Lukas Zhang

Results 5 comments of Lukas Zhang

@huanghoujing Hi houjing! But when I trained the model with local branch(local loss and local_dist_own_hard_sample=True) on three datasets, it showed no ~1 point improvement, even worse! I am not clear...

@huanghoujing Yes. It is that! And I have the last one question: for with mutual learning, would it improve ~1 points with local distance than without local distance? is "~1...

@jingjingxupku 我把 numpy 版本降到了1.16.0,报错还是 numpy 的问题,请问有什么解决方案的吗?

@jingjingxupku 安装numpy 1.16.0的时候需要卸载之前的版本,已经可以在 macos 上使用pkuseg 0.0.15,但是新的版本0.0.16好像还是不适用于 macos