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 conformant 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.

Latest release#

AMD OpenVX™#

AMD OpenVX™ is a highly optimized conformant open source implementation of the Khronos OpenVX™ 1.3 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 functionality to OpenVX by vendors. This project has below mentioned OpenVX modules and utilities to extend amd_openvx, which contains the AMD OpenVX™ Core Engine.

amd_loomsl: AMD Radeon Loom stitching library for live 360 degree video applications
amd_media: AMD media extension module is for encode and decode applications
amd_migraphx: amd_migraphx extension integrates the AMD’s MIGraphx into an OpenVX graph. This extension allows developers to combine the vision funcions in OpenVX with the MIGraphX and build an end-to-end application for inference.
amd_nn: OpenVX neural network module
amd_opencv: OpenVX module that implements a mechanism to access OpenCV functionality as OpenVX kernels
amd_rpp: OpenVX extension providing an interface to some of the RPP’s (ROCm Performance Primitives) functions. This extension is used to enable rocAL to perform image augmentation.
amd_winml: WinML extension will allow developers to import a pre-trained ONNX model into an OpenVX graph and add hundreds of different pre & post processing vision / generic / user-defined functions, available in OpenVX and OpenCV interop, to the input and output of the neural net model. This will allow developers to build an end to end application for inference.

Applications#

MIVisionX has several applications built on top of OpenVX modules, it uses AMD optimized libraries to build applications that can be used to prototype or use as a model to develop products.

Neural network model compiler and optimizer#

Neural net model compiler and optimizer converts pre-trained neural net models to MIVisionX runtime code for optimized inference.

rocAL#

The ROCm Augmentation Library - rocAL 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.

rocAL is now available as an independent module at ROCm/rocAL. rocAL will be deprecated in MIVisionX with ROCm 6.2.0.

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#

loom_shell: an interpreter to prototype 360 degree video stitching applications using a script
mv_deploy: consists of a model-compiler and necessary header/.cpp files which are required to run inference for a specific NeuralNet model
RunCL: command-line utility to build, execute, and debug OpenCL programs
RunVX: command-line utility to execute OpenVX graph described in GDF text file

Prerequisites#

Hardware#

CPU: AMD64
GPU: AMD Radeon™ Graphics [optional]
APU: AMD Radeon™ Mobile/Embedded [optional]

Note: Some modules in MIVisionX can be built for CPU ONLY. To take advantage of Advanced Features And Modules we recommend using AMD GPUs or AMD APUs.

Operating System#

Linux#

Ubuntu - 20.04 / 22.04
CentOS - 7
RedHat - 8 / 9
SLES - 15-SP4

Windows#

Windows 10 / 11

macOS#

macOS - Ventura 13 / Sonoma 14

Build and install instructions#

Linux#

ROCm supported hardware
Install ROCm with amdgpu-install with --usecase=graphics,rocm --no-32

Package install#

Install MIVisionX runtime, development, and test packages.

Runtime package - mivisionx only provides the dynamic libraries and executables
Development package - mivisionx-dev/mivisionx-devel provides the libraries, executables, header files, and samples
Test package - mivisionx-test provides ctest to verify installation

On `Ubuntu`#

sudo apt-get install mivisionx mivisionx-dev mivisionx-test

On `CentOS`/`RedHat`#

sudo yum install mivisionx mivisionx-devel mivisionx-test

On `SLES`#

sudo zypper install mivisionx mivisionx-devel mivisionx-test

Note:

Package install requires OpenCV V4.6 and Protobuf V3.12.4 manual install
CentOS/RedHat/SLES requires FFMPEG Dev package manual install

Source build and install#

Prerequisites setup script for Linux#

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

NOTE: This script only needs to be executed once.

