Open lixiang-ucas opened 6 years ago
I test the performance using the default parameters on modelnet40 classification task, and got an overall accuracy of 90.4%, but the reported is 90.7%. (with msg model)
the last checkpoint model doesn't perform the best, 90.4% was reached with 65 epoches.
Are you using MRG (multi-resolution grouping) method mentioned in the paper? @lixiang-ucas
I test the performance using the default parameters on modelnet40 classification task, and got an overall accuracy of 90.4%, but the reported is 90.7%. (with msg model)