MLHandPoseClassifier.DataSource.labeledKeypointsDataFrame(_:sessionIdColumn:labelColumn:featureColumn:)
Creates a data source from a data frame of hand pose observations that each contain the locations of each hand joint and an annotation.
Declaration
case labeledKeypointsDataFrame(DataFrame, sessionIdColumn: String = __Defaults.sessionIdColumnName, labelColumn: String = __Defaults.labelColumnName, featureColumn: String = __Defaults.featureColumnName)Discussion
dataFrame: A data frame that contains the hand-joint locations and annotations for a set of hand poses.
sessionIdColumn: The name of the column in the data frame that contains the hand pose session identifiers.
labelColumn: The name of the column in the data frame that contains the hand pose label names.
featureColumn: The name of the column in the data frame that contains the hand-joint location data. Each entry in the column must be a ShapedData instance that contains three dimensions:
The first dimension has a size of one.
The second dimension has three channels: the x-coordinate, the y-coordinate, and the confidence value, respectively. - The third dimension has 21 channels, one for each hand joint.
See Also
Creating a data source
MLHandPoseClassifier.DataSource.labeledDirectories(at:)MLHandPoseClassifier.DataSource.labeledFiles(at:)MLHandPoseClassifier.DataSource.directoryWithImagesAndAnnotation(at:annotationFile:imageColumn:labelColumn:)MLHandPoseClassifier.DataSource.labeledImageDataFrame(_:imageColumn:labelColumn:)MLHandPoseClassifier.DataSource.labeledImageData(table:imageColumn:labelColumn:)MLHandPoseClassifier.DataSource.labeledKeypointsData(table:sessionIdColumn:labelColumn:featureColumn:)