机器学习实战（二）—Softmax 回归

数字识别

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#读取数据集
mnist = input_data.read_data_sets("MNIST_data/",one_hot = True)

#设置训练数据 x，连接权重 W 和偏置 b
x = tf.placeholder("float",[None,784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))

#对 x 和 W 进行内积运算后把结果传递给 softmax 函数，计算输出 y
y = tf.nn.softmax(tf.matmul(x,W)+b)

#设置期望输出 y
y_ = tf.placeholder("float",[None,10])

#计算交叉熵
cross_entropy = -tf.reduce_sum(y_*tf.log(y))

#使用梯度下降最小化交叉熵
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

#初始化
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

#迭代训练
for i 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,"float"))
print(sess.run(accuracy,feed_dict = {x:mnist.test.images,y_:mnist.test.labels}))

运行之后的分类准确率在91%左右