Python-сообщество

    pat = [
        [[0,0], [0]],
        [[0,1], [1]],
        [[1,0], [1]],
        [[1,1], [0]]
    ]

import math
import random
import string
random.seed(0)
# calculate a random number where:  a <= rand < b
def rand(a, b):
    return (b-a)*random.random() + a
# Make a matrix (we could use NumPy to speed this up)
def makeMatrix(I, J, fill=0.0):
    m = []
    for i in range(I):
        m.append([fill]*J)
    return m
# our sigmoid function, tanh is a little nicer than the standard 1/(1+e^-x)
def sigmoid(x):
    return math.tanh(x)
# derivative of our sigmoid function, in terms of the output (i.e. y)
def dsigmoid(y):
    return 1.0 - y**2
class NN:
    def __init__(self, ni, nh, no):
        # number of input, hidden, and output nodes
        self.ni = ni + 1 # +1 for bias node
        self.nh = nh
        self.no = no
        # activations for nodes
        self.ai = [1.0]*self.ni
        self.ah = [1.0]*self.nh
        self.ao = [1.0]*self.no
        
        # create weights
        self.wi = makeMatrix(self.ni, self.nh)
        self.wo = makeMatrix(self.nh, self.no)
        # set them to random vaules
        for i in range(self.ni):
            for j in range(self.nh):
                self.wi[i][j] = rand(-0.2, 0.2)
        for j in range(self.nh):
            for k in range(self.no):
                self.wo[j][k] = rand(-2.0, 2.0)
        # last change in weights for momentum   
        self.ci = makeMatrix(self.ni, self.nh)
        self.co = makeMatrix(self.nh, self.no)
    def save(self, fname):
        f = open(fname, "w")
        f.write(str(self.ni)+";")
        f.write(str(self.nh)+";")
        f.write(str(self.no)+";")
        for i in xrange(self.ni):
            for j in xrange(self.nh):
                f.write(str(self.wi[i][j])+";")
        for i in xrange(self.nh):
            for j in xrange(self.no):
                f.write(str(self.wo[i][j])+";")
        f.close()
    def load(self, fname):
        f = open(fname, "r")
        line = f.read()
        f.close()
        arr = string.split(line, ";")
        self.ni, self.nh, self.no = int(arr[0]), int(arr[1]), int(arr[2])
        self.wi = makeMatrix(self.ni, self.nh)
        self.wo = makeMatrix(self.nh, self.no)
        n = 2
        for i in xrange(self.ni):
            for j in xrange(self.nh):
                n += 1
                self.wi[i][j] = float(arr[n])
        for i in xrange(self.nh):
            for j in xrange(self.no):
                n += 1
                self.wo[i][j] = float(arr[n])
    def update(self, inputs):
        if len(inputs) != self.ni-1:
            raise ValueError('wrong number of inputs')
        # input activations
        for i in range(self.ni-1):
            #self.ai[i] = sigmoid(inputs[i])
            self.ai[i] = inputs[i]
        # hidden activations
        for j in range(self.nh):
            sum = 0.0
            for i in range(self.ni):
                sum = sum + self.ai[i] * self.wi[i][j]
            self.ah[j] = sigmoid(sum)
        # output activations
        for k in range(self.no):
            sum = 0.0
            for j in range(self.nh):
                sum = sum + self.ah[j] * self.wo[j][k]
            self.ao[k] = sigmoid(sum)
        return self.ao[:]
    def backPropagate(self, targets, N, M):
        if len(targets) != self.no:
            raise ValueError('wrong number of target values')
        # calculate error terms for output
        output_deltas = [0.0] * self.no
        for k in range(self.no):
            error = targets[k]-self.ao[k]
            output_deltas[k] = dsigmoid(self.ao[k]) * error
        # calculate error terms for hidden
        hidden_deltas = [0.0] * self.nh
        for j in range(self.nh):
            error = 0.0
            for k in range(self.no):
                error = error + output_deltas[k]*self.wo[j][k]
            hidden_deltas[j] = dsigmoid(self.ah[j]) * error
        # update output weights
        for j in range(self.nh):
            for k in range(self.no):
                change = output_deltas[k]*self.ah[j]
                self.wo[j][k] = self.wo[j][k] + N*change + M*self.co[j][k]
                self.co[j][k] = change
                #print N*change, M*self.co[j][k]
        # update input weights
        for i in range(self.ni):
            for j in range(self.nh):
                change = hidden_deltas[j]*self.ai[i]
                self.wi[i][j] = self.wi[i][j] + N*change + M*self.ci[i][j]
                self.ci[i][j] = change
        # calculate error
        error = 0.0
        for k in range(len(targets)):
            error = error + 0.5*(targets[k]-self.ao[k])**2
        return error
    def test(self, patterns):
        for p in patterns:
            print(p[0], '->', self.update(p[0]))
    def weights(self):
        print('Input weights:')
        for i in range(self.ni):
            print(self.wi[i])
        print()
        print('Output weights:')
        for j in range(self.nh):
            print(self.wo[j])
    def train(self, patterns, iterations=1000, N=0.5, M=0.1):
        # N: learning rate
        # M: momentum factor
        for i in range(iterations):
            error = 0.0
            for p in patterns:
                inputs = p[0]
                targets = p[1]
                self.update(inputs)
                error = error + self.backPropagate(targets, N, M)
            if i % 100 == 0:
                print('error %-.5f' % error)
def demo():
    # Teach network XOR function
    pat = [
        [[0,0], [0]],
        [[0,1], [1]],
        [[1,0], [1]],
        [[1,1], [0]]
    ]
    # create a network with two input, two hidden, and one output nodes
    n = NN(2, 2, 1)
    # train it with some patterns
    n.train(pat)
    # test it
    n.test(pat)
    n.save("z.txt")
    n.load("z.txt")
    n.test(pat)
if __name__ == '__main__':
    demo()

