三层神经网络

实验题目：三层神经网络

单一处理代码：

import sys,os
sys.path.append(os.pardir)
import numpy as np
import time
import pickle
from dataset.mnist import load_mnist

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

def softmax(a):
 c = np.max(a)
 exp_a = np.exp(a - c) # 溢出对策
 sum_exp_a = np.sum(exp_a)
 y = exp_a / sum_exp_a
 return y

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

#单一计算
x, t = get_data()
network = init_network()
accuracy_cnt = 0

start = time.perf_counter()

for i in range(len(x)):
    y = predict(network,x[i])
    p = np.argmax(y) 
    
    if p == t[i].all():
        accuracy_cnt +=1
    

end= time.perf_counter()
print('单一计算使用时间:'+str(end-start)+'秒')
print('精度：'+ str(float(accuracy_cnt)/len(x)))

批处理代码：

import sys,os
sys.path.append(os.pardir)
import numpy as np
import time
import pickle
from dataset.mnist import load_mnist

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

def softmax(a):
 c = np.max(a)
 exp_a = np.exp(a - c) # 溢出对策
 sum_exp_a = np.sum(exp_a)
 y = exp_a / sum_exp_a
 return y

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

#批处理
x, t = get_data()
network = init_network()
batch_size = 100 # 批数量
accuracy_cnt = 0

start = time.perf_counter()

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].all())
        
end= time.perf_counter()
print('批处理使用时间:'+str(end-start)+'秒')
print('精度：'+ str(float(accuracy_cnt)/len(x)))

---

实验结果：

欢迎访问作者个人技术博客:BlackvonCode(www.blackvon.top)
作者的微信公众号和小程序