【算法】8比特数值也能训练模型?商汤提训练加速新算法丨CVPR 2020( 五 )


https://arxiv.org/pdf/1912.12607.pdf
References
[1].Ruihao Gong, Xianglong Liu, Shenghu Jiang, Tianxiang Li,Peng Hu, Jiazhen Lin, Fengwei Yu, and Junjie Yan. Differen-tiable soft quantization: Bridging full-precision and low-bitneural networks. In ICCV, October 2019.
[2].Rundong Li, Yan Wang, Feng Liang, Hongwei Qin, Junjie Yan, and Rui Fan. Fully quantized network for object detection. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
[3]. Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, and Dmitry Kalenichenko. Quantization and training of neural networks for efficient integer-arithmetic-only inference. 2018 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), June 2018.
[4]. Yukuan Yang, Shuang Wu, Lei Deng, Tianyi Yan, Yuan Xie, and Guoqi Li. Training high-performance and large-scale deep neural networks with full 8-bit integers, 2019.
【算法】8比特数值也能训练模型?商汤提训练加速新算法丨CVPR 2020
本文插图

【算法】8比特数值也能训练模型?商汤提训练加速新算法丨CVPR 2020
本文插图

  • GitHub标星2000+ , 如何用30天啃完TensorFlow2.0?
  • 斩获GitHub 2000+ Star , 阿里云开源的Alink机器学习平台如何跑赢双11数据“博弈”?
  • 百年 IBM 终于 All In 人工智能和混合云!
  • 微软为一人收购一公司?破解索尼程序、写黑客小说 , 看他彪悍的程序人生!
  • 机器学习项目模板:ML项目的6个基本步骤
  • 【【算法】8比特数值也能训练模型?商汤提训练加速新算法丨CVPR 2020】BM、微软、苹果、谷歌、三星……这些区块链中的科技巨头原来已经做了这么多事!


推荐阅读