Revision history [back]

Regarding the weights, I did some small tests to check the influence. Here are my results:

No weights:

With weights [0.9, 0.1] (0.9 for the largest class, 0.1 for the smallest class):

You can see the change of the weights clearly in these pictures. I hope this clears things up a bit.

On a side note: I tried to do this in python but the class_weights variable does not appear to get set properly (see this question for more information). To circumvent this I had hardcoded the weights in the opencv source, using c++ would've most likely given the correct results as well.

Regarding the weights, I did some small tests to check the influence. Here are my results:

No weights:

With weights [0.9, 0.1] (0.9 for the largest class, 0.1 for the smallest class):

You can see the change of the weights clearly in these pictures. I hope this clears things up a bit.

On a side note: I tried to do this in python but the class_weights variable does not appear to get set properly (see this question for more information). To circumvent this I had hardcoded the weights in the opencv source, using c++ would've most likely given the correct results as well.well, as the weights seem to get properly set for c++.

Regarding the weights, I did some small tests to check the influence. Here are my results:

No weights:

With weights [0.9, 0.1] (0.9 for the largest class, 0.1 for the smallest class):

You can see the change of the weights clearly in these pictures. I hope this clears things up a bit.

On a side note: I tried to do this in python but the class_weights variable does not appear to get set properly (see this question for more information). To circumvent this I had hardcoded the weights in the opencv source, using c++ would've most likely given the correct results as well, as the weights seem to get properly set for c++.

import numpy as np
import cv2
import matplotlib.pyplot as plt
from os.path import isfile, join
import scipy.misc
import xml.dom.minidom

"""Originally from: http://stackoverflow.com/questions/8687885/python-opencv-svm-implementation"""
class StatModel(object):
    """parent class - starting point to add abstraction"""
    def load(self, fn):
        self.model.load(fn)
    def save(self, fn):
        self.model.save(fn)

"""Wrapper for OpenCV SimpleVectorMachine algorithm"""
class SVM(StatModel):
    def __init__(self):
        self.model = cv2.SVM()

    def train(self, X, Y):
        #setting algorithm parameters
        params = dict( kernel_type = cv2.SVM_LINEAR, 
                       svm_type = cv2.SVM_C_SVC,
                       C = 1,
                       class_weights = [0.9, 0.1],) # THIS DOES NOT WORK IN OPENCV PYTHON

        self.model.train(X.astype(np.float32), Y.astype(np.float32), params = params)

# generates Gaussian dataset
def gen_gauss_dat(mu1, cov1, N1, mu2, cov2, N2):
    X1 = np.random.multivariate_normal(mu1, cov1, (N1))
    X2 = np.random.multivariate_normal(mu2, cov2, (N2))
    X = np.vstack([X1,X2])
    Y = np.hstack([np.ones((X1.shape[0]))*-1, np.ones((X2.shape[0]))])
    return X, Y

def load_model(path):
    if path == None:
        return None

    if isfile(path) == False:
        return None

    print "Loading model from {}".format(path)
    model = xml.dom.minidom.parse(path)

    # TODO: handle multiple support vectors?
    weights = np.fromstring(model.getElementsByTagName("_")[0].childNodes[0].nodeValue, sep=" ")
    alpha = float(model.getElementsByTagName("alpha")[0].childNodes[0].nodeValue)
    rho = float(model.getElementsByTagName("rho")[0].childNodes[0].nodeValue)
    weights = weights * -alpha
    return weights, rho

# generate Gaussian data
X, Y = gen_gauss_dat([0,0], np.identity(2)*1.5, 1000, [2,2], np.identity(2) * 0.5, 100)

# train on the generated Gaussian data
svm = SVM()
svm.train(X, Y)
svm.save("svm.xml")
w, b = load_model("svm.xml", )

# plot the data
plt.scatter(X[Y==-1,0],X[Y==-1,1], c="g", alpha=0.6, s=100)
plt.scatter(X[Y==1,0],X[Y==1,1], c="r", alpha=0.6, s=100)

x = [-10, 10]
y = [(-w[0] * x[0] - b) / w[1], \
     (-w[0] * x[1] - b) / w[1]]
plt.plot(x, y)
plt.axis("off")
plt.title("Linear SVM classifier Gaussian dataset")
plt.show()

Regarding the weights, I did some small tests to check the influence. Here are my results:

No weights:

With weights [0.9, 0.1] (0.9 for the largest class, 0.1 for the smallest class):

You can see the change of the weights clearly in these pictures. I hope this clears things up a bit.

On a side note: I tried to do this in python but the class_weights variable does not appear to get set properly (see this question for more information). To circumvent this I had hardcoded the weights in the opencv source, using c++ would've most likely given the correct results as well, as the weights seem to get properly set for c++.

Code used to generate the example:

import numpy as np
import cv2
import matplotlib.pyplot as plt
from os.path import isfile, join
isfile
import scipy.misc
import xml.dom.minidom

"""Originally from: http://stackoverflow.com/questions/8687885/python-opencv-svm-implementation"""
class StatModel(object):
    """parent class - starting point to add abstraction"""
    def load(self, fn):
        self.model.load(fn)
    def save(self, fn):
        self.model.save(fn)

"""Wrapper for OpenCV SimpleVectorMachine algorithm"""
class SVM(StatModel):
    def __init__(self):
        self.model = cv2.SVM()

    def train(self, X, Y):
        #setting algorithm parameters
        params = dict( kernel_type = cv2.SVM_LINEAR, 
                       svm_type = cv2.SVM_C_SVC,
                       C = 1,
                       class_weights = [0.9, 0.1],) # THIS DOES NOT WORK IN OPENCV PYTHON

        self.model.train(X.astype(np.float32), Y.astype(np.float32), params = params)

# generates Gaussian dataset
def gen_gauss_dat(mu1, cov1, N1, mu2, cov2, N2):
    X1 = np.random.multivariate_normal(mu1, cov1, (N1))
    X2 = np.random.multivariate_normal(mu2, cov2, (N2))
    X = np.vstack([X1,X2])
    Y = np.hstack([np.ones((X1.shape[0]))*-1, np.ones((X2.shape[0]))])
    return X, Y

def load_model(path):
    if path == None:
        return None

    if isfile(path) == False:
        return None

    print "Loading model from {}".format(path)
    model = xml.dom.minidom.parse(path)

    # TODO: handle multiple support vectors?
    weights = np.fromstring(model.getElementsByTagName("_")[0].childNodes[0].nodeValue, sep=" ")
    alpha = float(model.getElementsByTagName("alpha")[0].childNodes[0].nodeValue)
    rho = float(model.getElementsByTagName("rho")[0].childNodes[0].nodeValue)
    weights = weights * -alpha
    return weights, rho

# generate Gaussian data
X, Y = gen_gauss_dat([0,0], np.identity(2)*1.5, 1000, [2,2], np.identity(2) * 0.5, 100)

# train on the generated Gaussian data
svm = SVM()
svm.train(X, Y)
svm.save("svm.xml")
w, b = load_model("svm.xml", )

# plot the data
plt.scatter(X[Y==-1,0],X[Y==-1,1], c="g", alpha=0.6, s=100)
plt.scatter(X[Y==1,0],X[Y==1,1], c="r", alpha=0.6, s=100)

x = [-10, 10]
y = [(-w[0] * x[0] - b) / w[1], \
     (-w[0] * x[1] - b) / w[1]]
plt.plot(x, y)
plt.axis("off")
plt.title("Linear SVM classifier Gaussian dataset")
plt.show()