Developing Industrial Inspection Workflows With Metropolis for Factories

AI Industrial applications present unique challenges, including the need for near-perfect accuracy (99%+) and high throughput. These already demanding requirements are further complicated by the widespread issue of data scarcity in the industrial sector, attributed to factors such as data ownership, privacy concerns, and the prevalence of unbalanced datasets.
This hands-on lab offers a breakthrough approach to these obstacles. Participants will discover how foundational models can significantly boost accuracy with limited datasets, including synthetic ones. Moreover, the lab will guide you through the creation of GPU-accelerated pipelines using NVIDIA's Vision AI tools.
Within a span of less than two hours, this lab will equip you with the knowledge to setup your end-to-end AI development workflow. This interactive session will supercharge your AI development skills by providing you insights into generating synthetic data. You'll experience how easy is to fine-tune NVIDIA's foundational models with your synthetic data generated achieving over 98% accuracy in under five minutes. Finally, you will get an exclusive preview of the upcoming release of DeepStream and master the construction of a complete AI inference pipeline with just a few lines of code.
Prerequisite(s):

Basic understanding of programming is required.
Familiarity with industrial inspection is ideal.

Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.
Ready to validate your skills? Get NVIDIA certified and distinguish yourself in the industry.