Niax23 issues

Repositories
Issues
Comments

Results 1 issues of


                                            Niax23

Transformer每个尺度的输入为什么是整个f_hat而不是前一个尺度的特征

``` # ===================== idxBl_to_var_input: only used in VAR training, for getting teacher-forcing input ===================== def idxBl_to_var_input(self, gt_ms_idx_Bl: List[torch.Tensor]) -> torch.Tensor: next_scales = [] B = gt_ms_idx_Bl[0].shape[0] C = self.Cvae H...