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.

Samples

MIVisionX samples using OpenVX and OpenVX extensions. In the samples below we will learn how to run computer vision, inference, and a combination of computer vision & inference efficiently on target hardware.

GDF - Graph Description Format

MIVisionX samples using RunVX

Note:

export PATH=$PATH:/opt/rocm/mivisionx/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/rocm/mivisionx/lib
runvx -h

skintonedetect.gdf

usage:

runvx gdf/skintonedetect.gdf

canny.gdf

usage:

runvx gdf/canny.gdf

skintonedetect-LIVE.gdf

Using a live camera

usage:

runvx -frames:live gdf/skintonedetect-LIVE.gdf

canny-LIVE.gdf

Using a live camera

usage:

runvx -frames:live gdf/canny-LIVE.gdf

OpenCV_orb-LIVE.gdf

Using live camera

usage:

runvx -frames:live gdf/OpenCV_orb-LIVE.gdf

C/C++ Samples for OpenVX and OpenVX Extensions

MIVisionX samples in C/C++

Canny

usage:

cd c_samples/canny/
cmake .
make
./cannyDetect --image <imageName> 
./cannyDetect --live

Orb Detect

usage:

cd c_samples/opencv_orb/
cmake .
make
./orbDetect

Loom 360 Stitch - Radeon Loom 360 Stitch Samples

MIVisionX samples using LoomShell

Loom Stitch

Note:

Sample - 1

usage:

Sample - 2

usage:

Sample - 3

usage:

Model Compiler Samples - Run Efficient Inference

In this sample, we will learn how to run inference efficiently using OpenVX and OpenVX Extensions. The sample will go over each step required to convert a pre-trained neural net model into an OpenVX Graph and run this graph efficiently on any target hardware. In this sample, we will also learn about AMD MIVisionX which delivers open source implementation of OpenVX and OpenVX Extensions along with MIVisionX Neural Net Model Compiler & Optimizer.

Sample-1: Classification Using Pre-Trained ONNX Model

Sample-2: Detection Using Pre-Trained Caffe Model

Sample-3: Classification Using Pre-Trained NNEF Model

Sample-4: Classification Using Pre-Trained Caffe Model