You find the meaning of those parameters in the source code (usually with 
some comments).  The .model files are not plain text files, even though they 
contain text for the parameters.

Generally, after a model has been trained, you should not change the 
parameters, since the statistical models are optimized for the input 
distributions they receive.

If you do want to change something, you should read the model, set the 
parameter, then write it back out again, using the OCRopus I/O functions.

Generally, the term "cost" in OCRopus refers to negative log probabilities.

Tom

-- 
You received this message because you are subscribed to the Google Groups 
"ocropus" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/ocropus?hl=en.

Reply via email to