Customize AI Models and Optimize for Real-Time Inference Serving at Scale with NVIDIA AI on Azure Machine Learning

AI Models, Ignite 2022, Real-Time Inferencing, Scalability -

Customize AI Models and Optimize for Real-Time Inference Serving at Scale with NVIDIA AI on Azure Machine Learning

Simplifying and accelerating AI model development workflows is hugely valuable, whether you have an army of data scientists or just a few developers.

From adapting a model to fit your use-case to optimizing it for production deployment - it is a complex and iterative process. In this session, we'll show how easy it is to train and optimize an object detection model with NVIDIA TAO, a low-code AI toolkit, and deploy it for inference using the NVIDIA Triton Inference Server on Azure ML.

AI captioning languages supported: Arabic, Bulgarian, Chinese Simplified, Czech, Danish, Dutch, English, Finnish, French, French Canadian, German, Greek, Hebrew, Hindi, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Portuguese (Brazil), Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Thai, Turkish, Ukrainian, Vietnamese, Welsh
Audio languages supported: English


Profile picture of Paul DeCarlo

Principal Cloud Advocate and Lead for Data in Developer Relations - Microsoft

Paul DeCarlo is a Principal Cloud Developer Advocate for Microsoft Data and Professor for the Bauer College of Business at the University of Houston. His current technology interests focus on Internet of Things, Artificial Intelligence, and Edge-to-Cloud Applications. 
Profile picture of Manuel Reyes-Gomez

Developer Relations Manager - NVIDIA

Manuel J. Reyes-Gomez is a seasoned data science and machine learning practitioner. He's also a NVIDIA developer relations manager for the Microsoft account, overseeing collaborative AI and machine learning projects between both companies.
Profile picture of Chintan Shah

Sr. Product Manager - NVIDIA

Chintan Shah is a product manager at NVIDIA, focusing on AI products for intelligent video analytics solutions. He manages products and toolchains for efficient Deep Learning training and real-time inference. In his previous role, he developed hardware IPs for NVIDIA GPUs. He holds a master’s degree in electrical engineering from North Carolina State University.


Leave a comment

#WebChat .container iframe{ width: 100%; height: 100vh; }