276ce637023964c7ea1e40 Merge: 4bf45de5d b78f228fa Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 3 09:11:44 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 4bf45de5dc2bd53de1c5385407c39f9ca8db884d Merge: 18476fe1b 07f7061f9 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 2 08:54:23 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 18476fe1b9dd1a39d35b1380f56ab19783fc9d8b Merge: e92f5928d f77d838e6 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Aug 23 09:48:34 2021 +0900 Merge remote-tracking branch 'upstream/master' commit e92f5928dcd779f147effc6b95ba019bea583d6b Merge: ef937a5a5 2fefe1164 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Aug 20 14:40:00 2021 +0900 Merge remote-tracking branch 'upstream/master' commit ef937a5a52b6d15af7fe1a3e5f2ca718d19b0a7e Merge: 04fed4c2a 184b3cbe4 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Aug 20 13:32:53 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 04fed4c2afa45d530da5e251aa93709c215272a1 Merge: 508c61615 39131968c Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Aug 13 13:27:26 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 508c616151f3b715b838bccdac47bede71d07a9c Merge: 0647e6827 273c7188a Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Aug 13 10:49:35 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 0647e68277d9cd1f21d4aa6dab9bac5a53657735 Merge: 89ba7c1bf 04ff7a6ed Author: Steve Yoo <steve.yoo@intel.com> Date: Wed Aug 11 13:39:51 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 89ba7c1bf166e9f860a0979943599a147b4ec9ba Merge: ebdbea67c b11a2220b Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Aug 9 09:01:44 2021 +0900 Merge remote-tracking branch 'upstream/master' commit ebdbea67cbdef3bfbacc5810df469d0a111f844d Merge: 4880bd11d d921e7a9c Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Jul 26 11:57:49 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 4880bd11d4fe3fbb3d5b1d440ffe204b62c4bb16 Merge: eef72406c 1e1e3bfff Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jul 22 14:58:56 2021 +0900 Merge remote-tracking branch 'upstream/master' commit eef72406cc8cac5a6021184ed97cecd86bd8db58 Merge: 9ccacedef 2a15e3e79 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Jul 16 12:58:14 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 9ccacedefef5e86289d4204952375cbf06ddb05c Merge: 14020554d c14edd413 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jul 15 13:48:24 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 14020554d2dd411ea5c1129f433c09cc556a606e Merge: 54182c03b 2a970a56d Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Jul 9 08:04:43 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 54182c03b2b76aeecf9c4c527701683689e4bd14 Merge: 7654df0d9 35d9bd0f6 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jul 8 08:15:46 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 7654df0d93ce2e920e0f63b95a0a9a6ba821fc26 Merge: 8ab309328 64cbdb9c2 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Jul 5 13:00:33 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 8ab30932820484b5bdb4331771fa4a9e232ac901 Merge: b77d127d7 db0145be1 Author: Steve Yoo <steve.yoo@intel.com> Date: Wed Jun 30 13:27:58 2021 +0900 Merge remote-tracking branch 'upstream/master' commit b77d127d789d6487180769eea8b3483f5b11f989 Merge: 4a5811623 632709012 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Jun 28 10:01:50 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 4a5811623d589739ff67bbe0686f3bc148c0886b Merge: 6ce8d8ce6 7e6641192 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Jun 21 09:31:00 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 6ce8d8ce66b71675558a35a87c430c4bbdf0c681 Merge: 84bc851ec db67c1b2b Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jun 17 08:28:23 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 84bc851ecf43b793e83769dd0f728083ddec7f00 Merge: 5a2cb750e fb7435a64 Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Jun 15 08:24:23 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 5a2cb750ec04779aa862a1edf8d654444ff13831 Merge: 19ab2100a 