A security company’s goal was to maximize the efficiency of their existing infrastructure by increasing the number of live video streams that can be processed in real-time on their NVIDIA Jetson Xavier NX hardware.
However, after increasing the number of video streams to be processed, their object detection model (YOLOX) did not achieve the required level of throughput (192 frames per seconds, inference batch of 8) for the solution to be viable.
The Deci platform is used by data scientists and machine learning engineers to build, optimize, and deploy highly accurate and efficient models to production. Teams can easily develop production grade models and gain unparalleled accuracy and speed tailored for any performance targets and hardware environment.
Deci is powered by AutoNAC (Automated Neural Architecture Construction), the most advanced and commercially scalable Neural Architecture Search engine in the market. AutoNAC performs a multi-constraints search to find the architecture that delivers the highest accuracy for any performance targets and hardware environment.
By using Deci’s AutoNAC engine, the customer built an architecture that delivered 1.7X acceleration reaching a throughput of 192 frames per seconds, while also improving the accuracy by 1% mAP. This allowed the customer to double the number of video streams from 4 to 8, increasing the scalability and profitability of their video analytics solution.
Improve latency and throughput and reduce model size by up to 10x while maintaining the model’s accuracy.
Maximize hardware utilization and cost-efficiently scale your solution at the edge.
Eliminate inference cloud compute cost and avoid data privacy issues by running your models directly on edge devices.
Tell us about your use case, needs, goals, and the obstacles in your way. We’ll show you how you can use the Deci platform to overcome them.
Learn 12 inference acceleration techniques that you can immediately implement to improve the speed, efficiency, and accuracy of your existing AI models.