search

coarse-graining / cgnet

learning coarse-grained force fields
BSD 3-Clause "New" or "Revised" License
57 stars 26 forks source link

eval/training_mode in dataset_loss #157

Closed nec4 closed 4 years ago

nec4 commented 4 years ago

Now that we are using BatchNorm1d (a layer that behaves differently in eval and train modes), we should add this as an option for the dataset_loss function.

brookehus commented 4 years ago

Done in #158