training loss

Open xhlbetter opened this issue 2 years ago • 2 comments

3DMM's shape_para, exp_para, and Tm values are very large, causing a large loss in the early stages of training. How can this be addressed?

Aug 31 '23 08:08 xhlbetter

@lhyfst loss['shape_para_ms'] = self.rse(targets['shape_para'],shape_para_ms)*1e-5 loss['shape_para_is'] = self.rse(targets['shape_para'],shape_para_is)*1e-5

Sep 11 '23 07:09 xhlbetter

想请问如何快速学到Tm的值，Tm矩阵的数据分布差异较大

Sep 22 '23 14:09 xhlbetter