Skip to content

A scenario when this model is worse than original EAST  #122

@t170815518

Description

@t170815518

When scanning the phone screen that contains multiple lines of text, this model gets very weird result:
actual_phone_screen
actual_phone_screen png_act
actual_phone_screen png_predict

While in the original EAST model,
image

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