Towards Efficient Convolutional Neural Network for Domain-Specific Applications on FPGA

Ruizhe Zhao, Ho-Cheung Ng, Wayne Luk, Xinyu Niu
2018 2018 28th International Conference on Field Programmable Logic and Applications (FPL)  
FPGA becomes a popular technology for implementing Convolutional Neural Network (CNN) in recent years. Most CNN applications on FPGA are domain-specific, e.g., detecting objects from specific categories, in which commonlyused CNN models pre-trained on general datasets may not be efficient enough. This paper presents TuRF, an end-to-end CNN acceleration framework to efficiently deploy domain-specific applications on FPGA by transfer learning that adapts pre-trained models to specific domains,
more » ... lacing standard convolution layers with efficient convolution blocks, and applying layer fusion to enhance hardware design performance. We evaluate TuRF by deploying a pre-trained VGG-16 model for a domain-specific image recognition task onto a Stratix V FPGA. Results show that designs generated by TuRF achieve better performance than prior methods for the original VGG-16 and ResNet-50 models, while for the optimised VGG-16 model TuRF designs are more accurate and easier to process.
doi:10.1109/fpl.2018.00033 dblp:conf/fpl/ZhaoNLN18 fatcat:juidwpy2jrgfldzkn3j4pc4mpi