search

luigibonati / mlcolvar

A unified framework for machine learning collective variables for enhanced sampling simulations
MIT License
89 stars 24 forks source link

MultiTaskCV: Save lists of auxiliary losses in ModuleList #52

Closed andrrizzi closed 1 year ago

andrrizzi commented 1 year ago

Currently they auxiliary loss functions are saved in a normal list, but we could save them in a ModuleList. I think this way if the loss function has trainable parameters (e.g., a decoder for reconstruction losses) they will be optimized as well.

luigibonati commented 1 year ago

is this closed by the related commit?

andrrizzi commented 1 year ago

Should be, but didn't work! Possibly the colon tripped GitHub up. Closing manually.