This is the unofficial code of Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data
请问作者复现的时候有尝试过syncBN吗？我看原文作者在分布式训练的时候用的是syncBN。