文章标题

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

def add_layer(inputs,in_size,out_size,activation_function=None):
Weights = tf.Variable(tf.random_normal([in_size,out_size])) #in_size 行，out_size列
biases = tf.Variable(tf.zeros([1,out_size])+0.1)
Wx_plus_b = tf.matmul(inputs,Weights) + biases
if activation_function == None:
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b)
return outputs

x_data = np.linspace(-1,1,300)[:,np.newaxis]
noise = np.random.normal(0,0.05,x_data.shape)
y_data = pow(x_data,7) - 0.5 + noise

xs = tf.placeholder(tf.float32,[None,1])
ys = tf.placeholder(tf.float32,[None,1])

L1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
predition = add_layer(L1,10,1,activation_function=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(y_data - predition),
reduction_indices=[1]))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(loss)

train = train_step.minimize(loss)

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

下面是将结果可视化

fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data) #先将所有数据都可视化
plt.ion() #暂停一下
plt.show()

#

for i in range(1000):
sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
if i%10==0:
#print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))
try:
ax.lines.remove(lines[0]) #尝试抹除前一条线
except Exception:
pass
prediction_value = sess.run(predition,feed_dict={xs:x_data})
lines = ax.plot(x_data,prediction_value,’r-‘,lw=5) #相当于输出一条 坐标为 （x，pridiction_value)线段
plt.pause(0.1)