Skip to content

Mode collapse on MNIST #9

Description

@fiy2W

sample_16201_last

In the MNIST experiment, I found that the generated numbers in each category were the same, with no diversity. I've checked the init_noise, and it is random. Is there something wrong with the code or the algorithm's limitation?

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

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