Training code issues

[Llf0703]

Thank you for your work! But I can't find the code for the backward propagation. Also, style_loss in train.py is a tensor with 4 items, which makes an error in total_cd_pc += cd_pc_item.

[XuHang0806]

Thank you for your careful comment! This is an error during code reorganization, we have fix it.
The style_loss should be added up during forward function. This part only affects the display of the training process, and can be deleted if an error is reported.