MIVisionX Applications

A Compilation of all MIVisionX applications available open-source

MIVisionX has several applications built on top of OpenVX and its modules, it uses AMD optimized libraries to build applications that can be used as prototypes or used as models to develop products.

Computer Vision Applications

Bubble Pop

This sample application creates bubbles and donuts to pop using OpenVX & OpenCV functionality.

SkinTone Detector

This sample application is set to showcase how to use AMD’s OpenVX and RunVX application.

RGBD SLAM V2

RGBDSLAMv2-MIVisionX - This is an implementation of RGBDSLAM_V2 that utilizes AMD MIVisionX for feature detection and ROCm OpenCL for offloading computations to Radeon GPUs. This application is used to create 3D maps using RGB-D Cameras.

Canny Edge Detector

This sample application is set to showcase how to use AMD’s OpenVX and RunVX application.

Computer Vision & Machine Learning Applications

Recognize Digits

This sample application is used to recognize handwritten digits.

Kubernetes Scaling of Inference with MIVisionX

This sample application uses Kubernetes infrastructure to launch Dockers to perform inference on multi-GPU multi-Rack to acheive linear scaling in Inference applications

MIVisionX Validation Tool

MIVisionX ML Model Validation Tool using pre-trained ONNX / NNEF / Caffe models to analyze, summarize, & validate.

AMD Data Analysis Toolkit

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

Cloud Application

This sample application does inference using a client-server system.

MIVisionX Inference Analyzer

MIVisionX Inference Analyzer Application using pre-trained ONNX / NNEF / Caffe models to analyze and summarize images.

Image Augmentation

This sample application demonstrates the basic usage of RALI’s C API to load JPEG images from the disk and modify them in different possible ways and displays the output images.

MIVisionX OpenVX Classsification

This sample application shows how to run supported pre-trained caffe models with MIVisionX RunTime.

MIVisionX WinML Classification

This sample application shows how to run supported ONNX models with MIVisionX RunTime on Windows.

MIVisionX WinML YoloV2

This sample application shows how to run tiny yolov2(20 classes) with MIVisionX RunTime on Windows.

Classifier

MIVisionX-Classifier - This application runs know CNN image classifiers on live/pre-recorded video stream.

YoloV2

YOLOv2 - Run tiny yolov2 (20 classes) with AMD’s MIVisionX

Traffic Vision

Traffic Vision - This app detects cars/buses in live traffic at a phenomenal 50 frames/sec with HD resolution (1920x1080) using deep learning network Yolo-V2. The model used in the app is optimized for inferencing performance on AMD-GPUs using the MIVisionX toolkit.