Tomasz Jankowski
dcfaf424a0
[ONNX FE] Add support for partial shapes with boundaries ( #9321 )
2021-12-21 16:38:15 +01:00
Andrew Kwangwoong Park
6f437fc1bd
[GPU] Exclude peak memory usage from the result of memory statistics ( #9332 )
...
Signed-off-by: Andrew Kwangwoong Park <andrew.kwangwoong.park@intel.com>
2021-12-21 18:03:38 +03:00
Katarzyna Mitrus
132b755a46
Enable Slice-8 dynamic lower bounds serialization tests ( #9323 )
2021-12-21 15:57:04 +03:00
Vitaliy Urusovskij
de980b8089
Actualize DeterministicityTest: update headers and used opset ( #9335 )
2021-12-21 15:31:43 +03:00
Gorokhov Dmitriy
2d73eb6157
[CPU] Migration on oneDNN v2.4.4 ( #9326 )
...
Co-authored-by: Anton Voronov <anton.voronov@intel.com>
2021-12-21 14:45:44 +03:00
Ivan Tikhonov
9334f34ff0
TensorFlow FrontEnd Refactoring ( #9173 )
...
* Move tensorflow fe to openvino subfolder; renaming; refactoring
* codestyle
* delete redundant file
* fix Win build
* fix missprint
2021-12-21 14:35:58 +03:00
Indira Salyahova
0100060cd9
Update README.md ( #9337 )
2021-12-21 11:16:41 +00:00
Vladimir Paramuzov
5f53e6f697
[GPU] Try disabling onednn primitive cache ( #9289 )
2021-12-21 13:49:15 +03:00
tgubanova-lohika
f9ece370f3
[GPU] Implement RandomUniform operation ( #9043 )
...
* [GPU] Implement Random Uniform kernel
* [GPU] Add random uniform kernel selector
* [GPU] Add random uniform primitive
* [GPU] Add random uniform instantiation helpers
* [GPU] Implement unit test for the random uniform operation
* [GPU] Add random uniform operation builder in cldnn_engine plugin
* [GPU] Add single layer tests for the random uniform operation
* [GPU] Add conversion for Random Uniform output type
* [GPU] Add RTTI macroses to RandomUniform operation
2021-12-21 13:24:07 +03:00
Aleksandr Korolev
4b0a2c9127
[VPU] Coverity fixes ( #9214 )
...
Some coverity fixes
2021-12-21 12:58:05 +03:00
Ilya Churaev
ec858fcffd
Add OV developer config ( #9298 )
...
* Introduced OV developer package config
* Remove new targets from old configs
* Fixed python build
* Removed OpenVINO_SOURCE_DIR from developer config
2021-12-21 12:25:07 +03:00
Maxim Shevtsov
3032f20e03
brushed the #streams logic when #requests is limited ( #9184 )
2021-12-21 12:07:59 +03:00
Milana Shhanukova
0262d05a77
[POT] Ports in input nodes in BC ( #8643 )
...
* Make ports visible in names in BC algo
* mistypes
* updates in regards to lstm
* lstm update
* delete code dublication
* mistype in get_node_data_type
2021-12-21 10:58:20 +03:00
Krzysztof Bruniecki
6c92ce48c1
Remove non official code ( #9315 )
...
- feature to export for embedded GNA3 which is not in fact supported.
- SW emulation modes like SSE etc, which are not useful and are undocumented.
2021-12-21 09:44:06 +03:00
Vitaliy Urusovskij
cf15cbd301
Save Parameters order during IR deserialization ( #9286 )
...
* Save Parameters order during IR deserialization
* Add test to check inputs/outputs in IR
2021-12-21 06:45:14 +03:00
Ilya Churaev
b5238e55e1
Removed inference_engine, ngraph, transformations libraries ( #9309 )
2021-12-21 05:27:53 +03:00
Maxim Gordeev
3c93c3e766
Hello classification, classification_async, hello_reshape_ssd python samples with API 2.0 ( #9091 )
...
