search

ketatam / DiffDock-PP

Implementation of DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models in PyTorch (ICLR 2023 - MLDD Workshop)
https://arxiv.org/abs/2304.03889
195 stars 38 forks source link

hyperparmeters and gpus. #30

Open zeqri opened 3 months ago

zeqri commented 3 months ago

Hi,

in train.sh the configuration sets ns, nv, max radius and batch_size to 16, 4, 5 and 2, but in the args file in the checkpoint folder for the best model provided these parameters are set to different values. to replicate the results should I stick with these values or the ones in the args file in checkpoint folder? what is exactly the number of gpus that were used in training?

thank you in advance.

onlyonewater commented 2 months ago

so, does anyone know the hype-parameters or reproduce the results successfully?