import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

#
# add layer
#
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'):
Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W') # hang lie
tf.summary.histogram(layer_name + '/weights', Weights)#保存成一个直方图，bin是取值
with tf.name_scope('biases'):
biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name = 'b')
tf.summary.histogram(layer_name + '/biases', biases)#注意histogram的路径
with tf.name_scope('Wx_plus_b'):
Wx_plus_b = tf.matmul(inputs, Weights) + biases

if activation\_function is None:  
  outputs = Wx\_plus\_b  
else:  
  outputs = activation\_function(Wx\_plus\_b)  

tf.summary.histogram(layer\_name + '/outputs', outputs)  
return outputs  

#make up some data

x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

#define placeholder

with tf.name_scope('inputs'):
xs = tf.placeholder(tf.float32, [None, 1], name = 'x_input') #注意命名
ys = tf.placeholder(tf.float32, [None, 1], name = 'y_input')

#add hidden layer
l1 = add_layer(xs, 1, 10, n_layer = 1,activation_function = tf.nn.relu)
#add output layer
prediction = add_layer(l1, 10, 1, n_layer = 2, activation_function = None)

#the error between prediction and real data
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
reduction_indices=[1] ))
tf.summary.scalar('loss', loss)#记录operation，是存储在scaler里的

with tf.name_scope('train'):
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

sess = tf.Session()
merged = tf.summary.merge_all() #所有的summary在merge以后，在一个run中就可执行
writer = tf.summary.FileWriter("logs/", sess.graph) #定义writer

#import step
sess.run(tf.global_variables_initializer() )

Session

#

for i in range(1000):
sess.run(train_step, feed_dict={xs:x_data, ys:y_data})
if i % 50 == 0:
result = sess.run(merged, # 否则要一个个run summary。
feed_dict = {xs:x_data, ys:y_data})

writer.add\_summary(result, i)#按序列写入结果  
print(sess.run(loss, feed\_dict={xs:x\_data, ys:y\_data}))