{"id":20280575,"url":"https://github.com/kiritigowda/mivisionx-applications","last_synced_at":"2026-03-08T15:31:37.267Z","repository":{"id":81714083,"uuid":"293888917","full_name":"kiritigowda/MIVisionX-Applications","owner":"kiritigowda","description":"A Compilation of all MIVisionX applications available open-source","archived":false,"fork":false,"pushed_at":"2020-09-08T22:43:03.000Z","size":101401,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-14T07:15:13.155Z","etag":null,"topics":["caffe","computer-vision","computer-vision-application","khronos-nnef","khronos-openvx","machine-learning-application","mivisionx","nnef","onnx","open-source","openvx","openvx-graph","winml"],"latest_commit_sha":null,"homepage":"https://kiritigowda.com/MIVisionX-Applications/","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kiritigowda.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-09-08T18:03:32.000Z","updated_at":"2020-09-08T22:43:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"d94a0002-497c-44ae-a0e6-6637c0938925","html_url":"https://github.com/kiritigowda/MIVisionX-Applications","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritigowda%2FMIVisionX-Applications","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritigowda%2FMIVisionX-Applications/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritigowda%2FMIVisionX-Applications/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritigowda%2FMIVisionX-Applications/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kiritigowda","download_url":"https://codeload.github.com/kiritigowda/MIVisionX-Applications/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241773256,"owners_count":20018064,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["caffe","computer-vision","computer-vision-application","khronos-nnef","khronos-openvx","machine-learning-application","mivisionx","nnef","onnx","open-source","openvx","openvx-graph","winml"],"created_at":"2024-11-14T13:35:59.891Z","updated_at":"2026-03-08T15:31:37.216Z","avatar_url":"https://github.com/kiritigowda.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"[![MIT licensed](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n\n# MIVisionX Applications\n\nA Compilation of all MIVisionX applications available open-source\n\nMIVisionX 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.\n\n## Computer Vision Applications\n\n### Bubble Pop\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/apps/bubble_pop) creates bubbles and donuts to pop using OpenVX \u0026 OpenCV functionality.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"90%\" src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/docs/images/vx-pop-app.gif\"\u003e \u003c/p\u003e\n\n### SkinTone Detector\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/samples#skintonedetectgdf) is set to showcase how to use AMD's OpenVX and RunVX application.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"90%\" src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/samples/images/skinToneDetect_image.PNG\"\u003e \u003c/p\u003e\n\n### RGBD SLAM V2\n\n[RGBDSLAMv2-MIVisionX](https://github.com/ICURO-AI-LAB/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.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"70%\" src=\"https://github.com/ICURO-AI-LAB/RGBDSLAMv2-MIVisionX/blob/master/media/rgbdslamv2_fr2desk_octomap.jpg?raw=true\" /\u003e \u003c/p\u003e\n\n### Canny Edge Detector\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/samples#cannygdf) is set to showcase how to use AMD's OpenVX and RunVX application.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"90%\" src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/samples/images/canny_image.PNG\"\u003e \u003c/p\u003e\n\n## Computer Vision \u0026 Machine Learning Applications\n\n### Recognize Digits\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/apps/dg_test#mivisionx-dgtest) is used to recognize handwritten digits.\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/docs/images/DGtest.gif\"\u003e \u003c/p\u003e\n\n### Kubernetes Scaling of Inference with MIVisionX\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/apps/cloud_inference#cloud-inference-application) uses Kubernetes infrastructure to launch Dockers to perform inference on multi-GPU multi-Rack to acheive linear scaling in Inference applications\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"./images/k8-MIVisionX.gif\"\u003e \u003c/p\u003e\n\n### MIVisionX Validation Tool\n\n[MIVisionX ML Model Validation Tool](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/blob/master/apps/mivisionx_validation_tool#mivisionx-python-ml-model-validation-tool) using pre-trained `ONNX` / `NNEF` / `Caffe` models to analyze, summarize, \u0026 validate.\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"./images/RALI-validation.gif\"\u003e \u003c/p\u003e\n\n### AMD Data Analysis Toolkit\n\n[ADAT](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/toolkit/analysis_and_visualization/classification#mivisionx---classification-visualization) 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.\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"./images/ADAT-MIVisionX.gif\"\u003e \u003c/p\u003e\n\n### Cloud Application\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/apps/cloud_inference#cloud-inference-application) does inference using a client-server system.\n\n\u003cp align=\"center\"\u003e \u003ca href=\"http://www.youtube.com/watch?v=0GLmnrpMSYs\"\u003e \u003cimg width=\"90%\" src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/docs/images/inferenceVideo.png\"\u003e \u003c/a\u003e\u003c/p\u003e\n\n### MIVisionX Inference Analyzer\n\n[MIVisionX Inference Analyzer Application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/apps/mivisionx_inference_analyzer#mivisionx-python-inference-analyzer) using pre-trained `ONNX` / `NNEF` / `Caffe` models to analyze and summarize images.\n\n\u003cp align=\"center\"\u003e\u003cimg width=\"90%\" src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/docs/images/inference_analyzer.gif\" /\u003e\u003c/p\u003e\n\n### Image Augmentation\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/blob/master/apps/image_augmentation#image-augmentation-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.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"90%\" src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/docs/images/image_augmentation.png\" /\u003e \u003c/p\u003e\n\n### MIVisionX OpenVX Classsification\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/blob/master/apps/mivisionx_openvx_classifier/README.md) shows how to run supported pre-trained caffe models with MIVisionX RunTime.\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/docs/images/mivisionx_openvx_classifier_imageClassification.png\"\u003e\u003c/p\u003e\n\n### MIVisionX WinML Classification\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/blob/master/apps/mivisionx_winml_classifier/README.md) shows how to run supported ONNX models with MIVisionX RunTime on Windows.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"60%\" src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/apps/mivisionx_winml_classifier/images/MIVisionX-ImageClassification-WinML.png\"\u003e \u003c/p\u003e\n\n### MIVisionX WinML YoloV2\n\nThis sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/blob/master/apps/mivisionx_winml_yolov2#yolov2-using-amd-winml-extension) shows how to run tiny yolov2(20 classes) with MIVisionX RunTime on Windows.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"60%\" src=\"https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/raw/master/apps/mivisionx_winml_yolov2/image/cat-yolo.jpg\"\u003e \u003c/p\u003e\n\n### Classifier\n\n[MIVisionX-Classifier](https://github.com/kiritigowda/MIVisionX-Classifier) - This application runs know CNN image classifiers on live/pre-recorded video stream.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"60%\" src=\"https://github.com/kiritigowda/MIVisionX-Classifier/raw/master/data/classifier.png\"\u003e \u003c/p\u003e\n\n### YoloV2\n\n[YOLOv2](https://github.com/kiritigowda/YoloV2NCS) - Run tiny yolov2 (20 classes) with AMD's MIVisionX\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"60%\" src=\"https://github.com/kiritigowda/YoloV2NCS/raw/master/data/yolo_dog.jpg\"\u003e \u003c/p\u003e\n\n### Traffic Vision\n\n[Traffic Vision](https://github.com/srohit0/trafficVision#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.\n\n\u003cp align=\"center\"\u003e \u003cimg width=\"70%\" src=\"https://raw.githubusercontent.com/srohit0/trafficVision/master/media/traffic_viosion.gif\" /\u003e \u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkiritigowda%2Fmivisionx-applications","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkiritigowda%2Fmivisionx-applications","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkiritigowda%2Fmivisionx-applications/lists"}