ma-xu/pointMLP-pytorch

关于复现精度的问题,无法达到您说的精度,可以公布一下您达到最好精度时的随机种子,谢谢

xiaobaitu123344 opened this issue · 1 comments

关于复现精度的问题,无法达到您说的精度,可以公布一下您达到最好精度时的随机种子,谢谢
ma-xu commented

@xiaobaitu123344
You can find all hyper-parameters (including reandom seeds) in the logs, e.g., https://web.northeastern.edu/smilelab/xuma/pointMLP/checkpoints/fixstd/modelnet40/pointMLP-20220209053148-404/out.txt

Also, please refer #67 for random seed issue, and #1 (comment) for reproducibility issue.