Skip to content

关于loss 函数 #1

Description

@liangjiubujiu

您好,

 请问文章中提到的local consistency 是如何实现的,因为我看到文中说是将w/wo形态学后处理的predcition results 做nce。对此,我想请问形态学后处理后(不可微)的results 如何参与网络反向传播?以及您代码里是否有进行这一项操作,感谢!

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions