Skip to content

Questions #2

@zhengnianqing

Description

@zhengnianqing

Hi,麻烦您解释一下在base_conv.py里面卷积的反向传播代码:flip_weights = np.flipud(np.fliplr(self.weights))
这里为什么需要左右上下翻转完了再进行reshape,谢谢啦

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