metadata
library_name: unity-sentis
pipeline_tag: object-detection
YOLOv8n validated for Unity Sentis (Version 2.1.2)
YOLOv8n is a real-time multi-object recognition model confirmed to run in Unity 6000.
How to Use
- Create a new scene in Unity 6000;
- Install
com.unity.sentisversion2.1.2from the package manager; - Add the
RunYOLO8n.csscript to the Main Camera; - Drag the
Models/yolov8n.onnxfile into theModel Assetfield; - Drag the
classes.txtfile into theClasses Assetfield; - Create a
GameObject > UI > Raw Imageobject in the scene, set its width and height to 640, and link it as theDisplay Imagefield; - Drag the
Border Texture.pngfile into theBorder Texturefield; - Select an appropriate font in the
Fontfield; - Put a video file in the
Assets/StreamingAssetsfolder and set theVideo Filenamefield to the filename of the video.
Preview
If working correctly you should see something like this:
Information
The NMS selection will be improved in later versions of Sentis. Currently uses singular-class approach.
Unity Sentis
Unity Sentis is the inference engine that runs in Unity 3D. More information can be found at here
License
The YOLO models use the GPLv3 license.
