import tensorflow as tf
import numpy as np
import input_data

mnist = input_data.read_data_sets('MNIST_data',one_hot=True)

def add_layer(inputs,in_size,out_size,n_layer,activation_function=None):
    layer_name = 'layer%s' %n_layer
    with tf.name_scope(layer_name):
        with tf.name_scope('weights'): #tf.name_scope()创建结点
            Weights = tf.Variable(tf.random_normal([in_size,out_size],mean=0,stddev=1))
            tf.histogram_summary(layer_name+'/weights',Weights)
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1,out_size])+0.25)
            tf.histogram_summary(layer_name+'/biases',biases) #tf.histogram_summary()创建值
        with tf.name_scope('out1'):
            out1 = tf.matmul(inputs,Weights)+biases
            tf.histogram_summary(layer_name+'/out1',out1)
        if activation_function is None:
            outputs = out1
        else:
            outputs = activation_function(out1)
        tf.histogram_summary(layer_name+'/output',outputs)
        return outputs

#define placeholder for inputs to network
with tf.name_scope('inputs'):
    xs = tf.placeholder(tf.float32,[None,784],name = 'input_x')
    ys = tf.placeholder(tf.float32,[None,10],name = 'input_y')

#add output layer
prediction = add_layer(xs,784,10,n_layer=1,activation_function=tf.nn.softmax)

#the error between prediction and real data
with tf.name_scope('cross_entropy'):
    cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
    tf.scalar_summary('cross_entropy',cross_entropy)
with tf.name_scope('train'):    
    train_step = tf.train.GradientDescentOptimizer(0.25).minimize(cross_entropy)

init = tf.initialize_all_variables()
sess = tf.Session()

def compute_accuracy(v_xs,v_ys):
    global prediction
    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


merged = tf.merge_all_summaries() #将所有summary merged
writer = tf.train.SummaryWriter('logs/',sess.graph) #写入logs文件夹下
sess.run(init)

for i in range(1000):
    batch_xs,batch_ys = mnist.train.next_batch(500)
    sess.run(train_step,feed_dict={xs:batch_xs,ys:batch_ys})
    if i % 50 == 0:
        result = sess.run(merged,feed_dict={xs:mnist.test.images,ys:mnist.test.labels})
        writer.add_summary(result,i)
        print(compute_accuracy(mnist.test.images,mnist.test.labels))

运行

tensorboard –logdir = ‘log/’

结果