Prerequisites for running the script#

Linux distribution
- Ubuntu - 20.04 / 22.04
- CentOS - 7
- RedHat - 8 / 9
- SLES - 15-SP4
ROCm supported hardware

Install ROCm with amdgpu-install with --usecase=graphics,rocm --no-32

usage:

python MIVisionX-setup.py --directory [setup directory - optional (default:~/)]
                          --opencv    [OpenCV Version - optional (default:4.6.0)]
                          --protobuf  [ProtoBuf Version - optional (default:3.12.4)]
                          --pybind11  [PyBind11 Version - optional (default:v2.10.4)]
                          --ffmpeg    [FFMPEG V4.4.2 Installation - optional (default:ON) [options:ON/OFF]]
                          --rocal     [MIVisionX rocAL Dependency Install - optional (default:ON) [options:ON/OFF]]
                          --neural_net[MIVisionX Neural Net Dependency Install - optional (default:ON) [options:ON/OFF]]
                          --inference [MIVisionX Neural Net Inference Dependency Install - optional (default:ON) [options:ON/OFF]]
                          --developer [Setup Developer Options - optional (default:OFF) [options:ON/OFF]]
                          --reinstall [Remove previous setup and reinstall (default:OFF)[options:ON/OFF]]
                          --backend   [MIVisionX Dependency Backend - optional (default:HIP) [options:HIP/OCL/CPU]]
                          --rocm_path [ROCm Installation Path - optional (default:/opt/rocm) - ROCm Installation Required]

Note:

ROCm upgrade requires the setup script rerun

Using MIVisionX-setup.py#

Clone MIVisionX git repository
```
git clone https://github.com/ROCm/MIVisionX.git
```
Note: MIVisionX has support for two GPU backends: OPENCL and HIP:
Instructions for building MIVisionX with the HIP GPU backend (default GPU backend):
- run the setup script to install all the dependencies required by the HIP GPU backend:
```
cd MIVisionX
python MIVisionX-setup.py
```
- run the below commands to build MIVisionX with the HIP GPU backend:
```
mkdir build-hip
cd build-hip
cmake ../
make -j8
sudo cmake --build . --target PyPackageInstall
sudo make install
```
- run tests - test option instructions
```
make test
```
Note:
- PyPackageInstall used for rocal_pybind installation
- sudo required for pybind installation
Instructions for building MIVisionX with OPENCL GPU backend

Windows#

Windows SDK
Visual Studio 2019 or later
Install the latest AMD drivers
Install OpenCL SDK
Install OpenCV 4.6.0
- Set OpenCV_DIR environment variable to OpenCV/build folder
- Add %OpenCV_DIR%\x64\vc14\bin or %OpenCV_DIR%\x64\vc15\bin to your PATH

Using Visual Studio#

Use MIVisionX.sln to build for x64 platform

NOTE: Some modules in MIVisionX are only supported on Linux

macOS#

macOS build instructions

NOTE: MIVisionX CPU backend is supported in macOS

Verify installation#

Linux / macOS#

The installer will copy
- Executables into /opt/rocm/bin
- Libraries into /opt/rocm/lib
- Header files into /opt/rocm/include/mivisionx
- Apps, & Samples folder into /opt/rocm/share/mivisionx
- Documents folder into /opt/rocm/share/doc/mivisionx
- Model Compiler, and Toolkit folder into /opt/rocm/libexec/mivisionx

Verify with sample application#

Canny Edge Detection

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

Note: More samples are available here

Note: For macOS use export DYLD_LIBRARY_PATH=$DYLD_LIBRARY_PATH:/opt/rocm/lib

Verify with mivisionx-test package#

Test package will install ctest module to test MIVisionX. Follow below steps to test packge install

mkdir mivisionx-test && cd mivisionx-test
cmake /opt/rocm/share/mivisionx/test/
ctest -VV

Windows#

MIVisionX.sln builds the libraries & executables in the folder MIVisionX/x64

Use RunVX to test the build

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

Docker#

MIVisionX provides developers with docker images for Ubuntu 20.04 / 22.04. 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.