05469e95e Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Jun 11 13:30:59 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 19ab2100a5c6f24dc8d16a232c4af05988e27494 Merge: b2bdc3976 4d9fe14ec Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Jun 8 09:49:38 2021 +0900 Merge remote-tracking branch 'upstream/master' commit b2bdc39760094af3d0084609984745435d1a399c Merge: 0a6c3cc9b ac1803c3a Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jun 3 08:46:13 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 0a6c3cc9bf62649bfc24482bcab101180b9e7baf Merge: e07337d53 97a9a76ff Author: Steve Yoo <steve.yoo@intel.com> Date: Wed May 26 10:51:49 2021 +0900 Merge remote-tracking branch 'upstream/master' commit e07337d533f61d7ca970e67a108ad158f0007b81 Merge: d4b251678 e41e25533 Author: Steve Yoo <steve.yoo@intel.com> Date: Tue May 18 08:46:00 2021 +0900 Merge remote-tracking branch 'upstream/master' commit d4b251678ed272fe2bdef672d40b9197f7bbddbb Merge: f396091bd 1b8a0f7ae Author: Steve Yoo <steve.yoo@intel.com> Date: Mon May 10 08:11:10 2021 +0900 Merge remote-tracking branch 'upstream/master' commit f396091bd8a3f4f507d3bf2e9feb3a7455ead615 Merge: f569dbc73 8645c0839 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri May 7 13:49:43 2021 +0900 Merge remote-tracking branch 'upstream/master' commit f569dbc73903d7f6c2843a1347c1d04c117665fa Merge: a6b2800be 31b161097 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Apr 29 07:15:08 2021 +0900 Merge remote-tracking branch 'upstream/master' commit a6b2800be23f4858a1515ea611b9113b5b7141d1 Merge: dc771f1c4 1ae1757a5 Author: Steve Yoo <steve.yoo@intel.com> Date: Wed Apr 28 07:50:13 2021 +0900 Merge remote-tracking branch 'upstream/master' commit dc771f1c4f75e32972c10b4eaec7e0e27e718739 Merge: 5320f7eae 5de5f4d7d Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Apr 27 15:00:05 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 5320f7eae0242e95e57df9169e90977a8fe0a976 Merge: 47dedfde5 39e1a21c4 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Apr 26 08:32:06 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 47dedfde5780480ea036fe5eadae3233a68c3c96 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Apr 19 09:06:56 2021 +0900 Add test cases for PReLU in cpu plugin * For case when slope is vector * fix build * remove exztra * Squashed commit of the following: commit 69d82175a815a8073b96cae0ee551852d32ae802 Merge: 4c5eb0f8f 068d31511 Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Sep 28 19:07:37 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit 4c5eb0f8f476e1bf0cba71d871a93c9138a0d6cb Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Sep 28 19:06:16 2021 +0900 Build all (Multiple target shape inputs removed) commit dd3d17c85f09c7074cf0ab98654420d0aad1ba49 Merge: 0870cc6cc 1d3df63d6 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 20:29:47 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit 0870cc6cc17b47dc259352bb76fd75edbb7edafa Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 20:23:27 2021 +0900 While working on applying multiple target shapes to templateFuncTests, still failed commit e73a9741deff84a5849e87c54b14637cfbcc93c5 Merge: 20ea316b0 3bf34b116 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 16:54:16 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit 20ea316b0d06d82aeafd9d85e129f5310b28fc86 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 16:52:39 2021 +0900 Apply Eltwise stype input shape to cpuFuncTests commit 080228297247e494b968177681f23599de3687d6 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 27 14:59:00 2021 +0900 Apply Eltwise input shape to templateFuncTests Modify GenerateInputs() to use functionRefs commit 25c399d922a50262590eed6da939a73b69f6041b Merge: ab476a9ba b3050c268 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 24 14:45:01 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit ab476a9ba36ffa5d5b9703eab4c9bce3c8b7649f Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 24 14:44:23 2021 +0900 Add functionRefs for PrePostProcessTest commit 451ce9096deecb051404130a9e4cff3a9b6963b1 