Phillip Lippe

Hi, sorry for getting back so late on it. DataLoaders quitting unexpectedly can happen in Colab or a notebook when you interrupted a cell during data loading. Did you try...

Thanks for pointing out the API change! It seems to me that the API is still in progress and possible subject to change, so I'll wait a bit longer before...

Hi, thanks for pointing that out! This is indeed a typo and should have used a stride of 1 and `x_max` as input to the conv. I'll leave this issue...

Hi Imahn, There is no specific reason for the meta-learning tutorial being not yet in JAX, I simply didn't find the time to do it yet. I hope to get...

Hi, thanks for your kind words! Householder flows are indeed an interesting topic. If I find the time, I will try to add a tutorial on them at some point...

Hi, the sigmoid model is indeed a fun one to play around in this tutorial. :) I had tried a couple of trainings in PyTorch with 50 epochs and noticed...

Hi @fountaindive, thanks for your interest in the categorical normalising flows! Yes, it is possible to combine categorical and continuous features in CNFs. In the CNF, we first map the...

Hi @fountaindive, sure that would be great! Let me summarize the important modules/classes and steps needed: * The general model class is [`FlowModel`](../blob/master/layers/flows/flow_model.py). This allows you to simply stack flow...

Hi, thanks for your interest in the repo! I'm planning to integrate data parallel with pmap soon, but for now, I recommend overwriting the jitting/training function in the child trainer...