写篇水文来记录一下随手写的神经网络。承接上篇的卷积神经网络反向传播推导。不过这个是三层的神经网络,数据是手写数字的识别。代码写的乱七八糟,没有整理。不过可以直接运行。。。测试阶段懒得整理啊。。。代码很冗余的。后期优化一下吧。以此纪念我一个简单的bug找了三天。粗心害死人!
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
from sklearn.utils import shuffle
def sigmoid(z):
return 1.0/(1.0+np.exp(-z))
def sigmoid_prime(z):
return sigmoid(z)*(1-sigmoid(z))
def normalise_images(imgs,dist):
std = np.std(dist)
mean = np.mean(dist)
return (imgs - mean) / std
def Loss(Out, Label):
loss = 0
for i,j in zip(Out, Label):
for a,b in zip(i[0],j):
loss += (a-b)**2
return loss/(2*len(Out))
def Testing(x_test, y_test, W_and_B):
W1 = W_and_B[0]
W2 = W_and_B[1]
B1 = W_and_B[2]
B2 = W_and_B[3]
acc = 0
Len = len(x_test)
for x,y in zip(x_test, y_test):
x = x.reshape([784,1])
y = y.reshape([10,1])
Hide = np.dot(W1, x) + B1
Hide_s = sigmoid(Hide)
Output = np.dot(W2, Hide_s) + B2
Output_s = sigmoid(Output)
a = np.argmax(Output_s)
b = np.argmax(y)
if a==b:
acc+=1
acc = acc/Len
print('准确率为:%f' %acc)
mnist = input_data.read_data_sets("mnist/", one_hot=True)
x_train, y_train = mnist.train.images,mnist.train.labels
x_test, y_test = mnist.test.images, mnist.test.labels
x_train= normalise_images(x_train, x_train)
x_test = normalise_images(x_test, x_train)
batch_size = 10
num_input = 784
num_hide = 30
num_classes = 10
lr = 3 #学习率
EPOCHS = 10
W1 = np.random.randn(num_hide, num_input)
B1 = np.random.randn(num_hide,1)
W2 = np.random.randn(num_classes, num_hide)
B2 = np.random.randn(num_classes,1)
LOSS = list()
for i in range(EPOCHS):
num_examples = len(x_train)
x_train,y_train = shuffle(x_train,y_train)
for offset in range(0,num_examples,batch_size):
end = offset+batch_size
batch_x,batch_y = x_train[offset:end],y_train[offset:end]
length = len(batch_x)
tmp = 1.0/length
Out_list = list()
delta_1 = np.zeros(B2.shape)
delta_2 = np.zeros(B1.shape)
delta_W1 = np.zeros(W1.shape)
delta_W2 = np.zeros(W2.shape)
for x,y in zip(batch_x, batch_y):
x = x.reshape([784,1])
y = y.reshape([10,1])
Hide = np.dot(W1, x) + B1
Hide_s = sigmoid(Hide)
Output = np.dot(W2, Hide_s) + B2
Output_s = sigmoid(Output)
Out_list.append(Output_s)
a = (Output_s-y)*sigmoid_prime(Output) #输出层误差,B2梯度
b = np.dot(W2.T, a)*sigmoid_prime(Hide) #隐藏层误差,B1梯度
c = np.dot(a, Hide_s.T) #W2梯度
d = np.dot(b, x.T) #W1梯度
delta_1 += a
delta_2 += b
delta_W2 += c
delta_W1 += d
W1 = W1 - lr*tmp*delta_W1
W2 = W2 - lr*tmp*delta_W2
B1 = B1 - lr*tmp*delta_2
B2 = B2 - lr*tmp*delta_1
loss = Loss(Out_list, batch_y)
LOSS.append(loss)
print('EPOCH %d......' %i)
plt.plot(LOSS)
W_and_B = [W1, W2, B1, B2]
Testing(x_train, y_train, W_and_B)
Testing(x_test, y_test, W_and_B)
再放一个大佬写的,然后我稍微修改的版本,通用的多层神经网络:
import random
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("mnist/", one_hot=True)
x_train, y_train = mnist.train.images,mnist.train.labels
x_test, y_test = mnist.test.images, mnist.test.labels
def turning_data(x_data, y_data):
Data = list()
for x,y in zip(x_data, y_data):
x = x.reshape([784,1])
y = y.reshape([10,1])
tmp = [x,y]
Data.append(tmp)
return Data
training_data = turning_data(x_train, y_train)
test_data = turning_data(x_test, y_test)
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):
if test_data: n_test = len(test_data)
n = len(training_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 {0}: {1} / {2}".format(j, self.evaluate(test_data), n_test))
else:
print("Epoch {0} 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)), np.argmax(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 (output_activations-y)
def sigmoid(z):
return 1.0/(1.0+np.exp(-z))
def sigmoid_prime(z):
return sigmoid(z)*(1-sigmoid(z))
net = Network([784, 30, 10])
net.SGD(training_data, 10, 10, 3.0, test_data=test_data)