神经网络 两层隐藏层

import numpy
import scipy.special


class neuralNetwork:
    
    def __init__(self, inputnodes, hiddennodes, hidden2nodes, outputnodes, learningrate):

        self.inodes = inputnodes
        self.hnodes = hiddennodes
        self.hnodes2 = hidden2nodes
        self.onodes = outputnodes

        self.wih = numpy.random.normal(0.0, pow(self.inodes, -0.5), (self.hnodes, self.inodes))
        self.wih2 = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.hnodes2, self.hnodes))
        self.who = numpy.random.normal(0.0, pow(self.hnodes2, -0.5), (self.onodes, self.hnodes2))

        self.lr = learningrate

        self.activation_function = lambda x: scipy.special.expit(x)
        
        pass

    

    def train(self, inputs_list, targets_list):
        inputs = numpy.array(inputs_list, ndmin=2).T
        targets = numpy.array(targets_list, ndmin=2).T
        

        hidden_inputs = numpy.dot(self.wih, inputs)
        hidden_outputs = self.activation_function(hidden_inputs)

        hidden_inputs2 = numpy.dot(self.wih2, hidden_outputs)
        hidden_outputs2 = self.activation_function(hidden_inputs2)
        
        final_inputs = numpy.dot(self.who, hidden_outputs2)
        final_outputs = self.activation_function(final_inputs)
        

        output_errors = targets - final_outputs
        hidden_errors = numpy.dot(self.who.T, output_errors)

        
        self.who += self.lr * numpy.dot((output_errors * final_outputs * (1.0 - final_outputs)), numpy.transpose(hidden_outputs2))
        self.wih += self.lr * numpy.dot((hidden_errors * hidden_outputs * (1.0 - hidden_outputs)), numpy.transpose(inputs))
        self.wih2 += self.lr * numpy.dot((hidden_errors * hidden_outputs2 * (1.0 - hidden_outputs2)), numpy.transpose(hidden_outputs))
        
        return final_outputs

    
    def query(self, inputs_list):
        inputs = numpy.array(inputs_list, ndmin=2).T
        
        hidden_inputs = numpy.dot(self.wih, inputs)
        hidden_outputs = self.activation_function(hidden_inputs)

        hidden_inputs2 = numpy.dot(self.wih2, hidden_outputs)
        hidden_outputs2 = self.activation_function(hidden_inputs2)
        
        final_inputs = numpy.dot(self.who, hidden_outputs2)
        final_outputs = self.activation_function(final_inputs)
        
        return final_outputs
    
    def wsave(self):
        numpy.save('w2.npy',self.wih)
        numpy.save('w1.npy',self.who)
        numpy.save('w3.npy',self.wih2)

input_nodes = 784  # 图片大小
hidden_nodes = 200  # 读取数量
hidden2_nodes = 200  # 读取数量
output_nodes = 10  # 输出大小

learning_rate = 0.1

n = neuralNetwork(input_nodes,hidden_nodes, hidden2_nodes,output_nodes, learning_rate)

training_data_file = open("mnist_train.csv", 'r')
training_data_list = training_data_file.readlines()
training_data_file.close()

epochs = 1
for e in range(epochs):
    for record in training_data_list:
        all_values = record.split(',')
        inputs = (numpy.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
        targets = numpy.zeros(output_nodes) + 0.01
        targets[int(all_values[0])] = 0.99
        data = n.train(inputs, targets)
        pass
    pass

n.wsave()

--------------------------------------------------------------------------

import numpy
import scipy.special
import cv2

data1 = numpy.load('w1.npy',fix_imports=True)
data2 = numpy.load('w2.npy',fix_imports=True)
data3 = numpy.load('w3.npy',fix_imports=True)

activation_function = lambda x: scipy.special.expit(x)

def query(inputs_list):
        inputs = numpy.array(inputs_list, ndmin=2).T
        
        hidden_inputs = numpy.dot(data2, inputs)
        hidden_outputs = activation_function(hidden_inputs)

        hidden_inputs2 = numpy.dot(data3, hidden_outputs)
        hidden_outputs2 = activation_function(hidden_inputs2)
        
        final_inputs = numpy.dot(data1, hidden_outputs2)
        final_outputs = activation_function(final_inputs)
        
        return final_outputs


img = cv2.imread('my_own_images/2828_my_own_6.png',0)

img_data  = 255.0 - img.reshape(784)
img_data = (img_data / 255.0 * 0.99) + 0.01
outputs = query(img_data)

label = numpy.argmax(outputs)
print("数字是： ", label)