Skip to content

Implementation of J-S divergence in Variational Autoencoder(Assignment 5) #1

@MaanasVohra

Description

@MaanasVohra

I've implemented the J-S divergence simply by taking

m(x) = (mu(x) + log_sigma(x)) / 2

and then evaluated the kl divergence by replacing the log_sigma term in the original K-L divergence term with m(x), which obviously isn't right. Could someone help me out with a way to implement it?

Metadata

Metadata

Assignees

No one assigned

    Labels

    HacktoberfestHacktoberfest-2020help wantedExtra attention is neededquestionFurther information is requested

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions