MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning

Autor:	Liu, Zechun, Mu, Haoyuan, Zhang, Xiangyu, Guo, Zichao, Yang, Xin, Cheng, Tim Kwang-Ting, Sun, Jian
Rok vydání:	2019
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure given the target network. We use a simple stochastic structure sampling method for training the PruningNet. Then, we apply an evolutionary procedure to search for good-performing pruned networks. The search is highly efficient because the weights are directly generated by the trained PruningNet and we do not need any finetuning at search time. With a single PruningNet trained for the target network, we can search for various Pruned Networks under different constraints with little human participation. Compared to the state-of-the-art pruning methods, we have demonstrated superior performances on MobileNet V1/V2 and ResNet. Codes are available on https://github.com/liuzechun/MetaPruning. Comment: ICCV 2019 Camera ready version. Codes are available on https://github.com/liuzechun/MetaPruning
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1903.10258 Zobrazit plný text záznamu View this record from Arxiv