TensorFlow MNIST（手写识别 softmax）实例运行

首先要有编译环境，并且已经正确的编译安装，关于环境配置参考：http://www.cnblogs.com/dyufei/p/8027517.html

一、MNIST 运行

1）首先下载训练数据

在 http://yann.lecun.com/exdb/mnist/ 将四个包都下载下来,在下面代码的运行目录下创建MNIST_data目录，将四个包放进去

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)

当然也可以不下载，前提是运行TensorFlow的服务器可以正常访问下载目录，如果出问题参照 【问题1）】解决）

2) MNIST 代码

A: 比较旧的版本（官方教程里面的）

https://tensorflow.google.cn/get_started/mnist/beginners
中文：http://www.tensorfly.cn/tfdoc/tutorials/mnist_beginners.html

完整代码如下：mnist.py

import input_data
import  tensorflow as tf
FLAGS = None
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)x = tf.placeholder("float",[None,784])
w = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))y =  tf.nn.softmax(tf.matmul(x,w) + b)
y_ =   tf.placeholder("float",[None,10])
cross_entroy = -tf.reduce_sum(y_ * tf.log(y))train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entroy)init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)for _ 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})

input_data.py

from __future__ import absolute_import
from __future__ import division
from __future__ import print_functionimport gzip
import os
import tempfileimport numpy
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets

运行

python mnist.py

2) 新版本mnist_softmax.py

input_data.py 文件内容相同，mnist_softmax.py文件不同
mnist_softmax.py 文件目录：

tensorflow\tensorflow\examples\tutorials\mnist\mnist_softmax.py

完整代码：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_functionimport argparse
import sys
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataimport tensorflow as tfFLAGS = Nonedef main(_):# Import datamnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)# Create the modelx = tf.placeholder(tf.float32, [None, 784])W = tf.Variable(tf.zeros([784, 10]))b = tf.Variable(tf.zeros([10]))y = tf.matmul(x, W) + b# Define loss and optimizery_ = tf.placeholder(tf.float32, [None, 10])# The raw formulation of cross-entropy,##   tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),#                                 reduction_indices=[1]))## can be numerically unstable.## So here we use tf.nn.softmax_cross_entropy_with_logits on the raw# outputs of 'y', and then average across the batch.cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)sess = tf.InteractiveSession()tf.global_variables_initializer().run()# Trainfor _ in range(1000):batch_xs, batch_ys = mnist.train.next_batch(100)sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})# Test trained modelcorrect_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))print(sess.run(accuracy, feed_dict={x: mnist.test.images,y_: mnist.test.labels}))if __name__ == '__main__':parser = argparse.ArgumentParser()parser.add_argument('--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',help='Directory for storing input data')FLAGS, unparsed = parser.parse_known_args()tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

数据路径不同,将训练数据copy过去：

cp MNIST_data/*.gz /tmp/tensorflow/mnist/input_data/

运行：

python mnist_softmax.py