November 2018
Intermediate to advanced
322 pages
7h 54m
English
TensorFlow Serving is a highly flexible serving system for deploying machine learning models in production. Before we go into the details, first let's try to understand what serving is by taking a look at its architecture:

We have some Data and we use that to train a machine learning Model. Once the Model is trained, it needs to be deployed onto a web or mobile App to serve the end users. One way to do that is through a remote procedure call (RPC) server (https://www.ibm.com/support/knowledgecenter/en/ssw_aix_72/com.ibm.aix.progcomc/ch8_rpc.htm). TensorFlow Serving can be used both as an RPC Server and as a set of libraries, ...
Read now
Unlock full access