public static interface CreateTransformJobRequest.Builder extends SageMakerRequest.Builder, SdkPojo, CopyableBuilder<CreateTransformJobRequest.Builder,CreateTransformJobRequest>
| Modifier and Type | Method and Description |
|---|---|
CreateTransformJobRequest.Builder |
batchStrategy(BatchStrategy batchStrategy)
Specifies the number of records to include in a mini-batch for an HTTP inference request.
|
CreateTransformJobRequest.Builder |
batchStrategy(String batchStrategy)
Specifies the number of records to include in a mini-batch for an HTTP inference request.
|
default CreateTransformJobRequest.Builder |
dataProcessing(Consumer<DataProcessing.Builder> dataProcessing)
The data structure used to specify the data to be used for inference in a batch transform job and to
associate the data that is relevant to the prediction results in the output.
|
CreateTransformJobRequest.Builder |
dataProcessing(DataProcessing dataProcessing)
The data structure used to specify the data to be used for inference in a batch transform job and to
associate the data that is relevant to the prediction results in the output.
|
CreateTransformJobRequest.Builder |
environment(Map<String,String> environment)
The environment variables to set in the Docker container.
|
CreateTransformJobRequest.Builder |
maxConcurrentTransforms(Integer maxConcurrentTransforms)
The maximum number of parallel requests that can be sent to each instance in a transform job.
|
CreateTransformJobRequest.Builder |
maxPayloadInMB(Integer maxPayloadInMB)
The maximum allowed size of the payload, in MB.
|
CreateTransformJobRequest.Builder |
modelName(String modelName)
The name of the model that you want to use for the transform job.
|
CreateTransformJobRequest.Builder |
overrideConfiguration(AwsRequestOverrideConfiguration overrideConfiguration) |
CreateTransformJobRequest.Builder |
overrideConfiguration(Consumer<AwsRequestOverrideConfiguration.Builder> builderConsumer) |
CreateTransformJobRequest.Builder |
tags(Collection<Tag> tags)
(Optional) An array of key-value pairs.
|
CreateTransformJobRequest.Builder |
tags(Consumer<Tag.Builder>... tags)
(Optional) An array of key-value pairs.
|
CreateTransformJobRequest.Builder |
tags(Tag... tags)
(Optional) An array of key-value pairs.
|
default CreateTransformJobRequest.Builder |
transformInput(Consumer<TransformInput.Builder> transformInput)
Describes the input source and the way the transform job consumes it.
|
CreateTransformJobRequest.Builder |
transformInput(TransformInput transformInput)
Describes the input source and the way the transform job consumes it.
|
CreateTransformJobRequest.Builder |
transformJobName(String transformJobName)
The name of the transform job.
|
default CreateTransformJobRequest.Builder |
transformOutput(Consumer<TransformOutput.Builder> transformOutput)
Describes the results of the transform job.
|
CreateTransformJobRequest.Builder |
transformOutput(TransformOutput transformOutput)
Describes the results of the transform job.
|
default CreateTransformJobRequest.Builder |
transformResources(Consumer<TransformResources.Builder> transformResources)
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
|
CreateTransformJobRequest.Builder |
transformResources(TransformResources transformResources)
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
|
buildoverrideConfigurationequalsBySdkFields, sdkFieldscopyapplyMutation, buildCreateTransformJobRequest.Builder transformJobName(String transformJobName)
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
transformJobName - The name of the transform job. The name must be unique within an AWS Region in an AWS account.CreateTransformJobRequest.Builder modelName(String modelName)
The name of the model that you want to use for the transform job. ModelName must be the name of
an existing Amazon SageMaker model within an AWS Region in an AWS account.
modelName - The name of the model that you want to use for the transform job. ModelName must be the
name of an existing Amazon SageMaker model within an AWS Region in an AWS account.CreateTransformJobRequest.Builder maxConcurrentTransforms(Integer maxConcurrentTransforms)
The maximum number of parallel requests that can be sent to each instance in a transform job. If
MaxConcurrentTransforms is set to 0 or left unset, Amazon SageMaker checks the
optional execution-parameters to determine the optimal settings for your chosen algorithm. If the
execution-parameters endpoint is not enabled, the default value is 1. For more information on
execution-parameters, see How Containers Serve Requests. For built-in algorithms, you don't need to set a value for
MaxConcurrentTransforms.
