Research Article: GPU-Efficient Distillation for Edge Vision Models

research-article
Received: Mar 4, 2024
Published: Apr 5, 2024
Authors: Nikhil Perez ✉

Abstract

A mixed-objective distillation pipeline reduces GPU hours by 34% while maintaining accuracy for three edge CNN families.

⬇ Download

Cite this article

Perez, N. (2024). Research Article: GPU-Efficient Distillation for Edge Vision Models. Research Explorations in Global Knowledge & Technology (REGKT), 3 (3). Retrieved from https://regkt.com/article.php?id=241&slug=gpu-efficient-distillation-edge-vision-models

Premium Membership Required

You need a premium account to view or download this article.

Become Premium