Also see our paper: Pretraining boosts out-of-domain robustness for pose estimation by Alexander Mathis, Mert Yüksekgönül, Byron Rogers, Matthias Bethge, Mackenzie W. Mathis https://arxiv.org/abs/1909.11229
Based on Slim implementation of mobilenets: https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py