声明：版权所有，转载请联系作者并注明出处: http://blog.csdn.net/u013719780?viewmode=contents
在做机器学习相关实验的时候，首先我们就是需要一份通用的数据集，以便与其他的算法得到的实验结果进行比较。在图像分类领域MNIST数据集就是这样一个通用的数据集，前面几篇博文都用到了MNIST数据集，本文对其进行一些简单的介绍！
In [1]:
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
%matplotlib inline
print ("packs loaded")
In [2]:
print ("Download and Extract MNIST dataset")
mnist = input_data.read_data_sets('/tmp/data/', one_hot=True)
print
print (" tpye of 'mnist' is %s" % (type(mnist)))
print (" number of trian data is %d" % (mnist.train.num_examples))
print (" number of test data is %d" % (mnist.test.num_examples))
In [3]:
# What does the data of MNIST look like?
print ("What does the data of MNIST look like?")
trainimg = mnist.train.images
trainlabel = mnist.train.labels
testimg = mnist.test.images
testlabel = mnist.test.labels
print
print (" type of 'trainimg' is %s" % (type(trainimg)))
print (" type of 'trainlabel' is %s" % (type(trainlabel)))
print (" type of 'testimg' is %s" % (type(testimg)))
print (" type of 'testlabel' is %s" % (type(testlabel)))
print (" shape of 'trainimg' is %s" % (trainimg.shape,))
print (" shape of 'trainlabel' is %s" % (trainlabel.shape,))
print (" shape of 'testimg' is %s" % (testimg.shape,))
print (" shape of 'testlabel' is %s" % (testlabel.shape,))
In [4]:
# How does the training data look like?
print ("How does the training data look like?")
nsample = 5
randidx = np.random.randint(trainimg.shape[0], size=nsample)
for i in randidx:
curr_img = np.reshape(trainimg[i, :], (28, 28)) # 28 by 28 matrix
curr_label = np.argmax(trainlabel[i, :] ) # Label
plt.matshow(curr_img, cmap=plt.get_cmap('gray'))
plt.title("" + str(i) + "th Training Data "
+ "Label is " + str(curr_label))
print ("" + str(i) + "th Training Data "
+ "Label is " + str(curr_label))
In [5]:
# Batch Learning?
print ("Batch Learning? ")
batch_size = 100
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
print ("type of 'batch_xs' is %s" % (type(batch_xs)))
print ("type of 'batch_ys' is %s" % (type(batch_ys)))
print ("shape of 'batch_xs' is %s" % (batch_xs.shape,))
print ("shape of 'batch_ys' is %s" % (batch_ys.shape,))
In [6]:
# Get Random Batch with 'np.random.randint'
print ("5. Get Random Batch with 'np.random.randint'")
randidx = np.random.randint(trainimg.shape[0], size=batch_size)
batch_xs2 = trainimg[randidx, :]
batch_ys2 = trainlabel[randidx, :]
print ("type of 'batch_xs2' is %s" % (type(batch_xs2)))
print ("type of 'batch_ys2' is %s" % (type(batch_ys2)))
print ("shape of 'batch_xs2' is %s" % (batch_xs2.shape,))
print ("shape of 'batch_ys2' is %s" % (batch_ys2.shape,))
In [7]:
randidx
Out[7]: