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

• Ubuntu 20.04/22.04
• ROCm supported hardware
• Install ROCm with --usecase=rocm
• Docker

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

• new component added to the level
• existing component from the previous level

Build Level	MIVisionX Dependencies	Modules	Libraries and Executables	Docker File
Level_1	cmake gcc g++	amd_openvx utilities	libopenvx.so - OpenVX™ Lib - CPU libvxu.so - OpenVX™ immediate node Lib - CPU runvx - OpenVX™ Graph Executor - CPU with Display OFF	level-1.dockerfile
Level_2	ROCm OpenCL +Level 1	amd_openvx amd_openvx_extensions utilities	libopenvx.so - OpenVX™ Lib - CPU/GPU libvxu.so - OpenVX™ immediate node Lib - CPU/GPU libvx_loomsl.so - Loom 360 Stitch Lib loom_shell - 360 Stitch App runcl - OpenCL™ program debug App runvx - OpenVX™ Graph Executor - Display OFF	level-2.dockerfile
Level_3	OpenCV FFMPEG +Level 2	amd_openvx amd_openvx_extensions utilities	libopenvx.so - OpenVX™ Lib libvxu.so - OpenVX™ immediate node Lib libvx_loomsl.so - Loom 360 Stitch Lib loom_shell - 360 Stitch App runcl - OpenCL™ program debug App libvx_amd_media.so - OpenVX™ Media Extension libvx_opencv.so - OpenVX™ OpenCV InterOp Extension mv_compile - Neural Net Model Compile runvx - OpenVX™ Graph Executor - Display ON	level-3.dockerfile
Level_4	MIOpenGEMM MIOpen ProtoBuf +Level 3	amd_openvx amd_openvx_extensions apps utilities	libopenvx.so - OpenVX™ Lib libvxu.so - OpenVX™ immediate node Lib libvx_loomsl.so - Loom 360 Stitch Lib loom_shell - 360 Stitch App libvx_amd_media.so - OpenVX™ Media Extension libvx_opencv.so - OpenVX™ OpenCV InterOp Extension mv_compile - Neural Net Model Compile runcl - OpenCL™ program debug App runvx - OpenVX™ Graph Executor - Display ON libvx_nn.so - OpenVX™ Neural Net Extension inference_server_app - Cloud Inference App	level-4.dockerfile
Level_5	AMD_RPP AMD RPP deps +Level 4	amd_openvx amd_openvx_extensions apps VX RPP utilities	libopenvx.so - OpenVX™ Lib libvxu.so - OpenVX™ immediate node Lib libvx_loomsl.so - Loom 360 Stitch Lib loom_shell - 360 Stitch App libvx_amd_media.so - OpenVX™ Media Extension libvx_opencv.so - OpenVX™ OpenCV InterOp Extension mv_compile - Neural Net Model Compile runcl - OpenCL™ program debug App runvx - OpenVX™ Graph Executor - Display ON libvx_nn.so - OpenVX™ Neural Net Extension inference_server_app - Cloud Inference App libvx_rpp.so - OpenVX™ RPP Extension	level-5.dockerfile