Jacob Schreiber

Can you download a version of Cython around 0.22 first and then try to pip install?

I forked v0.14.8 and added the changes suggested by @kkchau. If you could confirm that this resolves the issues you're facing, I'll release it on PyPI. https://github.com/jmschrei/pomegranate/tree/v0.14.9

@kkchau I just got back from some travel. Can you try `pip install pomegranate==0.14.9` and let me know if that works for you?

No problem, thanks for checking! @tyrrellgit does 0.14.9 work for you as well?

v0.15.0 should resolve these problems. Please re-open if problems persist.

This has been added to v1.1.0, which will be released shortly.

This should be fixed in v1.0.4. Please let me know if you encounter any other issues. In the future, if you run into challenges you can pass in `n_categories` to...

Hi Laura It is possible to use a variety of distributions with pomegranate. Binomial distributions are already implemented (https://github.com/jmschrei/pomegranate/blob/master/pomegranate/distributions/bernoulli.py) but these assume a fixed number of total trials. However, you...

I understand, good luck! If you're new to the field I'd suggest starting with a more basic model, like using Gaussian emissions, and seeing how good you can get that...

I'm able to reproduce this with the following script: ```python import torch from pomegranate.distributions import Normal from pomegranate.hmm import DenseHMM X = [torch.randn(i // 5, i, 3) for i in...