设计思路

全部代码

#TF：利用是Softmax回归+GD算法实现手写数字识别(10000张图片测试得到的准确率为92%)

#思路：对输入的图像，计算它属于每个类别的概率，找出最大概率即为预测值

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data  

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)#读入MNIST数据

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)))                

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)  

sess = tf.InteractiveSession()

tf.global_variables_initializer().run()

print('start training...')

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, tf.float32))

print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))  # 0.9185