Jos van de Wolfshaar

Hi there, I have a suspicion it's trying to JSON serialize the one hot kernels in one of the conv products layers. Will have to make a fix for this....

Hi Aaron, I think what you aim to use is a cumulative distribution function, right? That should be quite doable to implement, thought API-wise I'm not sure how to achieve...

@anicolson I remember coming across this CDF idea in a recent paper. Could you point me to it? I will need it to get the naming right

Ah, bingo! I already read your paper some weeks ago, just didn't make the connection at first :sweat_smile: nice work! I'll go ahead and read the two once more to...

Could you show me the traceback of the error? Where in the code is it happening? Also, I was wondering why you want to duplicate SPNs? Do they take in...

So, you need this feature to work on feature/convspn specifically? I will merge `jostosh/libspn/dev-refactor-for-release` to it soon which hopefully fixes this issue.

Thanks for reporting this! I will look into it and see if I can implement some testing around this too. For the time being, I'd suggest you simply store the...

Thanks for raising this. I admit with the current state of the library that's going to be a complicated thing to do. The `region_graph_to_dense_spn` indeed is now limited to building...

I have given it some thought and had a shot at an initial draft implementation. I think I know what piece to add to the puzzle. A convenient way of...

I managed to complete the conversion, but I'm afraid that a single stack of Keras layers would require lots and lots of zero padding. For a 4x4 block (the finer...