no code implementations • 26 May 2021 • Lizeth Gonzalez-Carabarin, Iris A. M. Huijben, Bastiaan S. Veeling, Alexandre Schmid, Ruud J. G. van Sloun
Relevantly, the non-magnitude-based nature of DPP allows for joint optimization of pruning and weight quantization in order to even further compress the network, which we show as well.
no code implementations • 1 Jan 2021 • Lizeth Gonzalez Carabarin, Iris A.M. Huijben, Bastiaan S. Veeling, Alexandre Schmid, Ruud Van Sloun
Deep Learning (DL) models are known to be heavily over-parametrized, resulting in a large memory footprint and power consumption.