In this tutorial, I will walk you through the steps involved in hosting a PyTorch model on AWS Lambda backed by an Amazon EFS file system. The function is exposed through an API Gateway. Assuming you followed the steps mentioned in the previous tutorial, you should have the EFS file system ready with PyTorch modules and the ResNet model. We will attach that to a Lambda function to host the inference API.
This article is a part of the series on making AWS Lambda functions stateful with Amazon EFS (Part 1, Part 2, Part 3).
Read the entire article at The New Stack
Janakiram MSV is an analyst, advisor, and architect. Follow him on Twitter, Facebook and LinkedIn.