深度学习入门ch3b推理 jupyter note

In [3]:

#coding=utf-8
#Depending on ../dataset/mnist.py, please download it by yourself
#Depending on ../common/functions.py, download it before hand.
#Depending on ./sample_weight.pkl, download it.
#准备数据
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 matplotlib.pyplot import imshow   #adapted for jupyter note
%pylab inline

def img_show(img):
    imshow(np.asarray(img))

(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)

Output:

Downloading train-images-idx3-ubyte.gz ... 
Done
Downloading train-labels-idx1-ubyte.gz ... 
Done
Downloading t10k-images-idx3-ubyte.gz ... 
Done
Downloading t10k-labels-idx1-ubyte.gz ... 
Done
Converting train-images-idx3-ubyte.gz to NumPy Array ...
Done
Converting train-labels-idx1-ubyte.gz to NumPy Array ...
Done
Converting t10k-images-idx3-ubyte.gz to NumPy Array ...
Done
Converting t10k-labels-idx1-ubyte.gz to NumPy Array ...
Done
Creating pickle file ...
Done!
5
(784,)
(28, 28)

In [7]:

#跳过训练，直接推理
import pickle
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 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

x, t = get_data()   #本段用训练好的权重，所以这里不需要x_train, t_train,只需要x_test, t_test
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)))

Output:

Accuracy:0.9352

In [ ]:

#        X         W1          W2           W3       Y
#形状： 784   784 × 50   50 × 100    100 × 10    10  
#   每批100张
#          X         W1          W2           W3           Y 
#形状： 100X784   784 × 50   50 × 100    100 × 10    100X10

Output:

In [8]:

#batch : 100 pics every time
x, t = get_data()
network = init_network()
batch_size = 100 # 批数量
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) 
    #给定了参数axis=1。这指定了在100 × 10 的数组中，沿着第1 维方向（以第1 维为轴）找到值最大的元素的索引（第0 维对应第1 个维度）
    accuracy_cnt += np.sum(p == t[i:i+batch_size])
print("Accuracy:" + str(float(accuracy_cnt) / len(x)))

Output:

Accuracy:0.9352