AWS::SageMaker::ModelQualityJobDefinition EndpointInput - AWS CloudFormation
SyntaxProperties

AWS::SageMaker::ModelQualityJobDefinition EndpointInput

Input object for the endpoint

Syntax

To declare this entity in your AWS CloudFormation template, use the following syntax:

JSON

{
  "EndpointName" : String,
  "EndTimeOffset" : String,
  "InferenceAttribute" : String,
  "LocalPath" : String,
  "ProbabilityAttribute" : String,
  "ProbabilityThresholdAttribute" : Number,
  "S3DataDistributionType" : String,
  "S3InputMode" : String,
  "StartTimeOffset" : String
}

Properties

EndpointName

An endpoint in customer's account which has enabled DataCaptureConfig enabled.

Required: Yes

Type: String

Pattern: ^[a-zA-Z0-9](-*[a-zA-Z0-9])*

Maximum: 63

Update requires: Replacement

EndTimeOffset

If specified, monitoring jobs substract this time from the end time. For information about using offsets for scheduling monitoring jobs, see Schedule Model Quality Monitoring Jobs.

Required: No

Type: String

Pattern: ^.?P.*

Minimum: 1

Maximum: 15

Update requires: Replacement

InferenceAttribute

The attribute of the input data that represents the ground truth label.

Required: No

Type: String

Maximum: 256

Update requires: Replacement

LocalPath

Path to the filesystem where the endpoint data is available to the container.

Required: Yes

Type: String

Pattern: .*

Maximum: 256

Update requires: Replacement

ProbabilityAttribute

In a classification problem, the attribute that represents the class probability.

Required: No

Type: String

Maximum: 256

Update requires: Replacement

ProbabilityThresholdAttribute

The threshold for the class probability to be evaluated as a positive result.

Required: No

Type: Number

Update requires: Replacement

S3DataDistributionType

Whether input data distributed in Amazon S3 is fully replicated or sharded by an Amazon S3 key. Defaults to FullyReplicated

Required: No

Type: String

Allowed values: FullyReplicated | ShardedByS3Key

Update requires: Replacement

S3InputMode

Whether the Pipe or File is used as the input mode for transferring data for the monitoring job. Pipe mode is recommended for large datasets. File mode is useful for small files that fit in memory. Defaults to File.

Required: No

Type: String

Allowed values: Pipe | File

Update requires: Replacement

StartTimeOffset

If specified, monitoring jobs substract this time from the start time. For information about using offsets for scheduling monitoring jobs, see Schedule Model Quality Monitoring Jobs.

Required: No

Type: String

Pattern: ^.?P.*

Minimum: 1

Maximum: 15

Update requires: Replacement