欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

tensorflow实现加载mnist数据集

程序员文章站 2022-05-18 22:32:16
mnist作为最基础的图片数据集,在以后的cnn,rnn任务中都会用到 import numpy as np import tensorflow as tf...

mnist作为最基础的图片数据集,在以后的cnn,rnn任务中都会用到

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

#数据集存放地址,采用0-1编码
mnist = input_data.read_data_sets('f:/mnist/data/',one_hot = true)
print(mnist.train.num_examples)
print(mnist.test.num_examples)

trainimg = mnist.train.images
trainlabel = mnist.train.labels
testimg = mnist.test.images
testlabel = mnist.test.labels

#打印相关信息
print(type(trainimg))
print(trainimg.shape,)
print(trainlabel.shape,)
print(testimg.shape,)
print(testlabel.shape,)

nsample = 5
randidx = np.random.randint(trainimg.shape[0],size = nsample)

#输出几张数字的图
for i in randidx:
  curr_img = np.reshape(trainimg[i,:],(28,28))
  curr_label = np.argmax(trainlabel[i,:])
  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()

程序运行结果如下:

extracting f:/mnist/data/train-images-idx3-ubyte.gz
extracting f:/mnist/data/train-labels-idx1-ubyte.gz
extracting f:/mnist/data/t10k-images-idx3-ubyte.gz
extracting f:/mnist/data/t10k-labels-idx1-ubyte.gz
55000
10000
<class 'numpy.ndarray'>
(55000, 784)
(55000, 10)
(10000, 784)
(10000, 10)
52636th 

输出的图片如下:

training datalabel is9

tensorflow实现加载mnist数据集

下面还有四张其他的类似图片

以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持。