Python教程

python深度学习入门代码(一)

本文主要是介绍python深度学习入门代码(一),对大家解决编程问题具有一定的参考价值,需要的程序猿们随着小编来一起学习吧!

看的是《深度学习入门:基于 Python 的理论与实现》这本书的配套代码,但是不太看得懂,慢慢看。。。。

mnist.py#该脚本支持从下载MNIST数据集到将这些数据转换成NumPy数组等处理

# coding: utf-8
try:
    import urllib.request#网页请求
except ImportError:#只有python3支持这个库
    raise ImportError('You should use Python 3.x')
import os.path#获取文件的属性
import gzip#解压文件
import pickle#用于序列化和反序列化Python对象结构的二进制协议
import os#文件相关操作
import numpy as np#基础数字计算库


url_base = 'http://yann.lecun.com/exdb/mnist/'#需要访问的网站
key_file = {#数据集字典
    'train_img':'train-images-idx3-ubyte.gz',
    'train_label':'train-labels-idx1-ubyte.gz',
    'test_img':'t10k-images-idx3-ubyte.gz',
    'test_label':'t10k-labels-idx1-ubyte.gz'
}

dataset_dir = os.path.dirname(os.path.abspath(__file__))#获取当前路径
save_file = dataset_dir + "/mnist.pkl"

train_num = 60000
test_num = 10000
img_dim = (1, 28, 28)
img_size = 784


def _download(file_name):
    file_path = dataset_dir + "/" + file_name#设置下载路径

    if os.path.exists(file_path):#若此路径已经存在,说明已经下载了,返回
        return

    print("Downloading " + file_name + " ... ")#输出当前下载文件
    urllib.request.urlretrieve(url_base + file_name, file_path)#网络对象复制到本地文件
    print("Done")
    
def download_mnist():
    for v in key_file.values():
       _download(v)#下载文件
        
def _load_label(file_name):
    file_path = dataset_dir + "/" + file_name
    
    print("Converting " + file_name + " to NumPy Array ...")
    with gzip.open(file_path, 'rb') as f:
            labels = np.frombuffer(f.read(), np.uint8, offset=8)
    print("Done")
    
    return labels

def _load_img(file_name):
    file_path = dataset_dir + "/" + file_name#文件所在路径

    print("Converting " + file_name + " to NumPy Array ...")    
    with gzip.open(file_path, 'rb') as f:#打开压缩文件
            data = np.frombuffer(f.read(), np.uint8, offset=16)#将缓冲去解释为一维数组
    data = data.reshape(-1, img_size)#将数组变为img_size列,总元素个数保持不变,有多少行就变成多少行
    print("Done")
    
    return data
    
def _convert_numpy():
    dataset = {}#建立一个字典,来存放下载的文件
    dataset['train_img'] =  _load_img(key_file['train_img'])
    dataset['train_label'] = _load_label(key_file['train_label'])    
    dataset['test_img'] = _load_img(key_file['test_img'])
    dataset['test_label'] = _load_label(key_file['test_label'])
    
    return dataset

def init_mnist():
    download_mnist()
    dataset = _convert_numpy()
    print("Creating pickle file ...")
    with open(save_file, 'wb') as f:
        pickle.dump(dataset, f, -1)#序列化对象
    print("Done!")

def _change_one_hot_label(X):
    T = np.zeros((X.size, 10))#给定一个用0填充的数组
    for idx, row in enumerate(T):#一个索引序列
        row[X[idx]] = 1
        
    return T
    

def load_mnist(normalize=True, flatten=True, one_hot_label=False):
    """读入MNIST数据集
    
    Parameters
    ----------
    normalize : 将图像的像素值正规化为0.0~1.0
    one_hot_label : 
        one_hot_label为True的情况下,标签作为one-hot数组返回
        one-hot数组是指[0,0,1,0,0,0,0,0,0,0]这样的数组
    flatten : 是否将图像展开为一维数组
    
    Returns
    -------
    (训练图像, 训练标签), (测试图像, 测试标签)
    """
    if not os.path.exists(save_file):#文件是否存在
        init_mnist()
        
    with open(save_file, 'rb') as f:#打开文件
        dataset = pickle.load(f)#反序列化对象,将文件中的数据解析为一个python对象
    
    if normalize:#矢量标准化
        for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].astype(np.float32)#转换数组的数据类型为float32
            dataset[key] /= 255.0#像素值正规化

    if one_hot_label:#是否为one-hot数组
        dataset['train_label'] = _change_one_hot_label(dataset['train_label'])
        dataset['test_label'] = _change_one_hot_label(dataset['test_label'])
    
    if not flatten:#是否将图像展开为了一维数组
         for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].reshape(-1, 1, 28, 28)

    return (dataset['train_img'], dataset['train_label']), (dataset['test_img'], dataset['test_label']) 


if __name__ == '__main__':#开始的主函数
    init_mnist()
View Code

 minis_show.py#划分数据集,查看数据集图片的格式

# coding: utf-8
import sys, os#文件处理
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#基础数字计算库
from dataset.mnist import load_mnist#自己写的下载数据集的py文件
from PIL import Image#图像库


def img_show(img):
    pil_img = Image.fromarray(np.uint8(img))#图像格式转化
    pil_img.show()

(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True, normalize=False)#分出训练集和测试集

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)
View Code

 neuralnet_mnist.py#我们对这个MNIST数据集实现神经网络的推理处理

# coding: utf-8
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
import pickle
from dataset.mnist import load_mnist
from common.functions import sigmoid, softmax#把自己在各个不同项目中可以共用的基础函数汇总起来,形成一个独立的项目库,并对每个函数配上单元测试


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():#读入保存在pickle文件sample_weight.pkl中的学习到的权重参数
    with open("sample_weight.pkl", 'rb') as f:
        network = pickle.load(f)
    return network


def predict(network, x):#定义神经网络,以字典变量的形式保存权重和偏置参数
    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()#获得测试集
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)))
View Code

 neuralnet_mnist_batch.py#批处理图像

# coding: utf-8
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
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(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()
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)
    accuracy_cnt += np.sum(p == t[i:i+batch_size])

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

 

这篇关于python深度学习入门代码(一)的文章就介绍到这儿,希望我们推荐的文章对大家有所帮助,也希望大家多多支持为之网!