from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

print(mnist.train.images.shape, mnist.train.labels.shape)
print(mnist.test.images.shape, mnist.test.labels.shape)
print(mnist.validation.images.shape, mnist.validation.labels.shape)

import tensorflow as tf
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, [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(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))//第二个参数reduction_indices不指定,那么就在所有的元素中取平均值;
                                         //指定第二个参数为0，则第一维的元素取平均值，即每一列求平均值;指定第二个参数为1，则第二维的元素取平均值，即每一行求平均值

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

tf.global_variables_initializer().run()                   //若是用的tf.Session,则这里初始化要用，sess.run(tf.initalize_all_variables())

for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    train_step.run({x: batch_xs, y_: batch_ys})     // sess.run(train_step, feed_dict={x:batch_xs, y_:batch_ys})也可以

correct_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.train.images, y_:mnist.train.labels}))
 print(sess.run(accuracy, feed_dict={x:mnist.test.images, y_:mnist.test.labels}))
 print(sess.run(accuracy, feed_dict={x:mnist.validation.images, y_:mnist.validation.labels}))
#保存模型
saver = tf.train.Saver() 
saver.save(sess, "/home/magina/Documents/mnist_model/model.ckpt")

 接下来就是试验自己写的数字了

rom PIL import Image
import tensorflow as tf
import matplotlib.pyplot as plt
im = Image.open('/home/magina/Downloads/0.jpg').convert('L')     //利用手机拍照，然后处理，不过图像不理想
img = im.resize((28, 28))
arr = []
for i in range(28):
    for j in range(28):
        # mnist 里的颜色是0代表白色（背景），1.0代表黑色
        pixel = 1-float(img.getpixel((j, i)))/255.0
        # getpixel返回指定位置的像素
        arr.append(pixel)
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W)+b)
saver=tf.train.Saver()
with tf.Session() as sess:
   saver.restore(sess, "/home/magina/Documents/mnist_model/model.ckpt")              //加载参数模型
   print ("Model restored.")
   prediction=tf.argmax(y,1)
   print(type(prediction))
   #predint=prediction.eval(feed_dict={x: [arr]})
  # print(predint[0])
   print(sess.run(prediction[0], feed_dict={x: [arr]}))

 把权重用图像表示

from PIL import Image
import tensorflow as tf
import matplotlib.pyplot as plt
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W)+b)
saver=tf.train.Saver()
with tf.Session() as sess:
   saver.restore(sess, "/home/magina/Documents/mnist_model/model.ckpt")
   print ("Model restored.")
   for i in range(10):
        plt.subplot(2, 5, i+1)
        weight = sess.run(W)[:,i]
        plt.title(i)
        plt.imshow(weight.reshape([28,28]), cmap=plt.get_cmap('seismic'))
        plt.show()