Creating REST API for TensorFlow models – Becoming Human: Artificial Intelligence Magazine

A while ago I wrote about Machine Learning model deployment with TensorFlow Serving. The main advantage of that approach, in my opinion, is a performance (thanks to gRPC and Protobufs) and direct use of classes generated from Protobufs instead of manual creation of JSON objects. The client calls a server as they were parts of the same program. That makes the code easy to understand and maintain. Now we host our model somewhere (for instance here) and can talk to it over gRPC using our special client.