Efficient Search for the Number of Channels for Convolutional Neural Networks

Latest algorithms for automatic neural architecture search perform remarkably but few of them can effectively design the number of channels for convolutional neural networks and consume less computational efforts. In this paper, we propose a method for efficient automatic search which is special to the widths of networks instead of the connections within neural architectures. Our method, functionally incremental search based on function-preserving, will explore the number of channels for almost any convolutional neural network rapidly while controlling the number of parameters and even the amount of computations (FLOPs). On CIFAR-10 and CIFAR-100 classification, our method using minimal computational resources (0.41 similar to 1.29 GPU-days) can discover more effective rules of the widths of networks to improve the accuracy (a similar to 1.08 on CIFAR-10 and b similar to 2.33 on CIFAR-100) with fewer number of parameters.