python编程入门与人工神经网络设计初步（代码部分）
本文章含此次开放实验的大实验部分代码，（从课件上搬运来的，可免去敲代码的麻烦）
第三周实验：
import numpy
import scipy.special
import matplotlib.pyplot
%matplotlib inline # 此行只在jupyter notebook 中需要
class neuralNetwork:
def __init__(self, inputnodes, hiddennodes, outputnodes, learningrate):
self.inodes = inputnodes
self.hnodes = hiddennodes
self.onodes = outputnodes
self.wih = numpy.random.normal(0.0, pow(self.inodes, -0.5), (self.hnodes, self.inodes))
self.who = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.onodes, self.hnodes))
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)
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 * (1.0 - final_outputs)),
numpy.transpose(hidden_outputs))
self.wih += self.lr * numpy.dot((hidden_errors * hidden_outputs * (1.0 - hidden_outputs)),
numpy.transpose(inputs))
pass
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)
final_inputs = numpy.dot(self.who, hidden_outputs)
final_outputs = self.activation_function(final_inputs)
return final_outputs
input_nodes = 784
hidden_nodes = 200
output_nodes = 10
learning_rate = 0.1
n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
training_data_file = open("mnist_dataset/train.csv", 'r')
training_data_list = training_data_file.readlines()
training_data_file.close()
epochs = 5
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
n.train(inputs, targets)
pass
pass
test_data_file = open("mnist_dataset/test.csv", 'r')
test_data_list = test_data_file.readlines()
test_data_file.close()
scorecard = []
for record in test_data_list:
all_values = record.split(',')
correct_label = int(all_values[0])
inputs = (numpy.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
outputs = n.query(inputs)
label = numpy.argmax(outputs)
if label == correct_label:
scorecard.append(1)
else:
scorecard.append(0)
pass
pass
scorecard_array = numpy.asarray(scorecard)
print("performance = ", scorecard_array.sum() / scorecard_array.size)第四周：
1.1：
import imageio
import glob
import numpy
import matplotlib.pyplot
# %matplotlib inline
our_own_dataset = []
for image_file_name in glob.glob('my_own_images/my7.png'):
print("loading ... ", image_file_name)
label = int(image_file_name[-5,-4])
img_array = imageio.imread(image_file_name, as_gray = True)
img_data = 255.0 - img_array.reshape(784)
img_data = (img_data / 255.0 * 0.99) + 0.01
print(numpy.min(img_data))
print(numpy.max(img_data))
record = numpy.append(label, img_data)
print(record)
our_own_dataset.append(record)
pass
matplotlib.pyplot.imshow(our_own_dataset[3][1:].reshape(28, 28), cmap = 'Greys', interpolation='None')
print(our_own_dataset[0])1.2：
import numpy
import scipy.special
import matplotlib.pyplot
# %matplotlib inline
import imageio
class neuralNetwork:
def __init__(self, inutndes, hiddennodes, outputnodes, learningrate):
self.inodes = inutndes
self.hnodes = hiddennodes
self.onodes = outputnodes
self.wih = numpy.random.normal(0.0, pow(self.inodes, -0.5), (self.hnodes, self.inodes))
self.who = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.onodes, self.hnodes))
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)
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 * (1.0 - final_outputs)), numpy.transpose(hidden_outputs))
self.wih += self.lr * numpy.dot((hidden_errors * hidden_outputs * (1.0 - hidden_outputs)), numpy.transpose(inputs))
pass
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)
final_inputs = numpy.dot(self.who, hidden_outputs)
final_outputs = self.activation_function(final_inputs)
return final_outputs
input_nodes = 784
hidden_nodes = 200
output_nodes = 10
learning_rate = 0.1
n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
training_data_file = open("mnist_dataset/train.csv", 'r')
training_data_list = training_data_file.readlines()
training_data_file.close()
epochs = 10
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
n.train(inputs, targets)
pass
pass
print("loading ... my_own_images/my7.png")
img_array = imageio.imread('my_own_images/my7.png', as_gray = True)
img_data = 255.0 - img_array.reshape(784)
img_data = (img_data / 255.0 * 0.99) + 0.01
print("min=", numpy.min(img_data))
print("max=", numpy.max(img_data))
matplotlib.pyplot.imshow(img_data.reshape(28, 28), cmap='Greys', interpolation='None')
outputs = n.query(img_data)
print(outputs)
label = numpy.argmax(outputs)
print("network says ", label)2：
import numpy
import scipy.special
import matplotlib.pyplot
# %matplotlib inline
class neuralNetwork:
def __init__(self, inputnodes, hiddennodes, outputnodes, learningrate):
self.inodes = inputnodes
self.hnodes = hiddennodes
self.onodes = outputnodes
self.wih = numpy.random.normal(0.0, pow(self.inodes, -0.5), (self.hnodes, self.inodes))
self.who = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.onodes, self.hnodes))
self.lr = learningrate
self.activation_function = lambda x: scipy.special.expit(x)
self.inverse_activation_function = lambda x: scipy.special.logit(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)
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 * (1.0 - final_outputs)), numpy.transpose(hidden_outputs))
