Relationship between Recognition Accuracy and Numerical Precision in Convolutional Neural Network Models
Yasuhiro Nakahara, Masato Kiyama, Motoki Amagasaki, Masahiro Iida · IEICE Transactions on Information and Systems · 2020
Quantization is an important technique for implementing convolutional neural networks on edge devices. Quantization often requires relearning, but relearning sometimes cannot be always be applied because of issues such as cost or privacy. In such cases, it is important to know the numerical precision required to maintain accuracy. We accurately simulate calculations on hardware and accurately measure the relationship between accuracy and numerical precision.