Skip to content

why take first 32 channels as attention map in model.py at line 112 #5

Open
Open
why take first 32 channels as attention map in model.py at line 112#5
@zhangjinyangnwpu

Description

@zhangjinyangnwpu
zhangjinyangnwpu
opened on Dec 30, 2021

could you tell me why just take 32 channels feature map as attention map for fusioning？

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions