Skip to content

VAE loss #225

Closed
Closed
@ghost

Description

According to the expression in line 95, the KL-divergence term is calculated from
0.5 * sum(1 + log(sigma^2) - mu^2 - sigma^2)
but I think the code in line 96-97 represents
0.5 * sum(1 + log(sigma^2) - mu^2 - sigma)

This might not be essential because whether the last term is squared or not, the loss descending behavior stays unchanged.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions