Not like common self-attention

Open warmbodytt opened this issue 2 years ago • 0 comments

https://github.com/qq456cvb/Point-Transformers/blob/545ecc4fe55120338447c99016429b54dc022b5a/models/Menghao/model.py#L65 The tensor 'attention' here may be transposed. I'm not sure. Please have a check.

Mar 02 '24 09:03 warmbodytt