Red Hat OpenShift Data Science gives data scientists and developers a powerful artificial intelligence/machine learning (AI/ML) platform for building intelligent applications. With OpenShift Data Science, data scientists and developers can rapidly develop, train, test, and iterate ML and deep learning (DL) models using their choice of certified tools in a fully supported environment—without waiting for infrastructure provisioning. OpenShift Data Science combines Red Hat components, open source software, and certified partner technology with public cloud scalability. In this session, we’ll follow the OpenShift Data Science object detection workshop using 3rd Gen Intel Xeon CPUs to demo an easy way to incorporate data science and AI/ML into a Red Hat OpenShift development workflow, including:

How to use Jupyter Notebooks and TensorFlow to explore a pre-trained object detection model.
How to serve the model in a REST application programming interface (API) as a Flask app.
How to use Source-to-Image (S2I) to build and deploy the Flask app.
How to use Red Hat OpenShift Streams for Apache Kafka streams from notebooks.
How to deploy a Kafka consumer with the same object detection model.

Mayur Shetty, Global Partner Principal Solution Architect, Red Hat
Sridhar Kayathi, Global Ecosystem Development Manager, Intel Corporation

source