Gaopeng Ren
Gaopeng Ren
Thank you for your reply. Strickly speaking, I think the `k_hop_subgraph` should generate all the **edges** reachable within k hops instead of nodes . However, since the generated additional edges...
It is a sign of runout RAM, but I am unclear whether it is due to the `subgraph_index` function or the dataset itself problem. Could you provide more details about...
Could you split the dataset into several smaller datasets, and see whether the problem still occurs. I doubt this problem may be due to big calculation cost in feature generating...
Could you reduce the amount of data points to 1k, even one hundred, and try again (I understand you have a big memory but I still doubt the problem is...
Hi, B. This error seems to be related to inconsistent save and load processes, it would be more clear if you provide the code where you changed the original code...
I'm sorry for not getting back to you sooner. I test the code under python=3.8.3, and it runs OK, so the Python version is not the problem. As for the...
Thank you for your prompt response and detailed explanation! I understand that the `dtype` issue could contribute to the performance drop when I modified the allowed bond dictionary. However, I...
Sorry for not mentioning that I actually also changed the allowed bond valence for nitrogen when its charge is +1. I think if the charge is +1, then the allowed...
> So the current situation is: > > 1. neutral 3-valence carbon and neutral 2-valence nitrogen appear in the valid valence lookup table likely due to a bug in valency...
Thank you so much for the release!