NAME¶
hmm_train - hidden markov model (hmm) training
SYNOPSIS¶
hmm_train [-h] [-v] -i string -t string [-b] [-g int] [-l string] [-m string] [-o string] [-s int] [-n int] [-T double] -V
DESCRIPTION¶
This program allows a Hidden Markov Model to be trained on labeled or unlabeled
data. It support three types of HMMs: discrete HMMs, Gaussian HMMs, or GMM
HMMs.
Either one input sequence can be specified (with
--input_file), or, a
file containing files in which input sequences can be found (when
--input_file and
--batch are used together). In addition, labels
can be provided in the file specified by
--label_file, and if
--batch is used, the file given to
--label_file should contain a
list of files of labels corresponding to the sequences in the file given to
--input_file.
The HMM is trained with the Baum-Welch algorithm if no labels are provided. The
tolerance of the Baum-Welch algorithm can be set with the
--tolerance
option.
Optionally, a pre-created HMM model can be used as a guess for the transition
matrix and emission probabilities; this is specifiable with
--model_file.
REQUIRED OPTIONS¶
- --input_file (-i) [string]
- File containing input observations.
- --type (-t) [string]
- Type of HMM: discrete | gaussian | gmm.
OPTIONS¶
- --batch (-b)
- If true, input_file (and if passed, labels_file) are expected to contain a
list of files to use as input observation sequences (and label
sequences).
- --gaussians (-g) [int]
- Number of gaussians in each GMM (necessary when type is 'gmm'. Default
value 0.
- --help (-h)
- Default help info.
- --info [string]
- Get help on a specific module or option. Default value ''.
- --labels_file (-l) [string]
- Optional file of hidden states, used for labeled training. Default value
''.
- --model_file (-m) [string]
- Pre-existing HMM model (optional). Default value ''.
- --output_file (-o) [string]
- File to save trained HMM to (XML). Default value 'output_hmm.xml'.
- --seed (-s) [int]
- Random seed. If 0, 'std::time(NULL)' is used. Default value 0.
- --states (-n) [int]
- Number of hidden states in HMM (necessary, unless model_file is specified.
Default value 0.
- --tolerance (-T) [double]
- Tolerance of the Baum-Welch algorithm. Default value 1e-05.
- --verbose (-v)
- Display informational messages and the full list of parameters and timers
at the end of execution.
- --version (-V)
- Display the version of mlpack.
For further information, including relevant papers, citations, and theory,
consult the documentation found at
http://www.mlpack.org or included with your
distribution of MLPACK.