<!--
{
  "availability" : [
    "iOS: 17.0.0 -",
    "iPadOS: 17.0.0 -",
    "macCatalyst: 17.0.0 -",
    "macOS: 14.0.0 -",
    "tvOS: 17.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateMLComponents",
  "identifier" : "/documentation/CreateMLComponents/FullyConnectedNetworkMultiLabelClassifierModel/prediction(from:confidenceThresholds:)",
  "metadataVersion" : "0.1.0",
  "role" : "Instance Method",
  "symbol" : {
    "kind" : "Instance Method",
    "modules" : [
      "Create ML Components"
    ],
    "preciseIdentifier" : "s:18CreateMLComponents46FullyConnectedNetworkMultiLabelClassifierModelV10prediction4from20confidenceThresholdsAA26ClassificationDistributionVyq_G6CoreML13MLShapedArrayVyxG_SDyq_xGtKF::OverloadGroup"
  },
  "title" : "prediction(from:confidenceThresholds:)"
}
-->

# prediction(from:confidenceThresholds:)

Performs a prediction and keeps label-confidence pairs that are greater than or equal to the provided
confidence thresholds.

```
func prediction(from input: FullyConnectedNetworkMultiLabelClassifierModel<Scalar, Label>.Input, confidenceThresholds: [Label : Scalar]) throws -> ClassificationDistribution<Label>
```

## Parameters

`input`

The classifier input.

`confidenceThresholds`

A dictionary of label and confidence threshold pairs.

## Return Value

A dictionary of labels and confidences.

## Discussion

When the confidence threshold is `NaN`, the label-confidence pair is not included in the
result, regardless of the label’s confidence.

---

Copyright &copy; 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)