Google's MobileNets definition with Alpha = 0.25, 0.5, 0.75, 1.0, in Caffe prototxt.

Howard A G, Zhu M, Chen B, et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications[J]. 2017. This paper proposes two hyperparameters: Alpha to control the width of layers, Beta to control size of feature maps.

This repository includes four MobileNets models for Alpha = 0.25, 0.5, 0.75, 1.0.

One can modify the Input data size to adjust the beta value.