Tensorflow 搭建神经网络（单层）

#coding=utf-8
import tensorflow as tf
import numpy as np

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

#make train 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
#print (x_data)
#print (y_data)
#define placeholder
xs = tf.placeholder(tf.float32,[None,1])
ys = tf.placeholder(tf.float32,[None,1])
#add hidden layer
l1 = add_layer(xs,1,10,activation_function = tf.nn.relu)
#add output layer
prediction = add_layer(l1,10,1,activation_function = None)

#define loss function
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices = [1]))
#定义用什么方法减少loss
optimizer = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
for i in range(1001):
sess.run(optimizer,feed_dict = {xs:x_data,ys:y_data})
if i%100 == 0:
print (sess.run(loss,feed_dict = {xs:x_data,ys:y_data}))
#pre = sess.run(prediction,feed_dict = {xs:x_data,ys:y_data})
#aa = np.abs(pre - y_data)
#print (aa)