Early stopping only works when save_checkpoint set True

materialsvirtuallab / megnet

Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals

BSD 3-Clause "New" or "Revised" License

493 stars 155 forks source link

Open Nokimann opened 3 years ago

Nokimann commented 3 years ago

The early stoping works if

model.train(save_checkpoint=True, patience=1)

The early stopping doesn't work if

model.train(save_checkpoint=False, patience=1)

chc273 commented 3 years ago

You can use keras early stop callback