Kotaro Kikuchi

LayoutNet is almost the same as Discriminator, except for where the fake samples come from. The code looks like below. ```python # fake layout generation if random.random() < 0.5: data.x...

The environment at that time was as follows. The version difference might be the cause. ``` Distributor ID: Ubuntu Description: Ubuntu 18.04.5 LTS pytorch-fid==0.2.0 torch==1.8.1+cu111 torch-cluster==1.5.9 torch-geometric==1.7.2 torch-scatter==2.0.7 torch-sparse==0.6.10 torch-spline-conv==1.2.1...

Could you give me the error message or more details?