Reproducing results on Teubingen about causaldiscoverytoolbox HOT 5 CLOSED

There should be a performance issue ; it should be really fast for 10 epochs.
The accuracy issue here comes from the number of epochs, you need those at least 1000 epochs for the neural networks to have learned something.

Can you give me your hardware setup ?

from causaldiscoverytoolbox.

You should try with more epochs. I will be closing this issue for inactivity, don't hesitate to reopen-it.

from causaldiscoverytoolbox.

Actually, we found a small bug that prevented the algorithm to run on the gpu.
I can send you the corrections if you want.

from causaldiscoverytoolbox.

Sure, I would be glad to fix this !

from causaldiscoverytoolbox.

When you want to run on one gpu and not multiple gpus, since you use a multi gpu wrapper, it switched to cpu by default. Therefore, we replaced the wrapper to the default single gpu wrapper.
Hope it helps!

from causaldiscoverytoolbox.