ryhhtn

Thank you for your advice. generate sample script well done! 

I'm using following library ``` torch==1.7.1+cu92 torchfile==0.1.0 torchinfo==0.0.9 torchmetrics==0.3.1 torchtext==0.8.1 torchvision==0.8.2+cu92 ```

thank you for your reply. I succeeded with reference to #6 and [advice](https://github.com/menyifang/ADGAN/issues/30#issuecomment-894569487) 

Thanks for the reply. On a related note, ask about Discriminator Loss (loss_D). Not mentioned in this paper about loss_D formula, especially [147 lines](https://github.com/ktrk115/const_layout/blob/master/train.py#L147) This could be the reason.