Merge: 5710141cd 846c9c91f Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 24 12:20:34 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit 5710141cd8a89ada4f5cf289c53559479b7dde6e Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 24 12:16:06 2021 +0900 templateFuncTests * Remove StaticShape and add DynamicShape to make existing test cases static default * Fix typos cpuFuncTests * Add functionRefs to each case commit c3b87f098d439e6e4fd5f96e64a2ab473ce218c0 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 23 12:51:40 2021 +0900 Fix to use ngraph::clone_function() commit fa7e87b1469be04cad6e41c08df95d9f87d21dee Merge: a8890950d d7dfce209 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 23 10:47:15 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit a8890950d315027a89b7a6c189b5851d1c334085 Merge: ceb802d97 5847b35ed Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 16 19:24:08 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit ceb802d9781c3305eb9751bdbe5c90eb96b614df Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 16 19:24:00 2021 +0900 templateFuncTest runs except multiple input shape cases commit 8adbaba71d877ed74be023fcb6c5f0c0f7ab3793 Merge: d11e3e917 f44369ce4 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 15:30:48 2021 +0900 Merge remote-tracking branch 'upstream/master' into sy/test/ConvolutionLayerTest_dynamic_shape_case commit d11e3e917e5fb83c23cb4e80a59c792059006fb3 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 15:30:27 2021 +0900 ConvolutionLayerTest for dynamic shape case (Test only) commit d8eaf21acd7c7682c39820b0263bf456c6299a80 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 14:41:38 2021 +0900 ConvolutionLayerTest for dynamic shape case commit fe57d0faa6562cfa902c4456814c2f0883b6bbce Merge: 39a691ab9 7a392253d Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 09:59:44 2021 +0900 Merge branch 'master' into sy/ilyachur/draft_dynamic_plugin_rebased commit 7a392253d7e59f9b742ef6f136ee4689e2bce658 Merge: b8966457b 021639a04 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 09:59:01 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 39a691ab9533503871697eee36158d252b70420e Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Sep 13 09:55:38 2021 +0900 Remove redundant line commit 109cafeffea18d2d374ae72e0d630d51e601e9af Merge: 0245e05cc b8966457b Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 9 10:25:36 2021 +0900 Merge branch 'master' into sy/ilyachur/draft_dynamic_plugin_rebased commit b8966457b9236a1397255209ee963362f4ce0456 Merge: 904384fee 1c1401b06 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 9 10:24:37 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 0245e05cc852cda081d273cb2ea71eacdb3438f4 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 9 10:18:54 2021 +0900 Remove comments used for indivisual testing Change unproper function names Remove unnecessary template<> commit 0854f07291abc4cf2e3d223103533e8e9fdc30ef Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 3 13:31:22 2021 +0900 ConvolutionLayerTest and SoftMaxLayerTest on template_plugin for dynamic shapes rebased commit 904384fee3c86b6e3f276ce637023964c7ea1e40 Merge: 4bf45de5d b78f228fa Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Sep 3 09:11:44 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 4bf45de5dc2bd53de1c5385407c39f9ca8db884d Merge: 18476fe1b 07f7061f9 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Sep 2 08:54:23 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 18476fe1b9dd1a39d35b1380f56ab19783fc9d8b Merge: e92f5928d f77d838e6 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Aug 23 09:48:34 2021 +0900 Merge remote-tracking branch 'upstream/master' commit e92f5928dcd779f147effc6b95ba019bea583d6b Merge: ef937a5a5 2fefe1164 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Aug 20 14:40:00 2021 +0900 Merge remote-tracking branch 'upstream/master' commit ef937a5a52b6d15af7fe1a3e5f2ca718d19b0a7e Merge: 04fed4c2a 184b3cbe4 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Aug 20 13:32:53 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 