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

E3NN vs Diffusion #9

Closed kevinbdsouza closed 1 year ago

kevinbdsouza commented 1 year ago

Hi,

The default model_type in args.py is "diffusion" but in factory.py the model is loaded only if the model_type is "e3nn" and raises an exception otherwise. Could you explain what's going on here?

Thanks,

Kevin

ketatam commented 1 year ago

Hi Kevin,

Thanks for your interest in our work and for pointing out this issue.

The "diffusion" model_type is just legacy code from previous experiments and there is no intended difference between the two types. We have only one single model_type in this sense and it is "e3nn". I will update the args.py to reflect this.

Sorry for the confusion!

Amine