1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
|
#!/usr/bin/env python
'''
The sample demonstrates how to train Random Trees classifier
(or Boosting classifier, or MLP, or Knearest, or Support Vector Machines) using the provided dataset.
We use the sample database letter-recognition.data
from UCI Repository, here is the link:
Newman, D.J. & Hettich, S. & Blake, C.L. & Merz, C.J. (1998).
UCI Repository of machine learning databases
[http://www.ics.uci.edu/~mlearn/MLRepository.html].
Irvine, CA: University of California, Department of Information and Computer Science.
The dataset consists of 20000 feature vectors along with the
responses - capital latin letters A..Z.
The first 10000 samples are used for training
and the remaining 10000 - to test the classifier.
======================================================
USAGE:
letter_recog.py [--model <model>]
[--data <data fn>]
[--load <model fn>] [--save <model fn>]
Models: RTrees, KNearest, Boost, SVM, MLP
'''
# Python 2/3 compatibility
from __future__ import print_function
import numpy as np
import cv2 as cv
def load_base(fn):
a = np.loadtxt(fn, np.float32, delimiter=',', converters={ 0 : lambda ch : ord(ch)-ord('A') })
samples, responses = a[:,1:], a[:,0]
return samples, responses
class LetterStatModel(object):
class_n = 26
train_ratio = 0.5
def load(self, fn):
self.model = self.model.load(fn)
def save(self, fn):
self.model.save(fn)
def unroll_samples(self, samples):
sample_n, var_n = samples.shape
new_samples = np.zeros((sample_n * self.class_n, var_n+1), np.float32)
new_samples[:,:-1] = np.repeat(samples, self.class_n, axis=0)
new_samples[:,-1] = np.tile(np.arange(self.class_n), sample_n)
return new_samples
def unroll_responses(self, responses):
sample_n = len(responses)
new_responses = np.zeros(sample_n*self.class_n, np.int32)
resp_idx = np.int32( responses + np.arange(sample_n)*self.class_n )
new_responses[resp_idx] = 1
return new_responses
class RTrees(LetterStatModel):
def __init__(self):
self.model = cv.ml.RTrees_create()
def train(self, samples, responses):
self.model.setMaxDepth(20)
self.model.train(samples, cv.ml.ROW_SAMPLE, responses.astype(int))
def predict(self, samples):
_ret, resp = self.model.predict(samples)
return resp.ravel()
class KNearest(LetterStatModel):
def __init__(self):
self.model = cv.ml.KNearest_create()
def train(self, samples, responses):
self.model.train(samples, cv.ml.ROW_SAMPLE, responses)
def predict(self, samples):
_retval, results, _neigh_resp, _dists = self.model.findNearest(samples, k = 10)
return results.ravel()
class Boost(LetterStatModel):
def __init__(self):
self.model = cv.ml.Boost_create()
def train(self, samples, responses):
_sample_n, var_n = samples.shape
new_samples = self.unroll_samples(samples)
new_responses = self.unroll_responses(responses)
var_types = np.array([cv.ml.VAR_NUMERICAL] * var_n + [cv.ml.VAR_CATEGORICAL, cv.ml.VAR_CATEGORICAL], np.uint8)
self.model.setWeakCount(15)
self.model.setMaxDepth(10)
self.model.train(cv.ml.TrainData_create(new_samples, cv.ml.ROW_SAMPLE, new_responses.astype(int), varType = var_types))
def predict(self, samples):
new_samples = self.unroll_samples(samples)
_ret, resp = self.model.predict(new_samples)
return resp.ravel().reshape(-1, self.class_n).argmax(1)
class SVM(LetterStatModel):
def __init__(self):
self.model = cv.ml.SVM_create()
def train(self, samples, responses):
self.model.setType(cv.ml.SVM_C_SVC)
self.model.setC(1)
self.model.setKernel(cv.ml.SVM_RBF)
self.model.setGamma(.1)
self.model.train(samples, cv.ml.ROW_SAMPLE, responses.astype(int))
def predict(self, samples):
_ret, resp = self.model.predict(samples)
return resp.ravel()
class MLP(LetterStatModel):
def __init__(self):
self.model = cv.ml.ANN_MLP_create()
def train(self, samples, responses):
_sample_n, var_n = samples.shape
new_responses = self.unroll_responses(responses).reshape(-1, self.class_n)
layer_sizes = np.int32([var_n, 100, 100, self.class_n])
self.model.setLayerSizes(layer_sizes)
self.model.setTrainMethod(cv.ml.ANN_MLP_BACKPROP)
self.model.setBackpropMomentumScale(0.0)
self.model.setBackpropWeightScale(0.001)
self.model.setTermCriteria((cv.TERM_CRITERIA_COUNT, 20, 0.01))
self.model.setActivationFunction(cv.ml.ANN_MLP_SIGMOID_SYM, 2, 1)
self.model.train(samples, cv.ml.ROW_SAMPLE, np.float32(new_responses))
def predict(self, samples):
_ret, resp = self.model.predict(samples)
return resp.argmax(-1)
def main():
import getopt
import sys
models = [RTrees, KNearest, Boost, SVM, MLP] # NBayes
models = dict( [(cls.__name__.lower(), cls) for cls in models] )
args, dummy = getopt.getopt(sys.argv[1:], '', ['model=', 'data=', 'load=', 'save='])
args = dict(args)
args.setdefault('--model', 'svm')
args.setdefault('--data', 'letter-recognition.data')
datafile = cv.samples.findFile(args['--data'])
print('loading data %s ...' % datafile)
samples, responses = load_base(datafile)
Model = models[args['--model']]
model = Model()
train_n = int(len(samples)*model.train_ratio)
if '--load' in args:
fn = args['--load']
print('loading model from %s ...' % fn)
model.load(fn)
else:
print('training %s ...' % Model.__name__)
model.train(samples[:train_n], responses[:train_n])
print('testing...')
train_rate = np.mean(model.predict(samples[:train_n]) == responses[:train_n].astype(int))
test_rate = np.mean(model.predict(samples[train_n:]) == responses[train_n:].astype(int))
print('train rate: %f test rate: %f' % (train_rate*100, test_rate*100))
if '--save' in args:
fn = args['--save']
print('saving model to %s ...' % fn)
model.save(fn)
print('Done')
if __name__ == '__main__':
print(__doc__)
main()
cv.destroyAllWindows()
|