04fed4c2afa45d530da5e251aa93709c215272a1 Merge: 508c61615 39131968c Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Aug 13 13:27:26 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 508c616151f3b715b838bccdac47bede71d07a9c Merge: 0647e6827 273c7188a Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Aug 13 10:49:35 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 0647e68277d9cd1f21d4aa6dab9bac5a53657735 Merge: 89ba7c1bf 04ff7a6ed Author: Steve Yoo <steve.yoo@intel.com> Date: Wed Aug 11 13:39:51 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 89ba7c1bf166e9f860a0979943599a147b4ec9ba Merge: ebdbea67c b11a2220b Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Aug 9 09:01:44 2021 +0900 Merge remote-tracking branch 'upstream/master' commit ebdbea67cbdef3bfbacc5810df469d0a111f844d Merge: 4880bd11d d921e7a9c Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Jul 26 11:57:49 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 4880bd11d4fe3fbb3d5b1d440ffe204b62c4bb16 Merge: eef72406c 1e1e3bfff Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jul 22 14:58:56 2021 +0900 Merge remote-tracking branch 'upstream/master' commit eef72406cc8cac5a6021184ed97cecd86bd8db58 Merge: 9ccacedef 2a15e3e79 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Jul 16 12:58:14 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 9ccacedefef5e86289d4204952375cbf06ddb05c Merge: 14020554d c14edd413 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jul 15 13:48:24 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 14020554d2dd411ea5c1129f433c09cc556a606e Merge: 54182c03b 2a970a56d Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Jul 9 08:04:43 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 54182c03b2b76aeecf9c4c527701683689e4bd14 Merge: 7654df0d9 35d9bd0f6 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jul 8 08:15:46 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 7654df0d93ce2e920e0f63b95a0a9a6ba821fc26 Merge: 8ab309328 64cbdb9c2 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Jul 5 13:00:33 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 8ab30932820484b5bdb4331771fa4a9e232ac901 Merge: b77d127d7 db0145be1 Author: Steve Yoo <steve.yoo@intel.com> Date: Wed Jun 30 13:27:58 2021 +0900 Merge remote-tracking branch 'upstream/master' commit b77d127d789d6487180769eea8b3483f5b11f989 Merge: 4a5811623 632709012 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Jun 28 10:01:50 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 4a5811623d589739ff67bbe0686f3bc148c0886b Merge: 6ce8d8ce6 7e6641192 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Jun 21 09:31:00 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 6ce8d8ce66b71675558a35a87c430c4bbdf0c681 Merge: 84bc851ec db67c1b2b Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jun 17 08:28:23 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 84bc851ecf43b793e83769dd0f728083ddec7f00 Merge: 5a2cb750e fb7435a64 Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Jun 15 08:24:23 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 5a2cb750ec04779aa862a1edf8d654444ff13831 Merge: 19ab2100a 05469e95e Author: Steve Yoo <steve.yoo@intel.com> Date: Fri Jun 11 13:30:59 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 19ab2100a5c6f24dc8d16a232c4af05988e27494 Merge: b2bdc3976 4d9fe14ec Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Jun 8 09:49:38 2021 +0900 Merge remote-tracking branch 'upstream/master' commit b2bdc39760094af3d0084609984745435d1a399c Merge: 0a6c3cc9b ac1803c3a Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Jun 3 08:46:13 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 0a6c3cc9bf62649bfc24482bcab101180b9e7baf Merge: e07337d53 97a9a76ff Author: Steve Yoo <steve.yoo@intel.com> Date: Wed May 26 10:51:49 2021 +0900 Merge remote-tracking branch 'upstream/master' commit e07337d533f61d7ca970e67a108ad158f0007b81 Merge: d4b251678 e41e25533 Author: Steve Yoo <steve.yoo@intel.com> Date: Tue May 18 08:46:00 2021 +0900 Merge remote-tracking branch 'upstream/master' commit d4b251678ed272fe2bdef672d40b9197f7bbddbb