# VNCoreMLFeatureValueObservation An object that represents a collection of key-value information that a Core ML image-analysis request produces. ``` class VNCoreMLFeatureValueObservation ``` ## Overview This type of observation results from performing a [`VNCoreMLRequest`](/documentation/Vision/VNCoreMLRequest) image analysis with a Core ML model whose role is prediction rather than classification or image-to-image processing. Vision infers that an object is a predictor model if that model predicts multiple features. You can tell that a model predicts multiple features when its object has a `nil` value for its property, or when it inserts its output in an dictionary. ## Topics ### Obtaining Feature Values [`featureValue`](/documentation/Vision/VNCoreMLFeatureValueObservation/featureValue) The feature result of a [`VNCoreMLRequest`](/documentation/Vision/VNCoreMLRequest) that outputs neither a classification nor an image. [`featureName`](/documentation/Vision/VNCoreMLFeatureValueObservation/featureName) The name used in the model description of the CoreML model that produced this observation. --- Copyright © 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)