深度学习入门-（基于python的理论与实现）1-代码练习

照着书上敲的

import os, sys
sys.path.append(os.pardir)

""""
sys.path.append
sys.path.append(os.pardir)
python程序中使用 import XXX 时，python解析器会在当前目录、
已安装和第三方模块中搜索 xxx，如果都搜索不到就会报错。

mnist_show.py文件的当前工作目录为ch03，
但是load_mnist（）函数的mnist.py文件在dataset目录下。
因此，mnist_show.py文件不可以跨文件直接导入mnist.py文件。
sys.path.append(os.pardir)语句实际上是把
父目录deep-learning-from-scatch加入到
sys.path（Python 的搜索目录模块的路径集中），
从而可以导入deep-learning-from-scatch下的任何目录(包括dataset目录)中的任何文件。
"""

from dataset.mnist import load_mnist

(x_train,t_train),(x_test,t_test) = load_mnist(flatten=True,normalize=False) #flatten是展开成一维数组，原图像28X28 展开后是 一维数组（784）个数据
#训练图像 ,训练标签 ，测试图像，测试标签
print(x_train.shape) #矩阵是 (60000, 784) 60000张图片，每一行是一张图片的信息。
print(t_train.shape)
print(x_test.shape)
print(t_test.shape)
"""
(60000, 784)
(60000,)
(10000, 784)
(10000,)
"""

完整版： 

import sys,os
sys.path.append(os.pardir)

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)

print(img.shape)
img = img.reshape(28,28)
print(img.shape)

img_show(img)

利用神经网络测试正确率：

get_data 是获取数据

init_network 是用现成的（训练好的）网络模型

predict是统计成功率

import os,sys
sys.path.append(os.pardir)
import numpy as np
from PIL import Image
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(flatten=True, normalize=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): # 把现成的参数（偏执和权重）取过来
    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 = sigmoid(a3)
    return y  # y可以认为是概率矩阵


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)))

上个for是一个个的检测，有点慢，采用批处理的形式会快一些。可以改成下面的形式。

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)
    accuracy_cnt += np.sum( p == t[i:i+batch_size])

'''
>>> x = np.array([[0.1, 0.8, 0.1], [0.3, 0.1, 0.6],
... [0.2, 0.5, 0.3], [0.8, 0.1, 0.1]])
>>> y = np.argmax(x, axis=1)
>>> print(y)
[1 2 1 0]
'''

print("Accuracy:"+str(float(accuracy_cnt)/len(x)))

替换for循环之后的完整代码：

import os,sys
sys.path.append(os.pardir)
import numpy as np
from PIL import Image
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(flatten=True, normalize=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): # x是要训练的数据，network是现成的网络 把现成的参数（偏执和权重）取过来
    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)  # 做一次非线性变换 
    a2 = np.dot(z1,W2)+b2
    z2 = sigmoid(a2)  # 做一次非线性变换 
    a3 = np.dot(z2,W3)+b3
    y = sigmoid(a3)   # 做一次非线性变换 
    return y  # y可以认为是概率矩阵


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
'''


batch_size = 100  #batch 是批处理的意思
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])

'''
>>> x = np.array([[0.1, 0.8, 0.1], [0.3, 0.1, 0.6],
... [0.2, 0.5, 0.3], [0.8, 0.1, 0.1]])
>>> y = np.argmax(x, axis=1)
>>> print(y)
[1 2 1 0]
'''


print("Accuracy:"+str(float(accuracy_cnt)/len(x)))