https://github.com/kiritigowda/mivisionx-applications
A Compilation of all MIVisionX applications available open-source
https://github.com/kiritigowda/mivisionx-applications
caffe computer-vision computer-vision-application khronos-nnef khronos-openvx machine-learning-application mivisionx nnef onnx open-source openvx openvx-graph winml
Last synced: 3 months ago
JSON representation
A Compilation of all MIVisionX applications available open-source
- Host: GitHub
- URL: https://github.com/kiritigowda/mivisionx-applications
- Owner: kiritigowda
- License: mit
- Created: 2020-09-08T18:03:32.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2020-09-08T22:43:03.000Z (almost 6 years ago)
- Last Synced: 2025-01-14T07:15:13.155Z (over 1 year ago)
- Topics: caffe, computer-vision, computer-vision-application, khronos-nnef, khronos-openvx, machine-learning-application, mivisionx, nnef, onnx, open-source, openvx, openvx-graph, winml
- Homepage: https://kiritigowda.com/MIVisionX-Applications/
- Size: 96.7 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://opensource.org/licenses/MIT)
# 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](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/apps/bubble_pop) creates bubbles and donuts to pop using OpenVX & OpenCV functionality.
### SkinTone Detector
This 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.
### RGBD SLAM V2
[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.
### Canny Edge Detector
This 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.
## Computer Vision & Machine Learning Applications
### Recognize Digits
This sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/apps/dg_test#mivisionx-dgtest) is used to recognize handwritten digits.
### Kubernetes Scaling of Inference with MIVisionX
This 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
### MIVisionX Validation Tool
[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, & validate.
### AMD Data Analysis Toolkit
[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.
### Cloud Application
This sample [application](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/apps/cloud_inference#cloud-inference-application) does inference using a client-server system.
### MIVisionX Inference Analyzer
[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.
### Image Augmentation
This 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.
### MIVisionX OpenVX Classsification
This 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.
### MIVisionX WinML Classification
This 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.
### MIVisionX WinML YoloV2
This 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.
### Classifier
[MIVisionX-Classifier](https://github.com/kiritigowda/MIVisionX-Classifier) - This application runs know CNN image classifiers on live/pre-recorded video stream.
### YoloV2
[YOLOv2](https://github.com/kiritigowda/YoloV2NCS) - Run tiny yolov2 (20 classes) with AMD's MIVisionX
### Traffic Vision
[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.
