Skip to content

semantic_video_search_demo

0

Has anyone completed this AWS tutorial successfully? or any of the AWS tutorials successfully?

https://github.com/aws-samples/sample-semantic-video-search-with-lvm-on-sagemaker/blob/61ef85a4029bdb34153910fe75a043793474fcc7/semantic_video_search_demo.ipynb

I was wondering if there were any YouTube walk throughs of this tutorial or any additional information?

Additionally, I could use some guidance / insight into billing, monitor and limiting or turning off. I feel like the billing center information is too high level for me to figure out how I'm incurring costs and how to start or stop.

1 Answer
0

I don't have specific information about whether anyone has completed that particular semantic video search tutorial successfully, or if there are YouTube walkthroughs available for it. The sources I have access to cover other Amazon SageMaker tutorials, but not that specific GitHub repository.

However, I can provide some general guidance on AWS tutorials and billing management based on similar SageMaker projects:

Tutorial Completion and Resources: Many AWS tutorials are designed to be completed within 1-2 hours and typically cost less than $1-10 when following recommended configurations and terminating resources promptly. The tutorials generally include step-by-step instructions with code snippets to help you replicate the workflow. For additional support, you might want to check AWS documentation, AWS forums, or the GitHub repository's issues section for community discussions.

Billing Management and Cost Control: To better manage and understand your AWS costs:

  1. Resource Cleanup: The most important step is terminating all resources after completing tutorials. This includes stopping or deleting SageMaker notebook instances, endpoints, processing jobs, and any S3 buckets you created.

  2. Instance Selection: When running tutorials, choose smaller instance types (like ml.t3.medium) which are often Free Tier eligible and less expensive.

  3. Monitoring: Set up AWS Budgets to receive alerts when your spending approaches thresholds you define. This gives you advance warning before costs accumulate.

  4. Time Management: Complete tutorials in one session when possible, as leaving resources running (especially deployed endpoints and notebook instances) will continue to incur charges.

The key to controlling costs is being diligent about cleaning up resources immediately after completing your work, rather than leaving them running.
Sources
Build a semantic content recommendation system with Amazon SageMaker
Build, train, deploy, and monitor a machine learning model with Amazon SageMaker Studio
How to build, train, and deploy a machine learning model with Amazon SageMaker
Tutorial - Train a Machine Learning Model - Amazon Web Services

answered a month ago
AWS
EXPERT
reviewed a month ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.