To solve the problem that the image classification algorithm is difficult to be applied to mobile devices with limited sto-rage space and computing power due to the large amount of calculation and the parameter redundancy,a lightweight convolution calculation module,namely Extremely Lightweight Block(ELBlock)was proposed.The method of point-by-point convolution superposition depthwise separable convolution was adopted.The point-by-point convolution was grouped to increase the diagonal correlation between filters of adjacent layers and the computational complexity of convolution operation was further reduced.The channel shuffle was used to correlate the input and output channels to improve the information expression ability of features.Based on ELBlock,an extremely lightweight small neural network architecture ELNet was designed,which was more concise and efficient.Experimental results on Android mobile phones show that the proposed ELNet has the advantages of less computa-tion,fewer parameters and shorter inference time while ensuring the prediction accuracy.
关键词
深度学习/图像分类/轻量级神经网络/模型优化/模型压缩/模型部署/移动终端
Key words
deep learning/image classification/lightweight neural network/model optimization/model compression/model deployment/mobile terminals
维普
万方数据