Performance on different setting.

[ZhaochongAn]

Hi, I suffer from performance variance by rerunning the model on different settings. It seems you use different parameters for different dataset and few-shot setting that you did not mention in the paper according to this issue (https://github.com/Na-Z/attMPTI/issues/8). And you only provide one set of parameters for S3DIS-N2-K1 in the codebase. Can you provide your parameters on other settings (i.e., S3DIS-N2-K5, Scannet-N2-K1, Scannet-N2-K5) for both pretraining and model training? Thank you very much!