This document describes research into very deep convolutional neural networks for large-scale image recognition. The researchers investigated the effect of convolutional network depth on accuracy by developing networks with increasing depth from 11 to 19 weight layers. Their deepest networks achieved state-of-the-art accuracy on the ImageNet challenge, demonstrating that greater depth can improve performance compared to prior architectures. The researchers released their best-performing models to facilitate further research on deep visual representations.