Docker files to build MIVisionX containers and suggested workflow are available

MIVisionX docker#

Documentation#

Run the steps below to build documentation locally.

sphinx documentation

cd docs
pip3 install -r sphinx/requirements.txt
python3 -m sphinx -T -E -b html -d _build/doctrees -D language=en . _build/html

Doxygen

doxygen .Doxyfile

Technical support#

Please email mivisionx.support@amd.com for questions, and feedback on MIVisionX.

Please submit your feature requests, and bug reports on the GitHub issues page.

Release notes#

Latest release version#

Changelog#

Review all notable changes with the latest release

Tested configurations#

Windows 10 / 11
Linux distribution
- Ubuntu - 20.04 / 22.04
- CentOS - 7 / 8
- RHEL - 8 / 9
- SLES - 15-SP4
ROCm: rocm-core - 5.7.0.50700-6
miopen-hip - 2.20.0.50700-63
migraphx - 2.7.0.50700-63
Protobuf - V3.12.4
OpenCV - 4.6.0
RPP - [1.5.0]
FFMPEG - n4.4.2
Dependencies for all the above packages
MIVisionX Setup Script - V2.6.1

Known issues#

OpenCV 4.X support for some apps missing
MIVisionX Package install requires manual prerequisites installation

MIVisionX dependency map#

HIP Backend#

Docker Image: sudo docker build -f docker/ubuntu20/{DOCKER_LEVEL_FILE_NAME}.dockerfile -t {mivisionx-level-NUMBER} .

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

Build Level	MIVisionX Dependencies	Modules	Libraries and Executables
`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_2`	ROCm HIP +Level 1	amd_openvx amd_openvx_extensions utilities	`libopenvx.so` - OpenVX™ Lib - CPU/GPU `libvxu.so` - OpenVX™ immediate node Lib - CPU/GPU `runvx` - OpenVX™ Graph Executor - Display OFF
`Level_3`	OpenCV FFMPEG +Level 2	amd_openvx amd_openvx_extensions utilities	`libopenvx.so` - OpenVX™ Lib `libvxu.so` - OpenVX™ immediate node Lib `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_4`	MIOpen MIGraphX ProtoBuf +Level 3	amd_openvx amd_openvx_extensions apps utilities	`libopenvx.so` - OpenVX™ Lib `libvxu.so` - OpenVX™ immediate node Lib `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 `libvx_nn.so` - OpenVX™ Neural Net Extension
`Level_5`	AMD_RPP rocAL deps +Level 4	amd_openvx amd_openvx_extensions apps rocAL utilities	`libopenvx.so` - OpenVX™ Lib `libvxu.so` - OpenVX™ immediate node Lib `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 `libvx_nn.so` - OpenVX™ Neural Net Extension `libvx_rpp.so` - OpenVX™ RPP Extension `librocal.so` - Radeon Augmentation Library `rocal_pybind.so` - rocAL Pybind Lib

NOTE: OpenVX and the OpenVX logo are trademarks of the Khronos Group Inc.

Latest release

Contents

Latest release#

AMD OpenVX™#

AMD OpenVX™ Extensions#

Applications#

Neural network model compiler and optimizer#

rocAL#

Toolkit#

Utilities#

Prerequisites#

Hardware#

Operating System#

Linux#

Windows#

macOS#

Build and install instructions#

Linux#

Package install#

On Ubuntu#

On CentOS/RedHat#

On SLES#

Source build and install#

Prerequisites setup script for Linux#

Prerequisites for running the script#

Using MIVisionX-setup.py#

Windows#

Using Visual Studio#

macOS#

Verify installation#

Linux / macOS#

Verify with sample application#

Verify with mivisionx-test package#

Windows#

Docker#

MIVisionX docker#

Documentation#

Technical support#

Release notes#

Latest release version#

Changelog#

Tested configurations#

Known issues#

MIVisionX dependency map#

HIP Backend#

On `Ubuntu`#

On `CentOS`/`RedHat`#

On `SLES`#