Sign in
LOCP: Latency-optimized channel pruning for CNN inference acceleration on GPUs.
Yonghua Zhang
Hongxu Jiang
Yuting Zhu
Runhua Zhang
Yongxiang Cao
Chenhui Zhu
Wei Wang
Dong Dong
Xiaobin Li
Published in:
J. Supercomput. (2023)
Keyphrases
</>
cellular neural networks
search space
probabilistic inference
multi channel
convolutional neural network
general purpose
communication channels
bayesian networks
parallel processing
heterogeneous computing
neural network
search algorithm
bayesian inference
low latency
pruning method
wireless broadcast