Merge: f396091bd 1b8a0f7ae Author: Steve Yoo <steve.yoo@intel.com> Date: Mon May 10 08:11:10 2021 +0900 Merge remote-tracking branch 'upstream/master' commit f396091bd8a3f4f507d3bf2e9feb3a7455ead615 Merge: f569dbc73 8645c0839 Author: Steve Yoo <steve.yoo@intel.com> Date: Fri May 7 13:49:43 2021 +0900 Merge remote-tracking branch 'upstream/master' commit f569dbc73903d7f6c2843a1347c1d04c117665fa Merge: a6b2800be 31b161097 Author: Steve Yoo <steve.yoo@intel.com> Date: Thu Apr 29 07:15:08 2021 +0900 Merge remote-tracking branch 'upstream/master' commit a6b2800be23f4858a1515ea611b9113b5b7141d1 Merge: dc771f1c4 1ae1757a5 Author: Steve Yoo <steve.yoo@intel.com> Date: Wed Apr 28 07:50:13 2021 +0900 Merge remote-tracking branch 'upstream/master' commit dc771f1c4f75e32972c10b4eaec7e0e27e718739 Merge: 5320f7eae 5de5f4d7d Author: Steve Yoo <steve.yoo@intel.com> Date: Tue Apr 27 15:00:05 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 5320f7eae0242e95e57df9169e90977a8fe0a976 Merge: 47dedfde5 39e1a21c4 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Apr 26 08:32:06 2021 +0900 Merge remote-tracking branch 'upstream/master' commit 47dedfde5780480ea036fe5eadae3233a68c3c96 Author: Steve Yoo <steve.yoo@intel.com> Date: Mon Apr 19 09:06:56 2021 +0900 Add test cases for PReLU in cpu plugin * For case when slope is vector * temp * Cpu * All fix for softmax * ie + gna * Remove extra * fix crash * eltwise * Fix crash * fix failures * gpu myriad * fix * fix template * fix * tr * gpu skip * fix gpu * fix template commit c687929c19e644817ca19bee6be051f949042d12 Author: Mateusz Tabaka <mateusz.tabaka@intel.com> Date: Mon Oct 4 13:02:16 2021 +0200 Add support for ONNX op "com.microsoft.SkipLayerNormalization" (#7789) commit 111c502997c80868af63773981972002d0cb42d1 Author: Szymon Durawa <szymon.durawa@intel.com> Date: Mon Oct 4 12:09:58 2021 +0200 Remove ConvolutionBackprop as dynamic op. (#7800) commit 74a0ffb1b0e65babec12d800c5d7232569876380 Author: Anton Pankratv <anton.pankratov@intel.com> Date: Mon Oct 4 12:10:23 2021 +0300 Rduced SoPointer usage in internal API (#7761) commit d4e4e8d1e86ff17b6fcd7a92c4c7f831c1b15fcf Author: Gleb Kazantaev <gleb.kazantaev@intel.com> Date: Mon Oct 4 11:52:53 2021 +0300 Fix ConvertPrecision for NMS5 (#7778) * Fix FP32 to FP16 convert precision for NMS * Add tests * Code style * Codestyle commit 6a97decf67086ae46e605ed3931039051d239a57 Author: Maksim Kutakov <maksim.kutakov@intel.com> Date: Mon Oct 4 11:23:26 2021 +0300 [CPU] Klocwork fixes for Phase 2 dynamic shapes enablement (#7745) commit 268246e3bc69b89419d64c26b5ac4ff3cdfd2bf7 Author: Alexander Shchepetov <alexander.shchepetov@intel.com> Date: Mon Oct 4 11:14:13 2021 +0300 single-model test configs (#7734) commit 96519b1723e62fa17f09ea646f2f02a24001e2bd Author: Tomasz Jankowski <tomasz1.jankowski@intel.com> Date: Mon Oct 4 06:24:02 2021 +0200 [nGraph] Remove obsolete attribute from Result op (#7682) * Remove obsolete attribute from Result op m_needs_default_layout field had no effect to the Result operator state, even if set to true* by build_graph test. Its setter and getter were unused. * rather accidentaly considering implicit cast from const char* * Restore redundant ctor as deprecated It's user API so better keep it backward compatible * Restore useless accessors as deprecated commit 3d5c163c3d61a3fe104efff21f33989371c69d83 Author: Alexey Lebedev <alexey.lebedev@intel.com> Date: Sun Oct 3 19:27:58 2021 +0300 fix memory leak (#7654) commit ed60bfe3448cbb2b205a97253a9393b8d8ab8ca5 Author: Efode, Irina <irina.efode@intel.com> Date: Sat Oct 2 12:57:08 2021 +0300 Revert "Update windows.yml" This reverts commit 351ede4e1ee3781939216b37417a831dc1a54083. commit f47eaa80eb0461c460300c593cde77fa83b67fd8 Author: Efode, Irina <irina.efode@intel.com> Date: Sat Oct 2 12:56:33 2021 +0300 Revert "Update windows.yml" This reverts commit 5eb4bf875a235bef45e0d6df2f6a59c86b372717. commit 3078e954827452a1a8379f9c905b8cb159e1c043 Author: Taylor Yeonbok Lee <taylor.lee@intel.com> Date: Sat Oct 2 11:23:15 2021 +0900 Make ngraph dump to be