Skip to content

Nice code! Some tips #1

@Jeff-Zilence

Description

@Jeff-Zilence

Very nice code for this paper.

I found that the performance of cnn under attach is very unstable. Sometimes the performance can be much better than claimed in your table. The improvement from kervolution is limited.

I found a little mistake in your implementation that can affect the performance. The bias term should be added after the kernel trick, not as in your code. Better to change it.

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