In Chapter 2, Classifying Twitter Feeds with Naive Bayes, we deployed our first model with SageMaker. At that point, we had trained our classifier using BlazingText and stored it in a variable called bt_model. To deploy the model, we just need to call the deploy method, stating the number and kinds of machines to use:
bt_model.deploy(initial_instance_count = 1,instance_type = 'ml.m4.xlarge')
SageMaker can balance the requests made to the endpoint across the number of instances and automatically scale up or down the depending on the service load. Details can be found at https://docs.aws.amazon.com/sagemaker/latest/dg/endpoint-auto-scaling.html.
Once we invoke the deploy method, an endpoint should appear in the AWS SageMaker console at https://console.aws.amazon.com/sagemaker. The following screenshot shows the endpoint for our BlazingText...
