FPGA-based CNN Processor with Filter-Wise-Optimized Bit Precision

التفاصيل البيبلوغرافية
العنوان: FPGA-based CNN Processor with Filter-Wise-Optimized Bit Precision
المؤلفون: Kengo Nakata, Daisuke Miyashita, Jun Deguchi, Tomoya Suzuki, Asuka Maki, Fumihiko Tachibana
المصدر: A-SSCC
بيانات النشر: IEEE, 2018.
سنة النشر: 2018
مصطلحات موضوعية: Hardware architecture, Computer science, business.industry, 020209 energy, Computation, 02 engineering and technology, Convolutional neural network, Convolution, Bit (horse), Filter (video), 0202 electrical engineering, electronic engineering, information engineering, business, Quantization (image processing), Field-programmable gate array, Computer hardware
الوصف: Many efforts have been made to improve the efficiency for inference of deep convolutional neural network. To achieve further improvement of the efficiency without penalty of accuracy, we propose filter-wise optimized quantization with variable precision and the hardware architecture that fully supports it; as the bit precision for operations is reduced by granulariy optimizing weight bit precision filter-by-filter, the execution time is reduced proportionally to the total number of computations multiplied with the number of weight bit. We implement the proposed architecture on FPGA and demonstrate that ResNet-50 run with 5.3× less execution cycles without penalty of accuracy.
DOI: 10.1109/asscc.2018.8579342
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_________::78c65e28160f4c8f29fa03136266fd7b
https://doi.org/10.1109/asscc.2018.8579342
رقم الانضمام: edsair.doi...........78c65e28160f4c8f29fa03136266fd7b
قاعدة البيانات: OpenAIRE
الوصف
DOI:10.1109/asscc.2018.8579342