AWS SDK for C++
1.8.129
AWS SDK for C++
|
#include <CreateTransformJobRequest.h>
Additional Inherited Members | |
![]() | |
virtual void | DumpBodyToUrl (Aws::Http::URI &uri) const |
Definition at line 31 of file CreateTransformJobRequest.h.
Aws::SageMaker::Model::CreateTransformJobRequest::CreateTransformJobRequest | ( | ) |
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 449 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 437 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 461 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 443 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 431 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 455 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 467 of file CreateTransformJobRequest.h.
|
inline |
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
Definition at line 696 of file CreateTransformJobRequest.h.
|
inline |
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
Definition at line 704 of file CreateTransformJobRequest.h.
|
inline |
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 the SplitType
property 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
.
Definition at line 328 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 591 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 401 of file CreateTransformJobRequest.h.
|
inline |
Definition at line 711 of file CreateTransformJobRequest.h.
|
inline |
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 the SplitType
property 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
.
Definition at line 313 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 579 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 395 of file CreateTransformJobRequest.h.
|
inline |
Definition at line 708 of file CreateTransformJobRequest.h.
|
inline |
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 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
.
Definition at line 164 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 255 of file CreateTransformJobRequest.h.
|
inline |
Configures the timeout and maximum number of retries for processing a transform job invocation.
Definition at line 210 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 101 of file CreateTransformJobRequest.h.
|
overridevirtual |
Reimplemented from Aws::SageMaker::SageMakerRequest.
|
inlineoverridevirtual |
Implements Aws::AmazonWebServiceRequest.
Definition at line 40 of file CreateTransformJobRequest.h.
|
inline |
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
Definition at line 648 of file CreateTransformJobRequest.h.
|
inline |
Describes the input source and the way the transform job consumes it.
Definition at line 473 of file CreateTransformJobRequest.h.
|
inline |
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
Definition at line 51 of file CreateTransformJobRequest.h.
|
inline |
Describes the results of the transform job.
Definition at line 504 of file CreateTransformJobRequest.h.
|
inline |
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
Definition at line 536 of file CreateTransformJobRequest.h.
|
inline |
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 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
.
Definition at line 177 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 269 of file CreateTransformJobRequest.h.
|
inline |
Configures the timeout and maximum number of retries for processing a transform job invocation.
Definition at line 216 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 108 of file CreateTransformJobRequest.h.
|
overridevirtual |
Convert payload into String.
Implements Aws::AmazonSerializableWebServiceRequest.
|
inline |
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 the SplitType
property 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
.
Definition at line 358 of file CreateTransformJobRequest.h.
|
inline |
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 the SplitType
property 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
.
Definition at line 343 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 603 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 615 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 413 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 407 of file CreateTransformJobRequest.h.
|
inline |
Definition at line 714 of file CreateTransformJobRequest.h.
|
inline |
Definition at line 717 of file CreateTransformJobRequest.h.
|
inline |
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 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
.
Definition at line 190 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 283 of file CreateTransformJobRequest.h.
|
inline |
Configures the timeout and maximum number of retries for processing a transform job invocation.
Definition at line 222 of file CreateTransformJobRequest.h.
|
inline |
Configures the timeout and maximum number of retries for processing a transform job invocation.
Definition at line 228 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 122 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 115 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 129 of file CreateTransformJobRequest.h.
|
inline |
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
Definition at line 672 of file CreateTransformJobRequest.h.
|
inline |
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
Definition at line 664 of file CreateTransformJobRequest.h.
|
inline |
Describes the input source and the way the transform job consumes it.
Definition at line 483 of file CreateTransformJobRequest.h.
|
inline |
Describes the input source and the way the transform job consumes it.
Definition at line 488 of file CreateTransformJobRequest.h.
|
inline |
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
Definition at line 69 of file CreateTransformJobRequest.h.
|
inline |
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
Definition at line 63 of file CreateTransformJobRequest.h.
|
inline |
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
Definition at line 75 of file CreateTransformJobRequest.h.
|
inline |
Describes the results of the transform job.
Definition at line 514 of file CreateTransformJobRequest.h.
|
inline |
Describes the results of the transform job.
Definition at line 519 of file CreateTransformJobRequest.h.
|
inline |
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
Definition at line 548 of file CreateTransformJobRequest.h.
|
inline |
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
Definition at line 554 of file CreateTransformJobRequest.h.
|
inline |
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
Definition at line 656 of file CreateTransformJobRequest.h.
|
inline |
Describes the input source and the way the transform job consumes it.
Definition at line 478 of file CreateTransformJobRequest.h.
|
inline |
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
Definition at line 57 of file CreateTransformJobRequest.h.
|
inline |
Describes the results of the transform job.
Definition at line 509 of file CreateTransformJobRequest.h.
|
inline |
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
Definition at line 542 of file CreateTransformJobRequest.h.
|
inline |
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 the SplitType
property 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
.
Definition at line 388 of file CreateTransformJobRequest.h.
|
inline |
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 the SplitType
property 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
.
Definition at line 373 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 627 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 639 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 425 of file CreateTransformJobRequest.h.
|
inline |
The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.
Definition at line 419 of file CreateTransformJobRequest.h.
|
inline |
Definition at line 720 of file CreateTransformJobRequest.h.
|
inline |
Definition at line 723 of file CreateTransformJobRequest.h.
|
inline |
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 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
.
Definition at line 203 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 297 of file CreateTransformJobRequest.h.
|
inline |
Configures the timeout and maximum number of retries for processing a transform job invocation.
Definition at line 234 of file CreateTransformJobRequest.h.
|
inline |
Configures the timeout and maximum number of retries for processing a transform job invocation.
Definition at line 240 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 143 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 136 of file CreateTransformJobRequest.h.
|
inline |
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.
Definition at line 150 of file CreateTransformJobRequest.h.
|
inline |
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
Definition at line 688 of file CreateTransformJobRequest.h.
|
inline |
(Optional) An array of key-value pairs. For more information, see Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide.
Definition at line 680 of file CreateTransformJobRequest.h.
|
inline |
Describes the input source and the way the transform job consumes it.
Definition at line 493 of file CreateTransformJobRequest.h.
|
inline |
Describes the input source and the way the transform job consumes it.
Definition at line 498 of file CreateTransformJobRequest.h.
|
inline |
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
Definition at line 87 of file CreateTransformJobRequest.h.
|
inline |
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
Definition at line 81 of file CreateTransformJobRequest.h.
|
inline |
The name of the transform job. The name must be unique within an AWS Region in an AWS account.
Definition at line 93 of file CreateTransformJobRequest.h.
|
inline |
Describes the results of the transform job.
Definition at line 524 of file CreateTransformJobRequest.h.
|
inline |
Describes the results of the transform job.
Definition at line 529 of file CreateTransformJobRequest.h.
|
inline |
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
Definition at line 560 of file CreateTransformJobRequest.h.
|
inline |
Describes the resources, including ML instance types and ML instance count, to use for the transform job.
Definition at line 566 of file CreateTransformJobRequest.h.