no code implementations • 6 Sep 2018 • Chuhan Min, Aosen Wang, Yiran Chen, Wenyao Xu, Xin Chen
To overcome this challenge, we propose a novel filter-pruning framework, two-phase filter pruning based on conditional entropy, namely \textit{2PFPCE}, to compress the CNN models and reduce the inference time with marginal performance degradation.
no code implementations • 16 Aug 2017 • Aosen Wang, Hua Zhou, Wenyao Xu, Xin Chen
However, the capacity of deep neural network architecture is still a mystery to the researchers.