使用线性回归识别手写数字

   下载数据集

from __future__ import absolute_import      # 加入绝对引入这个新特性
from __future__ import division             # 精确除法
from __future__ import print_function       # 在python2.X，使用print就得像python3.X那样加括号使用

import os          # 导入系统库
import numpy       # 导入科学计算库
import gzip        # 导入解压库
import tempfile    # 导入临时文件库，可以用于生成临时文件和目录

from six.moves import urllib
from six.moves import xrange
import tensorflow as tf    # 导入tensorflow
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets

MNIST数据集（包含训练集和测试集，images是图像集，label是图像对应的标签集）

构建线性模型

import tensorflow as tf

# Y=Wx+b
def regression(x):
    W = tf.Variable(tf.zeros([784, 10]), name="W")
    b = tf.Variable(tf.zeros([10]), name="b")
    y = tf.nn.softmax(tf.matmul(x, W)+b)

    return y, [W, b]

线性回归regression

import os
import input_data
import model
import tensorflow as tf
data = input_data.read_data_sets('MNIST_data', one_hot=True)

with tf.variable_scope("regression"):
        x = tf.placeholder(tf.float32, [None, 784])
        y, variables = model.regression(x)

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)
correct_prediction =tf.equal(tf.argmax(y_, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

saver = tf.train.Saver(variables)
with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        for _ in range(1000):
            batch_xs, batch_ys = data.train.next_batch(100)
            sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

        print(sess.run(accuracy, feed_dict={x: data.test.images, y_: data.test.labels}))

        path = saver.save(
            sess,os.path.join(os.path.dirname(__file__),'data',"regression.ckpt"),
            write_meta_graph=False,write_state=False)

        print("saved:", path)