Puppet Task: sagemaker_aws_create_notebook_instance
- Defined in:
-
tasks/sagemaker_aws_create_notebook_instance.json,
tasks/sagemaker_aws_create_notebook_instance.rb
Overview
Creates an Amazon SageMaker notebook instance. A notebook instance is a machine learning (ML) compute instance running on a Jupyter notebook. In a CreateNotebookInstance request, specify the type of ML compute instance that you want to run. Amazon SageMaker launches the instance, installs common libraries that you can use to explore datasets for model training, and attaches an ML storage volume to the notebook instance. Amazon SageMaker also provides a set of example notebooks. Each notebook demonstrates how to use Amazon SageMaker with a specific algorithm or with a machine learning framework. After receiving the request, Amazon SageMaker does the following: Creates a network interface in the Amazon SageMaker VPC. (Option) If you specified SubnetId, Amazon SageMaker creates a network interface in your own VPC, which is inferred from the subnet ID that you provide in the input. When creating this network interface, Amazon SageMaker attaches the security group that you specified in the request to the network interface that it creates in your VPC. Launches an EC2 instance of the type specified in the request in the Amazon SageMaker VPC. If you specified SubnetId of your VPC, Amazon SageMaker specifies both network interfaces when launching this instance. This enables inbound traffic from your own VPC to the notebook instance, assuming that the security groups allow it. After creating the notebook instance, Amazon SageMaker returns its Amazon Resource Name (ARN). After Amazon SageMaker creates the notebook instance, you can connect to the Jupyter server and work in Jupyter notebooks. For example, you can write code to explore a dataset that you can use for model training, train a model, host models by creating Amazon SageMaker endpoints, and validate hosted models. For more information, see How It Works.