done for each subnetwork (#7733) commit 056515e7356c7a4dec153b009f8d7e91dc7bcf36 Author: Ilya Lavrenov <ilya.lavrenov@intel.com> Date: Fri Oct 1 22:54:06 2021 +0300 Fixed CVS-66710 (#7805) commit 5eb4bf875a235bef45e0d6df2f6a59c86b372717 Author: Alexander Zhogov <alexander.zhogov@intel.com> Date: Fri Oct 1 22:45:39 2021 +0300 Update windows.yml commit 6f69166f370ebfe5fb0ffced3a0e0aef8d2ee6dc Author: Ilya Lavrenov <ilya.lavrenov@intel.com> Date: Fri Oct 1 21:58:12 2021 +0300 Removed cross_check_tool from installation (#7804) commit f8ed1958415e5fcde392a3d67ee68026ec263767 Author: Mikhail Nosov <mikhail.nosov@intel.com> Date: Fri Oct 1 20:21:52 2021 +0300 Fix 'NV12 batch case' (was sporadic failure) (#7790) Introduced 'absolute threshold' for LayerTests and BaseReferenceTests to consistently catch absolute differences Previously, when set 'threshold=1.f' it was treated as 'allowed difference is 100%", so there was no way to allow absolute difference as 1.f commit 5b39e407d9b531dab7960cda4ec1bfdffaf3a900 Author: Mikhail Nosov <mikhail.nosov@intel.com> Date: Fri Oct 1 19:45:40 2021 +0300 [OV2.0] Preprocessing - add 'convert_layout' (#7772) * Preprocessing - add 'convert_layout' * Fix comments, removed 'set_data_shape' for time being commit e496e72907c5dcfda05cffb4afde8e9ac4d51b6d Author: Efode, Irina <irina.efode@intel.com> Date: Fri Oct 1 18:10:10 2021 +0300 ddd commit 0f875bdfc7152db313b59f097150468d8e89a86a Author: Efode, Irina <irina.efode@intel.com> Date: Fri Oct 1 18:02:05 2021 +0300 Revert "Update windows.yml" This reverts commit 93e326229cae52dd656b5b0f6e7ce7580dcaaf7e. commit 93e326229cae52dd656b5b0f6e7ce7580dcaaf7e Author: Irina Efode <irina.efode@intel.com> Date: Fri Oct 1 15:51:33 2021 +0300 Update windows.yml commit 351ede4e1ee3781939216b37417a831dc1a54083 Author: Irina Efode <irina.efode@intel.com> Date: Fri Oct 1 15:50:06 2021 +0300 Update windows.yml commit dc1a1d70e8be5c33c6fff7947968d1ae54470257 Author: Victor Kuznetsov <victor.kuznetsov@intel.com> Date: Fri Oct 1 15:44:26 2021 +0300 [Memory_tests] Work with DB (#7492) * uncomment upload db func * upd CMakeLists.txt * fix template path * fix CmakeLists * fix imports * fix work with cmd and with models our_dir * add quotation marks * fix quotation marks * add base config for test * upd work with db instance * revert changes with test config commit 899427abc12dda2d4a3882709f8e8e1256008323 Merge: 7adc7955c 09d20360a Author: Efode, Irina <irina.efode@intel.com> Date: Fri Oct 1 15:22:41 2021 +0300 Merge remote-tracking branch 'upstream/master' into plugin commit 7adc7955c8aef8dbb7c8c03ed808e79d9569621d Merge: bf42f8a66 a883b5c09 Author: Efode, Irina <irina.efode@intel.com> Date: Fri Oct 1 12:34:19 2021 +0300 Merge remote-tracking branch 'upstream/master' into plugin commit 09d20360a97c210e08e460e121ea0337de8cc43e Author: Alina Kladieva <alina.kladieva@intel.com> Date: Fri Oct 1 13:34:07 2021 +0300 Add MO coveragerc to tests install pkg (#7707) * Add MO coveragerc to tests install pkg * Use directory install with FILES_MATCHING * Coveragerc to tools folder * Update CMakeLists.txt * Use tests/model_optimizer folder commit f3be68d164b076b3d9a0329326367bff41d799eb Author: Yegor Kruglov <yegor.kruglov@intel.com> Date: Fri Oct 1 13:03:49 2021 +0300 updated extender (#7763) commit 7fd0b9be48f64d922d4252bfc0728f46a85fd740 Author: Alina Kladieva <alina.kladieva@intel.com> Date: Fri Oct 1 12:37:51 2021 +0300 Exclude sporadic CPU canRun3SyncRequestsConsistentlyFromThreads (#7706) * Exclude sporadic CPU canRun3SyncRequestsConsistentlyFromThreads * Update skip_tests_config.cpp * Fix lint commit a883b5c097b91de2930d60f2b6f67473c6551da6 Author: Mikhail Nosov <mikhail.nosov@intel.com> Date: Fri Oct 1 10:25:08 2021 +0300 Temporary disable sporadically failed test (PR #7601) (#7782) * Temporary disable sporadically failed test * Looks like skip test config didn't skip the test commit 61c97edd40d25e7149d97a702783be371c4381e9 Author: Taylor Yeonbok Lee <taylor.lee@intel.com> Date: Fri Oct 1 15:18:15 2021 +0900 [GPU] Reduce unused macros to reduce loading time (#7435) * Reduce