MLModelDataclass is a self-contained archive containing an
MLModelalong with supplemental data that is useful to make predictions with the model.
.onnxmodel files are supported.
StreamingAssets. This function accepts the relative path of the model file.
MLModelis created from model data. The model can then be used with a predictor to make predictions.
MLModelDataincludes an opaque normalization struct that can be deconstructed like so:
aspectModecan be passed directly to an
MLModelDataprovides an audio format struct that can be deconstructed like so: