Mikhail Ryzhov
e2c67bd508
* Added onnx support for C samples * Added wheel packaging configuration * ADD cmake option * Small refactoring * Fixes for linux env * Fixed macOS issues * removed test code * Added requirements file * Added myriad plugin * [PIP] Runtime wheel packaging v2 * Added rpath logic * Setting rpath for bindings * Formatting fixes * Move target project 1 directory above * Added target dependencies * Added blacklist for runtime libs * Corrected blacklist scope * Added wheel packaging configuration * ADD cmake option * Small refactoring * Fixes for linux env * Fixed macOS issues * removed test code * Added requirements file * Added myriad plugin * [PIP] Runtime wheel packaging v2 * Added rpath logic * Setting rpath for bindings * Formatting fixes * Move target project 1 directory above * Added blacklist for runtime libs * Changed lib exstention om macOS * ADD cmake option * Revert "ADD cmake option" This reverts commit 36f98c713bb337a160f9af6c7c79c4371fdfc45f. * Revert "Changed lib exstention om macOS" This reverts commit 80086fe1230b64fbcf396de82bc731c10f738eae. * Revert "Merge branch 'feature/wheel_pack' of https://github.com/mryzhov/openvino into feature/wheel_pack" This reverts commit 7560d9ab55edc1f8877b83821542570060fb13d8, reversing changes made to c287798f994dcefc074a06ff7c3ef86222674cc7. * Revert "Added onnx support for C samples" This reverts commit 26c595ac136d99bd576d307d33ca15feb15f81e4. * Fixed merge issues * Fixed typo in mac tool * Code review fixes * Simplified deps and added fatal error code review fixes * Removed test data * Fixed setup.py review comments * Removed apache 2.0 license * Review fixes * fixed pylint issues * Fixed python api install directory * Using cmake detected python binary * Changed wheel build directory * Renamed subdir from install to wheel * Removed pylint log * Made license, description and requirements configurable by cmake options Those files may be changed in CI * Changed variable name * Glob instead of os.walk * Corrected package name in description * Added wheel building instructions to readme * small typo fix * Changes to support CI build 1) Setup.py can be run without cmake build 2) Wheel metadata can be set by environment variables 3) Cmake build uses configuration from .env file * Removed unused file
2.3 KiB
2.3 KiB
Software Requirements
- CMake* 3.9 or later
- Microsoft* Visual Studio 2015 or later on Windows*
- gcc 4.8 or later on Linux
- Python 2.7 or higher on Linux*
- Python 3.6 or higher on Windows*
Prerequisites
- Install Inference Engine Python API dependencies:
pip3 install -r requirements.txt
Building on Linux
Build Inference Engine Python API alongside with the Inference Engine build. You need to run Inference Engine build with the following flags:
cd <IE_ROOT>
mkdir -p build
cd build
cmake -DENABLE_PYTHON=ON -DPYTHON_EXECUTABLE=`which python3.6` \
-DPYTHON_LIBRARY=/usr/lib/x86_64-linux-gnu/libpython3.6m.so \
-DPYTHON_INCLUDE_DIR=/usr/include/python3.6 ..
make -j16
Building on Windows
You need to run Inference Engine build with the following flags:
cd <IE_ROOT>
mkdir build
cd build
set PATH=C:\Program Files\Python36\Scripts;%PATH%
cmake -G "Visual Studio 15 2017 Win64" ^
-DENABLE_PYTHON=ON ^
-DPYTHON_EXECUTABLE="C:\Program Files\Python36\python.exe" ^
-DPYTHON_INCLUDE_DIR="C:\Program Files\Python36\include" ^
-DPYTHON_LIBRARY="C:\Program Files\Python36\libs\python36.lib" ..
Then build generated solution INFERENCE_ENGINE_DRIVER.sln using Microsoft* Visual Studio or run cmake --build . --config Release to build from the command line.
Building Python wheel
- Install Inference Engine Python API dependencies:
pip3 install -r wheel/requirements-dev.txt
- Install the patchelf tool on Linux only:
sudo apt install patchelf
- Run Inference Engine build with the following options:
-DENABLE_PYTHON=ON
-DENABLE_WHEEL=ON
If you need to include other components to the package you need to enable them too. For example, to include ngraph python API:
-NGRAPH_PYTHON_BUILD_ENABLE=ON
Running sample
Before running the Python samples:
- add the folder with built
openvinoPython module (located atbin/intel64/Release/lib/python_api/python3.6for Linux) to the PYTHONPATH environment variable. - add the folder with Inference Engine libraries to LD_LIBRARY_PATH variable on Linux (or PATH on Windows).
Example of command line to run classification sample:
python3 sample/classification_sample.py -m <path/to/xml> -i <path/to/input/image> -d CPU