Priors

The probability that object classes will be seen in video.

This parameter accepts a list of object class names mapped to floating point numbers. The numbers must be proportional to the prior probability that the object class will be seen. You must assign a value to every class that exists in the classifier.

In the example below, the object classification task expects that more video frames will contain cars than other types of vehicle.

If you do not set this parameter, the object classification task expects that all of the classes are equally likely to be present in video.

Note: You can only use this parameter with Bayesian classifiers. The type of classifier is specified with the ClassifierType training option (see SetClassifierTrainingOption).

Type: String (comma-separated list)
Default:  
Required: No
Configuration Section: TaskName
Example:

Priors=cars : 5,vans : 3, hgvs : 2

or

Priors0=cars : 5
Priors1=vans : 3
Priors2=hgvs : 2
See Also:  

_HP_HTML5_bannerTitle.htm