An optional object to support inputs outside Vision.
- iOS 13.0+
- macOS 10.15+
- Mac Catalyst 13.0+
- tvOS 13.0+
This optional object conforms to the
MLFeature protocol that the model uses to predict inputs that are not supplied by Vision. Vision provides the MLModel with the image for the
input via the VNRequestHandler.
A feature provider is necessary for models that have more than one required input. Models with only one image input won't use the feature provider.