ArmMachineLearningModelFactory.ImageClassification Method
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Image Classification. Multi-class image classification is used when an image is classified with only a single label from a set of classes - e.g. each image is classified as either an image of a 'cat' or a 'dog' or a 'duck'.
public static Azure.ResourceManager.MachineLearning.Models.ImageClassification ImageClassification(Azure.ResourceManager.MachineLearning.Models.MachineLearningLogVerbosity? logVerbosity = default, string targetColumnName = default, Azure.ResourceManager.MachineLearning.Models.MachineLearningTableJobInput trainingData = default, Azure.ResourceManager.MachineLearning.Models.ImageModelSettingsClassification modelSettings = default, System.Collections.Generic.IEnumerable<Azure.ResourceManager.MachineLearning.Models.ImageModelDistributionSettingsClassification> searchSpace = default, Azure.ResourceManager.MachineLearning.Models.ImageLimitSettings limitSettings = default, Azure.ResourceManager.MachineLearning.Models.ImageSweepSettings sweepSettings = default, Azure.ResourceManager.MachineLearning.Models.MachineLearningTableJobInput validationData = default, double? validationDataSize = default, Azure.ResourceManager.MachineLearning.Models.ClassificationPrimaryMetric? primaryMetric = default);static member ImageClassification : Nullable<Azure.ResourceManager.MachineLearning.Models.MachineLearningLogVerbosity> * string * Azure.ResourceManager.MachineLearning.Models.MachineLearningTableJobInput * Azure.ResourceManager.MachineLearning.Models.ImageModelSettingsClassification * seq<Azure.ResourceManager.MachineLearning.Models.ImageModelDistributionSettingsClassification> * Azure.ResourceManager.MachineLearning.Models.ImageLimitSettings * Azure.ResourceManager.MachineLearning.Models.ImageSweepSettings * Azure.ResourceManager.MachineLearning.Models.MachineLearningTableJobInput * Nullable<double> * Nullable<Azure.ResourceManager.MachineLearning.Models.ClassificationPrimaryMetric> -> Azure.ResourceManager.MachineLearning.Models.ImageClassificationPublic Shared Function ImageClassification (Optional logVerbosity As Nullable(Of MachineLearningLogVerbosity) = Nothing, Optional targetColumnName As String = Nothing, Optional trainingData As MachineLearningTableJobInput = Nothing, Optional modelSettings As ImageModelSettingsClassification = Nothing, Optional searchSpace As IEnumerable(Of ImageModelDistributionSettingsClassification) = Nothing, Optional limitSettings As ImageLimitSettings = Nothing, Optional sweepSettings As ImageSweepSettings = Nothing, Optional validationData As MachineLearningTableJobInput = Nothing, Optional validationDataSize As Nullable(Of Double) = Nothing, Optional primaryMetric As Nullable(Of ClassificationPrimaryMetric) = Nothing) As ImageClassificationParameters
- logVerbosity
- Nullable<MachineLearningLogVerbosity>
Enum for setting log verbosity.
- targetColumnName
- String
Target column name: This is prediction values column. Also known as label column name in context of classification tasks.
- trainingData
- MachineLearningTableJobInput
[Required] Training data input.
- modelSettings
- ImageModelSettingsClassification
Settings used for training the model.
- searchSpace
- IEnumerable<ImageModelDistributionSettingsClassification>
Search space for sampling different combinations of models and their hyperparameters.
- limitSettings
- ImageLimitSettings
[Required] Limit settings for the AutoML job.
- sweepSettings
- ImageSweepSettings
Model sweeping and hyperparameter sweeping related settings.
- validationData
- MachineLearningTableJobInput
Validation data inputs.
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.
- primaryMetric
- Nullable<ClassificationPrimaryMetric>
Primary metrics for classification tasks.
Returns
A new ImageClassification instance for mocking.
