【DL--22】实现神经网络算法NeuralNetwork以及手写数字识别

1.NeuralNetwork.py

#coding:utf-8

import numpy as np

#定义双曲函数和他们的导数
def tanh(x):
    return np.tanh(x)

def tanh_deriv(x):
    return 1.0 - np.tanh(x)**2

def logistic(x):
    return 1/(1 + np.exp(-x))

def logistic_derivative(x):
    return logistic(x)*(1-logistic(x))

#定义NeuralNetwork 神经网络算法
class NeuralNetwork:
    #初始化,layes表示的是一个list,eg[10,10,3]表示第一层10个神经元,第二层10个神经元,第三层3个神经元
    def __init__(self, layers, activation='tanh'):
        """
        :param layers: A list containing the number of units in each layer.
        Should be at least two values
        :param activation: The activation function to be used. Can be
        "logistic" or "tanh"
        """
        if activation == 'logistic':
            self.activation = logistic
            self.activation_deriv = logistic_derivative
        elif activation == 'tanh':
            self.activation = tanh
            self.activation_deriv = tanh_deriv

        self.weights = []
        #循环从1开始,相当于以第二层为基准,进行权重的初始化
        for i in range(1, len(layers) - 1):
            #对当前神经节点的前驱赋值
            self.weights.append((2*np.random.random((layers[i - 1] + 1, layers[i] + 1))-1)*0.25)
            #对当前神经节点的后继赋值
            self.weights.append((2*np.random.random((layers[i] + 1, layers[i + 1]))-1)*0.25)

            #训练函数   ,X矩阵,每行是一个实例 ,y是每个实例对应的结果,learning_rate 学习率,
    # epochs,表示抽样的方法对神经网络进行更新的最大次数
    def fit(self, X, y, learning_rate=0.2, epochs=10000):
        X = np.atleast_2d(X) #确定X至少是二维的数据
        temp = np.ones([X.shape[0], X.shape[1]+1]) #初始化矩阵
        temp[:, 0:-1] = X  # adding the bias unit to the input layer
        X = temp
        y = np.array(y) #把list转换成array的形式

        for k in range(epochs):
            #随机选取一行,对神经网络进行更新
            i = np.random.randint(X.shape[0])
            a = [X[i]]

            #完成所有正向的更新
            for l in range(len(self.weights)):
                a.append(self.activation(np.dot(a[l], self.weights[l])))
                #
            error = y[i] - a[-1]
            deltas = [error * self.activation_deriv(a[-1])]

            #开始反向计算误差,更新权重
            for l in range(len(a) - 2, 0, -1): # we need to begin at the second to last layer
                deltas.append(deltas[-1].dot(self.weights[l].T)*self.activation_deriv(a[l]))
            deltas.reverse()
            for i in range(len(self.weights)):
                layer = np.atleast_2d(a[i])
                delta = np.atleast_2d(deltas[i])
                self.weights[i] += learning_rate * layer.T.dot(delta)

                #预测函数
    def predict(self, x):
        x = np.array(x)
        temp = np.ones(x.shape[0]+1)
        temp[0:-1] = x
        a = temp
        for l in range(0, len(self.weights)):
            a = self.activation(np.dot(a, self.weights[l]))
        return a

2、基于NeuralNetwork的手写数字识别

#-*-coding:utf-8-*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

import numpy as np
from sklearn.datasets import load_digits
from sklearn.metrics import confusion_matrix, classification_report
from sklearn.preprocessing import LabelBinarizer
from NeuralNetwork import NeuralNetwork
from sklearn.cross_validation import train_test_split

digits = load_digits()
X = digits.data
y = digits.target
X -= X.min() # normalize the values to bring them into the range 0-1
X /= X.max()



###############################训练模型########################
nn = NeuralNetwork([64,100,10],'logistic')
X_train, X_test, y_train, y_test = train_test_split(X, y)



labels_train = LabelBinarizer().fit_transform(y_train)
labels_test = LabelBinarizer().fit_transform(y_test)
print "start fitting"
nn.fit(X_train,labels_train,epochs=3000)

###############预测结果###############################
predictions = []
for i in range(X_test.shape[0]):
    o = nn.predict(X_test[i] )
    predictions.append(np.argmax(o))


###############混淆矩阵#####################################
print confusion_matrix(y_test,predictions)
print classification_report(y_test,predictions)

#################打印预测结果#####################
# for each in predictions:
#     print each


# for each in y_test:
#     print each

3、运行结果:


start fitting
[[44  0  0  0  0  0  0  0  0  0]
 [ 0 44  0  0  0  1  0  0  2  0]
 [ 0  1 39  0  0  0  0  0  0  0]
 [ 0  1  0 49  0  0  0  2  2  0]
 [ 0  2  0  0 34  0  0  2  1  0]
 [ 0  2  0  0  1 44  1  0  0  3]
 [ 1  2  0  0  0  0 43  0  0  0]
 [ 0  0  0  0  0  0  0 41  0  0]
 [ 0  4  0  0  0  1  0  1 31  2]
 [ 0  4  0  0  0  0  0  1  1 43]]
             precision    recall  f1-score   support

          0       0.98      1.00      0.99        44
          1       0.73      0.94      0.82        47
          2       1.00      0.97      0.99        40
          3       1.00      0.91      0.95        54
          4       0.97      0.87      0.92        39
          5       0.96      0.86      0.91        51
          6       0.98      0.93      0.96        46
          7       0.87      1.00      0.93        41
          8       0.84      0.79      0.82        39
          9       0.90      0.88      0.89        49

avg / total       0.92      0.92      0.92       450


Process finished with exit code 0
已标记关键词 清除标记
©️2020 CSDN 皮肤主题: 编程工作室 设计师:CSDN官方博客 返回首页