Skip to content

Experiments

Marcus Wieder edited this page May 15, 2024 · 13 revisions

Training performance

Training for each neural network is performed on a fixed testset with each implemented neural network potential. We repeat each training 5 times with random parameter initialization.

QM9

NNP average number of epochs time @ epoch [min:sec] test set performance [kJ/mol]
ANI2x 282 0:10 6.6 +-1.
SchNet 0:50
PaiNN
PhysNet
SAKE
TensorNet
AimNet2
Clone this wiki locally