« blib/lib/Paws/SageMaker/ConditionStepMetadata.pm
↑ Summary
blib/lib/Paws/SageMaker/ContextSource.pm »
| 1 | # Generated by default/object.tt | ||
| 2 | package Paws::SageMaker::ContainerDefinition; | ||
| 3 | use Moose; | ||
| 4 | has ContainerHostname => (is => 'ro', isa => 'Str'); | ||
| 5 | has Environment => (is => 'ro', isa => 'Paws::SageMaker::EnvironmentMap'); | ||
| 6 | has Image => (is => 'ro', isa => 'Str'); | ||
| 7 | has ImageConfig => (is => 'ro', isa => 'Paws::SageMaker::ImageConfig'); | ||
| 8 | has Mode => (is => 'ro', isa => 'Str'); | ||
| 9 | has ModelDataUrl => (is => 'ro', isa => 'Str'); | ||
| 10 | has ModelPackageName => (is => 'ro', isa => 'Str'); | ||
| 11 | has MultiModelConfig => (is => 'ro', isa => 'Paws::SageMaker::MultiModelConfig'); | ||
| 12 | |||
| 13 | 1; | ||
| 14 | |||
| 15 | ### main pod documentation begin ### | ||
| 16 | |||
| 17 | =head1 NAME | ||
| 18 | |||
| 19 | Paws::SageMaker::ContainerDefinition | ||
| 20 | |||
| 21 | =head1 USAGE | ||
| 22 | |||
| 23 | This class represents one of two things: | ||
| 24 | |||
| 25 | =head3 Arguments in a call to a service | ||
| 26 | |||
| 27 | Use the attributes of this class as arguments to methods. You shouldn't make instances of this class. | ||
| 28 | Each attribute should be used as a named argument in the calls that expect this type of object. | ||
| 29 | |||
| 30 | As an example, if Att1 is expected to be a Paws::SageMaker::ContainerDefinition object: | ||
| 31 | |||
| 32 | $service_obj->Method(Att1 => { ContainerHostname => $value, ..., MultiModelConfig => $value }); | ||
| 33 | |||
| 34 | =head3 Results returned from an API call | ||
| 35 | |||
| 36 | Use accessors for each attribute. If Att1 is expected to be an Paws::SageMaker::ContainerDefinition object: | ||
| 37 | |||
| 38 | $result = $service_obj->Method(...); | ||
| 39 | $result->Att1->ContainerHostname | ||
| 40 | |||
| 41 | =head1 DESCRIPTION | ||
| 42 | |||
| 43 | Describes the container, as part of model definition. | ||
| 44 | |||
| 45 | =head1 ATTRIBUTES | ||
| 46 | |||
| 47 | |||
| 48 | =head2 ContainerHostname => Str | ||
| 49 | |||
| 50 | This parameter is ignored for models that contain only a | ||
| 51 | C<PrimaryContainer>. | ||
| 52 | |||
| 53 | When a C<ContainerDefinition> is part of an inference pipeline, the | ||
| 54 | value of the parameter uniquely identifies the container for the | ||
| 55 | purposes of logging and metrics. For information, see Use Logs and | ||
| 56 | Metrics to Monitor an Inference Pipeline | ||
| 57 | (https://docs.aws.amazon.com/sagemaker/latest/dg/inference-pipeline-logs-metrics.html). | ||
| 58 | If you don't specify a value for this parameter for a | ||
| 59 | C<ContainerDefinition> that is part of an inference pipeline, a unique | ||
| 60 | name is automatically assigned based on the position of the | ||
| 61 | C<ContainerDefinition> in the pipeline. If you specify a value for the | ||
| 62 | C<ContainerHostName> for any C<ContainerDefinition> that is part of an | ||
| 63 | inference pipeline, you must specify a value for the | ||
| 64 | C<ContainerHostName> parameter of every C<ContainerDefinition> in that | ||
| 65 | pipeline. | ||
| 66 | |||
| 67 | |||
| 68 | =head2 Environment => L<Paws::SageMaker::EnvironmentMap> | ||
| 69 | |||
| 70 | The environment variables to set in the Docker container. Each key and | ||
| 71 | value in the C<Environment> string to string map can have length of up | ||
| 72 | to 1024. We support up to 16 entries in the map. | ||
| 73 | |||
| 74 | |||
| 75 | =head2 Image => Str | ||
| 76 | |||
| 77 | The path where inference code is stored. This can be either in Amazon | ||
| 78 | EC2 Container Registry or in a Docker registry that is accessible from | ||
