nmichlo / disent

🧶 Modular VAE disentanglement framework for python built with PyTorch Lightning ▸ Including metrics and datasets ▸ With strongly supervised, weakly supervised and unsupervised methods ▸ Easily configured and run with Hydra config ▸ Inspired by disentanglement_lib
https://disent.michlo.dev
MIT License
122 stars 18 forks source link

Thank you! #2

Closed smspillaz closed 3 years ago

smspillaz commented 3 years ago

Hi! I just wanted to leave a note to say that I'm doing some work on disentanglement at the moment and this repository has been super helpful (not to mention that I think you provide a really good example of how to use frameworks like hydra and pytorch-lightning).

Not sure if you're planning on taking contributions right now, since you did mention that this work was for your Master Thesis and that's already hard enough as is, but if you want, I can throw a couple of PRs your way.

nmichlo commented 3 years ago

Hi! Thank you very much for your kind words.

I am aiming to finish in the next month, so I might not have much time to review code until then but contributions are more than welcome, especially if they add new frameworks or datasets, or fix any of the mistakes in existing ones.

EDIT: next *few months