no code implementations • 27 Jul 2021 • Wenlong Cheng, Mingbo Zhao, Zhiling Ye, Shuhang Gu
In this paper, we propose a novel compression framework \textbf{M}ulti-scale \textbf{F}eature \textbf{A}ggregation Net based \textbf{GAN} (MFAGAN) for reducing the memory access cost of the generator.
Hardware Aware Neural Architecture Search Image Super-Resolution +1