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

[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!

[bxiang233]

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!

Hi @ryujiy4612

Thanks for your question!

Sorry, I haven’t encountered this issue myself, and no one else has reported it so far. I’d recommend checking in debug mode which tensors are on CPU vs GPU at the point where the error occurs — it’s likely a device mismatch between some input tensors.

Hope this helps, and feel free to share more details if you narrow it down!

Best,
Binbin