Package Exports

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (ai.natml.vision.yolox) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

YOLOX

YOLOX high performance general object detection.

Installing YOLOX

Add the following items to your Unity project's Packages/manifest.json:

{
  "scopedRegistries": [
    {
      "name": "NatML",
      "url": "https://registry.npmjs.com",
      "scopes": ["ai.natml", "ai.fxn"]
    }
  ],
  "dependencies": {
    "ai.natml.vision.yolox": "1.0.4"
  }
}

Detecting Objects in an Image

First, create the YOLOX predictor:

// Create the YOLOX predictor
var predictor = await YOLOXPredictor.Create();

Then detect objects in the image:

// Given an image
Texture2D image = ...;
// Detect objects
YOLOXPredictor.Detection[] detections = predictor.Predict(image);

The detection rects are provided in normalized coordinates in range [0.0, 1.0]. The score is also normalized in range [0.0, 1.0].

Requirements

Unity 2021.2+

Quick Tips

Join the NatML community on Discord.
Discover more ML models on NatML Hub.
See the NatML documentation.
Contact us at hi@natml.ai.

Thank you very much!