View on GitHub

MIVisionX

MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. Khronos OpenVX is also delivered with MIVisionX.

MIT licensed doc Build Status

MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX delivers highly optimized open-source implementation of the Khronos OpenVX™ and OpenVX™ Extensions along with Convolution Neural Net Model Compiler & Optimizer supporting ONNX, and Khronos NNEF™ exchange formats. The toolkit allows for rapid prototyping and deployment of optimized computer vision and machine learning inference workloads on a wide range of computer hardware, including small embedded x86 CPUs, APUs, discrete GPUs, and heterogeneous servers.

AMD OpenVX

AMD OpenVX is a highly optimized open source implementation of the Khronos OpenVX™ computer vision specification. It allows for rapid prototyping as well as fast execution on a wide range of computer hardware, including small embedded x86 CPUs and large workstation discrete GPUs.

Khronos OpenVX™ 1.0.1 conformant implementation is available in MIVisionX Lite

AMD OpenVX Extensions

The OpenVX framework provides a mechanism to add new vision functions to OpenVX by 3rd party vendors. This project has below mentioned OpenVX modules and utilities to extend amd_openvx project, which contains the AMD OpenVX Core Engine.

Applications

MIVisionX has several applications built on top of OpenVX modules, it uses AMD optimized libraries to build applications which can be used to prototype or used as models to develop a product.

Neural Net Model Compiler & Optimizer

Neural Net Model Compiler & Optimizer converts pre-trained neural net models to MIVisionX runtime code for optimized inference.

RALI

The Radeon Augmentation Library - RALI is designed to efficiently decode and process images and videos from a variety of storage formats and modify them through a processing graph programmable by the user.

Toolkit

MIVisionX Toolkit, is a comprehensive set of helpful tools for neural net creation, development, training, and deployment. The Toolkit provides you with helpful tools to design, develop, quantize, prune, retrain, and infer your neural network work in any framework. The Toolkit is designed to help you deploy your work to any AMD or 3rd party hardware, from embedded to servers.

MIVisionX provides you with tools for accomplishing your tasks throughout the whole neural net life-cycle, from creating a model to deploying them for your target platforms.

Utilities

Prerequisites

Windows

Linux

Prerequisites setup script for Linux - MIVisionX-setup.py

For the convenience of the developer, we here provide the setup script which will install all the dependencies required by this project.

MIVisionX-setup.py builds all the prerequisites required by MIVisionX. The setup script creates a deps folder and installs all the prerequisites, this script only needs to be executed once. If the directory option is not given, the script will install the deps folder in the home directory(~/) by default, else in the user-specified location.

Prerequisites for running the script
  1. Ubuntu 16.04 / 18.04 or CentOS 7.5 / 7.6
  2. ROCm supported hardware
  3. ROCm

usage:

python MIVisionX-setup.py --directory [setup directory - optional (default:~/)]
                          --installer [Package management tool - optional (default:apt-get) [options: Ubuntu:apt-get;CentOS:yum]]
                          --opencv    [OpenCV Version - optional (default:3.4.0)]
                          --miopen    [MIOpen Version - optional (default:2.5.0)]
                          --miopengemm[MIOpenGEMM Version - optional (default:1.1.5)]
                          --protobuf  [ProtoBuf Version - optional (default:3.12.0)]
                          --rpp       [RPP Version - optional (default:0.5)]
                          --ffmpeg    [FFMPEG Installation - optional (default:no) [options:yes/no]]
                          --rali      [MIVisionX RALI Dependency Install - optional (default:yes) [options:yes/no]]
                          --neural_net[MIVisionX Neural Net Dependency Install - optional (default:yes) [options:yes/no]]
                          --reinstall [Remove previous setup and reinstall (default:no)[options:yes/no]]

Note:

Refer to Wiki page for developer instructions.

