Cite
Notes
Only stored in your browser.
Attribution
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
deep-gradient-compression-reducing-the-1
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
arXiv 2016
from 2 papers
Song Han
Forrest N. Iandola
Huizi Mao
Khalid Ashraf
Kurt Keutzer
Matthew W. Moskewicz
Yu Wang
Yujun Lin