Describes the Docker container for the model package.
Contents
- Image
-
The Amazon Elastic Container Registry (Amazon ECR) path where inference code is stored.
If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both
registry/repository[:tag]andregistry/repository[@digest]image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.Type: String
Length Constraints: Maximum length of 255.
Pattern:
[\S]+Required: Yes
- AdditionalS3DataSource
-
The additional data source that is used during inference in the Docker container for your model package.
Type: AdditionalS3DataSource object
Required: No
- ContainerHostname
-
The DNS host name for the Docker container.
Type: String
Length Constraints: Maximum length of 63.
Pattern:
^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}Required: No
- Environment
-
The environment variables to set in the Docker container. Each key and value in the
Environmentstring to string map can have length of up to 1024. We support up to 16 entries in the map.Type: String to string map
Map Entries: Maximum number of 100 items.
Key Length Constraints: Maximum length of 1024.
Key Pattern:
[a-zA-Z_][a-zA-Z0-9_]*Value Length Constraints: Maximum length of 1024.
Value Pattern:
[\S\s]*Required: No
- Framework
-
The machine learning framework of the model package container image.
Type: String
Required: No
- FrameworkVersion
-
The framework version of the Model Package Container Image.
Type: String
Length Constraints: Minimum length of 3. Maximum length of 10.
Pattern:
[0-9]\.[A-Za-z0-9.-]+Required: No
- ImageDigest
-
An MD5 hash of the training algorithm that identifies the Docker image used for training.
Type: String
Length Constraints: Maximum length of 72.
Pattern:
^[Ss][Hh][Aa]256:[0-9a-fA-F]{64}$Required: No
- ModelDataETag
-
The ETag associated with Model Data URL.
Type: String
Required: No
- ModelDataSource
-
Specifies the location of ML model data to deploy during endpoint creation.
Type: ModelDataSource object
Required: No
- ModelDataUrl
-
The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single
gzipcompressed tar archive (.tar.gzsuffix).Note
The model artifacts must be in an S3 bucket that is in the same region as the model package.
Type: String
Length Constraints: Maximum length of 1024.
Pattern:
^(https|s3)://([^/]+)/?(.*)$Required: No
- ModelInput
-
A structure with Model Input details.
Type: ModelInput object
Required: No
- NearestModelName
-
The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model. You can find a list of benchmarked models by calling
ListModelMetadata.Type: String
Required: No
- ProductId
-
The AWS Marketplace product ID of the model package.
Type: String
Length Constraints: Maximum length of 256.
Pattern:
^[a-zA-Z0-9](-*[a-zA-Z0-9])*$Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
