TensorFlow Serving

Introduction

TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments. TensorFlow Serving makes it easy to deploy new algorithms and experiments, while keeping the same server architecture and APIs.

Basic Serving Tutorial

See the basic tutorial on the TensorFlow Serving site to learn how to export a trained TensorFlow model and build a server to serve the exported model.

Advanced Serving Tutorial

See the advanced tutorial on the TensorFlow Serving site to learn how to build a server that dynamically discovers and serves new versions of a trained TensorFlow model.

Serving Inception Model Tutorial

See the serving inception tutorial on the TensorFlow Serving site to learn how to serve the inception model with TensorFlow Serving and Kubernetes.