unused macros, where two strategies are used: (1) Extract batch_headers and let them be included only once in each batch. (2) Static reduction in primitive_db_gen.py, which scans each macro's users and exclude the macro if there is no user. * Removed dependency from runtime to kernel_selector * Resolve too large string error * Fix duplicated definition (GET_FILTER_XXXX is defined in both fetch_weight.cl and by runtime. Removed from runtime because the definition is incorrect * Resolve GRN & deconv & gpu_select issues * Fix cldnn unittest issues * Minor fix * Applied review comments * Fix rebase error commit e0cea200e33bb1540022ce43e1b3b88cb1bfb6d4 Author: Sungeun Kim <sungeun.kim@intel.com> Date: Fri Oct 1 15:02:30 2021 +0900 [GPU] Onednn integration for pooling (#7753) * [GPU] Onednn integration for pooling primitive * layout_optimizer for pooling * Padding code merge for onednn Co-authored-by: Kim, Mingyu <mingyu.kim@intel.com> commit a16cc812332c0646443c8214f12bc2da56804ba5 Author: Gleb Kazantaev <gleb.kazantaev@intel.com> Date: Fri Oct 1 08:03:37 2021 +0300 Remove VariantWrapper for simple attr classes (#7771) * Remove VariantWrapper for simple attr classes * Code style commit faeaf045a99d288a364bc7bf574e10bbe903e6be Author: Ilya Churaev <ilya.churaev@intel.com> Date: Fri Oct 1 07:24:28 2021 +0300 Graph comparator to ngraph util (#7729) * Moved FrameworkNode to nGraph * Moved graph comparator to ngraph test util * Fixed build * Try to fix centos * Fix export target * Moved engine utils to separate library * Removed ONNX util from common library * Fixed build * Fixed code style commit f675df625c4e59915b2f02a5a82c1539180d4941 Author: Ilya Znamenskiy <ilya.znamenskiy@intel.com> Date: Fri Oct 1 06:18:00 2021 +0300 [GPU] Added post-ops support for OneDNN primitives (#7737) [GPU] Memory lock fix commit 302eb08dc570d7c373b3be43783da26e3946205d Author: Ilya Lavrenov <ilya.lavrenov@intel.com> Date: Fri Oct 1 03:46:32 2021 +0300 Replaced gtest deprecated macro (#7779) commit 778cc2ddbb59c7ac9bfd113af71f4f394c711bf4 Author: Egor Duplensky <egor.duplenskii@intel.com> Date: Thu Sep 30 20:25:49 2021 +0300 [CPU] Migration on oneDNN v2.3.2 (#7680) binary post binary post ops support for gemm convolution and gemm inner product plugin fixes mkldnn: avx512: fixed prelu post op Co-authored-by: dmitrygo <dmitry.gorokhov@intel.com> commit 7fade1e35748b76783150b941e356622bad2ced7 Author: Dmitry Pigasin <dmitry.pigasin@intel.com> Date: Thu Sep 30 16:58:11 2021 +0300 Fix a result shape for a model with a 3d tensor at the output (#7741) commit 3f0fea5c1be720088cf7b6c5c73668c1d9b1900a Author: Maksim Derbasov <maksim.derbasov@intel.com> Date: Thu Sep 30 16:57:43 2021 +0300 Fix for warning C4297 (#7740) commit 6e05cead1169b7c84217c4abac8e90d966dee4cf Author: Mikhail Nosov <mikhail.nosov@intel.com> Date: Thu Sep 30 16:34:46 2021 +0300 [OV20] Reference implementation for NV12toRGB and NV12toBGR operations (#7601) * Reference implementation for NV12toRGB and NV12toBGR operations Tests: - ngraph: visitor + type_prop - template plugin: reference implementation - inference-engine: shared tests for plugins - cpu plugin: compare with ref implementation tests * Fix clang * Serialization tests * Fix clang-format * Changed 'f32' to 'any supported floating-point type' Added appropriate shape inference tests Added error test for >2 inputs Fixed failed CI tests * Updates after rebase + Try to fix Ninja build * Fix CI * Support endianness + potential fix of win32 test fails * Fix review comment * Fix review comments * Fix unit test build * Fix unit test build #2 * Possible build fix 3 * Simplified reference tests Observed issue with shuffling Y pixels on little-endian systems, added tests commit b339bb780b6a8b3957a6a7d644ab91e2a9836589 Author: Evgenya Stepyreva <evgenya.stepyreva@intel.com> Date: Thu Sep 30 15:39:32 2021 +0300 Resolved unexpected -1s in IRs (#7709) commit fab4056ceb60fccade0d2040fba3ffb07919d016 Author: Anton Pankratv <anton.pankratov@intel.com> Date: Thu Sep 30 15:09:47 2021 +0300 Fixed callback copy count (#6607) commit 757db35528e3…

