Skip to main content

Getting started

OneWare.AI.Onnx is a helper library to get the predicted result from a OneAI generated .onnx model, which can be used for object-detection, classification or segmentation. The api is easy to use, has a clean architecture and is customizable.

With these few lines of code the api consumer is able to extract the OnnxOutput for further data processing:

using SKBitmap skBitmap = SKBitmap.Decode(bitmapPath);
OnnxModel model = new(onnxModelPath);
OnnxOutput result = model.PredictOutput(skBitmap, keepSessionOpen: false);

switch (result)
{
    case OnnxRectsOutput rectsOutput:
        //further data processing
        break;
    case OnnxClassesOutput classesOutput:
        //further data processing
        break;
    case OnnxSegmentationOutput segmentationOutput:
        //further data processing
        break;
}

The default IOnnxImageProcessor uses SkiaSharp for extracting the data out of the image. Therefore, the example uses the SKBitmap. This is customizable via the OnnxConfiguration of the OnnxModel.

Features​

  • entire data processing to get the result from a OneAI generated .onnx model
  • most efficient image data extraction when using the default IOnnxImageProcessor
  • customizable through the configuration property in the OnnxModel. Within this property the api consumer is e.g. able to specify his own IOnnxImageProcessor as well as override the default OnnxPrediction for full control of data processing.
  • advanced documentation

Getting help​

To learn more about OneAI or OneWare Studio, check out the documentation. If the package isn't working the way you expect, or you have questions in generally, don't hesitate to get in touch with us via support@one-ware.com. In addition, we welcome reproducible bug reports as well as feature requests.