pulumi-azure-native-kotlin/com.pulumi.azurenative.machinelearningservices.kotlin.outputs/ImageInstanceSegmentationResponse

ImageInstanceSegmentationResponse

data class ImageInstanceSegmentationResponse(val limitSettings: ImageLimitSettingsResponse, val logVerbosity: String? = null, val modelSettings: ImageModelSettingsObjectDetectionResponse? = null, val primaryMetric: String? = null, val searchSpace: List<ImageModelDistributionSettingsObjectDetectionResponse>? = null, val sweepSettings: ImageSweepSettingsResponse? = null, val targetColumnName: String? = null, val taskType: String, val trainingData: MLTableJobInputResponse, val validationData: MLTableJobInputResponse? = null, val validationDataSize: Double? = null)

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 ImageInstanceSegmentationResponse(limitSettings: ImageLimitSettingsResponse, logVerbosity: String? = null, modelSettings: ImageModelSettingsObjectDetectionResponse? = null, primaryMetric: String? = null, searchSpace: List<ImageModelDistributionSettingsObjectDetectionResponse>? = null, sweepSettings: ImageSweepSettingsResponse? = null, targetColumnName: String? = null, taskType: String, trainingData: MLTableJobInputResponse, validationData: MLTableJobInputResponse? = null, validationDataSize: Double? = null)

Types

Companion

object Companion

Properties

limitSettings

val limitSettings: ImageLimitSettingsResponse

Required Limit settings for the AutoML job.

logVerbosity

val logVerbosity: String? = null

Log verbosity for the job.

modelSettings

val modelSettings: ImageModelSettingsObjectDetectionResponse? = null

Settings used for training the model.

primaryMetric

val primaryMetric: String? = null

Primary metric to optimize for this task.

searchSpace

val searchSpace: List<ImageModelDistributionSettingsObjectDetectionResponse>? = null

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

sweepSettings

val sweepSettings: ImageSweepSettingsResponse? = null

Model sweeping and hyperparameter sweeping related settings.

targetColumnName

val targetColumnName: String? = null

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

taskType

val taskType: String

AutoMLJob Task type. Expected value is 'ImageInstanceSegmentation'.

trainingData

val trainingData: MLTableJobInputResponse

Required Training data input.

validationData

val validationData: MLTableJobInputResponse? = null

Validation data inputs.

validationDataSize

val validationDataSize: 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.