[3] [3] Szegedy C, Liu W, Jia Y, Iet al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 1-9.

[4] [4] Iandola F N, Han S, Moskewicz M W, et al. SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and <0.5 MB model size[J/OL]. http://arxiv.org/pdf/1602.07360.

[5] [5] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arxiv preprint arxiv: 1704.04861, 2017.

[6] [6] Zhang X, Zhou X, Lin M, et al. Shufflenet: an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 6848-6856.

[7] [7] Chollet F. Xception: Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1251-1258.

[8] [8] Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks[C]//International Conference on Machine Learning. PMLR, 2019: 6105-6114.

[10] [10] Lecun Y, Bottou L. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

[11] [11] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.

[12] [12] Xiao H, Li K, Zhu M. FPGA-based scalable and highly concurrent convolutional neural network acceleration[C]//2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA). IEEE, 2021: 367-370.