* Hello classification python with API 2.0
* Update samples/python/hello_classification/hello_classification.py
Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
* Update samples/python/hello_classification/hello_classification.py
Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
* changed linters processing
* Update samples/python/hello_classification/hello_classification.py
Co-authored-by: Vladimir Dudnik <vladimir.dudnik@intel.com>
* Update samples/python/hello_classification/hello_classification.py
Co-authored-by: Vladimir Dudnik <vladimir.dudnik@intel.com>
* Update samples/python/hello_classification/hello_classification.py
Co-authored-by: Vladimir Dudnik <vladimir.dudnik@intel.com>
* Update samples/python/hello_classification/hello_classification.py
Co-authored-by: Vladimir Dudnik <vladimir.dudnik@intel.com>
* Update samples/python/hello_classification/hello_classification.py
Co-authored-by: Vladimir Dudnik <vladimir.dudnik@intel.com>
* updated import
* Moved classification_sample_async to new API 2.0
* moved hello_reshape_ssd sample to new API 2.0
* [classification_sample_async] refactoring
* [hello_classification] refactoring
* [hello_reshape_ssd] refactoring
Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
Co-authored-by: Vladimir Dudnik <vladimir.dudnik@intel.com>
Co-authored-by: Dmitry Pigasin <dmitry.pigasin@intel.com>
2021-12-21 01:33:12 +03:00
Zlobin Vladimir
4f9d908c1e
Catch up https://github.com/openvinotoolkit/open_model_zoo/pull/3002 ( #9324 )
2021-12-21 00:44:47 +03:00
Mikhail Nosov
b7ffbe5459
Leftover: Added tests for fix for PR #8546 ( #9313 )
...
Added more preprocessing unit tests for fix of PR #8546
Testing: revert changes for the fix. Verify that new tests are failed
2021-12-20 23:32:14 +03:00
Tomasz Dołbniak
29eb83d904
MO: adding extra tensor names during the graph modification ( #9292 )
2021-12-20 23:23:03 +03:00
Vladimir Zinoviev
be0e77304f
[LPT] getDequantization: INT4 input support to avoid ConvertSubtract transformation ( #9288 )
2021-12-20 22:51:44 +03:00
Ivan Novoselov
fa9434494f
[Snippets][CPU] Eltwise subgraphs code generation ( #7936 )
2021-12-20 22:45:01 +03:00
Alexander Zhogov
c10a27f601
github_org_control: Update to the latest version ( #9322 )
2021-12-20 21:04:28 +03:00
Tomasz Dołbniak
46c9755b6e
ONNX FE tests: fix after a conflicting merge of 2 PRs ( #9320 )
...
* Fix after a conflicting merge of 2 PRs
* Even more alignment
2021-12-20 20:46:15 +03:00
Wang, Yang
808d6a3dc1
Add default device value for ie.LoadNetwork ( #8956 )
...
* [Auto Plugin] Change LoadNetwork api with default deviceName "AUTO" and add corrresponding test case.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Remove the changes for ImportNetwork API.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update LoadNetwork API.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update compile_network API for OV2.0.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Modify the visable scope of global value 'DEFAULT_DEVICE_NAME'.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update the test case for compile_model wit the default device.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Replace the pointer with the string object as the default name of device.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Add a new test case for compile_model to defatul device.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Add a new test case for compile_model loading network to defatul device.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Add a new test case for compile_model loading network to defatul device.
Signed-off-by: ywang2 <yang4.wang@intel.com>
* Update tese case for LoadNetwork and compile_model.
Signed-off-by: ywang2 <yang4.wang@intel.com>
2021-12-20 19:48:54 +03:00
Elizaveta Lobanova
d4fdbba7d8
[GNA] Fixed a bug with channel multiplier for int8 weights quantization ( #9234 )
2021-12-20 18:12:56 +03:00
song, bell
1901f33bd3
auto dynamic shape ( #8731 )
...
