diff --git a/dockerfiles/Dockerfile.openvino b/dockerfiles/Dockerfile.openvino index 9c2c9b336a..0d1a21b1f3 100644 --- a/dockerfiles/Dockerfile.openvino +++ b/dockerfiles/Dockerfile.openvino @@ -30,7 +30,7 @@ ENV LANG en_US.UTF-8 RUN apt update && \ apt -y install git sudo wget locales \ - zip x11-apps lsb-core cpio libboost-python-dev libpng-dev zlib1g-dev libnuma1 ocl-icd-libopencl1 clinfo libboost-filesystem1.58.0 libboost-thread1.58.0 protobuf-compiler libprotoc-dev libusb-1.0-0-dev autoconf automake libtool && \ + zip x11-apps lsb-core cpio libboost-python-dev libpng-dev zlib1g-dev libnuma1 ocl-icd-libopencl1 clinfo libboost-filesystem1.58.0 libboost-thread1.58.0 protobuf-compiler libprotoc-dev libusb-1.0-0-dev autoconf automake libtool libudev-dev libjson-c-dev && \ cd ${MY_ROOT} && \ git clone --recursive -b $ONNXRUNTIME_BRANCH $ONNXRUNTIME_REPO onnxruntime && \ cp onnxruntime/docs/Privacy.md /code/Privacy.md && \ diff --git a/dockerfiles/README.md b/dockerfiles/README.md index 8b95975e13..b1959dd9fc 100644 --- a/dockerfiles/README.md +++ b/dockerfiles/README.md @@ -157,15 +157,21 @@ Use `docker pull` with any of the images and tags below to pull an image and try ### OpenVINO on VAD-M Accelerator Version -1. Build the docker image from the DockerFile in this repository. - ``` - docker build --rm -t onnxruntime-vadr --build-arg DEVICE=VAD-M_FP16 --network host . - ``` -2. Install the HDDL drivers on the host machine according to the reference in [here](https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_linux_ivad_vpu.html) +1. Download OpenVINO **Full package** for version **2020.2** for Linux on host machine from [this link](https://software.intel.com/en-us/openvino-toolkit/choose-download) and install it with the help of instructions from [this link](https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_linux.html) -3. Run the docker image by mounting the device drivers +2. Install the drivers on the host machine according to the reference in [here](https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_linux_ivad_vpu.html) + +3. Build the docker image from the DockerFile in this repository. + ``` + docker build --rm -t onnxruntime-vadm --build-arg DEVICE=VAD-M_FP16 --network host . + ``` +4. Run hddldaemon on the host in a separate terminal session using the following command:  + ``` + $HDDL_INSTALL_DIR/bin/hddldaemon + ``` +5. Run the docker image by mounting the device drivers ``` - docker run -it --device --mount type=bind,source=/var/tmp,destination=/var/tmp --device /dev/ion:/dev/ion onnxruntime-hddl:latest + docker run -it --device --mount type=bind,source=/var/tmp,destination=/var/tmp --device /dev/ion:/dev/ion onnxruntime-vadm:latest ``` ## ARM 32v7 diff --git a/dockerfiles/scripts/install_common_deps.sh b/dockerfiles/scripts/install_common_deps.sh index d334b04232..26d246ee5a 100644 --- a/dockerfiles/scripts/install_common_deps.sh +++ b/dockerfiles/scripts/install_common_deps.sh @@ -19,6 +19,6 @@ pip install numpy rm -rf /opt/miniconda/pkgs # Dependencies: cmake -sudo wget --quiet https://github.com/Kitware/CMake/releases/download/v3.14.3/cmake-3.14.3-Linux-x86_64.tar.gz +wget --quiet https://github.com/Kitware/CMake/releases/download/v3.14.3/cmake-3.14.3-Linux-x86_64.tar.gz tar zxf cmake-3.14.3-Linux-x86_64.tar.gz rm -rf cmake-3.14.3-Linux-x86_64.tar.gz