Build & Install MIVisionX

Windows

Using .msi packages

Using Visual Studio 2017 on 64-bit Windows 10

Linux

Using apt-get / yum

Prerequisites
  1. Ubuntu 16.04 / 18.04 or CentOS 7.5 / 7.6
  2. ROCm supported hardware
  3. ROCm
Ubuntu
sudo apt-get install mivisionx
CentOS
sudo yum install mivisionx

Note:

Using MIVisionX-setup.py and CMake on Linux with ROCm

git clone https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX.git
cd MIVisionX
python MIVisionX-setup.py --directory [setup directory - optional (default:~/)]
                          --installer [Package management tool - optional (default:apt-get) [options: Ubuntu:apt-get;CentOS:yum]]
                          --opencv    [OpenCV Version - optional (default:3.4.0)]
                          --miopen    [MIOpen Version - optional (default:2.5.0)]
                          --miopengemm[MIOpenGEMM Version - optional (default:1.1.5)]
                          --protobuf  [ProtoBuf Version - optional (default:3.12.0)]
                          --rpp       [RPP Version - optional (default:0.5)]
                          --ffmpeg    [FFMPEG Installation - optional (default:no) [options:yes/no]]
                          --rali      [MIVisionX RALI Dependency Install - optional (default:yes) [options:yes/no]]
                          --neural_net[MIVisionX Neural Net Dependency Install - optional (default:yes) [options:yes/no]]
                          --reinstall [Remove previous setup and reinstall (default:no)[options:yes/no]]

Note: use --installer yum for CentOS

mkdir build
cd build
cmake ../
make -j8
sudo make install

Note:

Using CMake on Linux with ROCm

Verify the Installation

Linux

Canny Edge Detection

  export PATH=$PATH:/opt/rocm/mivisionx/bin
  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/rocm/mivisionx/lib
  runvx /opt/rocm/mivisionx/samples/gdf/canny.gdf 

Note: More samples are available here

Windows

./runvx.exe PATH_TO/MIVisionX/samples/gdf/skintonedetect.gdf

Docker

MIVisionX provides developers with docker images for Ubuntu 16.04 / 18.04 and CentOS 7.5 / 7.6. Using docker images developers can quickly prototype and build applications without having to be locked into a single system setup or lose valuable time figuring out the dependencies of the underlying software.

MIVisionX Docker

Docker Workflow Sample on Ubuntu 16.04

Prerequisites

Workflow

sudo apt update
sudo apt dist-upgrade
sudo apt install libnuma-dev
sudo reboot
wget -qO - http://repo.radeon.com/rocm/apt/debian/rocm.gpg.key | sudo apt-key add -
echo 'deb [arch=amd64] http://repo.radeon.com/rocm/apt/debian/ xenial main' | sudo tee /etc/apt/sources.list.d/rocm.list
sudo apt update
sudo apt install rocm-dkms
sudo reboot
sudo apt-get install curl
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
sudo apt-get update
apt-cache policy docker-ce
sudo apt-get install -y docker-ce
sudo systemctl status docker
sudo docker pull mivisionx/ubuntu-16.04
sudo docker run -it --device=/dev/kfd --device=/dev/dri --cap-add=SYS_RAWIO --device=/dev/mem --group-add video --network host mivisionx/ubuntu-16.04

Note:

Release Notes

Known issues

Tested configurations

Latest Release

GitHub tag (latest SemVer)

Docker Image

Docker Automated build

Docker Image: docker pull kiritigowda/ubuntu-18.04:tagname

Build Level MIVisionX Dependencies Modules Libraries and Executables Docker Tag
Level_1 cmake
gcc
g++
amd_openvx #c5f015 libopenvx.so - OpenVX™ Lib - CPU
#c5f015 libvxu.so - OpenVX™ immediate node Lib - CPU
#c5f015 runvx - OpenVX™ Graph Executor - CPU with Display OFF
Docker Image Version (tag latest semver)
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
Docker Image Version (tag latest semver)
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
Docker Image Version (tag latest semver)
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
Docker Image Version (tag latest semver)
Level_5 AMD_RPP
RALI deps
+Level 4
amd_openvx
amd_openvx_extensions
apps
rali
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 - Radeon Augmentation Library
#c5f015 rali_pybind.so - RALI Pybind Lib
Docker Image Version (tag latest semver)