Traffic-X / ViT-CoMer

Official implementation of the CVPR 2024 paper ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

关于代码中的batchnorm2d?

swjtulinxi opened this issue · comments

请问MultiDWConv模块中的batchnorm2d是不是应该换成SyncBatchNorm, 不然多卡训练会有影响?

我理解当batchsize过小时会有一定的影响,感谢指正。