TY - GEN
T1 - A hardware-friendly pruning approach by exploiting local statistical pruning and fine grain pruning techniques
AU - Chang, Chun Chi
AU - Huang, Chung Hsun
AU - Chu, Yuan Sun
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Deep neural networks (DNN) have recently become a popular research topic and achieved well success in many signal processing tasks. However, when we deploy these neural networks on resource-limited hardware; e.g., edge devices, computation complexity and memory capability become great challenges. Many researches devote in compressing model parameters without significant accuracy loss, which is so-call pruning approach, so as to reduce the requirements of computation resource and memory space. However, pruned neural network (NN) model often shows heavy irregular sparsity between layers, convolution kernels, etc. Thus the utilizations of multiply-and-accumulate (MAC) array or processing element (PE) array could be low so that the inference time could not be reduced accordingly. In this paper, we propose a hardware-friendly pruning approach by exploiting local statistical pruning and fine-grain pruning techniques to possibly improve the utilizations of MAC array or PE array. Performance evaluations demonstrate that the performance of a NN-based super-resolution was kept good (i.e., > 37dB) with a high pruning ratio (i.e.,
AB - Deep neural networks (DNN) have recently become a popular research topic and achieved well success in many signal processing tasks. However, when we deploy these neural networks on resource-limited hardware; e.g., edge devices, computation complexity and memory capability become great challenges. Many researches devote in compressing model parameters without significant accuracy loss, which is so-call pruning approach, so as to reduce the requirements of computation resource and memory space. However, pruned neural network (NN) model often shows heavy irregular sparsity between layers, convolution kernels, etc. Thus the utilizations of multiply-and-accumulate (MAC) array or processing element (PE) array could be low so that the inference time could not be reduced accordingly. In this paper, we propose a hardware-friendly pruning approach by exploiting local statistical pruning and fine-grain pruning techniques to possibly improve the utilizations of MAC array or PE array. Performance evaluations demonstrate that the performance of a NN-based super-resolution was kept good (i.e., > 37dB) with a high pruning ratio (i.e.,
UR - http://www.scopus.com/inward/record.url?scp=85143830820&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85143830820&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Asia57006.2022.9954768
DO - 10.1109/ICCE-Asia57006.2022.9954768
M3 - Conference contribution
AN - SCOPUS:85143830820
T3 - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
BT - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
Y2 - 26 October 2022 through 28 October 2022
ER -