python - SVM to gender recognition -

i've been working weeks in gender recognition project (in python) using @ first: fisherfaces feature extraction method , 1-nn classifier euclidean distance though not enough reliable (in humble opinion) i'm use svm im lost when have create , train model use in dataset of images, can't find solution commands need in http://scikit-learn.org. i've tried code doesn't work, dunno why have error while executing:

  file "prueba.py", line 46, in main     clf.fit(r, r)   file "/users/raul/anaconda/lib/python2.7/site-packages/sklearn/svm/base.py", line 139, in fit      x = check_array(x, accept_sparse='csr', dtype=np.float64, order='c')   file "/users/raul/anaconda/lib/python2.7/site-packages/sklearn/utils/validation.py", line 350, in check_array     array.ndim) valueerror: found array dim 3. expected <= 2 

and code:

import os, sys import numpy np import pil.image image import cv2 sklearn import svm   def read_images(path, id, sz=none):     c = id     x,y = [], []     dirname, dirnames, filenames in os.walk(path):         subdirname in dirnames:             subject_path = os.path.join(dirname, subdirname)             filename in os.listdir(subject_path):                 try:                     im = image.open(os.path.join(subject_path, filename))                     im = im.convert("l")                     # resize given size (if given)                     if (sz not none):                         im = im.resize(sz, image.antialias)                     x.append(np.asarray(im, dtype=np.uint8))                     y.append(c)                 except ioerror e:                     print "i/o error({0}): {1}".format(e.errno, e.strerror)                 except:                     print "unexpected error:", sys.exc_info()[0]                     raise                         #c = c+1     return [x,y]   def main():     # check arguments     if len(sys.argv) != 3:         print "usage: example.py </path/to/images/males> </path/to/images/females>"         sys.exit()     # read images , put them vectors , id's     [x,x] = read_images(sys.argv[1], 1)     [y, y] = read_images(sys.argv[2], 0)     # r images , r id's     [r, r] = [x+y, x+y]     clf = svm.svc()     clf.fit(r, r)      if __name__ == '__main__':     main() 

i'd appreciate kind of in how can make gender recognition svm reading

x.append(np.asarray(im, dtype=np.uint8)) 

i guess appending 2d-array. might want flatten before appending each instance becomes looking:

array([255, 255, 255, ..., 255, 255, 255], dtype=uint8) 

instead of:

array([    [255, 255, 255, ..., 255, 255, 255],    [255, 255, 255, ..., 255, 255, 255],    [255,   0,   0, ...,   0,   0,   0],    ...,     [255,   0,   0, ...,   0,   0,   0],    [255, 255, 255, ..., 255, 255, 255],    [255, 255, 255, ..., 255, 255, 255]], dtype=uint8) 

try this:

x.append(np.asarray(im, dtype=np.uint8).ravel())