import tensorflow as tf

import numpy as np  

def add_layer(inputs, in_size, out_size, activation_function = None):

  Weights = tf.Variable(tf.random_normal([in_size, out_size]))  # hang lie

  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  

x_data = np.linspace(-1,1,300)[:, np.newaxis] # 一列；[np.newaxis,:] 一行

noise  = np.random.normal(0, 0.05, x_data.shape)

y_data = np.square(x_data) - 0.5 + noise  

#input layer 1

#hidden layer 10

#output layer 1  

xs = tf.placeholder(tf.float32, [None, 1]) # 行数不固定，列数是1

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

l1 = add_layer(xs, 1, 10, activation_function = tf.nn.relu)

prediction = add_layer(l1, 10, 1, activation_function = None)  

loss = tf.reduce_mean(

  tf.reduce_sum(

    tf.square(ys - prediction),

    reduction_indices=[1]

    )

  )  

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)  

init = tf.initialize_all_variables()

sess = tf.Session()

sess.run(init)  

for i in range(1000):

  sess.run(train_step, feed_dict={xs:x_data, ys:y_data})

  if i % 50 == 0:

    print(sess.run(loss,

           feed_dict={xs:x_data, ys:y_data}

           )

      )