self.wih += self.lr * numpy.dot((hidden_errors * hidden_outputs * (1.0 - hidden_outputs)), numpy.transpose(inputs))
pass
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)
final_inputs = numpy.dot(self.who, hidden_outputs)
final_outputs = self.activation_function(final_inputs)
return final_outputs
def back_query(self, targets_list):
final_outputs = numpy.array(targets_list, ndmin=2).T
final_inputs = self.inverse_activation_function(final_outputs)
hidden_outputs = numpy.dot(self.who.T, final_inputs)
hidden_outputs -= numpy.min(hidden_outputs)
hidden_outputs /= numpy.max(hidden_outputs)
hidden_outputs *= 0.98
hidden_outputs += 0.01
hidden_inputs = self.inverse_activation_function(hidden_outputs)
inputs = numpy.dot(self.wih.T, hidden_inputs)
inputs -= numpy.min(inputs)
inputs /= numpy.max(inputs)
inputs *= 0.98
inputs += 0.01
return inputs
input_nodes = 784
hidden_nodes = 200
output_nodes = 10
learning_rate = 0.1
n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
training_data_file = open("mnist_dataset/train.csv", 'r')
training_data_list = training_data_file.readlines()
training_data_file.close()
epochs = 5
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
n.train(inputs, targets)
pass
pass
test_data_file = open("mnist_dataset/test.csv", 'r')
test_data_list = test_data_file.readlines()
test_data_file.close()
scorecard = []
for record in test_data_list:
all_values = record.split(',')
correct_label = int(all_values[0])
inputs = (numpy.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
outputs = n.query(inputs)
label = numpy.argmax(outputs)
if label == correct_label:
scorecard.append(1)
else:
scorecard.append(0)
pass
pass
scorecard_array = numpy.asarray(scorecard)
print("performance = ", scorecard_array.sum() / scorecard_array.size)
label = 0
targets = numpy.zeros(output_nodes) + 0.01
targets[label] = 0.99
print(targets)
image_data = n.back_query(targets)
matplotlib.pyplot.imshow(image_data.reshape(28, 28), cmap = 'Greys', interpolation='None')3.1：
import numpy
import matplotlib.pyplot
# %matplotlib inline
import scipy.ndimage
data_file = open("mnist_dataset/train.csv", 'r')
data_list = data_file.readlines()
data_file.close()
record = 6
all_values = data_list[record].split(',')
scaled_input = ((numpy.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01).reshape(28, 28)
print(numpy.min(scaled_input))
print(numpy.max(scaled_input))
matplotlib.pyplot.imshow(scaled_input, cmap='Greys', interpolation='None')
inputs_plus10_img = scipy.ndimage.rotate(scaled_input, 10.0, cval=0.01, order=1, reshape=False)
inputs_minus10_img = scipy.ndimage.rotate(scaled_input, -10.0, cval=0.01, order=1, reshape=False)
print(numpy.min(inputs_plus10_img))
print(numpy.max(inputs_minus10_img))
matplotlib.pyplot.imshow(inputs_plus10_img, cmap='Greys', interpolation='None')
matplotlib.pyplot.imshow(inputs_minus10_img, cmap='Greys', interpolation='None')3.2：
import numpy
import scipy.special
import scipy.ndimage
class neuralNetwork:
def __init__(self, inputnodes, hiddennodes, outputnodes, learningrate):
self.inodes = inputnodes
self.hnodes = hiddennodes
self.onodes = outputnodes
self.wih = numpy.random.normal(0.0, pow(self.inodes, -0.5), (self.hnodes, self.inodes))
self.who = numpy.random.normal(0.0, pow(self.hnodes, -0.5), (self.onodes, self.hnodes))
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)
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 * (1.0 - final_outputs)),
numpy.transpose(hidden_outputs))
self.wih += self.lr * numpy.dot((hidden_errors * hidden_outputs * (1.0 - hidden_outputs)),
numpy.transpose(inputs))
pass
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)
final_inputs = numpy.dot(self.who, hidden_outputs)
final_outputs = self.activation_function(final_inputs)
return final_outputs
input_nodes = 784
hidden_nodes = 200
output_nodes = 10
learning_rate = 0.1
n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
training_data_file = open("mnist_dataset/train.csv", 'r')
training_data_list = training_data_file.readlines()
training_data_file.close()
epochs = 10
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
n.train(inputs, targets)
inputs_plusx_img = scipy.ndimage.interpolation.rotate(inputs.reshape(28, 28), 10, cval=0.01, order=1, reshape=False)
n.train(inputs_plusx_img.reshape(784), targets)
inputs_minusx_img = scipy.ndimage.interpolation.rotate(inputs.reshape(28, 28), -10, cval=0.01, order=1, reshape=False)
n.train(inputs_minusx_img.reshape(784), targets)
pass
pass
test_data_file = open("mnist_dataset/test.csv", 'r')
test_data_list = test_data_file.readlines()
test_data_file.close()
scorecard = []
for record in test_data_list:
all_values = record.split(',')
correct_label = int(all_values[0])
inputs = (numpy.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
outputs = n.query(inputs)
label = numpy.argmax(outputs)
if label == correct_label:
scorecard.append(1)
else:
scorecard.append(0)
pass
pass
scorecard_array = numpy.asarray(scorecard)
print("performance = ", scorecard_array.sum() / scorecard_array.size)