Question

我正在从Michael Nielsen的书enter link description here中学习ANN

我在下面运行代码，它会产生错误

File "c:\python\handwritting\src\network.py", line 152, in <module>
    net.SGD(training_data, 30, 10, 3.0, test_data=test_data)
NameError: name 'training_data' is not defined

代码：

class Network(object):



def __init__(self, sizes):

    self.num_layers = len(sizes)
    self.sizes = sizes
    self.biases = [np.random.randn(y, 1) for y in sizes[1:]]
    self.weights = [np.random.randn(y, x)
                    for x, y in zip(sizes[:-1], sizes[1:])]

def feedforward(self, a):

    for b, w in zip(self.biases, self.weights):
        a = sigmoid(np.dot(w, a)+b)
    return a

def SGD(self, training_data, epochs, mini_batch_size, eta,
        test_data=None):

    training_data = list(training_data)
    n = len(training_data)

    if test_data:
        test_data = list(test_data)
        n_test = len(test_data)

    for j in range(epochs):
        random.shuffle(training_data)
        mini_batches = [
            training_data[k:k+mini_batch_size]
            for k in range(0, n, mini_batch_size)]
        for mini_batch in mini_batches:
            self.update_mini_batch(mini_batch, eta)
        if test_data:
            print("Epoch {} : {} / {}".format(j,self.evaluate(test_data),n_test));
        else:
            print("Epoch {} complete".format(j))

def update_mini_batch(self, mini_batch, eta):

    nabla_b = [np.zeros(b.shape) for b in self.biases]
    nabla_w = [np.zeros(w.shape) for w in self.weights]
    for x, y in mini_batch:
        delta_nabla_b, delta_nabla_w = self.backprop(x, y)
        nabla_b = [nb+dnb for nb, dnb in zip(nabla_b, delta_nabla_b)]
        nabla_w = [nw+dnw for nw, dnw in zip(nabla_w, delta_nabla_w)]
    self.weights = [w-(eta/len(mini_batch))*nw
                    for w, nw in zip(self.weights, nabla_w)]
    self.biases = [b-(eta/len(mini_batch))*nb
                   for b, nb in zip(self.biases, nabla_b)]

def backprop(self, x, y):

    nabla_b = [np.zeros(b.shape) for b in self.biases]
    nabla_w = [np.zeros(w.shape) for w in self.weights]
    # feedforward
    activation = x
    activations = [x] # list to store all the activations, layer by layer
    zs = [] # list to store all the z vectors, layer by layer
    for b, w in zip(self.biases, self.weights):
        z = np.dot(w, activation)+b
        zs.append(z)
        activation = sigmoid(z)
        activations.append(activation)
    # backward pass
    delta = self.cost_derivative(activations[-1], y) * \
        sigmoid_prime(zs[-1])
    nabla_b[-1] = delta
    nabla_w[-1] = np.dot(delta, activations[-2].transpose())

    for l in range(2, self.num_layers):
        z = zs[-l]
        sp = sigmoid_prime(z)
        delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
        nabla_b[-l] = delta
        nabla_w[-l] = np.dot(delta, activations[-l-1].transpose())
    return (nabla_b, nabla_w)

def evaluate(self, test_data):

    test_results = [(np.argmax(self.feedforward(x)), y)
                    for (x, y) in test_data]
    return sum(int(x == y) for (x, y) in test_results)

def cost_derivative(self, output_activations, y):
    """Return the vector of partial derivatives \partial C_x /
    \partial a for the output activations."""
    return (output_activations-y)

def sigmoid(z):
"""The sigmoid function."""
return 1.0/(1.0+np.exp(-z))

def sigmoid_prime(z):
"""Derivative of the sigmoid function."""
return sigmoid(z)*(1-sigmoid(z))

当我通过按以下步骤完成代码来运行整个程序时，它将产生错误。给出了剩余的代码

net = Network([784, 100, 10])

net.SGD(training_data, 30, 10, 3.0, test_data=test_data)

如何解决此错误

NameError：名称“ training_data”未定义

我将此模块导入另一个程序并运行该程序代码已给出

import network
import pickle

import gzip

import numpy as np


def load_data():   
tr_d, va_d, te_d = load_data()
training_inputs = [np.reshape(x, (784, 1)) for x in tr_d[0]]
training_results = [vectorized_result(y) for y in tr_d[1]]
training_data = zip(training_inputs, training_results)
validation_inputs = [np.reshape(x, (784, 1)) for x in va_d[0]]
validation_data = zip(validation_inputs, va_d[1])
test_inputs = [np.reshape(x, (784, 1)) for x in te_d[0]]
test_data = zip(test_inputs, te_d[1])

f = open('../data/mnist.pkl', 'rb')
training_data, validation_data, test_data = pickle.load(f)
f.close()

return (training_data, validation_data, test_data)

def vectorized_result(j):   
e = np.zeros((10, 1))
e[j] = 1.0
return e

我不知道出什么问题了。

NameError：名称“ training_data”未在

0 个答案: