class StumpMachine

This class is designed to train/support a (discrete) weak classifier

Inheritance:


Public Fields

[more]int n_features
number of possible features

Public Methods

[more] StumpMachine(int n_features_ = 0)
[more]virtual void setParams(int feature_id_, real threshold_, int direction_)
decode the parameters of the machine
[more]virtual real getFeature(int feature_id_, Sequence* inputs_)
compute the feature feature_id_ for the sequence inputs_
[more]virtual void forward(Sequence* inputs)
computes the output of the machine given an input sequence
[more]virtual void loadXFile(XFile* file)
load the parameters of the machine
[more]virtual void saveXFile(XFile* file)
save the parameters of the machine
[more]virtual ~StumpMachine()


Documentation

This class is designed to train/support a (discrete) weak classifier

It has three parameters:

oint n_features
number of possible features

o StumpMachine(int n_features_ = 0)

ovirtual void setParams(int feature_id_, real threshold_, int direction_)
decode the parameters of the machine

ovirtual real getFeature(int feature_id_, Sequence* inputs_)
compute the feature feature_id_ for the sequence inputs_

ovirtual void forward(Sequence* inputs)
computes the output of the machine given an input sequence

ovirtual void loadXFile(XFile* file)
load the parameters of the machine

ovirtual void saveXFile(XFile* file)
save the parameters of the machine

ovirtual ~StumpMachine()


Direct child classes:
HaarStumpMachine
Author:
Yann Rodriguez (yann.rodriguez@idiap.ch) Sebastien Marcel (marcel@idiap.ch)
Version:
2.0 Fri 15 Jul 2005 11:35:25 AM CEST
Since:
2.0

Alphabetic index HTML hierarchy of classes or Java



This page was generated with the help of DOC++.