Video

Webinar: How to Run Real Time Detection on 8 Live Streams Using 1 NVIDIA Jetson Xavier NX

AI-based video analytics applications are powered by various computer vision models that need to process video footage or live streams in real time and on edge devices.

In this webinar, you’ll learn how to process in real time 8 video streams while using only 1 NVIDIA Jetson Xavier NX device.

Join Avi Lumelsky, Software Architect, and Nave Assaf, Deep Learning Engineer, and discover:

  • The end-to-end pipeline that enables 8 live video streams to run on a NVIDIA Jetson in real time
  • Engineering tips on getting the most out of your edge hardware
  • A NAS-generated object detection model, that outperforms SOTA models and enables you to achieve better hardware utilization

Do you want to get similar results for your use case? Book a demo of our Deep Learning Development Platform or chat with one of our deep learning experts.

You May Also Like

Webinar: How to Optimize Latency for Edge AI Deployments

Gen AI Models: Open Source vs Closed Source—Pros, Cons & Everything in Between

Webinar: The Making of YOLO-NAS, a Foundation Model, with NAS

Add Your Heading Text Here
				
					from transformers import AutoFeatureExtractor, AutoModelForImageClassification

extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-50")

model = AutoModelForImageClassification.from_pretrained("microsoft/resnet-50")