The Dell Validated Design for Computer Vision solution is an award-winning Dell Validated Design that leverages the VxRail hyperconverged platform for hosting a suite of workloads critical to computer vision workflows. The platform has been shown to successfully leverage market-leading components from Dell, VMware, and NVIDIA to host a wide variety of applications, including video management, computer vision, and cybersecurity threat detection and remediation is widely used by transportation organizations worldwide.

Many organizations rely on pre-trained models from Independent Software Vendors (ISVs) to generate operational insights and real-time alerts from computer vision and AI software. However, other applications of machine learning that are specific to unique use cases are often needed. Meeting these needs requires a combination of an easy-to-manage, GPU-enabled hardware platform coupled with a full-feature MLOps platform.

This white paper describes the results of a proof-of-concept designed to show how both VMs and containers can be run together on a single Tanzu Kubernetes Grid (TKG) enabled VMware platform. We also demonstrate how this platform can be used to develop enhanced workflows that were not possible with previous releases by combining the functionality from multiple software products to achieve a better outcome. We showcase an enhanced workflow where data from computer vision applications running on virtual machines is analyzed with a data science modeling framework by installing and running the BOSS AI product using containers on TKG.

This proof-of-concept demonstrates the value of investing in Dell, VMware, and NVIDIA powered solutions to deliver a consolidated platform to organizations hosting virtual machines and container virtualized applications for environments using Computer Vision.