/AWS1/CL_SGM=>UPDATEINFERENCEEXPERIMENT()
¶
About UpdateInferenceExperiment¶
Updates an inference experiment that you created. The status of the inference experiment has to be either
Created
, Running
. For more information on the status of an inference experiment,
see DescribeInferenceExperiment.
Method Signature¶
IMPORTING¶
Required arguments:¶
IV_NAME
TYPE /AWS1/SGMINFERENCEEXPERIMENT00
/AWS1/SGMINFERENCEEXPERIMENT00
¶
The name of the inference experiment to be updated.
Optional arguments:¶
IO_SCHEDULE
TYPE REF TO /AWS1/CL_SGMINFERENCEEXPERIM00
/AWS1/CL_SGMINFERENCEEXPERIM00
¶
The duration for which the inference experiment will run. If the status of the inference experiment is
Created
, then you can update both the start and end dates. If the status of the inference experiment isRunning
, then you can update only the end date.
IV_DESCRIPTION
TYPE /AWS1/SGMINFERENCEEXPERIMENT02
/AWS1/SGMINFERENCEEXPERIMENT02
¶
The description of the inference experiment.
IT_MODELVARIANTS
TYPE /AWS1/CL_SGMMODELVARIANTCONFIG=>TT_MODELVARIANTCONFIGLIST
TT_MODELVARIANTCONFIGLIST
¶
An array of
ModelVariantConfig
objects. There is one for each variant, whose infrastructure configuration you want to update.
IO_DATASTORAGECONFIG
TYPE REF TO /AWS1/CL_SGMINFERENCEEXPERIM01
/AWS1/CL_SGMINFERENCEEXPERIM01
¶
The Amazon S3 location and configuration for storing inference request and response data.
IO_SHADOWMODECONFIG
TYPE REF TO /AWS1/CL_SGMSHADOWMODECONFIG
/AWS1/CL_SGMSHADOWMODECONFIG
¶
The configuration of
ShadowMode
inference experiment type. Use this field to specify a production variant which takes all the inference requests, and a shadow variant to which Amazon SageMaker replicates a percentage of the inference requests. For the shadow variant also specify the percentage of requests that Amazon SageMaker replicates.