使用工具:win10+anaconda+tensorflow包
参考文章:MNIST机器学习入门
使用官方给出的例子安装下载MNIST数据集失败,故采用手动下载的方式。
1.下载数据集安装包
网址:http://yann.lecun.com/exdb/mnist/
分别下载
train-images-idx3-ubyte.gz: training set images (9912422 bytes)
train-labels-idx1-ubyte.gz: training set labels (28881 bytes)
t10k-images-idx3-ubyte.gz: test set images (1648877 bytes)
t10k-labels-idx1-ubyte.gz: test set labels (4542 bytes)
创建文件夹MNIST_data,并将下载好的压缩包放入该文件。
2.创建python新文件用于检测数据包
创建tf_test.py,并将文件存放于MNIST_data文件夹同一目录下(不是MNIST_data文件夹里)
# -*- coding: utf-8 -*-
"""
Created on Wed Oct 3 12:02:52 2018
@author: zhaolun
"""
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10])+0.1)
y = tf.nn.softmax(tf.matmul(x,W) + b)
y_ = tf.placeholder("float", [None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
3.运行文件tf_test.py
使用anaconda打开tf_test.py文件,使用F5运行,得到结果为0.9148