mnist手写数据集初探
mnist数据集的简介及下载
MNIST是一个非常有名的手写体数字识别数据集,在很多资料中,这个数据集都会被用作深度学习的入门样例。
数据集下载网址:http://yann.lecun.com/exdb/mnist/
一共可以下载四个文件
train-images-idx3-ubyte.gz (9912422 bytes)
train-labels-idx1-ubyte.gz (28881 bytes)
t10k-images-idx3-ubyte.gz (1648877 bytes)
t10k-labels-idx1-ubyte.gz (4542 bytes)
前两个分别是训练用的图片和标签,共60000组,后两个分别是测试用的图片和标签,共10000组。官网这样声明了他们存储数据的方式:
如图,对于标签文件,前8个地址存储的是样本信息,也就是说我们需要从脚标为0008的单元开始度数据,同样的,对于图像文件,需要从0016的单元开始数据。
换言之,标签文件是一个【60000,10】的数组,10是0到9的one—hot 格式
而图像文件是28*28=784维的向量,用来存放灰度信息。
mnist数据集的导入
首先,如何读取一个.gz
文件呢?
我们可以利用pythongzip
库的gzip.open()
函数来打开数据包,而nmpy库提供了np.frombuffer()
函数可以让我们将数据流中的内容转化成numpy数组
def _load_img(file_name):
file_path = dataset_dir + "/" + file_name
print("Converting " + file_name + " to NumPy Array ...")
with gzip.open(file_path, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=16)
data = data.reshape(-1, img_size)#共image_siza=28*28列,-1为自适应行数
print("Done")
return data
同理,我们可以这样读入标签
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
整体文件
为了方便以后对数据集的使用,现将读取操作完善,添加pickle文件以保存读取结果,详细解释见注释:
# coding: utf-8
import os.path
import gzip
import pickle
import os
import numpy as np
url_base = 'http://yann.lecun.com/exdb/mnist/' #mnist官网,下载失败可以从此处下载,文件名见下方字典
key_file = { #字典存储下载好的文件名
'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__))#os.path.abspath(__file__)返回此片代码绝对路径,os.path.dirname()返回此路径文件的目录
save_file = dataset_dir + "/mnist.pkl"
train_num = 60000 #mnist数据集共60000个数据用于训练,10000个数据用于测试
test_num = 10000
img_size = 784
def _load_img(file_name):
file_path = dataset_dir + "/" + file_name
print("Converting " + file_name + " to NumPy Array ...")
with gzip.open(file_path, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=16)
data = data.reshape(-1, img_size)#共image_siza=28*28列,-1为自适应行数
print("Done")
return data
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 _convert_numpy():
dataset = {}
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():
dataset = _convert_numpy()
print("Creating pickle file ...")
with open(save_file, 'wb') as f:
pickle.dump(dataset, f, -1)
print("Done!")
def _change_one_hot_label(X):
T = np.zeros((X.size, 10))
for idx, row in enumerate(T):
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):
init_mnist()
with open(save_file, 'rb') as f:
dataset = pickle.load(f)
if normalize:
for key in ('train_img', 'test_img'):
dataset[key] = dataset[key].astype(np.float32)
dataset[key] /= 255.0
if one_hot_label:
dataset['train_label'] = _change_one_hot_label(dataset['train_label'])
dataset['test_label'] = _change_one_hot_label(dataset['test_label'])
if not flatten:
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'])
(x_train,t_train),(x_test,t_test) = load_mnist(flatten=False,normalize=False)
print(x_train[0])