Skip to content

questions with inpainting input in inpaint_imagebart.py #4

Open

Description

@mlyarthur

image
Should the input of first stage's vqgan encoder be the masked input? Because there should be no unmasked image in inference.

Activity

  1. mlyarthur commented on Jan 7, 2022

    @mlyarthur
    Author

    image
    the clean code cannot be extracted in testing since there is no unmasked input.

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

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions