MLHandActionClassifier.DataSource.labeledKeypointsDataFrame(_:sessionIdColumn:labelColumn:featureColumn:)
Creates a data source from a data frame of hand action 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)Parameters
- dataFrame :
A data frame that contains the hand-joint locations and annotations for a set of hand actions.
- sessionIdColumn:
The name of the column in the data frame that contains the session identifiers.
- labelColumn:
The name of the column in the data frame that contains the hand action 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
MLHandActionClassifier.DataSource.labeledDirectories(at:)MLHandActionClassifier.DataSource.labeledFiles(at:)MLHandActionClassifier.DataSource.directoryWithVideosAndAnnotation(at:annotationFile:videoColumn:labelColumn:startTimeColumn:endTimeColumn:)MLHandActionClassifier.DataSource.labeledVideoDataFrame(_:videoColumn:labelColumn:startTimeColumn:endTimeColumn:)MLHandActionClassifier.DataSource.labeledVideoData(table:videoColumn:labelColumn:startTimeColumn:endTimeColumn:)MLHandActionClassifier.DataSource.labeledKeypointsData(table:sessionIdColumn:labelColumn:featureColumn:)