chapter 3 神经网络

step_function.py

# coding: utf-8
import numpy as np
import matplotlib.pylab as plt

def step_function(x):
    return np.array(x > 0, dtype=np.int)

if __name__ = '__main__':
    X = np.arange(-5.0, 5.0, 0.1)
    Y = step_function(X)
    plt.plot(X, Y)
    plt.ylim(-0.1, 1.1)
    plt.show()

sigmoid.py

# coding: utf-8
import numpy as np
import matplotlib.pylab as plt

def sigmoid(x):
    return 1 / (1 + np.exp(-x))

if __name__ = '__main__':
    X = np.arange(-5.0, 5.0, 0.1)
    Y = sigmoid(X)
    plt.plot(X, Y)
    plt.ylim(-0.1, 1.1)
    plt.show()

sig_step_compare.py

# coding: utf-8
import numpy as np
import matplotlib.pylab as plt

def sigmoid(x):
    return 1 / ( 1 + np.exp(-x))

def step_function(x):
    return np.array(x > 0, dtype=np.int)

if __name__ == '__main__':
    x = np.arange(-5.0, 5.0, 0.1)
    y1 = sigmoid(x)
    y2 = step_function(x)

    plt.plot(x, y1)
    plt.plot(x, y2, 'k--')
    plt.ylim(-0.1, 1.1)
    plt.show()

relu.py

# coding: utf-8
import numpy as np
import matplotlib.pylab as plt

def relu(x):
    return np.maximum(0, x)

if __name__ = '__main__':
    x = np.arange(-5.0, 0.5, 0.1)
    y = relu(x)

    plt.plot(x, y)
    plt.ylim(-1.0, 5.5)
    plt.show()

mnist_show.py

# coding: utf-8
import sys, os
sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import numpy as np
from dataset.mnist import load_mnist
from PIL import Image


def img_show(img):
    pil_img = Image.fromarray(np.uint8(img))
    pil_img.show()

(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True, normalize=False)

img = x_train[0]
label = t_train[0]
print(label)  # 5

print(img.shape)  # (784,)
img = img.reshape(28, 28)  # 把图像的形状变为原来的尺寸
print(img.shape)  # (28, 28)

img_show(img)

neuralnet_mnist.py

# coding: utf-8
import sys, os
sys.path.append(os.pardir) #为了导入父目录的文件而进行的设定
import numpy as np
import pickle
from dataset.mnist import load_mnist
from common.functions import sigmoid, softmax

def get_date():
    (x_train, t_train),(x_test, t_test) = load_mnist(normalize=True, flatten=True, none_hot_label=False)
    return x_test, t_test

def init_network():
    with open('sample_weight.pkl', 'rb') as f:
        network = pickle.load(f)
    return network

def predict(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2 , b3 = network['b1'], network['b2'], network['b2']

    a1 = np.dot(x, W1) + b1
    z1 = sigmoid(a1)
    
    a2 = np.dot(z1, W2) + b2
    z2 = sigmoid(a2)

    a3 = np.dot(z2, W3) + b3
    y = softmax(a3)

    return y

if __name__ = '__main__':
    x, t = get_data()
    network = init_network()
    accuracy_cnt = 0
    
    for i in range(len(x)):
        y = predict(network, x[i])
        p = np.argmax(y) #获取概率最高的元素的索引
        if p == t[i]:
            accuracy_cnt += 1
    print("Accuracy:"+str(float(accuracy_cnt) / len(x)) 

neuralnet_mnist_batch.py

# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
import numpy as np
import pickle
from dataset.mnist import load_mnist
from common.functions import sigmoid, softmax

def get_data():
    (x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, flatten=True, one_hot_label=False)
    return x_test, t_test

def int_network():
    with open('sample_weight.plk','rb') as f:
        network = pickle.load(f)
    return network

def predict(network, x):
    w1, w2, w3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']

    a1 = np.dot(x, w1) + b1
    z1 = sigmoid(a1)
    a2 = np.dot(z1, w2) + b2
    z2 = sigmoid(a2)
    a3 = np.dot(z2, w3) + b3
    y = softmax(a3)

    return y

if __name__ == '__main__':
    x, t = get_data()
    network = init_network()
    
    batch_size =  100
    accuracy_cnt = 0
    
    for i in range(0, len(x), batch_size):
        x_batch = x[i:i+batch_size]
        y_batch = predict(network, x_batch)
        p = np.argmax(y_batch, axis=1)
        accuracy_cnt += np.sum(p == t[i:i+batch_size])
    print('Accuracy:'+ str(float(accuracy_cnt) / len(x))

本章所学内容

1. 神经网络中的激活函数使用平滑的sigmoid函数或ReLU函数。
2. 通过巧妙地使用NumPy多维数组，可以高效地实现神经网罗。
3. 机器学习地问题大体上可以分为回归问题和分类问题。
4. 关于输出层地激活函数，回归问题中一般用恒等函数，分类问题中一般用softmax函数。
5. 分类问题中，输出层的神经元的数量设置为要分类的类别数。
6. 输入数据的集合称为批。通过以批为单位进行推理处理，能够实现高速的运算。