mnist数据的预测结果以及批量处理

import sys, os

sys.path.append(‘F:\ml\DL\source-code‘)

from dataset.mnist import load_mnist

from PIL import Image

import numpy as np

#pickle提供了一个简单的持久化功能。可以将对象以文件的形式存放在磁盘上。
#pickle模块只能在python中使用，python中几乎所有的数据类型（列表，字典，集合，类等）都可以用pickle来序列化，
#pickle序列化后的数据，可读性差，人一般无法识别。
import pickle

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

def softmax(x):
    m = np.max(x)
    
    return np.exp(x- m) / np.sum(np.exp(x - m))

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 init_network():
    with open("F:\\ml\DL\\source-code\\ch03\\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(a1, 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)
    
    if p == t[i]:
        accuracy_cnt += 1
        
print("Accuracy:" + str(float(accuracy_cnt) / len(x)))

#批处理显示
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)))