TensorFlow手写识别

#coding:utf8
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import numpy as np

mnist = input_data.read_data_sets('MNIST_data',one_hot=True)
sess = tf.InteractiveSession()
x = tf.placeholder('float',shape = [None,784])
y_true = tf.placeholder('float',shape=[None,10])

#W = tf.Variable(tf.zeros([784,10]))
#b = tf.Variable(tf.zeros([10]))


#初始化权重
def weight_variable(shape):
    initial = tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)

#初始化偏值
def biase_variable(shape):
    initial = tf.constant(0.1,shape=shape)
    return tf.Variable(initial)

#二维卷积
def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')

#最大池化
def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')

#第一层卷积
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = biase_variable([32])

x_image = tf.reshape(x,[-1,28,28,1])
h_conv1 = tf.nn.softmax(conv2d(x_image,W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)


#第二层卷积
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = weight_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#密集全连接层

W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = biase_variable([1024])
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1) + b_fc1)

#Dropout减少过拟合
keep_prob = tf.placeholder('float')
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

#输出层

W_fc2 = weight_variable([1024,10])
b_fc2 = biase_variable([10])

y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2) + b_fc2)

#交叉熵计算误差
cross_entropy = -tf.reduce_mean(y_true*tf.log(y_conv))
#最小化交叉熵（优化误差）
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
#计算真实值与预测值之间的误差
correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y_true,1))
#正确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,'float'))
#执行图
sess.run(tf.global_variables_initializer())

for i in range(20000):
    batch = mnist.train.next_batch(50)
    if i % 100 == 0:
        train_accuracy = accuracy.eval(feed_dict = {
            x:batch[0],y_true:batch[1],keep_prob:1.0
        })
        print("step %d training accuracy %g"%(i,train_accuracy))
    train_step.run(feed_dict = {
        x:batch[0],y_true:batch[1],keep_prob:0.5
    })
print ("test accuracy %g"%accuracy.eval(feed_dict={
    x:mnist.test.images,y_true:mnist.test.labels,keep_prob:1.0
}))