How to deploy custom inference code on AWS?

  amazon-web-services, docker, opencv, pytorch, rest

I have an inference code perfectely working (remove background from image) I want to deploy this to AWS to get API calls? My question is how can I deploy this code to AWS, I have a top-level class that handles everything. I have never used AWS before, what should I?

P.S. – I am not particularly step by step answer (although it will be wonderful)

Source: Docker Questions

LEAVE A COMMENT