treb1en / hiddenmarkovmodel_pytorch Goto Github PK

Hello,
it seems that no NHMM is implemented in python (at least I could not find any). I just wanted to leave a suggestion for possible future improvements. Congratulations on the project, thank you very much!

Hello,

I had a look at your code, and I wanted to understand the syntax of the following:

in HiddenMarkovModel.py, line 183:

obs_prob_seq = self.E[obs_seq]

What is this syntax supposed to do?

Thanks in advance!

Hello,

I'm interested in playing around with and modifying your HMM code to support Gaussian HMMs, but I noticed that you do not have a license attached. Would you mind attaching a license, so the rights to use and modify your code are clear?

Thanks!

If I have some sequences， such as ['a', 'b', 'c' , 'f'] , ['s', 'w', 'c' , 'u'] ....
How to use HiddenMarkovModel_Pytorch to detect which is an abnormal sequence or compute the probability/loglikehood of the sequence ？

Hello TreB1eN,

I have a question about the code that predict the hidden state in viterbi_inference

I think to predict state, we have to choose the state with the highest probability like code that predict last state

Can you explain it to me?

Thanks!