lrjconan

It may be caused by the fact that your PyTorch version is low so that `tril` does not have batch mode, c.f., [this issue](https://github.com/dbolya/yolact/issues/4).

Hi, Thanks for your interest! I did not consider node feature since the paper is about pure graph generation. But it is not hard to add the conditioning on node...

> Great job! > I was wondering how I can do normalization for D^-1*A? Could you be more specific on what kind of normalization you hope to achieve?

Hi, Thanks for your interests in our work! You are right that we do not use the edge feature, e.g., the distance matrix, due to the reason you quoted. I...

Thanks for your interest! Sorry that I do not have a requirements.txt for now. You could bypass it by using `yaml.load(fo.read(), Loader=yaml.FullLoader)` or just install old pyyaml like 5.4.1 shown...