mit-han-lab / torchsparse

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

Home Page:https://torchsparse.mit.edu

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[BUG] `coords` batch index should be 0 instead of 3 in `bev.py`

ashawkey opened this issue · comments

commented

Is there an existing issue for this?

  • I have searched the existing issues

Current Behavior

coords = (coords - self.offset).t()[[3] + self.bev_dims].long()

It seems some modules still use 3 as the batch index instead of 0 in the latest implementation.

Expected Behavior

Modify to coords = (coords - self.offset).t()[[0] + self.bev_dims].long()

Environment

- GCC:
- NVCC:
- PyTorch:
- PyTorch CUDA:
- TorchSparse:

Anything else?

No response

Thank you for reporting this issue. Could you please submit a short pull request for this? Thanks!