CleanRoomsML / Client / start_trained_model_inference_job

start_trained_model_inference_job¶

CleanRoomsML.Client.start_trained_model_inference_job(**kwargs)¶

Defines the information necessary to begin a trained model inference job.

Request Syntax

response = client.start_trained_model_inference_job(
    membershipIdentifier='string',
    name='string',
    trainedModelArn='string',
    trainedModelVersionIdentifier='string',
    configuredModelAlgorithmAssociationArn='string',
    resourceConfig={
        'instanceType': 'ml.r7i.48xlarge'|'ml.r6i.16xlarge'|'ml.m6i.xlarge'|'ml.m5.4xlarge'|'ml.p2.xlarge'|'ml.m4.16xlarge'|'ml.r7i.16xlarge'|'ml.m7i.xlarge'|'ml.m6i.12xlarge'|'ml.r7i.8xlarge'|'ml.r7i.large'|'ml.m7i.12xlarge'|'ml.m6i.24xlarge'|'ml.m7i.24xlarge'|'ml.r6i.8xlarge'|'ml.r6i.large'|'ml.g5.2xlarge'|'ml.m5.large'|'ml.p3.16xlarge'|'ml.m7i.48xlarge'|'ml.m6i.16xlarge'|'ml.p2.16xlarge'|'ml.g5.4xlarge'|'ml.m7i.16xlarge'|'ml.c4.2xlarge'|'ml.c5.2xlarge'|'ml.c6i.32xlarge'|'ml.c4.4xlarge'|'ml.g5.8xlarge'|'ml.c6i.xlarge'|'ml.c5.4xlarge'|'ml.g4dn.xlarge'|'ml.c7i.xlarge'|'ml.c6i.12xlarge'|'ml.g4dn.12xlarge'|'ml.c7i.12xlarge'|'ml.c6i.24xlarge'|'ml.g4dn.2xlarge'|'ml.c7i.24xlarge'|'ml.c7i.2xlarge'|'ml.c4.8xlarge'|'ml.c6i.2xlarge'|'ml.g4dn.4xlarge'|'ml.c7i.48xlarge'|'ml.c7i.4xlarge'|'ml.c6i.16xlarge'|'ml.c5.9xlarge'|'ml.g4dn.16xlarge'|'ml.c7i.16xlarge'|'ml.c6i.4xlarge'|'ml.c5.xlarge'|'ml.c4.xlarge'|'ml.g4dn.8xlarge'|'ml.c7i.8xlarge'|'ml.c7i.large'|'ml.g5.xlarge'|'ml.c6i.8xlarge'|'ml.c6i.large'|'ml.g5.12xlarge'|'ml.g5.24xlarge'|'ml.m7i.2xlarge'|'ml.c5.18xlarge'|'ml.g5.48xlarge'|'ml.m6i.2xlarge'|'ml.g5.16xlarge'|'ml.m7i.4xlarge'|'ml.p3.2xlarge'|'ml.r6i.32xlarge'|'ml.m6i.4xlarge'|'ml.m5.xlarge'|'ml.m4.10xlarge'|'ml.r6i.xlarge'|'ml.m5.12xlarge'|'ml.m4.xlarge'|'ml.r7i.2xlarge'|'ml.r7i.xlarge'|'ml.r6i.12xlarge'|'ml.m5.24xlarge'|'ml.r7i.12xlarge'|'ml.m7i.8xlarge'|'ml.m7i.large'|'ml.r6i.24xlarge'|'ml.r6i.2xlarge'|'ml.m4.2xlarge'|'ml.r7i.24xlarge'|'ml.r7i.4xlarge'|'ml.m6i.8xlarge'|'ml.m6i.large'|'ml.m5.2xlarge'|'ml.p2.8xlarge'|'ml.r6i.4xlarge'|'ml.m6i.32xlarge'|'ml.p3.8xlarge'|'ml.m4.4xlarge',
        'instanceCount': 123
    },
    outputConfiguration={
        'accept': 'string',
        'members': [
            {
                'accountId': 'string'
            },
        ]
    },
    dataSource={
        'mlInputChannelArn': 'string'
    },
    description='string',
    containerExecutionParameters={
        'maxPayloadInMB': 123
    },
    environment={
        'string': 'string'
    },
    kmsKeyArn='string',
    tags={
        'string': 'string'
    }
)

Parameters:

membershipIdentifier (string) –
[REQUIRED]

The membership ID of the membership that contains the trained model inference job.
name (string) –
[REQUIRED]

The name of the trained model inference job.
trainedModelArn (string) –
[REQUIRED]

The Amazon Resource Name (ARN) of the trained model that is used for this trained model inference job.
trainedModelVersionIdentifier (string) – The version identifier of the trained model to use for inference. This specifies which version of the trained model should be used to generate predictions on the input data.
configuredModelAlgorithmAssociationArn (string) – The Amazon Resource Name (ARN) of the configured model algorithm association that is used for this trained model inference job.
resourceConfig (dict) –
[REQUIRED]

Defines the resource configuration for the trained model inference job.
- instanceType (string) – [REQUIRED]
  
  The type of instance that is used to perform model inference.
- instanceCount (integer) –
  
  The number of instances to use.
outputConfiguration (dict) –
[REQUIRED]

Defines the output configuration information for the trained model inference job.
- accept (string) –
  
  The MIME type used to specify the output data.
- members (list) – [REQUIRED]
  
  Defines the members that can receive inference output.
  - (dict) –
    
    Defines who will receive inference results.
    - accountId (string) – [REQUIRED]
      
      The account ID of the member that can receive inference results.
dataSource (dict) –
[REQUIRED]

Defines the data source that is used for the trained model inference job.
- mlInputChannelArn (string) – [REQUIRED]
  
  The Amazon Resource Name (ARN) of the ML input channel for this model inference data source.
description (string) – The description of the trained model inference job.
containerExecutionParameters (dict) –
The execution parameters for the container.
- maxPayloadInMB (integer) –
  
  The maximum size of the inference container payload, specified in MB.
environment (dict) –
The environment variables to set in the Docker container.
- (string) –
  - (string) –
kmsKeyArn (string) – The Amazon Resource Name (ARN) of the KMS key. This key is used to encrypt and decrypt customer-owned data in the ML inference job and associated data.
tags (dict) –
The optional metadata that you apply to the resource to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.

The following basic restrictions apply to tags:
- Maximum number of tags per resource - 50.
- For each resource, each tag key must be unique, and each tag key can have only one value.
- Maximum key length - 128 Unicode characters in UTF-8.
- Maximum value length - 256 Unicode characters in UTF-8.
- If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.
- Tag keys and values are case sensitive.
- Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Clean Rooms ML considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.
- (string) –
  - (string) –

Return type:

dict

Returns:

Response Syntax

{
    'trainedModelInferenceJobArn': 'string'
}

Response Structure

(dict) –
- trainedModelInferenceJobArn (string) –
  
  The Amazon Resource Name (ARN) of the trained model inference job.

start_trained_model_inference_job¶

Request Syntax

Response Syntax

Response Structure

Exceptions