Skip to content

[CodeGen] Generated benchmark method includes Python overhead #17

Description

@MadhurKumar004

Description: The generated benchmark() method wraps self.predict(), which includes _preprocess_input (OpenCV resize, float conversion). This measures app latency, not model inference latency

Fix: The generated benchmark loop should time only interpreter.invoke().

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions