-- coding: utf-8 --
“””
Created on Sun April 09 13:17:30 2017
@author: Zizhang Wu
“”“
#
数据加载
import input_data
mnist = input_data.read_data_sets(“MNIST_data/”, one_hot=True)
设置占位符,运行TensorFlow的InteractiveSession
import tensorflow as tf
sess = tf.InteractiveSession()
x = tf.placeholder(“float”, [None, 784])
y_ = tf.placeholder(“float”, shape=[None, 10])
模型参数初始化为0
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
变量初始化
sess.run(tf.initialize_all_variables())
选取交叉熵作为损失函数,使用梯度下降法来进行优化
y = tf.nn.softmax(tf.matmul(x,W) + b)
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
初始化变量与会话
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
让模型训练1000次,batch_size设置为100
for i in range(1000):
batch = mnist.train.next_batch(100)
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
#batch_xs, batch_ys = mnist.train.next_batch(100)
#sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
评估模型
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, “float”))
print accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels})