Sign in

Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe.

Jiong GongHaihao ShenGuoming ZhangXiaoli LiuShane LiGe JinNiharika MaheshwariEvarist FomenkoEden Segal
Published in: ReQuEST@ASPLOS (2018)
Keyphrases
  • highly efficient
  • convolutional neural networks
  • gray code
  • convolutional network
  • low cost
  • inference process
  • bayesian networks
  • low latency
  • image sequences
  • three dimensional
  • lower bound
  • coarse to fine