TripleNet: A Low Computing Power Platform of Low-Parameter Network

With the excellent performance of deep learning technology in the field of computer vision, convolutional neural network (CNN) architecture has become the main backbone of computer vision task technology. With the widespread use of mobile devices, neural network models based on platforms with low computing power are gradually being paid attention. This paper proposes a lightweight convolutional neural network model, TripleNet, an improved convolutional neural network based on HarDNet and ThreshNet, inheriting the advantages of small memory usage and low power consumption of the mentioned two models. TripleNet uses three different convolutional layers combined into a new model architecture, which has less number of parameters than that of HarDNet and ThreshNet. CIFAR-10 and SVHN datasets were used for image classification by employing HarDNet, ThreshNet, and our proposed TripleNet for verification. Experimental results show that, compared with HarDNet, TripleNet's parameters are reduced by 66% and its accuracy rate is increased by 18%; compared with ThreshNet, TripleNet's parameters are reduced by 37% and its accuracy rate is increased by 5%.