lucidrains / se3-transformer-pytorch

Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. This specific repository is geared towards integration with eventual Alphafold2 replication.
MIT License
262 stars 23 forks source link

trainnin pointcloud data #19

Open xins981 opened 1 year ago

xins981 commented 1 year ago

Hi, as se3-transfromer beginner, I want apply it to process point in order to get point-wise feature. I run successfully the first demo, but I don't understand the paramater means. image

in inference, what means the mask param?

can you share point trainning demo or any information about right path appling this model to pointcloud?