AWS ML Heroes in 15: Responsible ML on Amazon SageMaker- AWS Machine Learning in 15

68 Views

Thanks! Share it with your friends!

You disliked this video. Thanks for the feedback!

Published Feb 20, 2025

Learn from AWS ML Hero Francesco Pochetti on his latest project how he trained, optimized and deployed a privacy-first, Responsible ML computer vision segmentation model on Amazon SageMaker with NVIDIA TensorRT and NVIDIA Triton.

Learning Objectives:
* Objective 1: How to conceive of and develop a Responsible ML POC project.
* Objective 2: How to train an image segmentation model (UNET) using IceVision and a sample of face synthetic dataset.
* Objective 3: How to deploy a TorchScript model to an Amazon SageMaker real-time endpoint, deploy a TensorRT model to SageMaker on top of NVIDIA’s Triton inference server and compare performance between the two methods.

***To learn more about the services featured in this talk, please visit: https://aws.amazon.com/machine-learning/responsible-machine-learning/
To download the slides visit: https://pages.awscloud.com/rs/112-TZM-766/images/2023_0201-SN-MCL_Slide-Deck.pdf

Subscribe to AWS Developers: https://www.youtube.com/@AWSDevelopers?sub_confirmation=1

Follow Amazon Web Services:
Official Website: https://aws.amazon.com/what-is-aws
Twitch: https://twitch.tv/aws
Twitter: https://twitter.com/awsdevelopers
Facebook: https://facebook.com/amazonwebservices
Instagram: https://instagram.com/amazonwebservices

☁️ AWS Online Tech Talks cover a wide range of topics and expertise levels through technical deep dives, demos, customer examples, and live Q&A with AWS experts. Builders can choose from bite-sized 15-minute sessions, insightful fireside chats, immersive virtual workshops, interactive office hours, or watch on-demand tech talks at your own pace. Join us to fuel your learning journey with AWS.

#AWS