手写三层神经网络

import numpy
import scipy.special
import matplotlib.pyplot

class neuralNetwork:
    def __init__(self, inputnodes, hiddennodes, outputnodes, learningrate);
        self.inodes = inputnodes
        self.hnodes = hiddennodes
        self.onodes = outputnodes
        self.lr = learningrate
        
        self.wih = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.hnodes, self.inodes))
        self.who = numpy.random.normal(0.0, pow(self.onodes, -0.5), (self.onodes, self,hnodes))
        
        self.activation_function = lambda x: scipy.special.expit(x)
        
        
    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)
        
        final_inputs = numpy.dot(self.who, hidden_outputs)
        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 - final_outputs)), numpy.transpose(hidden_outputs))
        self.wih += seek.lr * numpy.dot((hidden_errors * (hidden_outputs * (1 - hidden_outputs), numpy.transpose(inputs))
        
        
     def query(self, inputs_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)
        
        final_inputs = numpy.dot(self.who, hidden_outputs)
        final_outputs = self.activation_function(final_inputs)
        
        return final_outputs
        
input_nodes = 784
hidden_nodes = 100
output_nodes = 10
learning_rate = 0.3

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

training_data_file = open("mnist_train_100.csv", r)
training_data_list = training_data_file.readlines()
training_data_file.close

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
    
    n.train(inputs, targets)