MorningEatDinner

About the loss of SDE_3Dto2D

1

I observed that in code **SDEModel3Dto2D_node_adj_dense_02**, loss is calculated by: losses_x = torch.square(score_x + z_x) # [B, max_num_nodes, num_class_X] or [B, max_num_nodes, 1] losses_adj = torch.square(score_adj + z_adj) # [B,...