nosovmik requested review from a team, e-nugmanova, ilya-lavrenov and ilyachur September 22, 2021 15:15

openvino-pushbot added category: TEMPLATE OpenVINO Template plugin category: IE Tests OpenVINO Test: plugins and common category: Core OpenVINO Core (aka ngraph) labels Sep 22, 2021

ilya-lavrenov approved these changes Sep 22, 2021

View reviewed changes

ngraph/core/include/ngraph/ops.hpp Outdated Show resolved Hide resolved

ilya-lavrenov reviewed Sep 22, 2021

View reviewed changes

...tests/functional/plugin/cpu/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp Outdated Show resolved Hide resolved

nosovmik added 4 commits September 22, 2021 21:24

Reference implementation for NV12toRGB and NV12toBGR operations

5dd65e6

Tests: - ngraph: visitor + type_prop - template plugin: reference implementation - inference-engine: shared tests for plugins - cpu plugin: compare with ref implementation tests

Fix clang

f78115e

Serialization tests

19af90f

Fix clang-format

dd418d7

ilya-lavrenov added this to the 2022.1 milestone Sep 22, 2021

ilyachur reviewed Sep 23, 2021

View reviewed changes

ngraph/core/include/openvino/op/nv12_to_bgr.hpp Show resolved Hide resolved

nosovmik added 3 commits September 23, 2021 13:53

Changed 'f32' to 'any supported floating-point type'

8d26f81

Added appropriate shape inference tests Added error test for >2 inputs Fixed failed CI tests

Merge remote-tracking branch 'upstream/master' into ov20/nv12_op_only

1fca192

Updates after rebase

50ec1f7

+ Try to fix Ninja build

ilyachur reviewed Sep 24, 2021

View reviewed changes

ngraph/core/include/ngraph/op/nv12_to_rgb.hpp Outdated Show resolved Hide resolved

ilya-lavrenov assigned ilyachur Sep 24, 2021

nosovmik added 2 commits September 24, 2021 16:15

Fix CI

2eb9d4e

Merge remote-tracking branch 'upstream/master' into ov20/nv12_op_only

86c482e

ilya-lavrenov reviewed Sep 27, 2021

View reviewed changes

ngraph/core/reference/include/ngraph/runtime/reference/convert_color_nv12.hpp Show resolved Hide resolved

Merge remote-tracking branch 'upstream/master' into ov20/nv12_op_only

14ca241

# Conflicts: # ngraph/core/src/preprocess/preprocess_steps_impl.cpp

ilya-lavrenov requested a review from ilyachur September 27, 2021 09:43

ilya-lavrenov approved these changes Sep 27, 2021

View reviewed changes

Support endianness + potential fix of win32 test fails

f6bf84a

ilya-lavrenov assigned e-nugmanova Sep 27, 2021

Fix review comment

90c5374

ilya-lavrenov requested a review from ArtemySkrebkov September 28, 2021 09:54

ilyachur reviewed Sep 28, 2021

View reviewed changes

nosovmik added 2 commits September 28, 2021 18:54

Merge remote-tracking branch 'upstream/master' into ov20/nv12_op_only

73cbde1

Fix review comments

dd7db91

ilyachur reviewed Sep 29, 2021

View reviewed changes

nosovmik added 4 commits September 29, 2021 13:24

Fix unit test build

877ee6e

Fix unit test build #2

3186d4a

Possible build fix 3

769c2f8

Simplified reference tests

cd0cb81

Observed issue with shuffling Y pixels on little-endian systems, added tests

ilyachur approved these changes Sep 30, 2021

View reviewed changes

e-nugmanova previously requested changes Sep 30, 2021

View reviewed changes

ilya-lavrenov merged commit 6e05cea into openvinotoolkit:master Sep 30, 2021

nosovmik mentioned this pull request Oct 1, 2021

Temporary disable sporadically failed test (PR #7601) #7782

Merged

ilyachur pushed a commit that referenced this pull request Oct 1, 2021

Temporary disable sporadically failed test (PR #7601) (#7782)

a883b5c

* Temporary disable sporadically failed test * Looks like skip test config didn't skip the test

nosovmik mentioned this pull request Oct 4, 2021

[OV20] Convert NV12 to RGB operation + preprocessing #7508

Merged

nosovmik mentioned this pull request Nov 18, 2021

[I420 color conversion] I420toRGB/I420toBGR reference implementation #8605

Merged

Conversation

nosovmik commented Sep 22, 2021

Details:

Tests:

Tickets:

Uh oh!

Uh oh!

ilya-lavrenov commented Sep 22, 2021

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

ilya-lavrenov commented Sep 28, 2021

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

ilya-lavrenov commented Sep 30, 2021

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants