* Renaming all frontends from "*_ngraph_frontend*" to "_ov_frontend*"
Also Debug builds on Windows release frontends without "d" suffix will not be loaded
* Fix review comments and add wheels test debug prints
* More debug prints
* Load by absolute path and remove debug prints
* added function for calculating the number of discret levels in the input tensors and tests for this function
* added function for calculating the number of discret levels in the input tensors and tests for this function
* fixed pylint issues
* changed the function for delta estimation from mean to min
* added empty delta array processing in get_num_levels func and tests for it
* Add inputs-to-files path to benchmark_tool
* Add inputs-to-files path to benchmark_tool
* Add inputs-to-files path to benchmark_tool
* Remove `<>`
* Fix binary input fill
* Remove redundant checks
Change `:` delimiter to `::`
* Delete print
* Change delimiter to `:`
Add support for list of files
* Add warning if some inputs filled with random values
* Add openvino-dev wheel build from opensource
* fix path to OMZ tools
* fix for working directory
* change order
* pull out requirements to requirements.txt for snyk scans
* fix patterns
* fix patterns
* fix AttributeError: : 'PosixPath' object has no attribute 'startswith'
* rebasing the perf-modes-2021.3 to the 2021.4
Caveats:
the (explicit) setting #streams is not disabled (as it was before for experiments with DLBenchmark), and the logic slighlty differ (streamsSet)
(cherry picked from commit 1ae1edc0ed)
* overriding streams (to force the TPUT mode to the DLBenchnark)
(cherry picked from commit 7f506cda31)
* disabling reducing #streams to fully mimic baseline c4df94d42d of the 2021.3 (before experiments)
(cherry picked from commit 85073dd1dd)
* clang/identation
(cherry picked from commit 050a4155a9)
* splitting the Transformation to general and CPU specific.
Now hopefully,this fully mimics the baseline c4df94d42d of the 2021.3 (before experiments), as the streams reduce num (as well as early exit on GRU/LSTM/TensorIterator) is deisabled
(cherry picked from commit e98b2c1a67)
* disabling GRU/LSTM/TI + reducing of streams + 5D considered compute-limited only for int8
(cherry picked from commit 32b8d80dee)
* refactored to avoid compute_limited_ratio, reverted the reducing #streams, removed LSTM from limitations
(cherry picked from commit f2b972171b)
* isa-based threshold logic
(cherry picked from commit b218457e1a)
* mode->hint
(cherry picked from commit ec20aa8eca)
* optional PERFORMANCE_HINT_NUM_REQUESTS
(cherry picked from commit 5a3883e3f3)
* moving the perfHints to the common OV config class + initial tests (CPU only, as the actual AUTO/MULTI should be accommodated on the master)
(cherry picked from commit (then fixed)45bafe7d527f466507dea0693aeed51be4ebf776)
* AUTO support for PerfHints
* MULTI support for PerfHints
* Enabling Perf hints for the GPU plugin
* brushing settings output a bit
* disabling "throughput" perf hint being default (until OV 2.0)
* uncommenting the logic which was disabled to force the DLBenchmark to use the throughput mode by default
* removing dead and experimental code, and debug printfs
* clang/code-style
* code-review remarks
* Moved the output of the actual params that the hint produced to the right place
* aligning MULTI's GetConfig beh to HETERO's as captured in the preso (CVS-59960) ratified with the ArchForum
* clang
* benchmark_app brushing
* Update inference-engine/samples/benchmark_app/README.md
* propagating the perf hints thru one more scenario in the merged AUTO-MULTI
* fixed mispint
* Python benchmark_app update for perf hints
* addresssing reviewers comments on the python benchmark_app
* simplifying/brushing logic a bit
* refactor the heuristic to the separate file (to be shared with iGPU soon)
* refactor conversion of modes to the specific GPU config per feedback from Vladimir
* add missed __init__.py files
* Update __init__.py
empty line
* Merge infirence_engine/tools/benchmark_tool with tools/benchmark_tool
* Update MD links
* remove benchmark_tool from package_BOM.txt
* add tools folder to the list of Doxygen files
* fix relative paths
* Update index.md
remove extra line
* Add input image scale flag in benchmark app.
- user set input image scale with -iscale.
input is divided by scale.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Apply image scale, mean parameter in benchmark APP
Means and sacles values per channel
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Fix clang-format
Signed-off-by: hyunback <hyunback.kim@intel.com>
* fix clang-format issue2.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Update benchmark tool to align the format of mean and sacle values with MO arguments.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Remove debug print.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Added pugixml as submodule
* CVS-34900: updated pugixml to v1.11.4
* Fixed link with pugixml
* USe pugixml::static
* Try to fix bug
* Removed GITHUB_PULL_REQUEST
* Replaced OpenVINO_MAIN_SOURCE_DIR -> OpenVINO_SOURCE_DIR
* Removed some usages of IE_MAIN_SOURCE_DIR
* Use ngraph target directly
* enable make clean to remove ie_wheel artifacts
* ./setup.py:132:1: E302 expected 2 blank lines
* fix CI build issue
* Removed not-needed components from ie_wheel
* Use explicit python3 vresion in ngraph pythpn
* Use python3 everywhere
* Reuse python3 more
* Added function to build with Py_LIMITED_API
* Sync 2 cmake python modules
* Fix for tools
* Fixed typo
* Enable python by default
* Enable python build iff python-dev is found
* More migration to Python3_VERSION
* Install wheel requirements
* Fixed ngraph Python separate build
* Fixed cython compilation
* Revert to old packages
* Added suffix
* Specify python version explicitly
* Don't depend on python interp to build python itself
* More improvements
* Revert offline transformations back to ie_wheel
* Refactoring
* Trying to build wheel independently on C++ runtime
* Build wheel only with main OpenVINO
* Fixed typo in test_utils cmake lists
* Adding link stage
* small fix
* git diff
* Try to fix python tests
Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com>
* Python API for LoadNetwork by model file name
* BenchmarkApp: Add caching and LoadNetworkFromFile support
2 new options are introduced
- cache_dir <dir> - enables models caching
- load_from_file - use new perform "LoadNetwork" by model file name
Using both parameters will achieve maximum performance of read/load network on startup
Tests:
1) Run "benchmark_app -h". Help will display 2 new options. After available devices there will be list of devices with cache support
2) ./benchmark_app -d CPU -i <model.xml> -load_from_file
Verify that some test steps are skipped (related to ReadNetwork, re-shaping etc)
3) Pre-requisite: support of caching shall be enabled for Template plugin
./benchmark_app -d TEMPLATE -i <model.onnx> -load_from_file -cache_dir someDir
Verify that "someDir" is created and generated blob is available
Run again, verify that loading works as well (should be faster as it will not load onnx model)
4) Run same test as (3), but without -load_from_file option. Verify that cache is properly created
For some devices loadNetwork time shall be improved when cache is available
* Removed additional timing prints
* Correction from old code
* Revert "Removed additional timing prints"
Additional change - when .blob is chosen instead of .xml, it takes priority over caching flags
* Removed new time printings
As discussed, these time measurements like 'total first inference time' will be available in 'timeTests' scripts
* Fix clang-format issues
* align pypi deps of benchmark, cross check tool, python API
* move cython from python API requirements to requirements-dev
* change requirements to >= for most packages
* update requirements
* set pinned numpy major version in wheel requirements
* set more strict pip requirements-dev in wheel
* change scikit-image version to 0.17
Indira Salyahova
Ilya Churaev
Mikhail Nosov
Milana Shhanukova
Tagir Rakipov
Artur Paniukov
Sergey Lyubimtsev
Nikita Malinin
Milana Shhanukova
Aleksei Kruglov
Julia Kamelina
Artyom Anokhov
Liubov Batanina
Maksim Proshin
Roman Lyamin
Alexander Kozlov
Ilya Lavrenov
Gleb Kazantaev
Roman Donchenko
Maxim Shevtsov
Michał Karzyński
hyunback kim
Ivan Kochin
Mingyu Kim
Vladimir Paramuzov
Ilya Naumov
Nadezhda Ageeva