load

fun load(pathToModel: String, vararg executionProviders: ExecutionProvider = arrayOf(CPU(true))): OnnxInferenceModel

Loads model from serialized ONNX file.

fun load(modelBytes: ByteArray, vararg executionProviders: ExecutionProvider = arrayOf(CPU(true))): OnnxInferenceModel

Loads model from a byte array representing an ONNX model.