Type Property

rotation

An option for augmenting training data by rotating each image.

Declaration

Discussion

Use this option to tell the image classifier to augment your training data set by rotating the original images.

Diagram showing how the original image results in four rotated variants.

The classifier creates four new images with random rotation angles for each original.

See Also

Selecting Augmentation Options

static let crop: MLImageClassifier.ImageAugmentationOptions

An option for augmenting training data by creating cropped versions of each image.

static let blur: MLImageClassifier.ImageAugmentationOptions

An option for augmenting training data by blurring each image.

static let exposure: MLImageClassifier.ImageAugmentationOptions

An option for augmenting training data by lightening or darkening each image.

static let noise: MLImageClassifier.ImageAugmentationOptions

An option for augmenting training data by adding random amounts of noise to each image.

static let flip: MLImageClassifier.ImageAugmentationOptions

An option for augmenting training data by flipping each image along the horizontal and vertical axes.