Approximated Oracle Filter Pruning for Destructive CNN Width Optimization

Xiaohan Ding, Guiguang Ding, Yuchen Guo, Jungong Han, Chenggang Yan

Abstract: It is not easy to design and run Convolutional Neural Networks (CNNs) due to: 1) finding the optimal number of filters (i.e., the width) at each layer is tricky, given an architecture; and 2) the c...