神经网络02

softmax 函数

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

def identity_function(x):
    return x


def softmax(a):
    
    c = np.max(a) # 为了方式溢出，取信号的最大值
    
    exp_a = np.exp(a-c)
    sum_exp_a = np.sum(exp_a)
    y = exp_a /sum_exp_a
    
    return y

a = np.array([1,2,3,4,5])

print(softmax(a)) # [0.01165623 0.03168492 0.08612854 0.23412166 0.63640865]

显示图像

import sys, os

print(os.getcwd())
sys.path.append(os.getcwd())

from mnist import load_mnist
import numpy as np

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

print(x_train.shape) # (60000, 784)
print(t_train.shape) # (60000,)
print(x_test.shape) # (10000, 784)
print(t_test.shape) # (10000,) 


from PIL import Image

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

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


print(img.shape) # (784,)

img = img.reshape(28,28)

print(img.shape) # (28, 28)

img_show(img) # 图像显示就是5 

神经网络推理处理

import sys, os

print(os.getcwd())
sys.path.append(os.getcwd())

from mnist import load_mnist
import numpy as np

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

# t_train  一维数组 [5 0 4 ... 5 6 8]    长度：60000
# t_test  一维数组 [7 2 1 ... 4 5 6]     

# x_train  二维数组 维度值： (60000, 784) 60000行， 784 列
# print(x_train[59999]) 第60000行的值
# x_test  二维数组 维度值： (10000, 784)

train_size = x_train.shape[0]  # (60000, 784) 的第一个元素 60000
batch_size = 10;

# 
batch_mask = np.random.choice(train_size, batch_size)

print(batch_mask)  # [28259  6378 19047  4077 55177 24777 25800 17717  7067 32450]


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


import pickle 

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


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

def identity_function(x):
    return x

def softmax(a):
    c = np.max(a) # 为了方式溢出，取信号的最大值
    exp_a = np.exp(a-c)
    sum_exp_a = np.sum(exp_a)
    y = exp_a /sum_exp_a
    return y    

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

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_cnt)   # 9207 
print (len(x)) # 10000
print("accuracy:" + str(float(accuracy_cnt) / len(x)))# accuracy:0.9207 

# 批处理 -- 替换上面最后那一部分代码
x, t = get_data()
network = init_network()
accuracy_cnt = 0
batch_size = 100

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) # 获取概率最高的元素的索引
    accuracy_cnt += np.sum(p == t[i: i+batch_size])
    
print("accuracy:" + str(float(accuracy_cnt) / len(x)))# accuracy:0.9207