pulumi-azure-native-kotlin/com.pulumi.azurenative.machinelearningservices.kotlin.inputs/ImageInstanceSegmentationArgs

ImageInstanceSegmentationArgs

data class ImageInstanceSegmentationArgs(val limitSettings: Output<ImageLimitSettingsArgs>, val logVerbosity: Output<Either<String, LogVerbosity>>? = null, val modelSettings: Output<ImageModelSettingsObjectDetectionArgs>? = null, val primaryMetric: Output<Either<String, InstanceSegmentationPrimaryMetrics>>? = null, val searchSpace: Output<List<ImageModelDistributionSettingsObjectDetectionArgs>>? = null, val sweepSettings: Output<ImageSweepSettingsArgs>? = null, val targetColumnName: Output<String>? = null, val taskType: Output<String>, val trainingData: Output<MLTableJobInputArgs>, val validationData: Output<MLTableJobInputArgs>? = null, val validationDataSize: Output<Double>? = null) : ConvertibleToJava<ImageInstanceSegmentationArgs>

Image Instance Segmentation. Instance segmentation is used to identify objects in an image at the pixel level, drawing a polygon around each object in the image.

Constructors

fun ImageInstanceSegmentationArgs(limitSettings: Output<ImageLimitSettingsArgs>, logVerbosity: Output<Either<String, LogVerbosity>>? = null, modelSettings: Output<ImageModelSettingsObjectDetectionArgs>? = null, primaryMetric: Output<Either<String, InstanceSegmentationPrimaryMetrics>>? = null, searchSpace: Output<List<ImageModelDistributionSettingsObjectDetectionArgs>>? = null, sweepSettings: Output<ImageSweepSettingsArgs>? = null, targetColumnName: Output<String>? = null, taskType: Output<String>, trainingData: Output<MLTableJobInputArgs>, validationData: Output<MLTableJobInputArgs>? = null, validationDataSize: Output<Double>? = null)

Functions

toJava

open override fun toJava(): ImageInstanceSegmentationArgs

Properties

limitSettings

val limitSettings: Output<ImageLimitSettingsArgs>

Required Limit settings for the AutoML job.

logVerbosity

val logVerbosity: Output<Either<String, LogVerbosity>>? = null

Log verbosity for the job.

modelSettings

val modelSettings: Output<ImageModelSettingsObjectDetectionArgs>? = null

Settings used for training the model.

primaryMetric

val primaryMetric: Output<Either<String, InstanceSegmentationPrimaryMetrics>>? = null

Primary metric to optimize for this task.

searchSpace

val searchSpace: Output<List<ImageModelDistributionSettingsObjectDetectionArgs>>? = null

Search space for sampling different combinations of models and their hyperparameters.

sweepSettings

val sweepSettings: Output<ImageSweepSettingsArgs>? = null

Model sweeping and hyperparameter sweeping related settings.

targetColumnName

val targetColumnName: Output<String>? = null

Target column name: This is prediction values column. Also known as label column name in context of classification tasks.

taskType

val taskType: Output<String>

AutoMLJob Task type. Expected value is 'ImageInstanceSegmentation'.

trainingData

val trainingData: Output<MLTableJobInputArgs>

Required Training data input.

validationData

val validationData: Output<MLTableJobInputArgs>? = null

Validation data inputs.

validationDataSize

val validationDataSize: Output<Double>? = null

The fraction of training dataset that needs to be set aside for validation purpose. Values between (0.0 , 1.0) Applied when validation dataset is not provided.