To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference.

Qing Qin Jie Ren 0007 Jialong Yu Hai Wang 0010 Ling Gao Jie Zheng 0005 Yansong Feng 0002 Jianbin Fang Zheng Wang 0001 To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference. 729-736 2018 ISPA/IUCC/BDCloud/SocialCom/SustainCom https://doi.org/10.1109/BDCloud.2018.00110 conf/ispa/2018 db/conf/ispa/ispa2018.html#QinRYWG0FFW18