BuildingForRaspbianStretchOS

Build for Raspbian Stretch* OS

NOTE: MYRIAD plugin and ARM CPU plugin are supported. The detailed instruction how to build ARM plugin is available in OpenVINO contrib wiki.

Table of content

• Hardware Requirements
• Native Compilation
• Cross Compilation Using Docker*
• Additional Build Options
• (Optional) Additional Installation Steps for the Intel® Neural Compute Stick 2
  • For Linux, Raspbian Stretch* OS

Hardware Requirements

• Raspberry Pi* 2 or 3 with Raspbian* Stretch OS (32-bit). Check that it's CPU supports ARMv7 instruction set (uname -m command returns armv7l).

  NOTE: Despite the Raspberry Pi* CPU is ARMv8, 32-bit OS detects ARMv7 CPU instruction set. The default gcc compiler applies ARMv6 architecture flag for compatibility with lower versions of boards. For more information, run the gcc -Q --help=target command and refer to the description of the -march= option.

You can compile the Inference Engine for Raspberry Pi* in one of the two ways:

• Native Compilation, which is the simplest way, but time-consuming
• Cross Compilation Using Docker*, which is the recommended way

Native Compilation

Native compilation of the Inference Engine is the most straightforward solution. However, it might take at least one hour to complete on Raspberry Pi* 3.

1. Install dependencies:

• for MYRIAD support only:

  sudo apt-get update
  sudo apt-get install -y git cmake libusb-1.0-0-dev

• for both MYRIAD and ARM CPU plugins support:

  sudo apt-get update
  sudo apt-get install -y git cmake libusb-1.0-0-dev scons build-essential

2. Clone needed repositories:

• for MYRIAD support only:

git clone --recurse-submodules --single-branch --branch=master https://github.com/openvinotoolkit/openvino.git 

• for both MYRIAD and ARM CPU plugins support:

git clone --recurse-submodules --single-branch --branch=master https://github.com/openvinotoolkit/openvino.git 
git clone --recurse-submodules --single-branch --branch=master https://github.com/openvinotoolkit/openvino_contrib.git 

3. Go to the cloned openvino repository:

cd openvino

4. Create a build folder:

mkdir build && cd build

5. Build the Inference Engine:

• for MYRIAD support only:

  cmake -DCMAKE_BUILD_TYPE=Release \
        -DTHREADING=SEQ \
  .. && make

• for both MYRIAD and ARM CPU plugins support:

  cmake -DCMAKE_BUILD_TYPE=Release \
        -DTHREADING=SEQ \
        -DCMAKE_CXX_FLAGS="-pthread" \
        -DIE_EXTRA_MODULES=<OPENVINO_CONTRIB_PATH>/openvino_contrib/modules/arm_plugin \
        -DARM_COMPUTE_SCONS_JOBS=$(nproc --all) \
  .. && make

  NOTE: By default OpenVINO CMake scripts try to introspect the system and enable all possible functionality based on that. You can look at the CMake output and see warnings, which show that some functionality is turned off and the corresponding reason, guiding what to do to install additionally to enable unavailable functionality. Additionally, you can change CMake options to enable / disable some functionality, add / remove compilation flags, provide custom version of dependencies. Please, read CMake options for custom compilation for this information..

Cross Compilation Using Docker*

To cross-compile MYRIAD and ARM CPU plugins using pre-configured Dockerfile you can use the following instruction: Build OpenCV, OpenVINO™ and the plugin using pre- configured Dockerfile.

NOTE: Native applications that link to cross-compiled Inference Engine library require an extra compilation flag -march=armv7-a.

Additional Build Options

You can use the following additional build options:

• Required versions of OpenCV packages are downloaded automatically by the CMake-based script. If you want to use the automatically downloaded packages but you have already installed OpenCV packages configured in your environment, you may need to clean the OpenCV_DIR environment variable before running the cmake command; otherwise they won't be downloaded and the build may fail if incompatible versions were installed.

• If the CMake-based build script cannot find and download the OpenCV package that is supported on your platform, or if you want to use a custom build of the OpenCV library, see how to Use Custom OpenCV Builds.

• To build Python API wrapper, install libpython3-dev:armhf and python3-pip packages using apt-get; then install numpy and cython python modules via pip3, adding the following options:

  -DENABLE_PYTHON=ON \
  -DPYTHON_EXECUTABLE=/usr/bin/python3.7 \
  -DPYTHON_LIBRARY=/usr/lib/arm-linux-gnueabihf/libpython3.7m.so \
  -DPYTHON_INCLUDE_DIR=/usr/include/python3.7

• nGraph-specific compilation options: -DNGRAPH_ONNX_IMPORT_ENABLE=ON enables the building of the nGraph ONNX importer. -DNGRAPH_DEBUG_ENABLE=ON enables additional debug prints.

(Optional) Additional Installation Steps for the Intel® Neural Compute Stick 2

NOTE: These steps are only required if you want to perform inference on the Intel® Neural Compute Stick 2 using the Inference Engine MYRIAD Plugin. See also Intel® Neural Compute Stick 2 Get Started.

For Linux, Raspbian* Stretch OS

1. Add the current Linux user to the users group; you will need to log out and log in for it to take effect:

sudo usermod -a -G users "$(whoami)"

2. To perform inference on Intel® Neural Compute Stick 2, install the USB rules as follows:

cat <<EOF > 97-myriad-usbboot.rules
SUBSYSTEM=="usb", ATTRS{idProduct}=="2485", ATTRS{idVendor}=="03e7", GROUP="users", MODE="0666", ENV{ID_MM_DEVICE_IGNORE}="1"
SUBSYSTEM=="usb", ATTRS{idProduct}=="f63b", ATTRS{idVendor}=="03e7", GROUP="users", MODE="0666", ENV{ID_MM_DEVICE_IGNORE}="1"
EOF

sudo cp 97-myriad-usbboot.rules /etc/udev/rules.d/

sudo udevadm control --reload-rules

sudo udevadm trigger

sudo ldconfig

rm 97-myriad-usbboot.rules