From the course: Amazon Web Services Machine Learning Essential Training
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Use model from SageMaker endpoint - Amazon Web Services (AWS) Tutorial
From the course: Amazon Web Services Machine Learning Essential Training
Use model from SageMaker endpoint
- [Instructor] Now we're going to validate our model for use. We're going to generate a classification from a single observation from the train model using the endpoint. So you can see in this code cell we're setting a result variable equal to K-Means predictor calling predict against the training set and we're going to print the result. And I'm going to click in here and press shift-return to execute this cell. And you can see that we get this output in the format adjacent. The key is closest cluster. The value is a float 32 tensor and it's a 3, which is what we're expecting. And the label is the distance to cluster and the value is a tensor. This is the result that we expected. So a single prediction works. So next we can do a whole batch and see how well the clustering works. So we're going to scroll down and use this time value again and set the result to K-Means predictor predict from a set. And we're going to set a clusters variable equal to a label the closest cluster for r in…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
(Locked)
Understanding ML platforms3m 53s
-
(Locked)
Understanding and using AWS Machine Learning9m 15s
-
(Locked)
Understanding SageMaker3m 54s
-
Create Jupyter notebooks with SageMaker6m 12s
-
(Locked)
Get data with SageMaker notebook6m 25s
-
(Locked)
Train model with SageMaker job3m 6s
-
(Locked)
Deploy and host model with SageMaker model2m 31s
-
(Locked)
Use model from SageMaker endpoint4m 7s
-
(Locked)
Selecting algorithm for model training5m 36s
-
(Locked)
Advanced use of SageMaker2m 37s
-
(Locked)
-
-
-