maxConcurrentTransforms - The maximum number of parallel requests that can be sent to each instance in a transform job. If
MaxConcurrentTransforms is set to 0 or left unset, Amazon SageMaker checks
the optional execution-parameters to determine the optimal settings for your chosen algorithm. If the
execution-parameters endpoint is not enabled, the default value is 1. For more
information on execution-parameters, see How Containers Serve Requests. For built-in algorithms, you don't need to set a value for
MaxConcurrentTransforms.CreateTransformJobRequest.Builder maxPayloadInMB(Integer maxPayloadInMB)
The maximum allowed size of the payload, in MB. A payload is the data portion of a record (without
metadata). The value in MaxPayloadInMB must be greater than, or equal to, the size of a single
record. To estimate the size of a record in MB, divide the size of your dataset by the number of records. To
ensure that the records fit within the maximum payload size, we recommend using a slightly larger value. The
default value is 6 MB.
For cases where the payload might be arbitrarily large and is transmitted using HTTP chunked encoding, set
the value to 0. This feature works only in supported algorithms. Currently, Amazon SageMaker
built-in algorithms do not support HTTP chunked encoding.
maxPayloadInMB - The maximum allowed size of the payload, in MB. A payload is the data portion of a record
(without metadata). The value in MaxPayloadInMB must be greater than, or equal to, the
size of a single record. To estimate the size of a record in MB, divide the size of your dataset by
the number of records. To ensure that the records fit within the maximum payload size, we recommend
using a slightly larger value. The default value is 6 MB.
For cases where the payload might be arbitrarily large and is transmitted using HTTP chunked encoding,
set the value to 0. This feature works only in supported algorithms. Currently, Amazon
SageMaker built-in algorithms do not support HTTP chunked encoding.
CreateTransformJobRequest.Builder batchStrategy(String batchStrategy)
Specifies the number of records to include in a mini-batch for an HTTP inference request. A record is a single unit of input data that inference can be made on. For example, a single line in a CSV file is a record.
To enable the batch strategy, you must set SplitType to Line, RecordIO
, or TFRecord.
To use only one record when making an HTTP invocation request to a container, set BatchStrategy
to SingleRecord and SplitType to Line.
To fit as many records in a mini-batch as can fit within the MaxPayloadInMB limit, set
BatchStrategy to MultiRecord and SplitType to Line.
batchStrategy - Specifies the number of records to include in a mini-batch for an HTTP inference request. A
record is a single unit of input data that inference can be made on. For example, a single
line in a CSV file is a record.
To enable the batch strategy, you must set SplitType to Line,
RecordIO, or TFRecord.
To use only one record when making an HTTP invocation request to a container, set
BatchStrategy to SingleRecord and SplitType to
Line.
To fit as many records in a mini-batch as can fit within the MaxPayloadInMB limit, set
BatchStrategy to MultiRecord and SplitType to Line.
BatchStrategy,
BatchStrategyCreateTransformJobRequest.Builder batchStrategy(BatchStrategy batchStrategy)
Specifies the number of records to include in a mini-batch for an HTTP inference request. A record is a single unit of input data that inference can be made on. For example, a single line in a CSV file is a record.
To enable the batch strategy, you must set SplitType to Line, RecordIO
, or TFRecord.
To use only one record when making an HTTP invocation request to a container, set BatchStrategy
to SingleRecord and SplitType to Line.
To fit as many records in a mini-batch as can fit within the MaxPayloadInMB limit, set
BatchStrategy to MultiRecord and SplitType to Line.
batchStrategy - Specifies the number of records to include in a mini-batch for an HTTP inference request. A
record is a single unit of input data that inference can be made on. For example, a single
line in a CSV file is a record.
To enable the batch strategy, you must set SplitType to Line,
RecordIO, or TFRecord.
To use only one record when making an HTTP invocation request to a container, set
BatchStrategy to SingleRecord and SplitType to
Line.
To fit as many records in a mini-batch as can fit within the MaxPayloadInMB limit, set
BatchStrategy to MultiRecord and SplitType to Line.
BatchStrategy,
BatchStrategyCreateTransformJobRequest.Builder environment(Map<String,String> environment)
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
environment - The environment variables to set in the Docker container. We support up to 16 key and values entries
in the map.CreateTransformJobRequest.Builder transformInput(TransformInput transformInput)
Describes the input source and the way the transform job consumes it.
transformInput - Describes the input source and the way the transform job consumes it.default CreateTransformJobRequest.Builder transformInput(Consumer<TransformInput.Builder> transformInput)
Describes the input source and the way the transform job consumes it.