* initial commit
Signed-off-by: fishbell <bell.song@intel.com>
* overwrite GetBlob/SetBlob to support dynamic shape when needed
Signed-off-by: fishbell <bell.song@intel.com>
* extend workers
Signed-off-by: fishbell <bell.song@intel.com>
* clean up code
Signed-off-by: fishbell <bell.song@intel.com>
* fix lock and add case for CPU,GPU
Signed-off-by: fishbell <bell.song@intel.com>
* fix mem leak
Signed-off-by: fishbell <bell.song@intel.com>
* clean up allocated worker
Signed-off-by: fishbell <bell.song@intel.com>
* fix test case failure
Signed-off-by: fishbell <bell.song@intel.com>
* enable case for chaining
Signed-off-by: fishbell <bell.song@intel.com>
* fix arm compile issue
Signed-off-by: fishbell <bell.song@intel.com>
* clang format, fix potential threading issue
Signed-off-by: fishbell <bell.song@intel.com>
* clean up idle request queue if infer request destroyed
Signed-off-by: fishbell <bell.song@intel.com>
* keep multi legacy behavior
Signed-off-by: fishbell <bell.song@intel.com>
* elegant way to handle recycling
Signed-off-by: fishbell <bell.song@intel.com>
* avoid the exception with set output blob in auto dynamic case
Signed-off-by: fishbell <bell.song@intel.com>
* remove increase workers logic
Signed-off-by: fishbell <bell.song@intel.com>
* formatting
Signed-off-by: fishbell <bell.song@intel.com>
* remove the irrelevant code to dynamic shape
Signed-off-by: fishbell <bell.song@intel.com>
* filter target device to CPU in the case of dynamic shape
Signed-off-by: fishbell <bell.song@intel.com>
* fix logic in selectdevice, add case for GPU
Signed-off-by: fishbell <bell.song@intel.com>
* add case for AUTO:GPU
Signed-off-by: fishbell <bell.song@intel.com>
* fix build error
Signed-off-by: fishbell <bell.song@intel.com>
* add comment for skipped cases
Signed-off-by: fishbell <bell.song@intel.com>
* fix the case failure caused by naming conflict
Signed-off-by: fishbell <bell.song@intel.com>
* move file to new folder
Signed-off-by: fishbell <bell.song@intel.com>
* change to 2.0 API in plugin
Signed-off-by: fishbell <bell.song@intel.com>
* refactor mkldnn code change
Signed-off-by: fishbell <bell.song@intel.com>
* formatting
Signed-off-by: fishbell <bell.song@intel.com>
2021-12-20 18:06:50 +03:00
Yuan Hu
cf92c54a12
[Auto plugin] select logic need to check CPU precision ( #9259 )
...
* cpu also need to check precision
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* fix test case failed issue
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
2021-12-20 17:32:00 +03:00
Piotr Szmelczynski
513867e168
[PYTHON] Rename arg names python api ( #9209 )
2021-12-20 14:31:48 +01:00
Gleb Kazantaev
249e1266fb
MO: --transform Pruning option ( #9304 )
2021-12-20 15:55:50 +03:00
Vladislav Golubev
191b15a228
build fix ( #9311 )
2021-12-20 14:58:04 +03:00
Sergey Lyubimtsev
ff330ea41e
Fetch requirements directly from openvino tools ( #9154 )
...
* Fetch requirements directly from accuracy_checker
* get requirements from pot & benchmark tool directly
2021-12-20 14:01:17 +03:00
Vladislav Golubev
f3dd39e3d2
DetectionOutput8ToDetectionOutput1 test disabled ( #9307 )
2021-12-20 13:25:09 +03:00
Liubov Talamanova
a847e1f7fa
[POT] Added printing IE, MO and POT versions during POT launch ( #8679 )
...
* Add POT version print
* Changed version in setup.py
* Add version to setup.py
* Update imports
2021-12-20 13:09:22 +03:00
Vladislav Golubev
ca7600edde
[dynamism][Transformations] Sequences conversions: dynamic shapes support ( #7766 )
...
* [Transformations] Sequences conversion: refactoring & dynamic shapes support
* tests moved
2021-12-20 12:49:39 +03:00
Vladimir Paramuzov
d56dc20956
[GPU] Moved GPU remote headers to intel_gpu folder and namespace ( #9290 )
2021-12-20 12:14:32 +03:00
Anton Pankratov
114d37b28c
Fixed release oreder ( #9218 )
2021-12-20 12:11:32 +03:00
Ilya Churaev
dbf8fcf556
Create ov_runtime library ( #9199 )
...
* Create ov_runtime library
* Added dev target
* Fixed SOURCE_DIR property for interface lib
* Fixed missed include path
* Fixed SOURCES for plugins and frontends
* Fixed Windows export
* Try to fix preproc build
* Fixed MKLDNNPlugin
* Fix C API
* Try to fix public CI
* Fixed comments
* Use TARGET_NAME variable
* Fixed static build
* Fixed target name in comfig
* Revert "Fixed target name in comfig"
This reverts commit f61c1e0c09
2021-12-20 11:59:08 +03:00
Edward Shogulin
37ad512d98
[CPU] Optimize quantization scheme for SPR/ATS ( #7549 )
...
* [CPU] Optimize quantization scheme for SPR/ATS
* [CPU] [LPT] plugin tests
* [GPU] [LPT] plugin tests
* [CPU] limitation was removed
* [CPU] optimization FP32 old way support
* [LPT] comment fix
* [LPT] Multiply plugin test improvement
* [LPT] Multiply support
* [LPT] GPU tests fix
* [LPT] test quick fix
* [LPT] new ppi fix
* look like spent time for tests refactoring
2021-12-20 11:19:40 +03:00
Egor Duplensky
abee3ea4d4
[CPU] Refactoring. Avoid using align arg when appending post ops ( #9225 )
...
