Skip to content

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) in region_grow during training #25

@ryujiy4612

Description

@ryujiy4612

I'm encountering a RuntimeError during training when running the PointGroup3heads model on my custom panoptic dataset. The error seems to occur inside the _cluster7() function, specifically when calling region_grow().RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)
❓ Question

How should I ensure consistent device placement inside _cluster7() or region_grow()? Is this a known issue? If so, are there recommendations for modifying the code to avoid this mismatch?

Let me know if you’d like me to share the exact _cluster7() implementation from PointGroup3heads.py.

Thanks for your help!

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