Deploying production ML models with TensorFlow Serving overview

Wei Wei, Developer Advocate at Google, overviews deploying ML models into production with TensorFlow Serving, a framework that makes it easy to serve the production ML models with low latency and high throughput. Learn how to start a TF Serving model server and send POST requests using the command line tool. Wei covers what it is, its architecture, general workflow, and how to use it. Stay tuned for the upcoming episodes on Deploying production ML models with TensorFlow Serving. Wei Wei will cover how to customize TF Serving, tune performance, perform A/B testing and monitoring, and more. Resources: TensorFlow Serving → TensorFlow Serving with Docker → Training and serving a TensorFlow model with TF Serving → Deploying Production ML Models with TensorFlow Serving playlist → Subscribe to TensorFlow →