tensorflow

# -*- coding: utf-8 -*-


'''
数据特征：每个手写数据都是28 * 28 = 784个数据点，55000个数据点；
类别：一个10维度的向量，那个位置是1代表数据点是哪个类别 -one-hot编码；
'''


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


mnist = input_data.read_data_sets('MNIST_data/', one_hot=True) #下载数据


#添加神经层
def add_layer(inputs, in_size, out_size, activation_function=None):
    Weight = tf.Variable(tf.random_normal([in_size, out_size]), name='w')#初始化随机矩阵
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b') #初始化随机偏差向量
    Wx_plus_b = tf.add(tf.matmul(inputs, Weight), biases) #矩阵乘法
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs


#计算准确率
def compute_accuracy(v_xs, v_ys):
    global prediction  #全局变量
    y_pre = sess.run(prediction, feed_dict={xs:v_xs})
    correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    result = sess.run(accuracy, feed_dict={xs:v_xs, ys:v_ys})
    return result
    
#define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784])# 28 * 28
ys = tf.placeholder(tf.float32, [None, 10])

#add_layer
prediction = add_layer(xs, 784, 10, activation_function=tf.nn.softmax)

#the error between prediction and real data
#分类问题：cross_entropy方法 + softmax 绝配
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                             reduction_indices=[1])) #指沿着哪个维度求和，相当于loss
                                             
#train:梯度下降，只需要指定学习率
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
#important step
sess.run(tf.initialize_all_variables())

for i in range(1000):
    #提取一部分数据 -- SDD随机梯度下降，加快速度
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={xs:batch_xs, ys:batch_ys})
    if i % 50 == 0:
        print(compute_accuracy(mnist.test.images, mnist.test.labels))