This is a convenience that creates an instance of theTransformInput.Builder avoiding the need to
create one manually via TransformInput.builder().
When the Consumer completes, SdkBuilder.build() is called immediately and its
result is passed to transformInput(TransformInput).transformInput - a consumer that will call methods on TransformInput.BuildertransformInput(TransformInput)CreateTransformJobRequest.Builder transformOutput(TransformOutput transformOutput)
Describes the results of the transform job.
transformOutput - Describes the results of the transform job.default CreateTransformJobRequest.Builder transformOutput(Consumer<TransformOutput.Builder> transformOutput)
Describes the results of the transform job.
This is a convenience that creates an instance of theTransformOutput.Builder avoiding the need to
create one manually via TransformOutput.builder().
When the Consumer completes, SdkBuilder.build() is called immediately and its
result is passed to transformOutput(TransformOutput).transformOutput - a consumer that will call methods on TransformOutput.BuildertransformOutput(TransformOutput)CreateTransformJobRequest.Builder transformResources(TransformResources transformResources)
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
transformResources - Describes the resources, including ML instance types and ML instance count, to use for the transform
job.default CreateTransformJobRequest.Builder transformResources(Consumer<TransformResources.Builder> transformResources)
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
This is a convenience that creates an instance of theTransformResources.Builder avoiding the need to
create one manually via TransformResources.builder().
When the Consumer completes, SdkBuilder.build() is called immediately and its
result is passed to transformResources(TransformResources).transformResources - a consumer that will call methods on TransformResources.BuildertransformResources(TransformResources)CreateTransformJobRequest.Builder dataProcessing(DataProcessing dataProcessing)
The data structure used to specify the data to be used for inference in a batch transform job and to associate the data that is relevant to the prediction results in the output. The input filter provided allows you to exclude input data that is not needed for inference in a batch transform job. The output filter provided allows you to include input data relevant to interpreting the predictions in the output from the job. For more information, see Associate Prediction Results with their Corresponding Input Records.
dataProcessing - The data structure used to specify the data to be used for inference in a batch transform job and to
associate the data that is relevant to the prediction results in the output. The input filter provided
allows you to exclude input data that is not needed for inference in a batch transform job. The output
filter provided allows you to include input data relevant to interpreting the predictions in the
output from the job. For more information, see Associate
Prediction Results with their Corresponding Input Records.default CreateTransformJobRequest.Builder dataProcessing(Consumer<DataProcessing.Builder> dataProcessing)
The data structure used to specify the data to be used for inference in a batch transform job and to associate the data that is relevant to the prediction results in the output. The input filter provided allows you to exclude input data that is not needed for inference in a batch transform job. The output filter provided allows you to include input data relevant to interpreting the predictions in the output from the job. For more information, see Associate Prediction Results with their Corresponding Input Records.
This is a convenience that creates an instance of theDataProcessing.Builder avoiding the need to
create one manually via DataProcessing.builder().
When the Consumer completes, SdkBuilder.build() is called immediately and its
result is passed to dataProcessing(DataProcessing).dataProcessing - a consumer that will call methods on DataProcessing.BuilderdataProcessing(DataProcessing)CreateTransformJobRequest.Builder tags(Collection<Tag> tags)
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
tags - (Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.CreateTransformJobRequest.Builder tags(Tag... tags)
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
tags - (Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.CreateTransformJobRequest.Builder tags(Consumer<Tag.Builder>... tags)
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
This is a convenience that creates an instance of theList.Builder avoiding the need to create
one manually via List#builder() .
When the Consumer completes, List.Builder#build() is called immediately and its result
is passed to #tags(List) .tags - a consumer that will call methods on List.Builder #tags(List) CreateTransformJobRequest.Builder overrideConfiguration(AwsRequestOverrideConfiguration overrideConfiguration)
overrideConfiguration in interface AwsRequest.BuilderCreateTransformJobRequest.Builder overrideConfiguration(Consumer<AwsRequestOverrideConfiguration.Builder> builderConsumer)
overrideConfiguration in interface AwsRequest.BuilderCopyright © 2019. All rights reserved.