<!--
{
  "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/ImageFeaturePrint/revision",
  "metadataVersion" : "0.1.0",
  "role" : "Instance Property",
  "symbol" : {
    "kind" : "Instance Property",
    "modules" : [
      "Create ML Components"
    ],
    "preciseIdentifier" : "s:18CreateMLComponents17ImageFeaturePrintV8revisionSivp"
  },
  "title" : "revision"
}
-->

# revision

The feature extractor revision number.

```
var revision: Int { get set }
```

## Discussion

There are two Image Feature Print revisions: 1 and 2. In most cases revision 2 produces better models because
it uses a smaller feature vector and better features.

In iOS 12 or later, tvOS 12 or later, and macOS 10.14 or later, revision 1 takes images with a size of 299x299
and produces a 2048 feature vector.

In iOS 17 or later, tvOS 17 or later, and macOS 14 or later, revision 2 takes images with a size of 360x360
and produces a 768 feature vector.

---

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)