search

XuyangBai / TransFusion

[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496
Apache License 2.0
640 stars 77 forks source link

The loss is abnormal when the height and widht of BEV feature is not equal #85

Open comwireless opened 1 year ago

comwireless commented 1 year ago

Thanks for your error report and we appreciate it a lot.

Checklist

  1. I have searched related issues but cannot get the expected help.
  2. The bug has not been fixed in the latest version.

Describe the bug A clear and concise description of what the bug is.

Reproduction

  1. What command or script did you run? 
    A placeholder for the command.
  2. Did you make any modifications on the code or config? Did you understand what you have modified?
  3. What dataset did you use?

Environment

  1. Please run python mmdet3d/utils/collect_env.py to collect necessary environment infomation and paste it here.
  2. You may add addition that may be helpful for locating the problem, such as
    • How you installed PyTorch [e.g., pip, conda, source]
    • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Error traceback If applicable, paste the error trackback here.

A placeholder for trackback.

Bug fix If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

comwireless commented 1 year ago

https://github.com/XuyangBai/TransFusion/blob/master/mmdet3d/models/dense_heads/transfusion_head.py#L759, I think the line should be meshgrid = [[0, y_size - 1, y_size], [0, x_size - 1, x_size]]], if the x_size != y_size