created a new class for SimulAELDA

luigibonati / mlcolvar

A unified framework for machine learning collective variables for enhanced sampling simulations

MIT License

91 stars 24 forks source link

created a new class for SimulAELDA #123

Closed charlotte-chaps closed 5 months ago

charlotte-chaps commented 5 months ago

Description

Provide a brief description of the PR's purpose here.

Todos

Notable points that this PR has either accomplished or will accomplish.

[ ] TODO 1

Questions

[ ] Question1

Status

[ ] Ready to go

charlotte-chaps commented 5 months ago

Hello, I apologize I wanted to merge this branch in the main of my fork and didn't realize it would merge it here when I opened the PR!

EnricoTrizio commented 4 months ago

Hello, I apologize I wanted to merge this branch in the main of my fork and didn't realize it would merge it here when I opened the PR!

@charlotte-chaps you could also use the MultiTaskCV framework to do the same thing your code was doing without implementing a new class. That way you could also use separate datasets for the two learning tasks. In the tutorials in the doc you can find all the info about that if interested!

charlotte-chaps commented 4 months ago

Oh nice I'll look into it, thank you for the tip !