Skip to content

weight normalization is probably implemented wrong #13

@jingjing-gong

Description

@jingjing-gong

def linear_mapping_weightnorm(inputs, out_dim, in_dim=None, dropout=1.0, var_scope_name="linear_mapping"):

you are not using V_norm any where except from initialization of variable tensor g. and according to the paper https://arxiv.org/abs/1602.07868, g should be a scalar instead of a variable tensor. correct me if I am wrong.

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