TrainMiniBatchKMeans Task

This task executes an unsupervised Mini Batch K-Means algorithm against the provided input training rasters. The algorithm iterates between two major steps, first step, samples are drawn randomly from the dataset, to form a mini-batch. These are then assigned to the nearest centroid. In the second step, the centroids are updated.

For background on the algorithm used, see Mini Batch K-Means Classification.

Example

; Start the application

e = ENVI()

; Open an input raster file

RasterFile = Filepath('qb_boulder_msi', Subdir=['data'], $

Root_Dir=e.Root_Dir)

Raster = e.OpenRaster(RasterFile)

; Get the statistics task from the catalog of ENVITasks

StatsTask = ENVITask('NormalizationStatistics')

; Define inputs

StatsTask.INPUT_RASTERS = Raster

; Run the task

StatsTask.Execute

; Get the training task from the catalog of ENVITasks

TrainTask = ENVITask('TrainMiniBatchKMeans')

; Define inputs

TrainTask.INPUT_RASTER = Raster

TrainTask.Number_of_Classes = 3

TrainTask.Normalize_Min_Max = StatsTask.Normalization

; Run the task

TrainTask.Execute

outputModel = TrainTask.OUTPUT_MODEL

Print, outputModel.Attributes

Syntax

Result = ENVITask('TrainExtraTrees')

Input parameters (Set, Get): BRANCHING_FACTOR, INPUT_RASTERS, MODEL_DESCRIPTION, MODEL_NAME, MODEL_VERSION, NORMALIZE_MIN_MAX, NUMBER_OF_CLASSES, OUTPUT_MODEL_URI, THRESHOLD

Output parameters (Get only): OUTPUT_MODEL

Parameters marked as "Set" are those that you can set to specific values. You can also retrieve their current values any time. Parameters marked as "Get" are those whose values you can retrieve but not set.

Input Parameters

BRANCHING_FACTOR (optional)

Specify the maximum number of clustering feature subclusters in each node. The default is 50.

INPUT_RASTERS (required)

Specify one or more preprocessed training rasters to be used for training.

MODEL_DESCRIPTION (optional)

Specify the purpose of the model.

MODEL_NAME (optional)

Specify the name of the model. The default is Mini Batch K-Means Unsupervised Classifier.

MODEL_VERSION (optional)

Specify a semantic version format (MAJOR.MINOR.PATCH) for the trained model (for example, 1.0.0). The version may indicate the following:

MAJOR: Breaking changes to the model
MINOR: Compatibility or new features
PATCH: Minor adjustments

NORMALIZE_MIN_MAX (required)

Specify the data value that corresponds to 0% and 100% reflectance.

NUMBER_OF_CLASSES (optional)

Number of clusters after the final clustering step, which treats the subclusters from the leaves as new samples. Specifies the number of classes to identify. The default is 3.

OUTPUT_MODEL_URI (optional)

Specify a string with the fully qualified filename and path of the associated OUTPUT_MODEL. If you do not specify this parameter, or set it to an exclamation symbol (!), a temporary file will be created.

THRESHOLD (optional)

Specify the radius of the subcluster obtained by merging a new sample and the closest subcluster should be less than the threshold. The default is 0.5.

Output Parameters

OUTPUT_MODEL

This is a reference to the output model file.

Methods

Execute

Parameter

ParameterNames

See ENVI Help for details on these ENVITask methods.

Properties

DESCRIPTION

DISPLAY_NAME

NAME

REVISION

See the ENVITask topic in ENVI Help for details.

Version History

Machine Learning 2.0	Introduced
Machine Learning 6.2	Added the MODEL_VERSION and OUTPUT_MODEL_URI parameters