MLHandPoseClassifier.DataSource.labeledFiles(at:)
Creates a data source from a folder that contains images, each named after the hand pose it represents.
Declaration
case labeledFiles(at: URL)Discussion
Create a hand-pose data source from a directory of images with the labeledFiles case. You must name each image file with a hand-pose label, followed by a period and an arbitrary string, ending with the image file’s extension. For example, you can name a hand-pose classifier’s training files as Peace.3.png, ThumbsUp.1.jpg, ThumbsUp.2.jpg, and so on.
In this example, these image names give a hand-pose classifier at least two class labels:
Peace-ThumbsUpat: The URL to a folder in the file system that contains folders of hand pose images. The data source uses each file’s name before the first period as its classification label.
See Also
Creating a data source
MLHandPoseClassifier.DataSource.labeledDirectories(at:)MLHandPoseClassifier.DataSource.directoryWithImagesAndAnnotation(at:annotationFile:imageColumn:labelColumn:)MLHandPoseClassifier.DataSource.labeledImageDataFrame(_:imageColumn:labelColumn:)MLHandPoseClassifier.DataSource.labeledKeypointsDataFrame(_:sessionIdColumn:labelColumn:featureColumn:)MLHandPoseClassifier.DataSource.labeledImageData(table:imageColumn:labelColumn:)MLHandPoseClassifier.DataSource.labeledKeypointsData(table:sessionIdColumn:labelColumn:featureColumn:)