Always align legacy scale shift post ops
2021-12-20 10:23:32 +03:00
Vladislav Golubev
fab4448ebd
[dynamism][Transformations] Fusing transformations: dynamic batch support ( #7351 )
2021-12-20 10:11:43 +03:00
Liubov Talamanova
4564867a44
Update POT tests for OMZ location in openvino/thirdparty ( #9171 )
...
* Move OMZ to thirdparty/open_model_zoo
* Improve diagnostic of issues
* Update path to OMZ in the Python wheel setup.py
* Update POT tests for OMZ location in openvino/thirdparty
* fix mo path
Co-authored-by: azhogov <alexander.zhogov@intel.com>
2021-12-20 09:10:39 +03:00
Jade Cho
a4518ae595
[GPU] Add DumpLayersLimitBatch config to GPU debug utils. ( #9196 )
...
* Add DumpLayersLimitBatch config to GPU debug utils.
+ Support OV_GPU_Help config
+ Only run first inference if OV_GPU_DumpLayersPath is set.
+ Fix dump graph bug.
* Apply some comments
* Remove unnecessary code.
2021-12-20 14:19:53 +09:00
Maxim Gordeev
abcd7486a9
Moving of C++ speech sample to OpenVINO API 2.0 ( #9027 )
...
* Moved Speech sample to OpenVINO 2.0
* improved samples's score
* changed code style
* added GNA configs
* renamed function due to new API
* added dynamic batch
* reordered includes
* speech_sample has more than 1 input
* added oname processing
* added multi input
* fixed notes
* removed getFullDeviceName with old api
* getFullDeviceName for benchmark
2021-12-19 20:56:40 +03:00
Anton Chetverikov
6b0d1525fd
[MO]Implement additional shape extraction for TF Placeholder operation ( #8817 )
...
* Implement additional shape extraction for TF placeholder operation
* Update checks and add comments
* Use more accurate check
* Extract _output_shapes attr only if we have problems with shape attr
* Add missed import
* Apply suggestions from code review
Update code comments
Co-authored-by: Anastasia Popova <anastasia.popova@intel.com>
* Add update condition to avoid unnecessary checks
* Remove unnecessary checks
Co-authored-by: Anastasia Popova <anastasia.popova@intel.com>
2021-12-18 19:55:06 +03:00
Ivan Tikhonov
526fe3098d
JsonConfig/JsonTranformation/DecoderTransformation Extensions ( #9042 )
...
* Squash commits: JsonConfig/JsonTranformation/DecoderTransformation extensions,
Unit tests, pybindings
* Call transformation_extensions in convert_partially method
* fix codestyle
* move json extensions to offline transformations
* Fix unit tests
* fix cmake files
* Refactor JsonConfig extensions and FrontEnds
* Update python bindings
* Add missing files
* correct mkl hash
* fix conflicts with master branch
* Resolve review comments
* Revert local changes
* code style
* Add lib destinations
* fix cmake
* correct nlohmann_json hash
* FunctionPass to ModelPass
* fix unit tests and pyopenvino
* fix pyopenvino
* resolve review comments
* revert local change
* Fix dynamic Win build
* Try to fix linux builds
* Fix Lin build: set correct lib directory
* Resolve review commets
* code style
* resolve review comments
* ubuntu20 issue investigation: temporary disable LTO for frontends
* ubuntu20 issue investigation: temporary disable LTO for unit tests
* ubuntu20 issue investigation: temporary disable LTO for thirdparty and core parts
* Revert "ubuntu20 issue investigation: temporary disable LTO for thirdparty and core parts"
This reverts commit 5489072e4a73bd3c6bacdce2ba4830
2021-12-18 18:19:25 +03:00
Tomasz Dołbniak
d82b58a408
Handling of cut + reshape in MO using ONNX FE ( #9102 )
2021-12-18 13:29:40 +01:00
Ilya Churaev
be86ec51ab
Renamed frontends from *ov_frontend to ov_*_frontend ( #9275 )
...
* Renamed frontends from *ov_frontend to ov_*_frontend
* Fixed MO
* Fixed include
2021-12-18 13:25:42 +03:00
Ilya Churaev
e02e777df3
Fixed codeowners ( #9283 )
2021-12-18 02:03:09 +03:00
Mikhail Nosov
c7a3c93d3f
FrontEnd API - change 'shared_ptr' to 'const shared_ptr&' ( #9287 )
...
* FrontEnd API - change 'shared_ptr' to 'const shared_ptr&' in public arguments
* Fix clang-format
2021-12-17 22:39:13 +03:00
