-
I've defined 3 different HMMs:
'GMM-HMM': hmm.GMMHMM(n_components=4, covariance_type='diag', n_iter=20000),
'Gaussian-HMM': hmm.GaussianHMM(n_components=4,covariance_type='diag', n_iter=20000),
'Gaus…
-
The first thing to do is probably to revert to the identical array type used for the original `Viterbi.hs`. Just to eliminate a possibly gratuitous source of variation.
-
Amongst other things, they have logic in their **init**.
@jaquesgrobler : do you think that you can put this on your todo list?
-
When fitting data with the multinomial HMM,
- First, the number of symbols is undefined
- Second, it crashes when unpacking a shape on the first line of the forward pass.
Here is how to reproduce the…
fmder updated
12 years ago
-
The following test failure seen on both a Sun Ultra 27 running OpenSolaris 06/2009 and a Dell Optiplex 755 running Solaris 10 on the x86 processor.
## On a Sun Ultra 27 running OpenSolaris
* Sun U…
-
The forthcoming 4.5.2.alpha0 includes #9219, which appears to cause the following docbuild warnings:
```
docstring of sage.stats.hmm.chmm.GaussianHiddenMarkovModel:14: (WARNING/2) Literal block exp…
-
An almost complete 32-bit port of Sage 4.5.2 to Solaris 10 on x86 processors had been done on the following hardware:
* Dell OptiPlex 755
* 2.40 GHz Intel Quad-Core Core2 Q6600 CPU
* 8 GB RAM, 8 GB…