from pybrain.tools.shortcuts import buildNetwork
from pybrain.structure import TanhLayer
from pybrain.datasets import SupervisedDataSet
from PIL import Image
import os
from pybrain.supervised.trainers import BackpropTrainer
import pickle
##################################################
ds = SupervisedDataSet(400, 1)
iconset = ['0','1','2','3','4','5','6','7','8','9']
imageset = []
#перебираем в папке изображения и преобразуем в массив пикселей
#сам массив подаем в формате (1-0), 1-пиксели черного цвета, 0- белого
#создаем сеть ds.addSample(sl,letter)
for letter in iconset:
  
  for img in os.listdir('./iconset/%s/'%(letter)):
    
    temp = []
    if img != "Thumbs.db": # windows check...
        im=(Image.open("./iconset/%s/%s"%(letter,img)))
        im = im.convert("P")
        im2 = Image.new("P",im.size,255)
        im = im.convert("P")
        temp = {}
        for x in range(im.size[1]):
          for y in range(im.size[0]):
            pix = im.getpixel((y,x))
            temp[pix] = pix
            if pix == 0: # these are the numbers to get
              im2.putpixel((y,x),0)
        sl=[]
        for i in im2.getdata():
            #print i
            if i==0:
                i=1
            else: i=0
            sl.append(i)
        
        ds.addSample(sl,letter)
        
net = buildNetwork(400, 133, 1, bias=True, hiddenclass=TanhLayer)
trainer = BackpropTrainer(net, ds)
#print trainer.trainUntilConvergence()
#тренеруем-обучаем
trainer = BackpropTrainer(net, ds)                                                 
for epoch in range(0, 10000):                                                                   
    error = trainer.train()                                                                    
    if error < 0.00006:                                                                          
        break
    
#преобразуем тестовое изображение    
def imag():
    im = Image.open("2-2.png")
    im = im.convert("P")
    im2 = Image.new("P",im.size,255)
    im = im.convert("P")
    temp = {}
    for x in range(im.size[1]):
      for y in range(im.size[0]):
        pix = im.getpixel((y,x))
        temp[pix] = pix
        if pix == 0: # these are the numbers to get
          im2.putpixel((y,x),0)
    sl=[]
    for i in im2.getdata():
        #print i
        if i==0:
            i=1
        else: i=0
        sl.append(i)
    return sl
#сохраняем обученную сеть
fileObject = open('filename', 'w')
pickle.dump(net, fileObject)
fileObject.close()
fileObject = open('filename','r')
net = pickle.load(fileObject)
#подаем на распознование массив пикселей, тестового изображения
test= imag()
print net.activate(test)
####################################################