tensorflow 学习笔记7 普通神经网络实现mnist手写识别

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#number 1 to 10 data自动下载数据集
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

def add_layer(inputs, in_size, out_size, activation_function=None,):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1,)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b,)
    return outputs

def compute_accuracy(v_xs, v_ys):
    global prediction
    #用v_xs得出y的预测值：y是根据哪个数值概率更高得出来的
    y_pre = sess.run(prediction, feed_dict={xs: v_xs})
    #比较预测值与真实值是否相等
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    #计算多少个是对的多少个是错的
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    #run得到一个百分比
    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]) # 28x28
ys = tf.placeholder(tf.float32, [None, 10]) #10种输出

# add output layer，激活函数softmax，用于分类的激活函数
prediction = add_layer(xs, 784, 10,  activation_function=tf.nn.softmax)

# the error between prediction and real data，分类的loss函数：交叉熵代价函数
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),reduction_indices=[1]))       # loss
#梯度下降优化法，最小化loss函数，学习率0.5
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
# important step
init = tf.global_variables_initializer()
sess.run(init)

for i in range(1000):
    #获取100个数据，100个100个学习
    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:
        #输出每一步的准确度
        print(compute_accuracy(mnist.test.images, mnist.test.labels))

因为这是一般神经网络实现的手写识别，所以准确度并不是很高: