Skip to content

Long inference time when using SMD's Mask R-CNN #2

Description

@fabmeyer

@akarazniewicz is it normal to get a very long inference time when using SMD's Mask R-CNN model on an arbitrary CPU? I get between 10s and 30s depending on image size (64px height up to 2048px height). Or am I doing something wrong here?

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