Red Hat Contributors: Mayur Shetty, Principal Solution Architect; Will McGrath, Senior Principal Product Marketing Manager
Intel Contributors: Sridhar Kayathi, Global Ecosystem Development Manager
Artificial intelligence (AI), machine learning (ML), and deep learning (DL) have rapidly become critical for businesses and organizations. Deploying these technologies, however, can be complicated. As data scientists strive to build their models, they often encounter a lack of alignment between rapidly evolving tools, impacting productivity & collaboration among themselves, software developers, and IT operations. Scaling AI/ML deployments can be resource-limited and administratively complex while requiring expensive resources for hardware acceleration. Popular cloud platforms offer scalability and attractive tool sets, but those same tools often lock users in, limiting architectural and deployment choices.
Red Hat® OpenShift® Data Science (RHODS) is a cloud service that gives data scientists and developers a powerful AI/ML platform for building intelligent applications. Teams can quickly move from experiment to production in a collaborative, consistent environment with their choice of certified tools.
With RHODS, data scientists and developers can rapidly develop, train, test, and iterate ML and DL models in a fully supported environment—without waiting for infrastructure provisioning. Available as an add-on to Red Hat OpenShift Service on AWS (ROSA) which is a turnkey application platform that provides a managed application platform service running natively on Amazon Web Services (AWS), RHODS combines Red Hat components, open source software, and certified partner technology with the public cloud scalability of Amazon Web Services (AWS).
For the demo, we’ve followed the OpenShift Data Science workshop - Object Detection. Here you'll learn an easy way to incorporate data science and AI/ML into an OpenShift development workflow.
Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos.[1] Well-researched domains of object detection include face detection and pedestrian detection. Object detection is used in many different domains, including autonomous driving, video surveillance, and healthcare.
The demo uses an object detection model in several different ways to highlight the following:
- Jupyter Notebooks and TensorFlow to explore a pre-trained object detection model
- Serve the model in a REST API as a Flask App
- Use source-to-image (S2I) to build and deploy the Flask App
- Explore Kafka streams from notebooks
- Deploy a Kafka consumer with the same object detection model
All of this running on Red Hat OpenShift Data Science and Red Hat OpenShift Streams for Apache Kafka, available as an add-on to ROSA using Intel Ice Lake instances (c6i instance types) for the worked nodes.
ROSA now supports 3rd Generation Intel® Xeon® Scalable Processor instances (m6i and c6i instance types). Amazon EC2 C6i instances offer better price performance for a wide variety of workloads. C6i instances feature a 2:1 ratio of memory to vCPU, and support up to 128 vCPUs per instance. These instances feature twice the networking bandwidth and are an ideal fit for compute-intensive workloads such as: batch processing, distributed analytics, high performance computing (HPC), ad serving, highly scalable multiplayer gaming, and video encoding. C6i are also available with local NVMe-based SSD block-level storage (C6id instances) for applications that need high-speed, low-latency local storage. C6i & C5 instances support Intel® Advanced Vector Extensions (AVX-512), Intel® Turbo Boost & Intel® Deep Learning Boost.
You can see this demo and other featured demos at the Red Hat booth at AWS Re:Invent 2022.
https://www.redhat.com/en/events/reInvent22
We look forward to seeing you there!
Sridhar Kayathi spearheads the Get-to & Go-to-market strategies and deployment of Intel technologies, including Intel® Xeon®, GPUs, Gaudi, and NICs, across key domains such as AI/ML, Intelligent Edge, security, networking, sustainability, and memory and storage. In his previous role within the Data Center & AI Group at Intel, Sridhar contributed to the development of unique use cases and solutions leveraging cutting-edge Intel technologies like Optane, successfully boosting customer adoption and driving sales. Before joining Intel in 2006, Sridhar accumulated diverse experience in various consulting and technical roles at notable organizations such as Jabil, FirstEnergy, Dana, and others. Sridhar holds an M.Engg from the University of Applied Sciences, Germany, and a Bachelor's degree in Computer Science.