graph-0 / jodo Goto Github PK

Hi Authors,

Congrats on the great work!

As I was reading your paper, I found that you retain one conformer with the lowest energy and discarded other conformers. This is a different experimental setting as compared to EDM. This processing also reduces the dataset size from 6million to 200k. May I know the effect of this operation? Why is it necessary? And does it positively or negatively influence performance?

Thanks!

Excuse me, how much memory does this code need and how many hours does it take?
I mean in Colab.

Dear author,

Thank you for releasing the code!
However, when I try to run an evaluation with the released checkpoint, the console prints out 'warning: detected nan, resetting output to zero.

Is this a bug, or is it normal to have nan values like that?

Here is the reproducible script:
python main.py --config configs/vpsde_qm9_uncond_jodo.py --mode eval --workdir exp_uncond/vpsde_qm9_jodo --config.eval.ckpts '30' --config.eval.batch_size 2500 --config.sampling.steps 1000

Best,
Vinh