Skip to content

Fix VAE training #54

Open
Open
@turnmanh

Description

@turnmanh

VAE training yields a suboptimal model. We're expecting better performance and think about the following:

  • increase batch size while keeping the rel. high learning rate
  • add Dense layer

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions