Share via


BatchDeploymentProperties Class

Definition

Batch inference settings per deployment.

[System.ComponentModel.TypeConverter(typeof(Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401.BatchDeploymentPropertiesTypeConverter))]
public class BatchDeploymentProperties : Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401.IBatchDeploymentProperties, Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Runtime.IValidates
[<System.ComponentModel.TypeConverter(typeof(Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401.BatchDeploymentPropertiesTypeConverter))>]
type BatchDeploymentProperties = class
    interface IBatchDeploymentProperties
    interface IJsonSerializable
    interface IEndpointDeploymentPropertiesBase
    interface IValidates
Public Class BatchDeploymentProperties
Implements IBatchDeploymentProperties, IValidates
Inheritance
BatchDeploymentProperties
Attributes
Implements

Constructors

BatchDeploymentProperties()

Creates an new BatchDeploymentProperties instance.

Properties

CodeConfiguration

Code configuration for the endpoint deployment.

CodeConfigurationCodeId

ARM resource ID of the code asset.

CodeConfigurationScoringScript

[Required] The script to execute on startup. eg. "score.py"

Compute

Compute target for batch inference operation.

DeploymentConfigurationType

[Required] The type of the deployment

Description

Description of the endpoint deployment.

EnvironmentId

ARM resource ID or AssetId of the environment specification for the endpoint deployment.

EnvironmentVariable

Environment variables configuration for the deployment.

ErrorThreshold

Error threshold, if the error count for the entire input goes above this value, the batch inference will be aborted. Range is [-1, int.MaxValue]. For FileDataset, this value is the count of file failures. For TabularDataset, this value is the count of record failures. If set to -1 (the lower bound), all failures during batch inference will be ignored.

LoggingLevel

Logging level for batch inference operation.

MaxConcurrencyPerInstance

Indicates maximum number of parallelism per instance.

MiniBatchSize

Size of the mini-batch passed to each batch invocation. For FileDataset, this is the number of files per mini-batch. For TabularDataset, this is the size of the records in bytes, per mini-batch.

Model

Reference to the model asset for the endpoint deployment.

OutputAction

Indicates how the output will be organized.

OutputFileName

Customized output file name for append_row output action.

Property

Property dictionary. Properties can be added, but not removed or altered.

ProvisioningState

Provisioning state for the endpoint deployment.

ResourceInstanceCount

Optional number of instances or nodes used by the compute target.

ResourceInstanceType

Optional type of VM used as supported by the compute target.

ResourceProperty

Additional properties bag.

RetrySettingMaxRetry

Maximum retry count for a mini-batch

RetrySettingTimeout

Invocation timeout for a mini-batch, in ISO 8601 format.

Methods

DeserializeFromDictionary(IDictionary)

Deserializes a IDictionary into an instance of BatchDeploymentProperties.

DeserializeFromPSObject(PSObject)

Deserializes a PSObject into an instance of BatchDeploymentProperties.

FromJson(JsonNode)

Deserializes a JsonNode into an instance of Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401.IBatchDeploymentProperties.

FromJsonString(String)

Creates a new instance of BatchDeploymentProperties, deserializing the content from a json string.

ToJson(JsonObject, SerializationMode)

Serializes this instance of BatchDeploymentProperties into a JsonNode.

ToJsonString()

Serializes this instance to a json string.

ToString()
Validate(IEventListener)

Validates that this object meets the validation criteria.

Applies to