ORNL / HydraGNN

Distributed PyTorch implementation of multi-headed graph convolutional neural networks
BSD 3-Clause "New" or "Revised" License
68 stars 29 forks source link

restructure pre-process data utils #192

Closed allaffa closed 1 year ago

allaffa commented 1 year ago

The function update_atom_features is already available in the file hydragnn\preprocess\utils.py. Therefore, there is no need to have a re-implementation as method inside the class abstractrawdataset.

The function stratified_sampling is a general functionality, and its use it not restricted to only datasets created with the class abstractrawdataset.