Pierre-Paul De Breuck comments

Results 16 comments of


                                            Pierre-Paul De Breuck

How to sample from the posterior distribution using the Bayesian module?

No, I haven't spent much time on the Bayesian model to be honest. Might be something to explore in the future ...

Is it possible to use Modnet with gpu acceleration ?

Hey all ! Sorry for the late reply. I would not spent time on this @naik-aakash: (i) MODNet uses small networks (intended for small datasets), with no benefit of GPU...

Is it possible to use Modnet with gpu acceleration ?

Great idea, and probably easier than translating to PyTorch given our frequent usage of tf.keras

Non-stratified splitting and overwriting of loss function in classification tasks

You are correct on the three points. For the second, I agree adding stratification by default makes sense as it follows what we do for k-fold (i.e. StratifiedKFold). For the...

Non-stratified splitting and overwriting of loss function in classification tasks

@ml-evs It's indeed not the intended behaviour, but note that GA never really uses bootstrapping. It's only when fitting EnsembleModel from scratch, so we never ran into this issue. I...

Validation data generation, removal of loss function overrides

> Hi @ppdebreuck I have a question regarding this comment: [#228 (comment)](https://github.com/ppdebreuck/modnet/issues/228#issuecomment-2437540148) > > Do you think it would make sense to enable the passing of a loss function for...