Skip to content

Questions #1

@Youngkl0726

Description

@Youngkl0726

Hi,
请问可以解释一下为什么Conv2D中:
weights_scale = math.sqrt(reduce(lambda x, y: x * y, shape) / self.output_channels),
这个weights_scale的作用和它为什么这么计算吗?

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