MIVisionX docker#

Docker is a set of platform as a service (PaaS) products that use OS-level virtualization to deliver software in packages called containers. Read More

Docker workflow on Ubuntu 20.04/22.04#

Prerequisites#

Workflow#

  • Step 1 - Get latest docker image

    sudo docker pull mivisionx/ubuntu-20.04:latest

    • NOTE: Use the above command to bring in latest changes from upstream

  • Step 2 - Run docker image

Run docker image: Local Machine#

sudo docker run -it --privileged --device=/dev/kfd --device=/dev/dri --device=/dev/mem --cap-add=SYS_RAWIO  --group-add video --shm-size=4g --ipc="host" --network=host mivisionx/ubuntu-20.04:latest

  • Test - Computer Vision Workflow

    python3 /workspace/MIVisionX/tests/vision_tests/runVisionTests.py --num_frames 1

  • Test - Neural Network Workflow

    python3 /workspace/MIVisionX/tests/neural_network_tests/runNeuralNetworkTests.py --profiler_level 1

  • Test - Khronos OpenVX 1.3.0 Conformance Test

    python3 /workspace/MIVisionX/tests/conformance_tests/runConformanceTests.py --backend_type HOST

Option 1: Map localhost directory on the docker image#

  • option to map the localhost directory with data to be accessed on the docker image

  • usage: -v {LOCAL_HOST_DIRECTORY_PATH}:{DOCKER_DIRECTORY_PATH}

    sudo docker run -it -v /home/:/root/hostDrive/ --privileged --device=/dev/kfd --device=/dev/dri --device=/dev/mem --cap-add=SYS_RAWIO  --group-add video --shm-size=4g --ipc="host" --network=host mivisionx/ubuntu-20.04:latest

Option 2: Display with docker#

  • Using host display for docker

    xhost +local:root
sudo docker run -it --privileged --device=/dev/kfd --device=/dev/dri --cap-add=SYS_RAWIO --device=/dev/mem --group-add video --network host --env DISPLAY=$DISPLAY --volume="$HOME/.Xauthority:/root/.Xauthority:rw" --volume /tmp/.X11-unix/:/tmp/.X11-unix mivisionx/ubuntu-20.04:latest

  • Test display with MIVisionX sample

    runvx -v /opt/rocm/share/mivisionx/samples/gdf/canny.gdf

Run docker image with display: Remote Server Machine#

sudo docker run -it --privileged --device=/dev/kfd --device=/dev/dri --cap-add=SYS_RAWIO --device=/dev/mem --group-add video --network host --env DISPLAY=$DISPLAY --volume="$HOME/.Xauthority:/root/.Xauthority:rw" --volume /tmp/.X11-unix/:/tmp/.X11-unix mivisionx/ubuntu-20.04:latest

  • Test display with MIVisionX sample

    runvx -v /opt/rocm/share/mivisionx/samples/gdf/canny.gdf

Build - dockerfiles#

sudo docker build --build-arg {ARG_1_NAME}={ARG_1_VALUE} [--build-arg {ARG_2_NAME}={ARG_2_VALUE}] -f {DOCKER_FILE_NAME}.dockerfile -t {DOCKER_IMAGE_NAME} .

Run - docker#

sudo docker run -it --privileged --device=/dev/kfd --device=/dev/dri --cap-add=SYS_RAWIO --device=/dev/mem --group-add video --network host --env DISPLAY=$DISPLAY --volume="$HOME/.Xauthority:/root/.Xauthority:rw" --volume /tmp/.X11-unix/:/tmp/.X11-unix {DOCKER_IMAGE_NAME}

Ubuntu 20/22 DockerFiles#

  • #c5f015 new component added to the level

  • #1589F0 existing component from the previous level

Build Level

MIVisionX Dependencies

Modules

Libraries and Executables

Docker File

Level_1

cmake
gcc
g++

amd_openvx
utilities

#c5f015 libopenvx.so - OpenVX™ Lib - CPU
#c5f015 libvxu.so - OpenVX™ immediate node Lib - CPU
#c5f015 runvx - OpenVX™ Graph Executor - CPU with Display OFF

level-1.dockerfile

Level_2

ROCm OpenCL
+Level 1

amd_openvx
amd_openvx_extensions
utilities

#c5f015 libopenvx.so - OpenVX™ Lib - CPU/GPU
#c5f015 libvxu.so - OpenVX™ immediate node Lib - CPU/GPU
#c5f015 libvx_loomsl.so - Loom 360 Stitch Lib
#c5f015 loom_shell - 360 Stitch App
#c5f015 runcl - OpenCL™ program debug App
#c5f015 runvx - OpenVX™ Graph Executor - Display OFF

level-2.dockerfile

Level_3

OpenCV
FFMPEG
+Level 2

amd_openvx
amd_openvx_extensions
utilities

#1589F0 libopenvx.so - OpenVX™ Lib
#1589F0 libvxu.so - OpenVX™ immediate node Lib
#1589F0 libvx_loomsl.so - Loom 360 Stitch Lib
#1589F0 loom_shell - 360 Stitch App
#1589F0 runcl - OpenCL™ program debug App
#c5f015 libvx_amd_media.so - OpenVX™ Media Extension
#c5f015 libvx_opencv.so - OpenVX™ OpenCV InterOp Extension
#c5f015 mv_compile - Neural Net Model Compile
#c5f015 runvx - OpenVX™ Graph Executor - Display ON

level-3.dockerfile

Level_4

MIOpenGEMM
MIOpen
ProtoBuf
+Level 3

amd_openvx
amd_openvx_extensions
apps
utilities

#1589F0 libopenvx.so - OpenVX™ Lib
#1589F0 libvxu.so - OpenVX™ immediate node Lib
#1589F0 libvx_loomsl.so - Loom 360 Stitch Lib
#1589F0 loom_shell - 360 Stitch App
#1589F0 libvx_amd_media.so - OpenVX™ Media Extension
#1589F0 libvx_opencv.so - OpenVX™ OpenCV InterOp Extension
#1589F0 mv_compile - Neural Net Model Compile
#1589F0 runcl - OpenCL™ program debug App
#1589F0 runvx - OpenVX™ Graph Executor - Display ON
#c5f015 libvx_nn.so - OpenVX™ Neural Net Extension
#c5f015 inference_server_app - Cloud Inference App

level-4.dockerfile

Level_5

AMD_RPP
rocAL deps
+Level 4

amd_openvx
amd_openvx_extensions
apps
rocAL
utilities

#1589F0 libopenvx.so - OpenVX™ Lib
#1589F0 libvxu.so - OpenVX™ immediate node Lib
#1589F0 libvx_loomsl.so - Loom 360 Stitch Lib
#1589F0 loom_shell - 360 Stitch App
#1589F0 libvx_amd_media.so - OpenVX™ Media Extension
#1589F0 libvx_opencv.so - OpenVX™ OpenCV InterOp Extension
#1589F0 mv_compile - Neural Net Model Compile
#1589F0 runcl - OpenCL™ program debug App
#1589F0 runvx - OpenVX™ Graph Executor - Display ON
#1589F0 libvx_nn.so - OpenVX™ Neural Net Extension
#1589F0 inference_server_app - Cloud Inference App
#c5f015 libvx_rpp.so - OpenVX™ RPP Extension
#c5f015 librali.so - ROCm Augmentation Library
#c5f015 rali_pybind.so - rocAL Pybind Lib

level-5.dockerfile