Skip to content

"OWL-ViT inference playground" script cannot conduct interactive demonstrations #1165

@1Fleeting-time

Description

@1Fleeting-time

I ran "OWL-ViT inference playground" in the locally installed jupyter all the way to the "Text-conditioned detection" cell and no error was reported, but there was no interactive function. Under the "text-conditioned detection" cell, image and Text input boxes will be displayed. However, when a text prompt word is entered in the text input box, the image does not display the predicted bounding box and there are no other output prompts.

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