mnist数据集

 

 

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
#from tensorflow.examples.tutorials.mnist import input_data
import input_data

print ("packs loaded")
print ("Download and Extract MNIST dataset")
mnist = input_data.read_data_sets('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))

packs loaded
Download and Extract MNIST dataset
Extracting data/train-images-idx3-ubyte.gz
Extracting data/train-labels-idx1-ubyte.gz
Extracting data/t10k-images-idx3-ubyte.gz
Extracting data/t10k-labels-idx1-ubyte.gz
 tpye of 'mnist' is <class 'tensorflow.contrib.learn.python.learn.datasets.base.Datasets'>
 number of trian data is 55000
 number of test data is 10000

#%%
#what does the data of MINIST look like?
print ("what does the data of MINIST 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,))#28*28,总共784个像素
print (" shape of 'trainlabel' is %s" % (trainlabel.shape,))#0-9十个标签
print (" shape of 'testimg' is %s"    % (testimg.shape,))
print (" shape of 'testlabel' is %s"  % (testlabel.shape,))

what does the data of MINIST look like?
 type of 'trainimg' is <class 'numpy.ndarray'>
 type of 'trainlabel' is <class 'numpy.ndarray'>
 type of 'testimg' is <class 'numpy.ndarray'>
 type of 'testlabel' is <class 'numpy.ndarray'>
 shape of 'trainimg' is (55000, 784)
 shape of 'trainlabel' is (55000, 10)
 shape of 'testimg' is (10000, 784)
 shape of 'testlabel' is (10000, 10)

#%%
# 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))
    plt.show()



How does the training data look like?
3218th Training Data Label is 1

7530th Training Data Label is 4

43267th Training Data Label is 0

51822th Training Data Label is 7

2941th Training Data Label is 1

15212th Training Data Label is 1