Skip to content

LVW损失问题 #8

Description

@lisa2342

感谢作者的工作,有一处疑问希望作者能解惑。在文章的"3.5. Local Variance Weighted Loss"的公式是∆m,n = ||Om,n − Lm,n||1,但是loss.py中的第18行实现是
delta = out - lab
请问是否应该加torch.abs呢

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions