So this is probably out of the scope of this course, however I'm curious if you have any good suggestions for reads when it comes to deploying our models that we have trained locally to the cloud so that it scales well with large amounts of data etc..?? I'm guessing that there are solutions in place for this already on GCP/AWS/Azure.
How to "deploy" a model to the cloud?
So this is probably out of the scope of this course, however I'm curious if you have any good suggestions for reads when it comes to deploying our models that we have trained locally to the cloud so that it scales well with large amounts of data etc..?? I'm guessing that there are solutions in place for this already on GCP/AWS/Azure.
This is a good introduction/overview to ML model deployment and its scaling:
https://course.fullstackdeeplearning.com/course-content/testing-and-deployment/web-deployment
There is also an associated walk-through handwriting recognition project (with videos) where they deploy a trained model to the web using AWS Lambda.
2
Add comment