Machine Learning as a Service: How to deploy ML Models as APIs without going nuts

Loading

Upvotes: DownVotes:
Age: a year     Page Views: 90
Votes / View: -56    Wilson Score: 0.00




Often, the most convenient way to deploy a machine model is an API. Itallows accessing it from various programming environments and alsodecouples the development and deployment of the models from its use.However, building an good API is hard. It involves many nitty-grittiesand many of them need to repeated everytime an API is built. Also, it isvery important to have a client library so that the API can be easilyaccessed. If you every plan to use it from Javascript directly, then youneed to worry about cross-origin-resource-sharing etc. All things add upand building APIs for machine very tedious.In this talk demonstrates how deploying machine learning models an APIscan be made fun by using right programming abstractions. This presentscouple of opensource libraries`firefly `__ and`rorolite `__ which are built forthis very purpose.