| 79 | the same VPC that you configure for your endpoint. If you are using | ||
| 80 | your own custom algorithm instead of an algorithm provided by Amazon | ||
| 81 | SageMaker, the inference code must meet Amazon SageMaker requirements. | ||
| 82 | Amazon SageMaker supports both C<registry/repository[:tag]> and | ||
| 83 | C<registry/repository[@digest]> image path formats. For more | ||
| 84 | information, see Using Your Own Algorithms with Amazon SageMaker | ||
| 85 | (https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms.html) | ||
| 86 | |||
| 87 | |||
| 88 | =head2 ImageConfig => L<Paws::SageMaker::ImageConfig> | ||
| 89 | |||
| 90 | Specifies whether the model container is in Amazon ECR or a private | ||
| 91 | Docker registry accessible from your Amazon Virtual Private Cloud | ||
| 92 | (VPC). For information about storing containers in a private Docker | ||
| 93 | registry, see Use a Private Docker Registry for Real-Time Inference | ||
| 94 | Containers | ||
| 95 | (https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-containers-inference-private.html) | ||
| 96 | |||
| 97 | |||
| 98 | =head2 Mode => Str | ||
| 99 | |||
| 100 | Whether the container hosts a single model or multiple models. | ||
| 101 | |||
| 102 | |||
| 103 | =head2 ModelDataUrl => Str | ||
| 104 | |||
| 105 | The S3 path where the model artifacts, which result from model | ||
| 106 | training, are stored. This path must point to a single gzip compressed | ||
| 107 | tar archive (.tar.gz suffix). The S3 path is required for Amazon | ||
| 108 | SageMaker built-in algorithms, but not if you use your own algorithms. | ||
| 109 | For more information on built-in algorithms, see Common Parameters | ||
| 110 | (https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-algo-docker-registry-paths.html). | ||
| 111 | |||
| 112 | The model artifacts must be in an S3 bucket that is in the same region | ||
| 113 | as the model or endpoint you are creating. | ||
| 114 | |||
| 115 | If you provide a value for this parameter, Amazon SageMaker uses Amazon | ||
| 116 | Web Services Security Token Service to download model artifacts from | ||
| 117 | the S3 path you provide. Amazon Web Services STS is activated in your | ||
| 118 | IAM user account by default. If you previously deactivated Amazon Web | ||
| 119 | Services STS for a region, you need to reactivate Amazon Web Services | ||
| 120 | STS for that region. For more information, see Activating and | ||
| 121 | Deactivating Amazon Web Services STS in an Amazon Web Services Region | ||
| 122 | (https://docs.aws.amazon.com/IAM/latest/UserGuide/id_credentials_temp_enable-regions.html) | ||
| 123 | in the I<Amazon Web Services Identity and Access Management User | ||
| 124 | Guide>. | ||
| 125 | |||
| 126 | If you use a built-in algorithm to create a model, Amazon SageMaker | ||
| 127 | requires that you provide a S3 path to the model artifacts in | ||
| 128 | C<ModelDataUrl>. | ||
| 129 | |||
| 130 | |||
| 131 | =head2 ModelPackageName => Str | ||
| 132 | |||
| 133 | The name or Amazon Resource Name (ARN) of the model package to use to | ||
| 134 | create the model. | ||
| 135 | |||
| 136 | |||
| 137 | =head2 MultiModelConfig => L<Paws::SageMaker::MultiModelConfig> | ||
| 138 | |||
| 139 | Specifies additional configuration for multi-model endpoints. | ||
| 140 | |||
| 141 | |||
| 142 | |||
| 143 | =head1 SEE ALSO | ||
| 144 | |||
| 145 | This class forms part of L<Paws>, describing an object used in L<Paws::SageMaker> | ||
| 146 | |||
| 147 | =head1 BUGS and CONTRIBUTIONS | ||
| 148 | |||
| 149 | The source code is located here: L<https://github.com/pplu/aws-sdk-perl> | ||
| 150 | |||
| 151 | Please report bugs to: L<https://github.com/pplu/aws-sdk-perl/issues> | ||
| 152 | |||
| 153 | =cut | ||
| 154 |