Rethinking the Value of Network Pruning

ICLR 2019 Zhuang LiuMingjie SunTinghui ZhouGao HuangTrevor Darrell

Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning... (read more)

PDF Abstract

Evaluation Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.